Nadia Saad Noori

• Birkeland, Simen; Fjeldvik, Lin Julie; Noori, Nadia Saad; Yeduri, Sreenivasa Reddy & Cenkeramaddi, Linga Reddy (2024). Video based hand gesture recognition dataset using thermal camera. Data in Brief. ISSN 2352-3409. doi: 10.1016/j.dib.2024.110299.
• Andreassen, Jarl; Eileraas, Martin; Herrera, Lucia Castro & Noori, Nadia Saad (2023). InCReASE: A dynamic framework towards enhancing situational awareness in cyber incidence response. In Gjøsæter, Terje; Radianti, Jaziar & Murayama, Yuko (Ed.), Information Technology in Disaster Risk Reduction. Springer. ISSN 978-3-031-34207-3. p. 230–243. doi: 10.1007/978-3-031-34207-3_15.
• Evensen, Vetle Nesland; Henriksen, Gabriel Bergman; Melhus, Sondre; Olsen, Ole Steine; Haugen, Kristina & Dolmen, Dag [Show all 11 contributors for this article] (2023). ReFrogID: Pattern Recognition for Pool Frog Identification Using Deep Learning and Feature Matching. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 14381, p. 365–376. doi: 10.1007/978-3-031-47994-6_33. Show summary

  The global decline in amphibian populations is a pressing issue, with numerous species facing the threat of extinction. One such species is the pool frog, Pelophylax lessonae, whose Norwegian population has experienced a significant long-term decline since monitoring began in 1996. This decline has pushed the species to the verge of local extinction. A substantial knowledge gap in the species’ biology hinders the proposal and evaluation of effective management actions. Consequently, there is a pressing need for efficient techniques to gather data on population size and composition. Recent advancements in Machine Learning (ML) and Deep Learning (DL) have shown promising results in various domains, including ecology and evolution. Current research in these fields primarily focuses on species modeling, behavior detection, and identity recognition. The progress in mobile technology, ML, and DL has equipped researchers across numerous disciplines, including ecology, with innovative data collection methods for building knowledge bases on species and ecosystems. This study addresses the need for systematic field data collection for monitoring endangered species like the pool frog by employing deep learning and image processing techniques. In this research, a multidisciplinary team developed a technique, termed ReFrogID, to identify individual frogs using their unique abdominal patterns. Utilizing RGB images, the system operates on two main principles: (1) a DL algorithm for automatic segmentation achieving AP@89.147, AP50@99.123, and AP75@98.942, and (2) pattern matching via local feature detection and matching methods. A new dataset, pelophylax_lessonae, addresses the identity recognition problem in pool frogs. The effectiveness of ReFrogIDis validated by its ability to identify frogs even when human experts fail. Source code is available at here.

• Anderson, Abraham; Olafarson, Einar Julius; Andersen, Per-Arne & Noori, Nadia Saad (2022). The ODeLIndA Dataset for Field-of-View Obstruction Detection Using Transfer Learning for Real-Time Industrial Applications. In Bramer, Max & Stahl, Frederic (Ed.), Artificial Intelligence XXXIX 42nd SGAI International Conference on Artificial Intelligence, AI 2022. Springer. ISSN 978-3-031-21441-7. p. 197–210. doi: 10.1007/978-3-031-21441-7_14. Show summary

  Several challenges arise in industrial applications when using machine vision in safety-critical operations, such as field of view (FoV) obstruction, limited visibility of the equipment’s operational perimeter, difficulty obtaining datasets, and high accuracy requirement. This research shows how machine learning methods such as convolutional neural networks (CNN) and transfer learning can tackle these challenges. Transfer learning works well when the source and target domain images are similar, which is the case for identifying the operational conditions and FoV status in a fixed industrial environment where heavy equipment is operating with the aid of a machine vision module. In this work, eight categories describing FoV status and environmental conditions were selected as follows: clean lens/clear view, cracked lens, dirty lens, foggy, frost, dark view, flares, and rainy images. We used 21 616 images for the training set and 9450 for the test and validation. We benchmark the performance of several transfer learning models and networks (i.e., MobileNet, VGG16, VGG19, DenseNet, Inceptionv3, ResNet50, and Xception) against a CNN model/network trained from scratch. The experiments show that MobileNet combined with transfer learning performs best, with 98% accuracy compared to 93% for the traditional CNN model. Furthermore, the model can detect obstructions in real-time using commodity hardware when tested with a video stream. Finally, we provide a novel dataset for multi-class obstruction detection, which can be found here.

