Lei Jiao

• Bhattarai, Bimal; Granmo, Ole-Christoffer; Lei, Jiao; Andersen, Per-Arne; Tunheim, Svein Anders & Shafik, Rishad Ahmed [Show all 7 contributors for this article] (2023). Contracting Tsetlin Machine with Absorbing Automata, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE conference proceedings. ISSN 979-8-3503-4477-6. doi: 10.1109/ISTM58889.2023.10455040.
• Tarasyuk, Olga; Rahman, Tousif; Shafik, Rishad Ahmed; Yakovlev, Alexandre; Gorbenko, Anatoliy & Granmo, Ole-Christoffer [Show all 7 contributors for this article] (2023). Systematic Search for Optimal Hyper-parameters of the Tsetlin Machine on MNIST Dataset, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE conference proceedings. ISSN 979-8-3503-4477-6. doi: 10.1109/ISTM58889.2023.10454969.
• Liland, Kristian Hovde; Tomic, Oliver; Indahl, Ulf Geir; Futsæther, Cecilia Marie; Lei, Jiao & Granmo, Ole-Christoffer [Show all 7 contributors for this article] (2023). Tsetlin Machine in DNA sequence classification : Application to prokaryote gene prediction / A match made in silico, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE conference proceedings. ISSN 979-8-3503-4477-6. doi: 10.1109/ISTM58889.2023.10454960.
• Granmo, Ole-Christoffer; Andersen, Per-Arne; Lei, Jiao; Zhang, Xuan; Blakely, Christian Dallas & Berge, Geir Thore [Show all 7 contributors for this article] (2023). Learning Minimalistic Tsetlin Machine Clauses with Markov Boundary-Guided Pruning, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE conference proceedings. ISSN 979-8-3503-4477-6. doi: 10.1109/ISTM58889.2023.10454914.
• Tunheim, Svein Anders; Lei, Jiao & Granmo, Ole-Christoffer (2023). Model Export for the Convolutional Coalesced Tsetlin Machine, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE conference proceedings. ISSN 979-8-3503-4477-6. doi: 10.1109/ISTM58889.2023.10455048.
• Sharma, Jivitesh; Yadav, Rohan Kumar; Granmo, Ole-Christoffer & Lei, Jiao (2023). Drop Clause: Enhancing Performance, Robustness and Pattern Recognition Capabilities of the Tsetlin Machine. In Chen, Yiling & Neville, Jennifer (Ed.), Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence. AAAI Press. ISSN 978-1-57735-880-0. p. 13547–13555. doi: 10.1609/aaai.v37i11.26588.
• Abeyrathna, Kuruge Darshana; Abouzeid, Ahmed Abdulrahem Othman; Bhattarai, Bimal; Giri, Charul; Glimsdal, Sondre & Granmo, Ole-Christoffer [Show all 11 contributors for this article] (2023). Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size . In Elkind, Edith (Eds.), Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. AAAI Press. ISSN 978-1-956792-03-4. p. 3395–3403. doi: 10.24963/ijcai.2023/378. Full text in Research Archive Show summary

  Tsetlin machine (TM) is a logic-based machine learning approach with the crucial advantages of being transparent and hardware-friendly. While TMs match or surpass deep learning accuracy for an increasing number of applications, large clause pools tend to produce clauses with many literals (long clauses). As such, they become less interpretable. Further, longer clauses increase the switching activity of the clause logic in hardware, consuming more power. This paper introduces a novel variant of TM learning – Clause Size Constrained TMs (CSC-TMs) – where one can set a soft constraint on the clause size. As soon as a clause includes more literals than the constraint allows, it starts expelling literals. Accordingly, oversized clauses only appear transiently. To evaluate CSC-TM, we conduct classifcation, clustering, and regression experiments on tabular data, natural language text, images, and board games. Our results show that CSC-TM maintains accuracy with up to 80 times fewer literals. Indeed, the accuracy increases with shorter clauses for TREC, IMDb, and BBC Sports. After the accuracy peaks, it drops gracefully as the clause size approaches a single literal. We fnally analyze CSC-TM power consumption and derive new convergence properties.

• Tunheim, Svein Anders; Lei, Jiao; Shafik, Rishad Ahmed; Yakovlev, Alexandre & Granmo, Ole-Christoffer (2023). Convolutional Tsetlin Machine-based Training and Inference Accelerator for 2-D Pattern Classification. Microprocessors and Microsystems: Embedded Hardware Design (MICPRO). ISSN 0141-9331. 103. doi: 10.1016/j.micpro.2023.104949. Full text in Research Archive Show summary

  The Tsetlin Machine (TM) is a machine learning algorithm based on an ensemble of Tsetlin Automata (TAs) that learns propositional logic expressions from Boolean input features. In this paper, the design and implementation of a Field Programmable Gate Array (FPGA) accelerator based on the Convolutional Tsetlin Machine (CTM) is presented. The accelerator performs classification of two pattern classes in 4 × 4 Boolean images with a 2 × 2 convolution window. Specifically, there are two separate TMs, one per class. Each TM comprises 40 propositional logic formulas, denoted as clauses, which are conjunctions of literals. Include/exclude actions from the TAs determine which literals are included in each clause. The accelerator supports full training, including random patch selection during convolution based on parallel reservoir sampling across all clauses. The design is implemented on a Xilinx Zynq XC7Z020 FPGA platform. With an operating clock speed of 40 MHz, the accelerator achieves a classification rate of 4.4 million images per second with an energy per classification of 0.6 J. The mean test accuracy is 99.9% when trained on the 2-dimensional Noisy XOR dataset with 40% noise in the training labels. To achieve this performance, which is on par with the original software implementation, Linear Feedback Shift Register (LFSR) random number generators of minimum 16 bits are required. The solution demonstrates the core principles of a CTM and can be scaled to operate on multi-class systems for larger images.

• Sharif, Md Haidar; Lei, Jiao & Omlin, Christian Walter Peter (2023). CNN-ViT Supported Weakly-Supervised Video Segment Level Anomaly Detection. Sensors. ISSN 1424-8220. 23(18). doi: 10.3390/s23187734. Full text in Research Archive
• Maheshwari, Sidharth; Rahman, Tousif; Shafik, Rishad; Yakovlev, Alex; Rafiev, Ashur & Lei, Jiao [Show all 7 contributors for this article] (2023). REDRESS: Generating Compressed Models for Edge Inference Using Tsetlin Machines. IEEE Transactions on Pattern Analysis and Machine Intelligence. ISSN 0162-8828. 45(9), p. 11152–11168. doi: 10.1109/TPAMI.2023.3268415. Show summary

  Inference at-the-edge using embedded machine learning models is associated with challenging trade-offs between resource metrics, such as energy and memory footprint, and the performance metrics, such as computation time and accuracy. In this work, we go beyond the conventional Neural Network based approaches to explore Tsetlin Machine (TM), an emerging machine learning algorithm, that uses learning automata to create propositional logic for classification. We use algorithm-hardware co-design to propose a novel methodology for training and inference of TM. The methodology, called REDRESS, comprises independent TM training and inference techniques to reduce the memory footprint of the resulting automata to target low and ultra-low power applications. The array of Tsetlin Automata (TA) holds learned information in the binary form as bits: {0,1} , called excludes and includes, respectively. REDRESS proposes a lossless TA compression method, called the include-encoding, that stores only the information associated with includes to achieve over 99% compression. This is enabled by a novel computationally minimal training procedure, called the Tsetlin Automata Re-profiling, to improve the accuracy and increase the sparsity of TA to reduce the number of includes, hence, the memory footprint. Finally, REDRESS includes an inherently bit-parallel inference algorithm that operates on the optimally trained TA in the compressed domain, that does not require decompression during runtime, to obtain high speedups when compared with the state-of-the-art Binary Neural Network (BNN) models. In this work, we demonstrate that using REDRESS approach, TM outperforms BNN models on all design metrics for five benchmark datasets viz. MNIST, CIFAR2, KWS6, Fashion-MNIST and Kuzushiji-MNIST. When implemented on an STM32F746G-DISCO microcontroller, REDRESS obtained speedups and energy savings ranging 5-5700× compared with different BNN models.

