Press photo Download business card

Touseef Sadiq

Doctoral Research Fellow

Department of Information and Communication Technology

Email: touseef.sadiq@uia.no
Phone: +47 37233755
Mobile phone: +4748671539

Office B115 (Jon Lilletuns vei 3, 4879 Grimstad, Norway)

Areas of responsibility

Touseef is a PhD researcher at University of Agder, Norway. His current research focuses on deep multimodal learning for descriptive object identification in urban environments.

He obtained his B.E degree in computer engineering from Bahria university Islamabad, Pakistan and completed his MS degree in communications and computer networks engineering from Polytechnic university of Turin, Italy on fully funded scholarship.

His primary research interests include machine learning, computer vision, deep multimodal learning, and their applications.

Research

Deep Learning, Multimodal Machine Learning, Computer Vision, Representation Learning, Object Identification and Reterivel, Vision and Language Processing, Smart Cities Applications

Publications

Scientific articles and book chapters

Yusuf, Muhammad Ovais; Hanzla, Muhammad; Rahman, Hameedur; Sadiq, Touseef; Mudawi, Naif Al & Almujally, Nouf Abdullah [Show all 7 contributors for this article] (2024). Enhancing Vehicle Detection and Tracking in UAV Imagery: A Pixel Labeling and Particle Filter Approach. IEEE Access. ISSN 2169-3536. 12, p. 72896–72911. doi: 10.1109/ACCESS.2024.3401253.
Han, Huimin; Zeeshan, Zeeshan; Talpur, Bandeh Ali; Sadiq, Touseef; Bhatti, Uzair Aslam & Awwad, Emad Mahrous [Show all 8 contributors for this article] (2024). Studying long term relationship between carbon Emissions, Soil, and climate Change: Insights from a global Earth modeling Framework. International Journal of Applied Earth Observation and Geoinformation. ISSN 1569-8432. 130. doi: 10.1016/j.jag.2024.103902.
Yang, Jing; Sadiq, Touseef; Xiong, Jiale; Awais, Muhammad; Aslam Bhatti, Uzair & Alizadehsani, Roohallah [Show all 7 contributors for this article] (2024). A novel myocarditis detection combining deep reinforcement learning and an improved differential evolution algorithm. CAAI Transactions on Intelligence Technology. ISSN 2468-6557. doi: 10.1049/cit2.12289.
Farooqi, Ashfaq Hussain; Akhtar, Shahzaib; Rahman, Hameedur; Sadiq, Touseef & Abbass, Waseem (2024). Enhancing Network Intrusion Detection Using an Ensemble Voting Classifier for Internet of Things. Sensors. ISSN 1424-8220. 24(1), p. 1–26. doi: 10.3390/s24010127.
Sadiq, Touseef & Omlin, Christian Walter Peter (2023). Scene Retrieval in Traffic Videos with Contrastive Multimodal Learning, 2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI 2023). IEEE Computer Society Digital Library. ISSN 9798350342734. p. 1020–1025. doi: 10.1109/ICTAI59109.2023.00153.
Rahman, Hameedur; Khan, Abdur Rehman; Sadiq, Touseef; Farooqi, Ashfaq Hussain; Khan, Inam Ullah & Lim, Wei Hong (2023). A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction. Tomography. ISSN 2379-1381. 9(6), p. 2158–2189. doi: 10.3390/tomography9060169. Full text in Research Archive
Sadiq, Touseef & Omlin, Christian Walter Peter (2023). NLP-based Traffic Scene Retrieval via Representation Learning. In Benedicenti, Luigi (Eds.), Proceedings of the 9th World Congress on Electrical Engineering and Computer Systems and Science (EECSS 2023) . Avestia Publishing. ISSN 978-1-990800-26-9. doi: 10.11159/mvml23.108. Show summary
Many automated systems require the interpretation of visual information, i.e., images, videos, and natural language input, i.e., speech or text, to comprehend their surroundings and communicate with interacting humans. One such hybrid application of computer vision using images and videos and natural language processing (NLP) recognizes traffic scenes, a crucial and challenging problem in automated transportation systems. Scene classification is just one of many areas where recent convolutional neural network (CNN) frameworks have proven to be highly effective. Still to be fully explored for application to problem-solving in the real world is CNN’s impressive, truly representative learning capability. However, newer CNN implementations, such as YOLO and DeepSort, show promise for object detection. The BERT model is the benchmark for text embeddings and the most efficient method currently available. Hence, we aim to retrieve the vehicles from the traffic videos using natural language-based description, i.e., text. The paper proposes a novel approach that combines YOLOv7, the recent version of YOLO, DeepSort algorithms for object detection, i.e., detecting the vehicles from the traffic scene from the frames of the videos and the transfer learning model, i.e., BERT model for text embeddings. Additionally, a Kalman filter is utilized to track the cars by providing the id and will retain them in the other frames of the videos. The machine learning model performs the similarity checking, i.e., siamese neural networks. The experiments are performed on the standard dataset of AI city challenge 2022. Moreover, the results depict that the proposed approach achieves 28.49 % of Recall@5, 42.08 % of Recall@10, and 20.73 % of MRR, indicating the proposed method’s effective approach
