Fatma Zahra Sayadi | Deep Learning | Best Innovation Award

Published on by Computer Vision Awards

Prof. Fatma Zahra Sayadi | Deep Learning | Best Innovation Award

Associate Professor | University of Sousse | Tunisia

Fatma Elzahra Sayadi is a highly accomplished researcher and academic specializing in electronics and microelectronics, with current research focused on video surveillance systems, real-time processing, and signal compression. She earned her PhD in electronics for real-time systems from the University of Bretagne Sud in collaboration with the University of Monastir and has also completed her engineering and master’s studies in electrical and electronic systems. She has extensive professional experience as a maître de conférences and previously as a maître assistante and assistant technologist, teaching courses in microprocessors, multiprocessors, programming, circuit testing, and industrial electronics. Her research interests include signal processing, parallel architectures, microelectronics, real-time systems, and communication networks. She has actively participated in national and international research projects and collaborations with institutions in France, Italy, Germany, and Morocco. Her work has been published in over 37 journal articles, 40 conference papers, and six book chapters, and she has supervised several doctoral and master’s theses. She has been recognized with awards such as the first prize at the Women in Research Forum at the University of Sharjah and contributes to professional communities as a reviewer, evaluator, and organizer of academic events. She is skilled in research methodologies, signal and data analysis, electronic system design, and digital education innovation. Her academic contributions have been cited by 395 documents, with 69 documents contributing to her citations, and she has an h-index of 13.

Profile: Google Scholar | Scopus | ORCID 

Featured Publications

  1. Basly, H., Ouarda, W., Sayadi, F. E., Ouni, B., & Alimi, A. M. (2020). CNN-SVM learning approach based human activity recognition. In International Conference on Image and Signal Processing (pp. 271–281). 77 citations.

  2. Bouaafia, S., Khemiri, R., Sayadi, F. E., & Atri, M. (2020). Fast CU partition-based machine learning approach for reducing HEVC complexity. Journal of Real-Time Image Processing, 17(1), 185–196. 53 citations.

  3. Haggui, O., Tadonki, C., Lacassagne, L., Sayadi, F., & Ouni, B. (2018). Harris corner detection on a NUMA manycore. Future Generation Computer Systems, 88, 442–452. 48 citations.

  4. Basly, H., Ouarda, W., Sayadi, F. E., Ouni, B., & Alimi, A. M. (2022). DTR-HAR: Deep temporal residual representation for human activity recognition. The Visual Computer, 38(3), 993–1013. 40 citations.

  5. Bouaafia, S., Khemiri, R., Messaoud, S., Ben Ahmed, O., & Sayadi, F. E. (2022). Deep learning-based video quality enhancement for the new versatile video coding. Neural Computing and Applications, 34(17), 14135–14149. 35 citations.

Ahmad Reza Naghsh Nilchi | Deep Learning | Best Researcher Award

Published on by Computer Vision Awards

Prof. Ahmad Reza Naghsh Nilchi | Deep Learning | Best Researcher Award

Faculty Member | University of Isfahan | Iran

Prof. Ahmad Reza Naghsh-Nilchi is a distinguished researcher in computer vision, artificial intelligence, and medical image processing with a strong academic and professional background. He completed his PhD in Electrical and Computer Engineering at Michigan State University, where he specialized in digital image processing, and has since built an influential career in both academia and research. Over the years, he has served in multiple leadership positions including department chair, dean of research, and head of research laboratories, while also supervising numerous PhD and master’s students in advanced AI and imaging topics. His professional experience extends internationally through collaborations with leading institutions such as UC Irvine, University of Toronto, York University, and University of Ireland, contributing significantly to global research initiatives. His research interests span robust deep learning, adversarial defense, trustworthy AI, multimodal action recognition, image captioning, retinal analysis, and robot-camera pose estimation, reflecting both theoretical innovation and practical applications. He has published more than 70 papers in prestigious journals and conferences indexed by IEEE and Scopus, and his work has received more than 2,200 citations. His excellence has been recognized through multiple honors, including awards as University Researcher of the Year and Industrial Researcher of the Year. He possesses advanced research skills in AI model development, medical imaging, digital signal processing, and multimodal data analysis, complemented by editorial roles, conference organization, and active memberships in professional associations such as IEEE and ACM. His career demonstrates a commitment to advancing science, mentoring the next generation, and fostering impactful interdisciplinary collaborations. His Scopus output reflects international impact, with 1,319 citations by 1,214 documents, 65 published documents, and an h-index of 21.