• Omslandseter, Rebekka Olsson; Lei, Jiao & Oommen, John (2023). Pioneering approaches for enhancing the speed of hierarchical LA by ordering the actions. Information Sciences. ISSN 0020-0255. 647, p. 1–17. doi: 10.1016/j.ins.2023.119487. Full text in Research Archive Show summary

  Fixed Structure Stocastic Automata (FSSA), Variable Structure Learning Automata (VSSA), and their discretized versions have been significantly improved by utilizing inexpensive estimates of the actions' reward probabilities. These represent the fastest LA to date. However, the concept of ordering the actions has never been used within the field, and the reason for this is that there is no way to order the actions a priori. The recently-introduced Hierarchical Discrete Pursuit Automaton (HDPA) has an interesting concept of placing two-action LA along the nodes of a tree, implying that the leaves signify an underlying ordering. In this paper, we show that if estimates are available (as in the case of estimator algorithms), these can be used to place the actions at the leaf level to further enhance the convergence capabilities of the overall ensemble of the two-action LAs. This paper contains the design of this HDPA, the proof of this assertion, and the simulation results on benchmark Environments. Based on the results, we believe that it is the fastest and most accurate LA to date. Our position is that it will be very hard to beat its performance, since it has been incorporated all the salient features of the entire field of LA.

• Opalic, Sven Myrdahl; Palumbo, Fabrizio; Goodwin, Morten; Lei, Jiao; Nielsen, Henrik Kofoed & Kolhe, Mohan Lal (2023). COST-WINNERS: COST reduction WIth Neural NEtworks-based augmented Random Search for simultaneous thermal and electrical energy storage control. Journal of Energy Storage. ISSN 2352-152X. 72(B). doi: 10.1016/j.est.2023.108202. Show summary

  The combination of local renewable energy production, dynamic loads, and multiple energy storage systems with different dynamics requires sophisticated control systems to maximize the energy cost efficiency of the combined energy system. Battery and thermal energy storage systems can be combined to increase the local use of on-site renewable energy, reduce peak power demand, and exploit time-of-use energy pricing. In this paper, we focus on how the augmented random search algorithm and artificial neural networks can be used together to solve an energy cost optimization problem involving the control of a battery energy storage system and a thermal energy storage system at the same time in a smart warehouse. As part of this work, a simulated training environment made using the data from the smart warehouse’s operations. In addition to the energy storage systems, the warehouse energy system has integrated a large roof mounted photovoltaic power plant and an industrial-scale cooling system. The developed solution is able to minimize the energy costs by modulating both energy systems, depending on the situation. Additionally, when it is tested against the state-of-the-art solutions, our developed solution at worst matches performance when the alternative algorithm is allowed to increase training time by a factor of nearly three. On average, our presented solution doubles the performance of the benchmark algorithm with much less computational resource expenditure.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2023). An Interpretable Knowledge Representation Framework for Natural Language Processing with Cross-Domain Application, Advances in Information Retrieval. ECIR 2023. Springer. ISSN 978-3-031-28244-7. p. 167–181. doi: 10.1007/978-3-031-28244-7_11. Full text in Research Archive Show summary

  Data representation plays a crucial role in natural language processing (NLP), forming the foundation for most NLP tasks. Indeed, NLP performance highly depends upon the effectiveness of the preprocessing pipeline that builds the data representation. Many representation learning frameworks, such as Word2Vec, encode input data based on local contextual information that interconnects words. Such approaches can be computationally intensive, and their encoding is hard to explain. We here propose an interpretable representation learning framework utilizing Tsetlin Machine (TM). The TM is an interpretable logic-based algorithm that has exhibited competitive performance in numerous NLP tasks. We employ the TM clauses to build a sparse propositional (boolean) representation of natural language text. Each clause is a class-specific propositional rule that links words semantically and contextually. Through visualization, we illustrate how the resulting data representation provides semantically more distinct features, better separating the underlying classes. As a result, the following classification task becomes less demanding, benefiting simple machine learning classifiers such as Support Vector Machine (SVM). We evaluate our approach using six NLP classification tasks and twelve domain adaptation tasks. Our main finding is that the accuracy of our proposed technique significantly outperforms the vanilla TM, approaching the competitive accuracy of deep neural network (DNN) baselines. Furthermore, we present a case study showing how the representations derived from our framework are interpretable. (We use an asynchronous and parallel version of Tsetlin Machine: available at https://github.com/cair/PyTsetlinMachineCUDA).

• Sharif, Md Haidar; Lei, Jiao & Omlin, Christian Walter Peter (2023). Deep Crowd Anomaly Detection by Fusing Reconstruction and Prediction Networks. Electronics. ISSN 2079-9292. 12(7). doi: 10.3390/electronics12071517. Full text in Research Archive Show summary

  Abnormal event detection is one of the most challenging tasks in computer vision. Many existing deep anomaly detection models are based on reconstruction errors, where the training phase is performed using only videos of normal events and the model is then capable to estimate frame-level scores for an unknown input. It is assumed that the reconstruction error gap between frames of normal and abnormal scores is high for abnormal events during the testing phase. Yet, this assumption may not always hold due to superior capacity and generalization of deep neural networks. In this paper, we design a generalized framework (rpNet) for proposing a series of deep models by fusing several options of a reconstruction network (rNet) and a prediction network (pNet) to detect anomaly in videos efficiently. In the rNet, either a convolutional autoencoder (ConvAE) or a skip connected ConvAE (AEc) can be used, whereas in the pNet, either a traditional U-Net, a non-local block U-Net, or an attention block U-Net (aUnet) can be applied. The fusion of both rNet and pNet increases the error gap. Our deep models have distinct degree of feature extraction capabilities. One of our models (AEcaUnet) consists of an AEc with our proposed aUnet has capability to confirm better error gap and to extract high quality of features needed for video anomaly detection. Experimental results on UCSD-Ped1, UCSD-Ped2, CUHK-Avenue, ShanghaiTech-Campus, and UMN datasets with rigorous statistical analysis show the effectiveness of our models.

• Oommen, John; Omslandseter, Rebekka Olsson & Lei, Jiao (2023). The object migration automata: its field, scope, applications, and future research challenges. Pattern Analysis and Applications. ISSN 1433-7541. 26, p. 917–928. doi: 10.1007/s10044-023-01163-x. Show summary

  Partitioning, in and of itself, is an NP-hard problem. Prior to the Artificial Intelligence (AI)-based solutions, it was solved in the 1970s by optimization-based strategies. However, AI-based solutions appeared in the 1980s in a pioneering way, by using a Learning Automaton (LA)-motivated strategy known as the so-called Object Migrating Automaton (OMA). Although the OMA and its derivatives have been used in numerous applications since then, the basic kernel has remained the same. Because the number of possible partitions in a partitioning problem can be combinatorially exponential and the underlying tasks are NP-hard, the most advanced OMA algorithms could, until recently, only solve issues involving equally sized groups. Due to our recent innovations cited in the body of this paper, the enhanced OMA now also handles non-equally sized groups. Earlier, we had presented in Omslandseter (Pattern Anal Appl, 2023), a comprehensive survey of the state-of-the-art enhancements of the best-known OMA. We believe that these results will be the benchmark for a few decades and that it will be very hard to beat these results. This is a companion paper, intended to augment the contents of Omslandseter (Pattern Anal Appl, 2023). In this paper, we first discuss the OMA’s prior applications, its historical and current innovations, and the OMA-based algorithms’ relevance to societal needs. We also provide well-specified guidelines for future researchers so that they can use them for unresolved tasks, and also develop further advancements.

• Oommen, John; Omslandseter, Rebekka Olsson & Lei, Jiao (2023). Learning automata-based partitioning algorithms for stochastic grouping problems with non-equal partition sizes. Pattern Analysis and Applications. ISSN 1433-7541. 26, p. 751–772. doi: 10.1007/s10044-023-01131-5. Show summary

  It is very fascinating that the principles of Artificial Intelligence, that were proposed many decades ago, have remained to be the foundations of many of the modern-day techniques, and a brief summary of these principles is given in the paper itself. While this truism is valid for problem solving and game playing, in the context of this paper, we emphasize that it is also pertinent for the so-called partitioning problems. In this paper, we consider the general partitioning problem that has been studied for decades. Unlike the heuristic and search strategies, our attention focuses on learning automata (LA) and reinforcement learning methods, and their powerful ability to solve problems in stochastic environments. These render the latter tools to be applicable to various complex tasks. As we shall explain, LA have been employed for partitioning, and in particular, the paradigm of Object Migration Automata (OMA) has offered state-of-the-art adaptive methods for solving grouping and partitioning problems. However, because the number of possible partitions is combinatorially exponential, and of the NP-hardness of the underlying tasks, the existing state-of-the-art OMA algorithms can only solve problems of equal-sized groups. To resolve this, in this paper, we propose two new OMA variants that can solve both equally and unequally sized partitioning problems. The key here is to provide additional information to the algorithms, and in doing so, to expand the solution space. The first variant, the Greatest Common Divisor OMA (GCD-OMA), relaxes the constraint of having equally sized groups by mapping the actions onto a larger state space, and thus permitting it to solve problems where the group sizes have a GCD that is greater than unity. Subsequently, we propose a second variant named the Partition Size Required OMA (PSR-OMA) to make the algorithm more versatile. The PSR-OMA can handle groups of arbitrary sizes when the group sizes are known a priori. We demonstrate the proposed algorithms’ strength in solving stochastic grouping problems through extensive simulations, even with high noise levels. The GCD-OMA and the PSR-OMA represent the current state-of-the-art when it concerns resolving the extremely complex problem of partitioning and can be used in any of the numerous applications in which the OMA itself has been utilized .