• Noori, Nadia; Shanbhag, Vignesh Vishnudas; Kandukuri, Surya Teja & Schlanbusch, Rune (2022). Data Driven Seal Wear Classifications using Acoustic Emissions and Artificial Neural Networks. Proceedings of the European Conference of the Prognostics and Health Management Society (PHME). ISSN 2325-016X. 7(1), p. 368–375. doi: 10.36001/phme.2022.v7i1.3327. Full text in Research Archive Show summary

  The work presented in this paper is built on a series of experiments aiming to develop a data-driven and automated method for seal diagnostics using Acoustic Emission (AE) features. Seals in machineries operate in harsh conditions, and seal wear in hydraulic cylinders results in fluid leakage, and instability of the piston rod movement. Therefore, regular inspection of seals is required using automated approaches to improve productivity and to reduce unscheduled maintenance. In this study, we implemented a data-driven diagnostics approach which utilizes AE measurements along with light weight Artificial Neural Networks (ANN) as a classifier to investigate the performance and resources (hardware & software) required for implementing a real-time soft sensor unit for monitoring seal wear condition. We used a feedforward multilayer perceptron ANN (Scaled Conjugate Gradient- SCG algorithm) that is trained with the back propagation algorithm, which is a popular network architecture for a multitude of applications (automotive, oil and gas, electronics). We benchmark the developed method against previous work conducted based on Support Vector Machine (SVM), and we compare ANN performance in classifying the running condition of seals in hydraulic cylinders by applying it to both raw (full frequency spectrum) and down sampled frequency measurements. The experiments were performed at varying pressure conditions on a hydraulic test rig that can simulate fluid leakage conditions like that of hydraulic cylinders. The test cases were generated with seals of three different conditions (unworn, semi-worn, worn). From the AE spectrum, the frequency bands were identified with peak power and by heterodyning the signal. This technique results in 10X down sampling without losing the information of interest. Further, the signal was divided into smaller “snapshots” to facilitate rapid diagnosis. In these tests, the diagnosis was made on short-time windows, as low as 0.3 seconds in length. A general set of 16 time and frequency domain features were designed. Then a training set was developed using relevant set of features (4, 5, and 16 features). The data was used to train the ANN (70% training – 30% test & validation) and SVM (60 % training - 40% test and validation). Classification of down sampled measurements, both ANN and SVM were able to accurately classify the status irrespective of the pressure conditions, with an accuracy of ~99% with execution time less than seconds. Therefore, the proposed approach can be applied as part of an automated seal wear classification technique based on AE and ANN/SVM and can be used for real-time monitoring of seal wear in hydraulic cylinders.

• Salvi, Andrea; Spagnoletti, Paolo & Noori, Nadia (2021). Cyber-resilience of Critical Cyber Infrastructures: integrating digital twins in the electric power ecosystem. Computers & Security. ISSN 0167-4048. doi: 10.1016/j.cose.2021.102507. Show summary

  Here in this work a simple and direct method to synthesize Rubik’s cube-like Linda Type (LTA) zeolite NaA structure is reported. Linda Type (LTA) zeolite was synthesized by hydrothermal method without using any organic template additives. The molar ratio of 3.165Na2O:Al2O3:1.926SiO2:128H2O have been used to prepare the zeolite NaA hydrogel. The thermal stability of the synthesized zeolite NaA was studied through the thermogravimetric analysis (TGA). The results of X-ray diffraction (XRD) analysis showed that the crystallinity of the synthesized zeolite is good and the material is of high purity. Through the FTIR study, functional groups belonging to the zeolite NaA was confirmed. From the FESEM analysis, morphology of the synthesized sample was found to be Rubik’s cube-like structure. The elemental composition of the material was studied using the EDAX analysis and the ratio of Si:Al was found to be ∼ 1. Further from the SAED patterns of the prepared sample, it was observed that the material is polycrystalline in nature. From the nitrogen adsorption/desorption results the zeolite NaA samples was found to be mesoporous in nature. The pore size of the samples have been obtained using the Barrett-Joyner-Halenda (BJH) analysis. The CO2 adsorption isotherm study was carried out at 298 K and the isotherm was fitted by using Langmuir and Freundlich adsorption isotherm.