Profile: Google Scholar | Scopus Profile | ORCID Profile

Featured Publications

Fathi, A., & Naghsh-Nilchi, A. R. (2012). Noise tolerant local binary pattern operator for efficient texture analysis. Pattern Recognition Letters, 33(9), 1093–1100.

Fathi, A., & Naghsh-Nilchi, A. R. (2012). Efficient image denoising method based on a new adaptive wavelet packet thresholding function. IEEE Transactions on Image Processing, 21(9), 3981–3990.

Fathi, A., & Naghsh-Nilchi, A. R. (2013). Automatic wavelet-based retinal blood vessels segmentation and vessel diameter estimation. Biomedical Signal Processing and Control, 8(1), 71–80.

Amirgholipour, S. K., & Ahmad, R. (2009). Robust digital image watermarking based on joint DWT-DCT. International Journal of Digital Content Technology and its Applications, 3(2), 42–48.*

Kasmani, S. A., & Naghsh-Nilchi, A. (2008). A new robust digital image watermarking technique based on joint DWT-DCT transformation. In 2008 Third International Conference on Convergence and Hybrid Information Technology (pp. 539–544). IEEE.

Zahra Yahyaoui | Deep Learning | Women Researcher Award

Published on by Computer Vision Awards

Dr. Zahra Yahyaoui | Deep Learning | Women Researcher Award

Teacher-Researcher at Higher Institute of Applied Sciences and Technology of Kasserine, Kairouan University | Tunisia

Dr. Zahra Yahyaoui is a dedicated researcher and educator with expertise in electronics, microelectronics, renewable energy systems, and artificial intelligence. She has established herself as an active contributor to the advancement of intelligent fault detection and diagnosis methods for photovoltaic and wind energy conversion systems. Her work bridges theory and practice, combining advanced machine learning techniques with embedded hardware implementation, ensuring her research is both academically rigorous and industrially relevant. Alongside her research activities, she has been deeply involved in teaching, supervision, and mentoring, helping to shape the academic and professional development of students in electronics and applied sciences. Her publications in high-impact journals and participation in international conferences highlight her growing recognition in the global research community. With technical versatility, adaptability, and strong teamwork skills, she continues to contribute to sustainable solutions in energy systems while promoting innovation, academic excellence, and interdisciplinary collaboration.

Professional Profiles 

Scopus Profile | ORCID Profile 

Education

Dr. Zahra Yahyaoui pursued her academic path in Tunisia, beginning with a bachelor’s degree in industrial computing with a specialization in embedded systems. She then advanced to a master’s research degree in nanomaterials and embedded electronics, where she specialized in embedded electronics and conducted important research on fault detection and diagnosis in wind energy systems using machine learning. Building on this foundation, she completed her doctoral studies in electronics and microelectronics at the Higher Institute of Applied Sciences and Technology of Kasserine, Kairouan University. Her PhD research focused on developing enhanced intelligent data-driven paradigms for fault detection and diagnosis in power systems, with practical applications on embedded architectures. She carried out her doctoral work within the Research Unit of Advanced Materials and Nanotechnologies, furthering her expertise at the intersection of artificial intelligence, renewable energy, and electronic systems. This strong academic background reflects her commitment to innovative, multidisciplinary research.

Professional Experience

Dr. Zahra Yahyaoui has built a solid academic and professional career through her teaching and research activities. She started as a part-time teacher at the Higher Institute of Applied Sciences and Technology of Kasserine, where she gained experience delivering courses and tutorials in electronics, microprocessor and microcontroller architectures, and embedded systems. Her role expanded to contractual teacher at the same institute under Kairouan University, where she was responsible for teaching system-on-chip design, combinational and sequential logic circuits, and analog signal processing, covering both theoretical and practical sessions. In addition to her teaching duties, she has co-supervised master’s theses on advanced topics such as interval-valued machine learning, deep learning for fault detection in renewable systems, and photovoltaic installation design. Through her academic contributions, she has combined teaching excellence with mentoring, ensuring students receive both theoretical knowledge and practical insights. Her professional journey highlights her commitment to education, innovation, and applied research.