• Omslandseter, Rebekka Olsson; Jiao, Lei; Zhang, Xuan; Yazidi, Anis & Oommen, John (2022). The Hierarchical Discrete Pursuit Learning Automaton: A Novel Scheme With Fast Convergence and Epsilon-Optimality. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X. p. 1–15. doi: 10.1109/TNNLS.2022.3226538. Full text in Research Archive
• Omslandseter, Rebekka Olsson; Jiao, Lei; Zhang, Xuan; Yazidi, Anis & Oommen, John (2022). The Hierarchical Discrete Learning Automaton Suitable for Environments with Many Actions and High Accuracy Requirements. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 13151, p. 507–518. doi: 10.1007/978-3-030-97546-3_41. Full text in Research Archive Show summary

  Since its early beginning, the paradigm of Learning Automata (LA), has attracted much interest. Over the last decades, new concepts and various improvements have been introduced to increase the LA’s speed and accuracy, including employing probability updating functions, discretizing the probability space, and implementing the “Pursuit” concept. The concept of incorporating “structure” into the ordering of the LA’s actions is one of the latest advancements to the field, leading to the ϵ-optimal Hierarchical Continuous Pursuit LA (HCPA) that has superior performance to other LA variants when the number of actions is large. Although the previously proposed HCPA is powerful, its speed has a handicap when the required action probability of an action is approaching unity. The reason for this slow convergence is that the learning parameter operates in a multiplicative manner within the probability space, making the increment of the action probability smaller as its probability becomes close to unity. Therefore, we propose the novel Hierarchical Discrete Learning Automata (HDPA) in this paper, which does not possess the same impediment as the HCPA. The proposed machine infuse the principle of discretization into the action probability vector’s updating functionality, where this type of updating is invoked recursively at every depth within a hierarchical tree structure and we pursue the best estimated action in all iterations through utilization of the Estimator phenomenon. The proposed machine is ϵ-optimal, and our experimental results demonstrate that the number of iterations required before convergence is significantly reduced for the HDPA, when compared with the HCPA.

• Omslandseter, Rebekka Olsson; Jiao, Lei & Oommen, John (2022). Enhancing the Speed of Hierarchical Learning Automata by Ordering the Actions - A Pioneering Approach. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 13728, p. 775–788. doi: 10.1007/978-3-031-22695-3_54. Show summary

  For the past six decades, the operation of Learning Automata (LA) has involved states and action probabilities. These have been central to “remembering” the quality of the actions chosen during the learning. The latest enhancements have also incorporated estimates of the actions’ reward probabilities. However, a phenomenon that has never been used to-date is that of considering how these actions themselves, can be ordered. Ordering the actions in traditional LA is rather meaningless unless one resorts to invoking the theory of Random Races [1]. However, we show that such an ordering makes sense if the automata operate hierarchically, within a tree, with the actions being placed at the leaves. In this paper, we shall show that when the LA are arranged “in a tree formation”, and when the learning is achieved within such a tree, the hierarchical LA has a superior performance if the actions located at the leaves of the tree are arranged suitably. While this concept can be incorporated in any hierarchical LA, we demonstrate its power for the most recent machine, i.e., the Hierarchical Discretized Pursuit Automaton (HDPA). These strategies can also be included in the Hierarchical Continuous Pursuit Automaton (HCPA), and to both of these which utilize traditional Maximum Likelihood (ML) or Bayesian estimates [2]. The experimental results presented here are very impressive, and so, if we consider the chronology of LA from FSSA through VSSA, the Estimator schemes, and the recent hierarchical LA, our modest claim is that the inclusion of the ADE represents the state-of-the-art which is not easily surpassed.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2022). Explainable Tsetlin Machine Framework for Fake News Detection with Credibility Score Assessment . In Calzolari, Nicoletta; Béchet, Frédéric; Blache, Philippe; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Odijk, Jan & Piperidis, Stelios (Ed.), Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association. ISSN 979-10-95546-72-6. p. 4894–4903. Show summary

  The proliferation of fake news, i.e., news intentionally spread for misinformation, poses a threat to individuals and society. Despite various fact-checking websites such as PolitiFact, robust detection techniques are required to deal with the increase in fake news. Several deep learning models show promising results for fake news classification, however, their black-box nature makes it difficult to explain their classification decisions and quality-assure the models. We here address this problem by proposing a novel interpretable fake news detection framework based on the recently introduced Tsetlin Machine (TM). In brief, we utilize the conjunctive clauses of the TM to capture lexical and semantic properties of both true and fake news text. Further, we use clause ensembles to calculate the credibility of fake news. For evaluation, we conduct experiments on two publicly available datasets, PolitiFact and GossipCop, and demonstrate that the TM framework significantly outperforms previously published baselines by at least 5% in terms of accuracy, with the added benefit of an interpretable logic-based representation. In addition, our approach provides a higher F1-score than BERT and XLNet, however, we obtain slightly lower accuracy. We finally present a case study on our model’s explainability, demonstrating how it decomposes into meaningful words and their negations.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2022). ConvTextTM: An Explainable Convolutional Tsetlin Machine Framework for Text Classification. In Calzolari, Nicoletta; Béchet, Frédéric; Blache, Philippe; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Odijk, Jan & Piperidis, Stelios (Ed.), Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association. ISSN 979-10-95546-72-6. p. 3761–3770. Show summary

  Recent advancements in natural language processing (NLP) have reshaped the industry, with powerful language models such as GPT-3 achieving superhuman performance on various tasks. However, the increasing complexity of such models turns them into “black boxes”, creating uncertainty about their internal operation and decision-making. Tsetlin Machine (TM) employs human-interpretable conjunctive clauses in propositional logic to solve complex pattern recognition problems and has demonstrated competitive performance in various NLP tasks. In this paper, we propose ConvTextTM, a novel convolutional TM architecture for text classification. While legacy TM solutions treat the whole text as a corpus-specific set-of-words (SOW), ConvTextTM breaks down the text into a sequence of text fragments. The convolution over the text fragments opens up for local position-aware analysis. Further, ConvTextTM eliminates the dependency on a corpus-specific vocabulary. Instead, it employs a generic SOW formed by the tokenization scheme of the Bidirectional Encoder Representations from Transformers (BERT) (Devlin et al., 2019a). The convolution binds together the tokens, allowing ConvTextTM to address the out-of-vocabulary problem as well as spelling errors. We investigate the local explainability of our proposed method using clause-based features. Extensive experiments are conducted on seven datasets, to demonstrate that the accuracy of ConvTextTM is either superior or comparable to state-of-the-art baselines.

• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2022). Robust Interpretable Text Classification against Spurious Correlations Using AND-rules with Negation. In de Raed, Luc (Eds.), Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. AAAI Press. ISSN 978-1-956792-00-3. p. 4439–4446. Show summary

  The state-of-the-art natural language processing models have raised the bar for excellent performance on a variety of tasks in recent years. However, concerns are rising over their primitive sensitivity to distribution biases that reside in the training and testing data. This issue hugely impacts the performance of the models when exposed to out-of-distribution and counterfactual data. The root cause seems to be that many machine learning models are prone to learn the shortcuts, modelling simple correlations rather than more fundamental and general relationships. As a result, such text classifiers tend to perform poorly when a human makes minor modifications to the data, which raises questions regarding their robustness. In this paper, we employ a rule-based architecture called Tsetlin Machine (TM) that learns both simple and complex correlations by ANDing features and their negations. As such, it generates explainable AND-rules using negated and non-negated reasoning. Here, we explore how non-negated reasoning can be more prone to distribution biases than negated reasoning. We further leverage this finding by adapting the TM architecture to mainly perform negated reasoning using the specificity parameter s. As a result, the AND-rules becomes robust to spurious correlations and can also correctly predict counterfactual data. Our empirical investigation of the model’s robustness uses the specifcity s to control the degree of negated reasoning. Experiments on publicly available Counterfactually-Augmented Data demonstrate that the negated clauses are robust to spurious correlations and outperform Naive Bayes, SVM, and Bi-LSTM by up to 20%, and ELMo by almost 6% on counterfactual test data.