• Imenes, Anne Gerd; Noori, Nadia Saad; Uthaug, Ole Andreas Nesvåg; Kröni, Robert; Bianchi, Filippo Maria & Belbachir, Nabil (2021). A Deep Learning Approach for Automated Fault Detection on Solar Modules Using Image Composites. In Angus, Rockett (Eds.), 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC). IEEE conference proceedings. ISSN 978-1-6654-1922-2. doi: 10.1109/PVSC43889.2021.9518540. Show summary

  Aerial inspection of solar modules is becoming increasingly popular in automatizing operations and maintenance in large-scale photovoltaic power plants. Current practices are typically time-consuming as they make use of manual acquisitions and analysis of thousands of images to scan for faults and anomalies in the modules. In this paper, we explore and evaluate the use of computer vision and deep learning methods for automating the analysis of fault detection and classification in large scale photovoltaic module installations. We use convolutional neural networks to analyze thermal and visible color images acquired by cameras mounted on unmanned aerial vehicles. We generate composite images by overlaying the thermal and visible images to investigate improvements in detection accuracy of faint features related to faults on modules. Our main goal is to evaluate whether image processing with multi-wavelength composite images can improve both the detection and the classification performance compared to using thermal images alone. The hypothesis is that fusion of images acquired at different wavelengths (i.e., thermal infrared, red, green, and blue visible ranges) would enhance the multi-wavelength representation of faults and thus their histogram feature signatures. The results showed a successful detection and localization of faint fault features using composite images. However, the classification of the fault categories did not show significant improvements and needs continued investigation. This research represents a step towards the design of robust automated methods to improve fault detection from airborne images. Further work is still necessary to reach a classification accuracy comparable with the performance of human experts.

• Kandukuri, Surya Teja; Shanbhag, Vignesh Vishnudas; Meyer, Thomas; Caspers, Leo; Noori, Nadia & Schlanbusch, Rune (2021). Automated and Rapid Seal Wear Classification Based on Acoustic Emission and Support Vector Machine. Proceedings of the European Conference of the Prognostics and Health Management Society (PHME). ISSN 2325-016X. 6(1), p. 203–210. doi: 10.36001/phme.2021.v6i1.2942. Full text in Research Archive Show summary

  Seal wear in hydraulic cylinders results in fluid leakage, and instability of the piston rod movement. Therefore, regular inspection of seals is required using automated approaches to improve productivity and to reduce unscheduled maintenance. In literature, successful attempts have been made using acoustic emission-based condition monitoring to classify the seal wear. However, limited attempts have been made to implement automated approaches to classify seal wear using acoustic emission features. Therefore, this article presents an automated approach for rapid and computationally economical diagnosis of seal wear using acoustic emission. The experiments were performed at varying pressure conditions on a hydraulic test rig that can simulate fluid leakage conditions similar to that of hydraulic cylinders. From the acoustic emission spectrum, the frequency bands were identified with peak power and by heterodyning the signal. This technique results in 10X downsampling without losing the information of interest. Further, the signal was divided into smaller “snapshots” to facilitate rapid diagnosis. In these tests, the diagnosis was made on short-time windows, as low as 0.3 seconds in length. A set of time and frequency domain features were designed, and the Support Vector Machine (SVM) was trained on 60 % of the test cases generated with seals of three different conditions. The SVM was able to accurately classify the status irrespective of the pressure conditions, with an accuracy of ~99 %. Therefore, the proposed automated seal wear classification technique based on acoustic emission and SVM can be used for real-time monitoring of seal wear in hydraulic cylinders.