Research Interest

Dr. Zahra Yahyaoui’s research interests lie at the intersection of electronics, artificial intelligence, and renewable energy systems. She focuses on developing intelligent data-driven approaches for fault detection and diagnosis, aiming to enhance the reliability and efficiency of power systems such as photovoltaic and wind energy converters. Her work emphasizes the use of advanced machine learning and deep learning techniques, including BiLSTM, GRU, and optimization algorithms, to address uncertainty in renewable energy conversion and monitoring. She is also interested in the implementation of these algorithms on embedded architectures, integrating software with hardware platforms like FPGA, Raspberry Pi, and microcontrollers for real-world applications. Beyond fault diagnosis, she explores forecasting methods for solar irradiance and power output, contributing to the broader field of sustainable energy management. By combining theoretical modeling, algorithm development, and embedded system integration, her research supports innovation in intelligent renewable energy technologies.

Research Skill

Dr. Zahra Yahyaoui has developed a diverse set of research skills that enable her to carry out impactful and interdisciplinary work. She is proficient in programming languages such as MATLAB and Python, which she uses extensively for data analysis, machine learning model development, and algorithm implementation. She is skilled in simulation tools like ISE and Simplorer, supporting her expertise in circuit and system design. Her hardware-related skills include working with Siemens S7-1200, FPGA boards, Raspberry Pi, and Arduino microcontrollers, allowing her to translate theoretical models into practical embedded system solutions. She has strong problem-solving abilities, adaptability, and teamwork skills, which contribute to successful research collaborations and academic projects. Her research methodology combines theoretical analysis with experimental validation, ensuring robust and application-oriented results. With certifications in artificial intelligence and embedded systems, she brings an advanced skillset for developing intelligent monitoring and diagnostic systems, particularly for renewable energy applications.

Publications Top Notes

Title: Fault detection and diagnosis in grid-connected PV systems under irradiance variations
Authors: Hajji, M.; Yahyaoui, Z.; Mansouri, M.; Nounou, H.; Nounou, M.
Year: 2023

Title: One-Class Machine Learning Classifiers-Based Multivariate Feature Extraction for Grid-Connected PV Systems Monitoring under Irradiance Variations
Authors: Yahyaoui, Z.; Hajji, M.; Mansouri, M.; Bouzrara, K.
Year: 2023

Title: Effective Fault Detection and Diagnosis for Power Converters in Wind Turbine Systems Using KPCA-Based BiLSTM
Authors: Yahyaoui, Z.; Hajji, M.; Mansouri, M.; Abodayeh, K.; Bouzrara, K.; Nounou, H.
Year: 2022

Title: Kernel PCA based BiLSTM for Fault Detection and Diagnosis for Wind Energy Converter Systems
Authors: Yahyaoui, Z.; Hajji, M.; Mansouri, M.; Bouzrara, K.; Nounou, H.; Nounou, M.
Year: 2022

Title: Efficient fault detection and diagnosis of wind energy converter systems
Authors: Yahyaoui, Z.; Hajji, M.; Mansouri, M.; Harkat, M.-F.; Kouadri, A.; Nounou, H.; Nounou, M.
Year: 2020

Conclusion

Dr. Zahra Yahyaoui is a deserving candidate for the Best Researcher Award due to her significant contributions in advancing intelligent data-driven techniques for renewable energy systems, fault detection, and embedded architectures. Her research has produced valuable publications in reputed international journals and conferences, with practical applications that support sustainable energy and technological innovation. Through her teaching, mentorship, and active participation in the academic community, she has demonstrated a strong commitment to knowledge sharing and capacity building. With her proven expertise, dedication, and potential for future leadership, she is well positioned to continue making impactful contributions to both research and society.

Rohan Duppala | Machine Learning | Young Researcher Award

Published on by Computer Vision Awards

Mr. Rohan Duppala | Machine Learning | Young Researcher Award

Student at VIT-AP University, India

Rohan Duppala is an emerging researcher and technologist with a strong foundation in artificial intelligence, machine learning, deep learning, and natural language processing. As a final-year B.Tech Computer Science student at VIT-AP University, he has demonstrated exceptional research capabilities, developing innovative solutions in healthcare, education, and smart transportation. Rohan has published multiple papers in reputed journals, including Scientific Reports and MDPI, and has worked on diverse AI-driven projects, from infant cry classification and Alzheimer’s detection to generative AI-based educational tools. His ability to integrate advanced AI models with real-world applications reflects a rare combination of academic rigor and practical insight. In addition to academic work, Rohan has engaged with leading technologies like Gemini, Llama 3, and Weights & Biases, earning several certifications and accolades. With a forward-thinking mindset and a passion for impactful research, he aspires to contribute meaningfully to global challenges through AI and interdisciplinary innovation.