• Oommen, John; Zhang, Xuan & Lei, Jiao (2022). A Comprehensive Survey of Estimator Learning Automata and Their Recent Convergence Results. Lecture Notes in Networks and Systems. ISSN 2367-3370. 289, p. 33–52. doi: 10.1007/978-3-030-87049-2_2. Show summary

  The pre-cursor field to Reinforcement Learning is that of Learning Automata (LA). Within this field, Estimator Algorithms (EAs) can be said to be the state-of-the-art. Further, the subset of Pursuit Algorithms (PAs), discovered by Thathachar and Sastry [34, 39], were the pioneering schemes. This chapter contains a comprehensive survey of the various EAs, and the most recent convergence results for PAs. Unlike the prior LA, EAs are based on a fundamentally distinct phenomenon. They are also the most accurate LA, converging in the least time. EAs operate on two vectors, namely, the action probability vector which is updated using responses from the Environment, and quickly-computed estimates of the reward probabilities of the various actions. The proofs that they are ε-optimal is thus very complex. They have to incorporate two rather snon-orthogonal phenomena, which are the convergence of these estimates and the convergence of the probabilities of selecting the various actions. For almost three decades, the reported proofs of PAs possessed an infirmity (or flaw), which we refer to as the claim of the “monotonicity” property. This flaw was discovered by the authors of [37], who also provided an alternate proof for a specific PA where the scheme’s parameter decreased with time. This paper first records all the reported EAs. It then reports a comprehensive survey of the proofs from a different perspective. These proofs have not required that the sequence of action probabilities of selecting the optimal action satisfies the property of monotonicity. On the other hand, whenever any action probability is close enough to unity, we require that the process jumps to an absorbing barrier at the next time instant, i.e., in a single step. By requiring such a constraint, these proofs invoke the weaker property, i.e., the submartinagale property of pm(t), to demonstrate the ε-optimality. We have thus proven the ε-optimality for the Absorbing CPA [49, 50], the Discretized PA [51, 52], and for the family of Bayesian PA [53], where the estimates are obtained by a Bayesian (rather than a Maximum Likelihood (ML)) process.

• Fei, Zixuan; Wang, Ying; Zhao, Junwei; Wang, Xue & Lei, Jiao (2022). Joint Computational and Wireless Resource Allocation in Multicell Collaborative Fog Computing Networks. IEEE Transactions on Wireless Communications. ISSN 1536-1276. 21(11), p. 9155–9169. doi: 10.1109/TWC.2022.3173365. Show summary

  In 6G and future networks, joint optimization of communication and computational resources lays the foundation for various delay-sensitive intelligent IoT services in the fog computing architecture. In this paper, we present a multi-device collaborative computing architecture in the cell association environment to accelerate the processing procedure of data generated by smart IoT devices. In this scenario, a two-tier task scheduling scheme and an uplink and downlink power allocation factor are jointly optimized to reduce the data processing delay and improve fairness among different users, which is in nature a hard problem due to a series of non-convex constraints. To make the problem tractable, the problem is transformed into a smooth non-convex problem with the introduction of auxiliary variables and then decoupled into two subproblems based on the data transmission and processing procedure. Thereafter, different methods such as Successive Convex Approximation (SCA) and Block Successive Upperbound Minimization (BSUM) are employed to reconstruct several upper-bound convex optimization subproblems. Besides, a fast 0–1 binary offloading scheme is proposed based on the original algorithm. Finally, the simulation results depict the effectiveness of the proposed algorithms in detail, and the scalability of the system is also examined.

• Opalic, Sven Myrdahl; Goodwin, Morten; Lei, Jiao; Nielsen, Henrik Kofoed & Kolhe, Mohan Lal (2022). Augmented Random Search with Artificial Neural Networks for energy cost optimization with battery control. Journal of Cleaner Production. ISSN 0959-6526. 380(2). doi: 10.1016/j.jclepro.2022.134676.
• Lei, Jiao; Zhang, Xuan; Granmo, Ole-Christoffer & Abeyrathna, Kuruge Darshana (2022). On the Convergence of Tsetlin Machines for the XOR Operator. IEEE Transactions on Pattern Analysis and Machine Intelligence. ISSN 0162-8828. 45(5), p. 6072–6085. doi: 10.1109/TPAMI.2022.3203150. Full text in Research Archive Show summary

  The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks. Although numerous papers explore the TM empirically, many of its properties have not yet been analyzed mathematically. In this article, we analyze the convergence of the TM when input is non-linearly related to output by the XOR-operator. Our analysis reveals that the TM, with just two conjunctive clauses, can converge almost surely to reproducing XOR, learning from training data over an infinite time horizon. Furthermore, the analysis shows how the hyper-parameter T guides clause construction so that the clauses capture the distinct sub-patterns in the data. Our analysis of convergence for XOR thus lays the foundation for analyzing other more complex logical expressions. These analyses altogether, from a mathematical perspective, provide new insights on why TMs have obtained the state-of-the-art performance on several pattern recognition problems.

• Jenul, Anna Selina; Bhattarai, Bimal; Liland, Kristian Hovde; Lei, Jiao; Schrunner, Stefan & Futsæther, Cecilia Marie [Show all 8 contributors for this article] (2022). Component Based Pre-filtering of Noisy Data for Improved Tsetlin Machine Modelling. In Shafik, Rishad (Eds.), 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE conference proceedings. ISSN 978-1-6654-7116-9. p. 57–64. doi: 10.1109/ISTM54910.2022.00019. Show summary

  Tabular data with few observations and many features are common in the healthcare domain. With its rule-based approach to data modelling, the Tsetlin Machine has considerable potential to be a valuable tool in healthcare data analysis by providing interpretability to medical personnel. However, the performance of Tsetlin Machine models may be hampered by the presence of noise, which may often be the case with healthcare data due to individual differences across patients. This study shows that intelligent pre-filtering of healthcare measurement data using so-called component-based methods, such as Principal Component Analysis or Partial Least Squares Regression, can be beneficial for the performance of Tsetlin Machines. Modelling four healthcare data sets shows that the Tsetlin Machine achieved better predictive performance on pre-filtered data for data sets with high features-to-observations ratios.

• Tunheim, Svein Anders; Lei, Jiao; Shafik, Rishad Ahmed; Yakovlev, Alexandre & Granmo, Ole-Christoffer (2022). A Convolutional Tsetlin Machine-based Field Programmable Gate Array Accelerator for Image Classification. In Shafik, Rishad (Eds.), 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE conference proceedings. ISSN 978-1-6654-7116-9. p. 21–28. doi: 10.1109/ISTM54910.2022.00013. Show summary

  This paper presents a Field Programmable Gate Array (FPGA) implementation of an image classification accelerator based on the Convolutional Tsetlin Machine (CTM). The work is a concept design, and the solution demonstrates recognition of two classes in 4 × 4 images with a 2 × 2 convolution window. More specifically, there are two sub-Tsetlin Machines (TMs), one per class. A single sub-TM employs 40 clauses, each controlled by 20 Tsetlin Automata. The accelerator features random patch selection, in parallel for all clauses, based on reservoir sampling. The design is implemented in a Xilinx Zync XC7Z020 FPGA. With an operating clock speed of 30 MHz, the accelerator is capable of inferring at the rate of 3.3 million images per second with an additional power consumption of 20 mW from idle mode. The average test accuracy is 96.7% when trained on data with 10% noise. A training session with 100 epochs and 8192 examples takes 1.5 seconds. Due to the limited hardware resources required, the CTM accelerator represents a promising concept for online learning in energy-frugal systems. The solution can be scaled to multi-class systems and larger images.

• Tunheim, Svein Anders; Yadav, Rohan Kumar; Lei, Jiao; Shafik, Rishad & Granmo, Ole-Christoffer (2022). Cyclostationary Random Number Sequences for the Tsetlin Machine. In Fournier-Viger, Philippe; Fujita, Hamido; Ali, Moonis & Wang, Yinglin (Ed.), Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence. 35th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2022, Kitakyushu, Japan, July 19–22, 2022, Proceedings. Springer. ISSN 978-3-031-08529-1. p. 844–856. doi: https:/doi.org/10.1007/978-3-031-08530-7_71. Full text in Research Archive Show summary

  The Tsetlin Machine (TM) constitutes an emerging machine learning algorithm that has shown competitive performance on several benchmarks. The underlying concept of the TM is propositional logic determined by a group of finite state machines that learns patterns. Thus, TM-based systems naturally lend themselves to low-power operation when implemented in hardware for micro-edge Internet-of-Things applications. An important aspect of the learning phase of TMs is stochasticity. For low-power integrated circuit implementations the random number generation must be carried out efficiently. In this paper, we explore the application of pre-generated cyclostationary random number sequences for TMs. Through experiments on two machine learning problems, i.e., Binary Iris and Noisy XOR, we demonstrate that the accuracy is on par with standard TM. We show that through exploratory simulations the required length of the sequences that meets the conflicting tradeoffs can be suitably identified. Furthermore, the TMs achieve robust performance against reduced resolution of the random numbers. Finally, we show that maximum-length sequences implemented by linear feedback shift registers are suitable for generating the required random numbers.