• Lazreg, Mehdi Ben; Noori, Nadia Saad; Comes, Tina & Goodwin, Morten (2019). Not a Target. A Deep Learning Approach for a Warning and Decision Support System to Improve Safety and Security of Humanitarian Aid Workers. In Barnaghi, Payam; Gottlob, Georg; Manolopoulos, Yannis; Tzouramanis, Theodoros & Vakali, Athena (Ed.), 2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2019). Association for Computing Machinery (ACM). ISSN 978-1-4503-6934-3. p. 378–382. doi: 10.1145/3350546.3352551.
• Radianti, Jaziar; Dokas, Ioannis; Boersma, Kees; Noori, Nadia Saad; Belbachir, Nabil & Stieglitz, Stefan (2019). Enhancing Disaster Response for Hazardous Materials Using Emerging Technologies: The Role of AI and a Research Agenda. Communications in Computer and Information Science (CCIS). ISSN 1865-0929. 1000, p. 368–376. doi: 10.1007/978-3-030-20257-6_31.
• Lanfranchi, Vitaveska; Noori, Nadia Saad & Sirbu, T (2018). GPS-based solution for tracking and protecting humanitarians in conflict zones. Proceedings of the International ISCRAM Conference. ISSN 2411-3387. 2018-May, p. 334–349.
• Aboughonim, Ahmed Abdeltawab Abdelgawad S.; Noori, Nadia Saad & Comes, Tina (2018). Automated Scenario Generation for Training of Humanitarian Responders in High-Risk Settings. International Journal of Simulation. Systems, Science and Technology. ISSN 1473-8031. 19(5), p. 23.1–23.9. doi: 10.5013/IJSSST.a.19.05.23. Show summary

  Scenarios are designed to support decision-makers in gaining a better understanding of the consequences of their decisions. Scenario-based simulations, hence, present an ideal way to train decision-makers for complex and high-risk situations. Usually, training scenarios are human-authored which is limiting in terms of the number and diversity of the generated scenarios, in addition to being a time- and resource-consuming process. In this paper, we are introducing a first-order logic rule-based design and implementation of an automated scenario generator system to support designers of virtual, augmented and simulated reality humanitarian training setups. The system is based on knowledge extracted from publicly available humanitarian related databases. Moreover, the system can produce scenarios that adapt to user performance in addition to meeting certain training requirements

• Noori, Nadia Saad (2018). Modeling the escalation/de-escalation of response operation levels in disaster response networks using hierarchical Colored Petri Nets (CPN) approach, 2018 Annual IEEE International Systems Conference (SysCon). IEEE conference proceedings. ISSN 978-1-5386-3664-0. p. 50–58. doi: 10.1109/SYSCON.2018.8369593.
• Noori, Nadia; Wang, Yan; Comes, Tina; Schwarz, Philipp & Lukosch, Heide (2017). Behind the scenes of scenario-based training: Understanding scenario design and requirements in high-risk and uncertain environments. Proceedings of the International ISCRAM Conference. ISSN 2411-3387. 2017-May, p. 948–959.

View all works in Cristin

• Havås, Robin; Noori, Nadia Saad; Auby, Christian & Cenkeramaddi, Linga Reddy (2024). Optimized Unmanned Aerial Vehicle (UAV) Localization and Autonomous Navigation Stack for Tightly Closed Industrial Spaces.
• Imenes, Anne Gerd; Noori, Nadia Saad; Uthaug, Ole Andreas Nesvåg; Kröni, Robert; Bianchi, Filippo Maria & Belbachir, Nabil (2021). A Deep Learning Approach for Automated Fault Detection on Solar Modules Using Image Composites. Show summary