Professional Profile 

Education🎓

Rohan Duppala is currently pursuing his Bachelor of Technology in Computer Science and Engineering at VIT-AP University in Andhra Pradesh. His education has provided a rigorous grounding in core computer science principles while enabling him to explore advanced technologies such as artificial intelligence, machine learning, and natural language processing. Prior to his undergraduate studies, he completed his intermediate education in the Mathematics, Physics, and Chemistry (MPC) stream at Narayana Junior College in Visakhapatnam. He also completed his schooling at Sri Chaitanya School in Palasa, Andhra Pradesh. Throughout his academic journey, Rohan has demonstrated consistent excellence and a strong inclination toward analytical thinking and computational problem-solving. This solid educational background has laid the foundation for his research endeavors and technical accomplishments in AI, edge computing, and intelligent systems.

Professional Experience📝

Rohan gained hands-on industry experience as an IoT Specialist at Prayana Electric between June and August 2024. During his tenure, he was instrumental in integrating IoT solutions into electric bicycles, leveraging microcontrollers, GPS, and LoRa technologies to enable real-time monitoring and smart navigation. He also spearheaded the development of a pothole detection system, optimized specifically for edge deployment on Raspberry Pi Pico, seamlessly integrating it into the e-bike ecosystem. This professional experience not only expanded his understanding of smart transportation and embedded systems but also allowed him to apply theoretical AI knowledge to practical, scalable solutions. Rohan’s work at Prayana Electric reflects his ability to bridge the gap between academic research and industry requirements, highlighting his skills in system design, data analysis, and sensor integration. His initiative, problem-solving abilities, and adaptability in a real-world setting underscore his potential as a well-rounded researcher and future technology leader.

Research Interest🔎

Rohan Duppala’s research interests lie at the intersection of artificial intelligence, healthcare, education, and smart systems. He is particularly focused on building explainable and ethically sound AI systems that can be deployed in real-world settings. His work in medical diagnostics, including projects on Alzheimer’s and Parkinson’s disease detection using deep learning, underscores a commitment to socially impactful research. Rohan also explores Generative AI and Large Language Models, applying them to applications such as automated script evaluation, infant care, and educational feedback systems. His interest in edge AI and IoT-enabled smart devices reflects a drive to create scalable, efficient, and context-aware solutions for real-time environments. By combining transformer models, retrieval augmented generation (RAG), signal processing, and explainable AI (XAI) techniques, Rohan aims to push the boundaries of intelligent automation in human-centric domains. His interdisciplinary approach and ethical consideration make his research both innovative and future-ready.

Award and Honor🏆

Rohan Duppala has been recognized for his academic and technical excellence with several awards and honors. He received a Certificate of Honor from OpenCV University in recognition of his outstanding performance in deep learning applications and project execution. Additionally, he was awarded a unique NFT (Non-Fungible Token) honor from The Hashgraph Association, celebrating his innovation and engagement in the decentralized technology community. His publications in reputed platforms such as Scientific Reports (Nature) and MDPI further reflect the quality and impact of his research. These accolades highlight not only his technical achievements but also his ability to stand out in competitive, global academic and developer communities. His participation in specialized bootcamps, advanced workshops, and certificate programs offered by Google, AWS, Cisco, and Weights & Biases has further solidified his position as an accomplished early-career researcher poised for excellence in AI-driven innovation.

Research Skill🔬

Rohan Duppala possesses an advanced and versatile skill set tailored for research in artificial intelligence and related domains. He is proficient in Python and Java, with hands-on experience in building custom convolutional neural networks, implementing transformer models, and deploying real-time deep learning systems on edge devices like Raspberry Pi. His practical expertise spans data preprocessing, hyperparameter tuning, model evaluation, explainable AI (XAI) techniques like LIME and Saliency Maps, and fine-tuning large models like LLaMA 3 8b using LoRA. He has also worked with tools such as Hugging Face Transformers, Weights & Biases, and Streamlit for model development and deployment. Rohan is skilled in retrieval augmented generation (RAG), multimodal data processing, and prompt engineering. His ability to combine AI techniques with IoT, computer vision, and NLP enables him to develop interdisciplinary solutions. These research skills, backed by strong implementation and critical thinking abilities, make him a technically mature and innovation-ready researcher.