• Omslandseter, Rebekka Olsson; Lei, Jiao; Liu, Yuanwei & Oommen, John (2022). User grouping and power allocation in NOMA systems: a novel semi-supervised reinforcement learning-based solution. Pattern Analysis and Applications. ISSN 1433-7541. doi: 10.1007/s10044-022-01091-2. Full text in Research Archive Show summary

  In this paper, we present a pioneering solution to the problem of user grouping and power allocation in non-orthogonal multiple access (NOMA) systems. The problem is highly pertinent because NOMA is a well-recognized technique for future mobile radio systems. The salient and difficult issues associated with NOMA systems involve the task of grouping users together into the pre-specified time slots, which are augmented with the question of determining how much power should be allocated to the respective users. This problem is, in and of itself, NP-hard. Our solution is the first reported reinforcement learning (RL)-based solution, which attempts to resolve parts of this issue. In particular, we invoke the object migration automaton (OMA) and one of its variants to resolve the grouping in NOMA systems. Furthermore, unlike the solutions reported in the literature, we do not assume prior knowledge of the channels’ distributions, nor of their coefficients, to achieve the grouping/partitioning. Thereafter, we use the consequent groupings to heuristically infer the power allocation. The simulation results that we have obtained confirm that our learning scheme can follow the dynamics of the channel coefficients efficiently, and that the solution is able to resolve the issue dynamically.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2022). Word-level human interpretable scoring mechanism for novel text detection using Tsetlin Machines. Applied intelligence (Boston). ISSN 0924-669X. doi: 10.1007/s10489-022-03281-1. Full text in Research Archive Show summary

  Recent research in novelty detection focuses mainly on document-level classification, employing deep neural networks (DNN). However, the black-box nature of DNNs makes it difficult to extract an exact explanation of why a document is considered novel. In addition, dealing with novelty at the word level is crucial to provide a more fine-grained analysis than what is available at the document level. In this work, we propose a Tsetlin Machine (TM)-based architecture for scoring individual words according to their contribution to novelty. Our approach encodes a description of the novel documents using the linguistic patterns captured by TM clauses. We then adapt this description to measure how much a word contributes to making documents novel. Our experimental results demonstrate how our approach breaks down novelty into interpretable phrases, successfully measuring novelty.

• Goodwin, Morten; Halvorsen, Kim Aleksander Tallaksen; Jiao, Lei; Knausgård, Kristian Muri; Martin, Angela Helen & Moyano, Marta [Show all 10 contributors for this article] (2022). Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook. ICES Journal of Marine Science. ISSN 1054-3139. 79(2), p. 319–336. doi: 10.1093/icesjms/fsab255. Full text in Research Archive Show summary

  The deep learning (DL) revolution is touching all scientific disciplines and corners of our lives as a means of harnessing the power of big data. Marine ecology is no exception. New methods provide analysis of data from sensors, cameras, and acoustic recorders, even in real time, in ways that are reproducible and rapid. Off-the-shelf algorithms find, count, and classify species from digital images or video and detect cryptic patterns in noisy data. These endeavours require collaboration across ecological and data science disciplines, which can be challenging to initiate. To promote the use of DL towards ecosystem-based management of the sea, this paper aims to bridge the gap between marine ecologists and computer scientists. We provide insight into popular DL approaches for ecological data analysis, focusing on supervised learning techniques with deep neural networks, and illustrate challenges and opportunities through established and emerging applications of DL to marine ecology. We present case studies on plankton, fish, marine mammals, pollution, and nutrient cycling that involve object detection, classification, tracking, and segmentation of visualized data. We conclude with a broad outlook of the field’s opportunities and challenges, including potential technological advances and issues with managing complex data sets.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Jiao, Lei (2021). A Tsetlin Machine Framework for Universal Outlier and Novelty Detection, Proceedings of the 13th International Conference on Agents and Artificial Intelligence (ICAART 2021). SciTePress. ISSN 978-989-758-484-8. doi: 10.1007/978-3-031-10161-8_14.
• Abeyrathna, Kuruge Darshana; Bhattarai, Bimal; Goodwin, Morten; Gorji, Saeed Rahimi; Granmo, Ole-Christoffer & Lei, Jiao [Show all 8 contributors for this article] (2021). Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling. Proceedings of Machine Learning Research (PMLR). ISSN 2640-3498. Full text in Research Archive Show summary

  Using logical clauses to represent patterns, Tsetlin Machine (TM) have recently obtained competitive performance in terms of accuracy, memory footprint, energy, and learning speed on several benchmarks. Each TM clause votes for or against a particular class, with classification resolved using a majority vote. While the evaluation of clauses is fast, being based on binary operators, the voting makes it necessary to synchronize the clause evaluation, impeding parallelization. In this paper, we propose a novel scheme for desynchronizing the evaluation of clauses, eliminating the voting bottleneck. In brief, every clause runs in its own thread for massive native parallelism. For each training example, we keep track of the class votes obtained from the clauses in local voting tallies. The local voting tallies allow us to detach the processing of each clause from the rest of the clauses, supporting decentralized learning. This means that the TM most of the time will operate on outdated voting tallies. We evaluated the proposed parallelization across diverse learning tasks and it turns out that our decentralized TM learning algorithm copes well with working on outdated data, resulting in no significant loss in learning accuracy. Furthermore, we show that the approach provides up to 50 times faster learning. Finally, learning time is almost constant for reasonable clause amounts (employing from 20 to 7,000 clauses on a Tesla V100 GPU). For sufficiently large clause numbers, computation time increases approximately proportionally. Our parallel and asynchronous architecture thus allows processing of more massive datasets and operating with more clauses for higher accuracy.

• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Enhancing Interpretable Clauses Semantically using Pretrained Word Representation, Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP . Association for Computational Linguistics. ISSN 978-1-955917-06-3. p. 265–274. doi: 10.18653/v1/2021.blackboxnlp-1.19.
• Abeyrathna, Kuruge Darshana; Granmo, Ole-Christoffer; Shafik, Rishad; Lei, Jiao; Wheeldon, Adrian & Yakovlev, Alex [Show all 8 contributors for this article] (2021). A multi-step finite-state automaton for arbitrarily deterministic Tsetlin Machine learning. Expert Systems. ISSN 0266-4720. doi: 10.1111/exsy.12836. Full text in Research Archive
• Omslandseter, Rebekka Olsson; Jiao, Lei & Oommen, John (2021). Object Migration Automata for Non-equal Partitioning Problems with Known Partition Sizes. IFIP Advances in Information and Communication Technology. ISSN 1868-4238. doi: 10.1007/978-3-030-79150-6_11. Full text in Research Archive
• Omslandseter, Rebekka Olsson; Jiao, Lei & Oommen, John (2021). A Learning-Automata Based Solution for Non-equal Partitioning: Partitions with Common GCD Sizes. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 12799, p. 227–239. doi: 10.1007/978-3-030-79463-7_19. Full text in Research Archive
• Abbas, Ziaul Haq; Ali, Zaiwar; Abbas, Ghulam; Lei, Jiao; Bilal, Muhammad & Suh, Doug-Young [Show all 7 contributors for this article] (2021). Computational Offloading in Mobile Edge with Comprehensive and Energy Efficient Cost Function: A Deep Learning Approach . Sensors. ISSN 1424-8220. 21(10), p. 1–18. doi: 10.3390/s21103523. Full text in Research Archive
• Nunavath, Vimala; Johansen, Sahand; Johannessen, Tommy Sandtorv; Jiao, Lei; Hansen, Bjørge Hermann & Berntsen, Sveinung [Show all 7 contributors for this article] (2021). Deep Learning for Classifying Physical Activities from Accelerometer Data. Sensors. ISSN 1424-8220. 21(16). doi: 10.3390/s21165564. Full text in Research Archive
• Zhang, Xuan; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). On the convergence of Tsetlin machines for the IDENTITY- and NOT operators. IEEE Transactions on Pattern Analysis and Machine Intelligence. ISSN 0162-8828. 44(10), p. 6345–6359. doi: 10.1109/TPAMI.2021.3085591.
• Chen, Yuanbin; Wang, Ying & Lei, Jiao (2021). Robust Transmission for Reconfigurable Intelligent Surface Aided Millimeter Wave Vehicular Communications with Statistical CSI. IEEE Transactions on Wireless Communications. ISSN 1536-1276. doi: 10.1109/TWC.2021.3100492.
• Knausgård, Kristian Muri; Wiklund, Arne; Sørdalen, Tonje Knutsen; Halvorsen, Kim Tallaksen; Kleiven, Alf Ring & Lei, Jiao [Show all 7 contributors for this article] (2021). Temperate fish detection and classification: a deep learning based approach. Applied intelligence (Boston). ISSN 0924-669X. doi: 10.1007/s10489-020-02154-9. Full text in Research Archive
• Yadav, Rohan Kumar; Lei, Jiao; Goodwin, Morten & Granmo, Ole-Christoffer (2021). Positionless aspect based sentiment analysis using attention mechanism. Knowledge-Based Systems. ISSN 0950-7051. 226. doi: 10.1016/j.knosys.2021.107136. Full text in Research Archive
• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Human-Level Interpretable Learning for Aspect-Based Sentiment Analysis . Proceedings of the AAAI Conference on Artificial Intelligence. ISSN 2159-5399. p. 14203–14212. Show summary