Nazir, Anjum; Memon, Zulfiqar; Sadiq, Touseef; Rahman, Hameedur & Khan, Inam Ullah (2023). A Novel Feature-Selection Algorithm in IoT Networks for Intrusion Detection. Sensors. ISSN 1424-8220. 23(19). doi: 10.3390/s23198153. Full text in Research Archive Show summary
The Internet of Things (IoT) and network-enabled smart devices are crucial to the digitally interconnected society of the present day. However, the increased reliance on IoT devices increases their susceptibility to malicious activities within network traffic, posing significant challenges to cybersecurity. As a result, both system administrators and end users are negatively affected by these malevolent behaviours. Intrusion-detection systems (IDSs) are commonly deployed as a cyber attack defence mechanism to mitigate such risks. IDS plays a crucial role in identifying and preventing cyber hazards within IoT networks. However, the development of an efficient and rapid IDS system for the detection of cyber attacks remains a challenging area of research. Moreover, IDS datasets contain multiple features, so the implementation of feature selection (FS) is required to design an effective and timely IDS. The FS procedure seeks to eliminate irrelevant and redundant features from large IDS datasets, thereby improving the intrusion-detection system’s overall performance. In this paper, we propose a hybrid wrapper-based feature-selection algorithm that is based on the concepts of the Cellular Automata (CA) engine and Tabu Search (TS)-based aspiration criteria. We used a Random Forest (RF) ensemble learning classifier to evaluate the fitness of the selected features. The proposed algorithm, CAT-S, was tested on the TON_IoT dataset. The simulation results demonstrate that the proposed algorithm, CAT-S, enhances classification accuracy while simultaneously reducing the number of features and the false positive rate.
Awais, Muhammad; Bhuva, Abhishek; Bhuva, Dipen; Fatima, Saman & Sadiq, Touseef (2023). Optimized DEC: An effective cough detection framework using optimal weighted Features-aided deep Ensemble classifier for COVID-19. Biomedical Signal Processing and Control. ISSN 1746-8094. 86(A). doi: 10.1016/j.bspc.2023.105026. Show summary
Since the year 2019, the entire world has been facing the most hazardous and contagious disease as Corona Virus Disease 2019 (COVID-19). Based on the symptoms, the virus can be identified and diagnosed. Amongst, cough is the primary syndrome to detect COVID-19. Existing method requires a long processing time. Early screening and detection is a complex task. To surmount the research drawbacks, a novel ensemble-based deep learning model is designed on heuristic development. The prime intention of the designed work is to detect COVID-19 disease using cough audio signals. At the initial stage, the source signals are fetched and undergo for signal decomposition phase by Empirical Mean Curve Decomposition (EMCD). Consequently, the decomposed signal is called “Mel Frequency Cepstral Coefficients (MFCC), spectral features, and statistical features”. Further, all three features are fused and provide the optimal weighted features with the optimal weight value with the help of “Modified Cat and Mouse Based Optimizer (MCMBO)”. Lastly, the optimal weighted features are fed as input to the Optimized Deep Ensemble Classifier (ODEC) that is fused together with various classifiers such as “Radial Basis Function (RBF), Long-Short Term Memory (LSTM), and Deep Neural Network (DNN)”. In order to attain the best detection results, the parameters in ODEC are optimized by the MCMBO algorithm. Throughout the validation, the designed method attains 96% and 92% concerning accuracy and precision. Thus, result analysis elucidates that the proposed work achieves the desired detective value that aids practitioners to early diagnose COVID-19 ailments.
Rasheed, Kumeel; Shahzad, Luqman; Saad, Syed; Khan, Hassaan Ali; Ahmed, Waqas & Sadiq, Touseef (2021). Parking Guidance System Using Wireless Sensor Networks, 2021 International Conference on Decision Aid Sciences and Application (DASA). IEEE conference proceedings. ISSN 978-1-6654-1634-4. doi: 10.1109/DASA53625.2021.9682213.

View all works in Cristin

Published Apr. 16, 2024 11:39 AM