Conclusion💡

Rohan Duppala is a highly deserving candidate for the Best Researcher Award, owing to his exceptional drive, technical acumen, and impactful research contributions at an early stage of his academic journey. His work spans critical societal applications—from medical diagnostics using deep learning to educational tools powered by large language models—demonstrating both depth and relevance. With peer-reviewed publications in reputed journals like Scientific Reports and MDPI, and hands-on innovation in smart technologies and AI systems, he has already laid a strong foundation for a distinguished research career. Given his dedication, continuous learning, and visionary approach to solving real-world problems, Rohan holds immense potential for future leadership in the fields of artificial intelligence and intelligent healthcare systems.

Publications Top Noted✍

  • Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques
    Authors: D. Rohan, G.P. Reddy, Y.V.P. Kumar, K.P. Prakash, C.P. Reddy
    Year: 2025
    Citations: 4

  • Title: A Custom Convolutional Neural Network Model-Based Bioimaging Technique for Enhanced Accuracy of Alzheimer’s Disease Detection
    Authors: P. Reddy G., S.M.A. Kareem, Y.V.P. Kumar, P.P. Kasaraneni, M. Janapati
    Year: 2025
    Citations: 1

  • Title: Artificial intelligence-based effective detection of Parkinson’s disease using voice measurements
    Authors: G. Pradeep Reddy, D. Rohan, Y.V.P. Kumar, K.P. Prakash, M. Srikanth
    Year: 2024
    Citations: 1

Mr. Andrews Tang | Deep Learning | Best Researcher Award

Published on by Computer Vision Awards

Mr. Andrews Tang | Deep Learning | Best Researcher Award

Andrews Tang at Kwame Nkrumah University of Science and Technology, Ghana

👨‍🎓 Profiles

Scopus

Google Scholar

Publications

Assessing blockchain and IoT technologies for agricultural food supply chains in Africa: A feasibility analysis

  • Authors: Andrews Tang, Eric Tutu Tchao, Andrew Selasi Agbemenu, Eliel Keelson, Griffith Selorm Klogo, Jerry John Kponyo
  • Journal: Heliyon
  • Year: 2024

An Open and Fully Decentralised Platform for Safe Food Traceability

  • Authors: Eric Tutu Tchao, Elton Modestus Gyabeng, Andrews Tang, Joseph Barnes Nana Benyin, Eliel Keelson, John Jerry Kponyo
  • Year: 2022

Prof. Ling Yang | Deep Learning | Women Researcher Award

Published on by Computer Vision Awards

Prof. Ling Yang | Deep Learning | Women Researcher Award

Professor at Kunming University of Science and Technology, China

👨‍🎓 Profiles

Scopus

Orcid

Publications

Enhancing Panax notoginseng Leaf Disease Classification with Inception-SSNet and Image Generation via Improved Diffusion Model

  • Authors: Wang, R., Zhang, X., Yang, Q., Liang, J., Yang, L.
  • Journal: Agronomy
  • Year: 2024

Deep learning implementation of image segmentation in agricultural applications: a comprehensive review

  • Authors: Lei, L., Yang, Q., Yang, L., Wang, R., Fu, C.
  • Journal: Artificial Intelligence Review
  • Year: 2024

Alternate micro-sprinkler irrigation and organic fertilization decreases root rot and promotes root growth of Panax notoginseng by improving soil environment and microbial structure in rhizosphere soil

  • Authors: Zang, Z., Yang, Q., Liang, J., Guo, J., Yang, L.
  • Journal: Industrial Crops and Products
  • Year: 2023

A BlendMask-VoVNetV2 method for quantifying fish school feeding behavior in industrial aquaculture

  • Authors: Yang, L., Chen, Y., Shen, T., Yu, H., Li, D.
  • Journal: Computers and Electronics in Agriculture
  • Year: 2023

An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images

  • Authors: Yang, L., Chen, Y., Shen, T., Li, D.
  • Journal: Applied Sciences (Switzerland)
  • Year: 2023