  This paper proposes human-interpretable learning of aspect-based sentiment analysis (ABSA), employing the recently introduced Tsetlin Machines (TMs). We attain interpretability by converting the intricate position-dependent textual semantics into binary form, mapping all the features into bag-of-words (BOWs). The binary form BOWs are encoded so that the information on the aspect and context words are nearly lossless for sentiment classification. We further adapt the BOWs as input to the TM, enabling learning of aspect-based sentiment patterns in propositional logic. To evaluate interpretability and accuracy, we conducted experiments on two widely used ABSA datasets of SemEval 2014: Restaurant 14 and Laptop 14. The experiments show how each relevant feature takes part in conjunctive clauses that contain the context information for the corresponding aspect word, demonstrating human-level interpretability. At the same time, the obtained accuracy is competitive with existing neural network models, reaching 78.02% on Restaurant 14 and 73.51% on Laptop 14.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Jiao, Lei (2021). Measuring the Novelty of Natural Language Text using the Conjunctive Clauses of a Tsetlin Machine Text Classifier, Proceedings of the 13th International Conference on Agents and Artificial Intelligence (ICAART 2021). SciTePress. ISSN 978-989-758-484-8. p. 410–417. doi: 10.5220/0010382204100417.
• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Interpretability in Word Sense Disambiguation using Tsetlin Machine, Proceedings of the 13th International Conference on Agents and Artificial Intelligence (ICAART 2021). SciTePress. ISSN 978-989-758-484-8. p. 402–409. doi: 10.5220/0010382104020409.
• Ali, Zaiwar; Khaf, Sadia; Abbas, Ziaul Haq; Abbas, Ghulam; Lei, Jiao & Irshad, Amna [Show all 8 contributors for this article] (2021). A Comprehensive Utility Function for Resource Allocation in Mobile Edge Computing. Computers, Materials and Continua (CMC). ISSN 1546-2218. 66(2), p. 1461–1477. doi: 10.32604/cmc.2020.013743.
• Xiao, Xiang; Zeng, Fanzi; Hu, Zhenzhen & Lei, Jiao (2020). Dynamic Flow-Adaptive Spectrum Leasing with Channel Aggregation in Cognitive Radio Networks. Sensors. ISSN 1424-8220. 20(13). doi: 10.3390/s20133800. Full text in Research Archive
• Li, Zhijiang; Zheng, Yingping; Cao, Liqin; Lei, Jiao; Zhong, Yanfei & Zhang, Caiyi (2020). A Student's t‐based density peaks clustering with superpixel segmentation (tDPCSS) method for image color clustering. Color Research and Application. ISSN 0361-2317. 45(4), p. 656–670. doi: 10.1002/col.22491.
• Chen, Yuanbin; Wang, Ying; Liu, Man; Zhang, Jiayi & Lei, Jiao (2020). Network Slicing Enabled Resource Management for Service-Oriented Ultra-Reliable and Low-Latency Vehicular Networks. IEEE Transactions on Vehicular Technology. ISSN 0018-9545. 69(7), p. 7847–7862. doi: 10.1109/TVT.2020.2991723. Full text in Research Archive
• Opalic, Sven Myrdahl; Goodwin, Morten; Lei, Jiao; Nielsen, Henrik Kofoed & Kolhe, Mohan Lal (2020). A Deep Reinforcement Learning scheme for Battery Energy Management. In Solic, P (Eds.), 2020 5th International Conference on Smart and Sustainable Technologies (SpliTech). IEEE Press. ISSN 978-953290105-4. p. 1–6. doi: 10.23919/SpliTech49282.2020.9243797.
• Yang, Zhong; Liu, Yuanwei; Chen, Yue & Lei, Jiao (2020). Learning Automata Based Q-Learning for Content Placement in Cooperative Caching. IEEE Transactions on Communications. ISSN 0090-6778. 68(6), p. 3667–3680. doi: 10.1109/TCOMM.2020.2982136. Full text in Research Archive
• Ullah, Arif; Haq Abbas, Ziaul; Muhammad, Fazal; Abbas, Ghulam & Lei, Jiao (2020). Capacity driven small cell deployment in heterogeneous cellular networks: Outage probability and rate coverage analysis. Transactions on Emerging Telecommunications Technologies. ISSN 1124-318X. 31(6), p. 1–21. doi: 10.1002/ett.3876. Full text in Research Archive
• Ullah, Arif; Haq, Abbas; Abbas, Ghulam; Muhammad, Fazal & Lei, Jiao (2020). Performance analysis of user-centric SBS deployment with load balancing in heterogeneous cellular networks: A Thomas cluster process approach. Computer Networks. ISSN 1389-1286. 170, p. 1–14. doi: 10.1016/j.comnet.2020.107120. Full text in Research Archive
• Omslandseter, Rebekka Olsson; Lei, Jiao; Liu, Yuanwei & Oommen, John (2020). User Grouping and Power Allocation in NOMA Systems: A Reinforcement Learning-Based Solution, Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices.. Springer Nature. ISSN 978-3-030-55789-8. p. 299–311. doi: 10.1007/978-3-030-55789-8_27. Full text in Research Archive
• Yadav, Rohan Kumar; Bhattarai, Bimal; Lei, Jiao; Goodwin, Morten & Granmo, Ole-Christoffer (2020). Indoor Space Classification Using Cascaded LSTM. IEEE Conference on Industrial Electronics and Applications. ISSN 2158-2297. p. 1110–1114. doi: 10.1109/ICIEA48937.2020.9248347. Full text in Research Archive Show summary

  Indoor space classification is an important part of localization that helps in precise location extraction, which has been extensively utilized in industrial and domestic domain. There are various approaches that employ Bluetooth Low Energy (BLE), Wi-Fi, magnetic field, object detection, and Ultra Wide Band (UWB) for indoor space classification purposes. Many of the existing approaches need extensive pre-installed infrastructure, making the cost higher to obtain reasonable accuracy. Therefore, improvements are still required to increase the accuracy with minimum requirements of infrastructure. In this paper, we propose an approach to classify the indoor space using geomagnetic field (GMF) and radio signal strength (RSS) as the identity. The indoor space is an open big test bed divided into different indiscernible subspace. We collect GMF and RSS at each subspace and classify it using cascaded Long Short Term Memory (LSTM). The experimental results show that the accuracy is significantly improved when GMF and RSS are combined to make distinct features. In addition, we compare the performance of the proposed model with the state-of-the-art machine learning methods.

• Opalic, Sven Myrdahl; Goodwin, Morten; Lei, Jiao; Nielsen, Henrik Kofoed; Pardiñas, Ángel Á. & Hafner, Armin [Show all 7 contributors for this article] (2020). ANN modelling of CO2 refrigerant cooling system COP in a smart warehouse. Journal of Cleaner Production. ISSN 0959-6526. 260, p. 1–10. doi: 10.1016/j.jclepro.2020.120887. Full text in Research Archive
• Abeyrathna, Kuruge Darshana; Granmo, Ole-Christoffer; Zhang, Xuan; Lei, Jiao & Goodwin, Morten (2019). The regression Tsetlin machine: a novel approach to interpretable nonlinear regression. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. ISSN 1364-503X. doi: 10.1098/rsta.2019.0165. Full text in Research Archive
• Zaiwar, Ali; Lei, Jiao; Baker, Thar; Abbas, Ghulam; Abbas, Ziaul Haq & Khaf, Sadia (2019). A Deep Learning Approach for Energy Efficient Computational Offloading in Mobile Edge Computing. IEEE Access. ISSN 2169-3536. 7(1), p. 149623–1496633. doi: 10.1109/ACCESS.2019.2947053. Full text in Research Archive Show summary

  Mobile edge computing (MEC) has shown tremendous potential as a means for computationally intensive mobile applications by partially or entirely offloading computations to a nearby server to minimize the energy consumption of user equipment (UE). However, the task of selecting an optimal set of components to offload considering the amount of data transfer as well as the latency in communication is a complex problem. In this paper, we propose a novel energy-efficient deep learning based offloading scheme (EEDOS) to train a deep learning based smart decision-making algorithm that selects an optimal set of application components based on remaining energy of UEs, energy consumption by application components, network conditions, computational load, amount of data transfer, and delays in communication. We formulate the cost function involving all aforementioned factors, obtain the cost for all possible combinations of component offloading policies, select the optimal policies over an exhaustive dataset, and train a deep learning network as an alternative for the extensive computations involved. Simulation results show that our proposed model is promising in terms of accuracy and energy consumption of UEs.