  Aerial inspection of solar modules is becoming increasingly popular in automatizing operations and maintenance in large-scale photovoltaic power plants. Current practices are typically time-consuming as they make use of manual acquisitions and analysis of thousands of images to scan for faults and anomalies in the modules. In this paper, we explore and evaluate the use of computer vision and deep learning methods for automating the analysis of fault detection and classification in large scale photovoltaic module installations. We use convolutional neural networks to analyze thermal and visible color images acquired by cameras mounted on unmanned aerial vehicles. We generate composite images by overlaying the thermal and visible images to investigate improvements in detection accuracy of faint features related to faults on modules. Our main goal is to evaluate whether image processing with multi-wavelength composite images can improve both the detection and the classification performance compared to using thermal images alone. The hypothesis is that fusion of images acquired at different wavelengths (i.e., thermal infrared, red, green, and blue visible ranges) would enhance the multi-wavelength representation of faults and thus their histogram feature signatures. The results showed a successful detection and localization of faint fault features using composite images. However, the classification of the fault categories did not show significant improvements and needs continued investigation. This research represents a step towards the design of robust automated methods to improve fault detection from airborne images. Further work is still necessary to reach a classification accuracy comparable with the performance of human experts.

• Noori, Nadia Saad (2020). Cyber Incident Management Challenges: no one-size fits all. Show summary

  The electrical energy infrastructure is one of the most complex and critical infrastructures as other sectors depend upon it to deliver their essential services. Cyber threat to the electrical grid is real and of grave importance. A large volume of documents exists providing guidance or direction on securing the grid against these threats; however, much of the work so far has been disjointed . Looking at the operational aspects of cyber incident management such as inter-organizational coordination and communication, overall, there is a low level of awareness regarding information infrastructure interdependencies and vulnerabilities for entities outside the organization’s boundaries . Moreover, entities involved in provisioning cybersecurity are not homogenous in terms of their goals, incentives, and disincentives. Each organization own its unique organizational culture, its standard operation procedures, and its internal supervisory controls condition the manner in which they coordinate with other entities. Therefore, this might lead to a conflict and might hinder efforts preventing, detecting and responding to cyber incidents. The absence of a process or a mechanism to coordinate interorganizational responses to a cyber security incident lead to a lack of awareness of vulnerabilities and capabilities of other organizations and how cyber-attacks might affect them. Often, communications channels for disseminating information before and during a cyber security incident can be through small, and informal information exchange networks, based on personal relationships and trust . Consequently, there is a lack of understanding concerning what capabilities and information each organization had access to and how to share it . This is highly problematic due to the interconnectedness of the organizations operating in the energy sector and due to the high risk of spill overs and cascading effects. Thus, there is a need to establish an integrated approach to cyber incident management addressing the specific needs of energy systems beyond to facilitate a collaborative and effective cyber incident response operations.

• Noori, Nadia Saad (2020). Cybersecurity between automation and sensemaking: are we still playing catch up? .
• Noori, Nadia Saad; Waag, Tor Inge; Viumdal, Håkon; Sharma, Roshan; Jondahl, Morten Hansen & Jinasena, Asanthi (2020). Non-Newtonian Fluid Flow Measurement in Open Venturi Channel Using Shallow Neural Network Time Series and Non-contact Level Measurement Radar Sensors .
• Noori, Nadia Saad; Waag, Tor Inge & Bianchi, Filippo Maria (2020). Condition Monitoring System for Internal Blowout Prevention (IBOP) in Top Drive Assembly System using Discrete Event Systems and Deep Learning Approaches. Full text in Research Archive
• Noori, Nadia Saad & Waag, Tor Inge (2019). Application of Hierarchical Colored Petri Nets for Real-Time Condition Monitoring of Internal Blowout Prevention (IBOP) in Top Drive Assembly System.
• Noori, Nadia Saad (2018). ICT role in supporting humanitarian aid missions in hostile environments: the case of iTRACK project.
• Noori, Nadia Saad (2017). Behind the Scenes of Scenario-Based Training: Understanding Scenario Design and Requirements in High-Risk and Uncertain Environments.
• Havås, Robin; Cenkeramaddi, Linga Reddy; Noori, Nadia Saad & Auby, Christian (2022). Implementation Of An Autonomous Navigation Stack For UAVs In Tightly Closed Industrial Spaces. Universitetet i Agder.

View all works in Cristin