• Yazidi, Anis; Zhang, Xuan; Lei, Jiao & Oommen, John (2019). The Hierarchical Continuous Pursuit Learning Automation: A Novel Scheme for Environments With Large Numbers of Actions. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X. doi: 10.1109/TNNLS.2019.2905162. Full text in Research Archive
• Li, Zhijiang; Zhu, Haonan; Cao, Liqin; Lei, Jiao; Zhong, Yanfei & Ma, Ailong (2019). Face Inpainting via Nested Generative Adversarial Networks. IEEE Access. ISSN 2169-3536. 7, p. 155462–155471. doi: 10.1109/ACCESS.2019.2949614. Full text in Research Archive
• Li, Zhijiang; Tan, Zhenshan; Cao, Liqin; Chen, Hu; Lei, Jiao & Zhong, Yanfei (2019). Directive local color transfer based on dynamic look-up table. Signal processing. Image communication. ISSN 0923-5965. 79, p. 1–12. doi: 10.1016/j.image.2019.06.010. Full text in Research Archive
• Granmo, Ole-Christoffer; Glimsdal, Sondre; Lei, Jiao; Goodwin, Morten; Omlin, Christian & Berge, Geir Thore (2019). The Convolutional Tsetlin Machine. arXiv.org. ISSN 2331-8422.
• Berge, Geir Thore; Granmo, Ole-Christoffer; Tveit, Tor Oddbjørn; Goodwin, Morten; Lei, Jiao & Matheussen, Bernt Viggo (2019). Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization With Medical Applications. IEEE Access. ISSN 2169-3536. 7. doi: 10.1109/ACCESS.2019.2935416. Full text in Research Archive
• Abeyrathna, Kuruge Darshana; Granmo, Ole-Christoffer; Lei, Jiao & Goodwin, Morten (2019). The Regression Tsetlin Machine: A Tsetlin Machine for Continuous Output Problems. In Moura Oliveira, P (Eds.), Progress in Artificial Intelligence. EPIA 2019. Springer. ISSN 978-3-030-30244-3. p. 268–280. doi: 10.1007/978-3-030-30244-3_23.
• Olsvik, Erlend; Trinh, Christian M.D.; Knausgård, Kristian Muri; Wiklund, Arne; Sørdalen, Tonje Knutsen & Kleiven, Alf Ring [Show all 8 contributors for this article] (2019). Biometric fish classification of temperate species using convolutional neural network with squeeze-and-excitation. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 11606 LNAI, p. 89–101. doi: 10.1007/978-3-030-22999-3_9. Full text in Research Archive
• Opalic, Sven Myrdahl; Goodwin, Morten; Lei, Jiao; Nielsen, Henrik Kofoed & Kolhe, Mohan Lal (2019). Modelling of Compressors in an Industrial CO 2-Based Operational Cooling System Using ANN for Energy Management Purposes, Engineering Applications of Neural Networks. EANN 2019.. Springer. ISSN 978-3-030-20256-9. doi: 10.1007/978-3-030-20257-6_4. Show summary

  Large scale cooling installations usually have high energy consumption and fluctuating power demands. There are several ways to control energy consumption and power requirements through intelligent energy and power management, such as utilizing excess heat, thermal energy storage and local renewable energy sources. Intelligent energy and power management in an operational setting is only possible if the time-varying performance of the individual components of the energy system is known. This paper presents an approach to model the compressors in an industrial, operational two-stage cooling system, with CO 2 as the working fluid, located in an advanced food distribution warehouse in Norway. An artificial neural network is adopted to model the compressors using the operational data. The model is trained with cooling medium evaporation and condensation temperature, suction gas temperature and compressor operating frequency, and outputs electrical power load and cooling load. The best results are found by using a single hidden layer with 45 hidden neurons and a hyperbolic tangent activation function trained with the Adam optimizer, with a resulting mean squared error as low as 0.08% for both the training and validation data sets. The trained model will be part of a system implemented in a real-world setting to determine the cooling load, compressor power load, and coefficient of performance. An intelligent energy management system will utilize the model for energy and power optimization of the cooling system by storing energy in a thermal energy storage, using predictions of energy demand and cooling system performance.

• Zhang, Xuan; Jiao, Lei; Oommen, John & Granmo, Ole-Christoffer (2019). A Conclusive Analysis of the Finite-Time Behavior of the Discretized Pursuit Learning Automaton. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X. doi: 10.1109/TNNLS.2019.2900639. Full text in Research Archive Show summary

  This paper deals with the finite-time analysis (FTA) of learning automata (LA), which is a topic for which very little work has been reported in the literature. This is as opposed to the asymptotic steady-state analysis for which there are, probably, scores of papers. As clarified later, unarguably, the FTA of Markov chains, in general, and of LA, in particular, is far more complex than the asymptotic steady-state analysis. Such an FTA provides rigid bounds for the time required for the LA to attain to a given convergence accuracy. We concentrate on the FTA of the Discretized Pursuit Automaton (DPA), which is probably one of the fastest and most accurate reported LA. Although such an analysis was carried out many years ago, we record that the previous work is flawed. More specifically, in all brevity, the flaw lies in the wrongly ``derived'' monotonic behavior of the LA after a certain number of iterations. Rather, we claim that the property should be invoked is the submartingale property. This renders the proof to be much more involved and deep. In this paper, we rectify the flaw and reestablish the FTA based on such a submartingale phenomenon. More importantly, from the derived analysis, we are able to discover and clarify, for the first time, the underlying dilemma between the DPA's exploitation and exploration properties. We also nontrivially confirm the existence of the optimal learning rate, which yields a better comprehension of the DPA itself.

• Omslandseter, Rebekka Olsson; Lei, Jiao & Haglund, Magne Arild (2019). Field Measurements and Parameter Calibrations of Propagation Model for Digital Audio Broadcasting in Norway. IEEE Vehicular Technology Conference (VTC). ISSN 1090-3038. doi: 10.1109/VTCFall.2018.8690746. Full text in Research Archive
• Naushad, Alamgir; Abbas, Ghulam; Abbas, Ziaul Haq; Lei, Jiao & Muhammad, Fazal (2019). A Novel Faster Failure Detection Strategy for Link Connectivity using Hello Messaging in Mobile Ad Hoc Networks. International Journal of Ad Hoc and Ubiquitous Computing. ISSN 1743-8225. 32(2), p. 75–98. doi: 10.1504/IJAHUC.2019.102451.
• Jordbru, Thomas; Lei, Jiao & Cenkeramaddi, Linga Reddy (2018). UDP flows in Cognitive Radios with Channel Aggregation and Fragmentation: A Test-bed Based Evaluation, 2018 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS). IEEE conference proceedings. ISSN 978-1-5386-8134-3. p. 1–4. doi: 10.1109/ANTS.2018.8710082. Show summary

  Channel aggregation (CA) and channel fragmentation (CF) have been studied extensively in cognitive radios (CRs) for many years. However, a test-bed evaluation for such techniques at flow level is still open. In this study, employing National Instruments devices, a test-bed is set up to evaluate the performance of UDP flows for CRs with CA and CF, considering the aspects of blocking, preemption, and throughput in probability. The measurements clearly show that there are performance improvements in applying CA and CF in CRs for UDP flows.

• Meng, Sachula; Wang, Ying; Lei, Jiao; Miao, Zhongyu & Sun, Kai (2018). Hierarchical evolutionary game based dynamic cloudlet selection and bandwidth allocation for mobile cloud computing environment. IET Communications. ISSN 1751-8628. 13(1), p. 16–25. doi: 10.1049/iet-com.2018.5100.
• Naushad, Alamgir; Abbas, Ghulam; Abbas, Ziaul Haq; Lei, Jiao & Muhammad, Fazal (2018). A Novel Dynamic Link Connectivity Strategy Using Hello Messaging for Maintaining Link Stability in MANETs. Wireless Communications & Mobile Computing. ISSN 1530-8669. 2018, p. 1–23. doi: 10.1155/2018/3780534.
• Albrigtsen, Svein Inge; Imenes, Alexander; Goodwin, Morten; Lei, Jiao & Nunavath, Vimala (2018). Neuroevolution of Actively Controlled Virtual Characters - An Experiment for an Eight-Legged Character, 19th International Conference on Engineering Applications of Neural Networks. Springer Publishing Company. ISSN 978-3-319-98203-8. p. 94–105. doi: 10.1007/978-3-319-98204-5_8. Full text in Research Archive
• Yazidi, Anis; Zhang, Xuan; Lei, Jiao & Oommen, John (2018). The Hierarchical Continuous Pursuit Learning Automation for Large Numbers of Actions. In Lazaros, Iliadis (Eds.), Artificial Intelligence Applications and Innovations. Springer. ISSN 978-3-319-92006-1. p. 451–461. doi: 10.1007/978-3-319-92007-8_38. Full text in Research Archive
• Zeng, Fanzi; Xu, Jisheng; Li, Yongfeng; Li, Kang & Lei, Jiao (2018). Performance analysis of underlay two-way relay cooperation in cognitive radio networks with energy harvesting. Computer Networks. ISSN 1389-1286. 142, p. 13–23. doi: 10.1016/j.comnet.2018.05.023. Full text in Research Archive
• Pervez, Muhammad Mussawer; Abbas, Ziaul Haq; Muhammad, Fazal & Lei, Jiao (2017). Location-Based Coverage and Capacity Analysis of a Two Tier HetNet. IET Communications. ISSN 1751-8628. 11(7), p. 1067–1073. doi: 10.1049/iet-com.2016.1244.
• Zhang, Min & Lei, Jiao (2017). On the Performance of Multiplexing Real-Time VBR Traffic with Multiple Hysteresis Areas, 23th European Wireless Conference; Proceedings of European Wireless 2017. IEEE conference proceedings. ISSN 978-3-8007-4426-8.
• Cao, Liqin; Lei, Jiao & Li, Zhijiang (2017). Image Colorization Method Using Texture Descriptors and ISLIC Segmentation, Advanced Graphic Communications and Media Technologies. Springer. ISSN 978-981-10-3529-6. doi: 10.1007/978-981-10-3530-2_2.
• Cao, Liqin; Lei, Jiao; Li, Zhijiang; TingTing, Liu & Zhong, Yanfei (2017). Grayscale image colorization using an adaptive weighted average method. Journal of Imaging Science and Technology. ISSN 1062-3701. 61(6). doi: 10.2352/J.ImagingSci.Technol.2017.61.6.060502.
• Thapa, Rajan; Lei, Jiao; Oommen, John & Yazidi, Anis (2017). A learning automaton-based scheme for scheduling domestic shiftable loads in smart grids. IEEE Access. ISSN 2169-3536. 6, p. 5348–5361. doi: 10.1109/ACCESS.2017.2788051. Full text in Research Archive
• Abbas, Ziaul Haq; Muhammad, Fazal & Lei, Jiao (2017). Analysis of load balancing and interference management in heterogeneous cellular networks. IEEE Access. ISSN 2169-3536. 5, p. 14690–14705. doi: 10.1109/ACCESS.2017.2732498. Full text in Research Archive
• Thapa, Rajan; Lei, Jiao; Oommen, John & Yazidi, Anis (2017). Scheduling domestic shiftable loads in smart grids: A learning automata-based scheme. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. ISSN 1867-8211. 203, p. 58–68. doi: 10.1007/978-3-319-61813-5_6.
• Wang, Ying; Li, Peilong; Lei, Jiao; Su, Zhou; Cheng, Nan & Shen, Xuemin (Sherman) [Show all 7 contributors for this article] (2017). A Data-Driven Architecture for Personalized QoE Management in 5G Wireless Networks. IEEE wireless communications. ISSN 1536-1284. 24(1), p. 102–110. doi: 10.1109/MWC.2016.1500184WC.
• Muhammad, Fazal; Abbas, Ziaul Haq & Lei, Jiao (2016). Analysis of Interference Avoidance with Load Balancing in Heterogeneous Cellular Networks, 2016 IEEE 27th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), 4-8 September 2016. IEEE (Institute of Electrical and Electronics Engineers). ISSN 978-1-5090-3254-9. doi: 10.1109/PIMRC.2016.7794897.
• Wang, Ying; Miao, Zhongyu; Sun, Ruilin & Lei, Jiao (2016). Distributed Coalitional Game for Friendly Jammer Selection in Ultra-dense Networks. EURASIP Journal on Wireless Communications and Networking. ISSN 1687-1472. doi: 10.1186/s13638-016-0702-5.
• Wang, Ying; Miao, Zhongyu & Lei, Jiao (2016). Safeguarding the Ultra-dense Networks with the aid of Physical Layer Security: A review and a case study. IEEE Access. ISSN 2169-3536. 4, p. 9082–9092. doi: 10.1109/ACCESS.2016.2635698.
• Ai, Songpu; Lei, Jiao; Li, Frank Yong & Radin, Milka (2016). Channel aggregation with guard-band in D-OFDM based CRNs: Modeling and performance evaluation. IEEE Wireless Communications and Networking Conference. ISSN 1525-3511. 2016-September. doi: 10.1109/WCNC.2016.7565054.

View all works in Cristin

• Shafik, Rishad; Granmo, Ole-Christoffer; Lei, Jiao & Zadorozhny, Vladimir (2022). 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE conference proceedings. ISBN 978-1-6654-7116-9.
• Lei, Jiao (2020). Channel Aggregation and Fragmentation for Traffic Flows. Springer. ISBN 978-3-030-33080-4. 107 p. Show summary

  This book introduces the impact of channel aggregation (CA) and channel fragmentation (CF) on traffic flows, through analytical models, computer simulations, and test-bed implementations. Its content includes the concept of CA and CF, the basic concept and calculation of Markov chains (MCs), the modeling process of the CA and CF enabled system via MCs, the process of simulations, and a test-bed study based on a software defined radio. This book can serve as a study guide for advanced-level students, who are interested in studying the impact of CA and CF techniques on traffic flows. This book would also interest communication engineers, who would like to learn MC modeling for performance evaluations, as it includes a step-by-step guidance for the modeling process via MCs, as well as its simulation approaches.

View all works in Cristin

• Tunheim, Svein Anders; Lei, Jiao & Granmo, Ole-Christoffer (2023). Model Export for the Convolutional Coalesced Tsetlin Machine.
• Liland, Kristian Hovde; Tomic, Oliver; Indahl, Ulf Geir; Futsæther, Cecilia Marie; Jiao, Lei & Granmo, Ole-Christoffer [Show all 7 contributors for this article] (2023). Tsetlin Machine in DNA sequence classification. Show summary

  The Tsetlin machine (TM) is a logic-based machine learning model with the crucial advantages of transparency and hardware-friendliness. In TM, groups of Tsetlin Automata (TAs) produce Boolean expressions in the form of conjunctive clauses in AND-rules. In this work, we show that the DNA nucleotide sequence, coded using the four-letter alphabet A, C, G, T, is a perfect match to the Boolean logic-based TM. A coalesced integer-weighted TM is applied to the problem of prokaryote gene prediction demonstrating beyond state-of-the-art performance on reference genomes. This paves the way for highly efficient bioinformatic analysis in a large range of applications.

• Asres, Mulugeta Weldezgina & Lei, Jiao (2022). Anonymization for CCTV footage: Challenges and Possible Solutions.
• Jasinskaite, Emilija; Ystad Skjei, Øyvor; Lei, Jiao & Goodwin, Morten (2022). DP-ATT: Combining DeepPrivacy with AttGAN to preserve gender and age in de-identified CCTV footage.
• Lei, Jiao; Granmo, Ole-Christoffer; Blakely, Christian Dallas & Zadorozhny, Vladimir (2021). Denne chipen skjuler en norsk oppfinnelse som kan redde liv. [Internet]. NRK.
• Opalic, Sven Myrdahl; Goodwin, Morten; Lei, Jiao; Nielsen, Henrik Kofoed & Kolhe, Mohan Lal (2020). A Deep Reinforcement Learning scheme for Battery Energy Management .
• Jordbru, Thomas; Lei, Jiao & Cenkeramaddi, Linga Reddy (2018). UDP flows in Cognitive Radios with Channel Aggregation and Fragmentation: A Test-bed Based Evaluation.
• Lei, Jiao (2016). Full speed ahead to the city on the hill. Science. ISSN 0036-8075. 352(6288), p. 889–889. doi: 10.1126/science.aag1520.
• Kolhe, Mohan Lal; Goodwin, Morten; Lei, Jiao; Nielsen, Henrik Kofoed & Opalic, Sven Myrdahl (2023). Advanced Warehouse Energy Storage System Control Using Deep Supervised- and Reinforcement Learning. Universitetet i Agder. ISSN 978-82-8427-152-1.

View all works in Cristin