Aggregated Fuzzy Signature Structures for Multi-class Medical Diagnosis

• Md Zakir Hossain, Zi Jin, Tom Gedeon, Amrijit Biswas, Ruchira Tabassum, Fahimul Hoque Shubho, Shafin Rahman

ChatGPT-guided Semantics for Zero-shot Learning

• F. H. Shubho, T. F. Chowdhury, A. Cheraghian, M. Saberi, N. Mohammed and S. Rahman, "ChatGPT-guided Semantics for Zero-shot Learning," 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Port Macquarie, Australia, 2023, pp. 418-425, doi: 10.1109/DICTA60407.2023.00064.

Abstract: Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class semantics include manual attributes or automatic word vectors from language models (like word2vec). We know attribute annotation is costly, whereas automatic word vectors are relatively noisy. To address this problem, we explore how ChatGPT, a large language model, can enhance class semantics for ZSL tasks. ChatGPT can be a helpful source to obtain text descriptions for each class containing related attributes and semantics. We use the word2vec model to get a word vector using the texts from ChatGPT. Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT. More specifically, we leverage ChatGPT to provide extra supervision for the class description, eventually benefiting ZSL models. We evaluate our approach on various 2D image (CUB and AwA) and 3D point cloud (ModelNet10, ModelNet40, and ScanObjectNN) datasets and show that it improves ZSL performance. Our work contributes to the ZSL literature by applying ChatGPT for class semantics enhancement and proposing a novel word vector fusion method.

Read more at:

IEEEXplore Google Scholar ResearchGate arXiv

Personality perception using scenario based stimulation and physiological signals

• A. Biswas, J. Li, F. H. Shubho, T. Gedeon, S. Rahman and M. Z. Hossain, "Personality Perception Using Scenario Based Stimulation and Physiological Signals," 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Honolulu, Oahu, HI, USA, 2023, pp. 1884-1891, doi: 10.1109/SMC53992.2023.10394366.

Abstract: Previous studies on automatic personality perception have primarily focused on a limited number of personality traits. However, in real-world situations, humans exhibit a wide range of personality traits. To overcome this limitation, a new methodology for automatic personality perception is proposed in this paper. This revised approach can predict various personality traits (17 traits) with satisfactory performance by utilizing physiological signals. The underlying concept is to stimulate participants with different emotional stimuli to elicit physiological responses in a specific scenario. Biomarkers such as Electroencephalogram (EEG), Skin Conductance, Blood Volume Pulse, and Pupil Dilation reflect an individual’s personality traits. Two experiments are conducted with different scenarios, including Image/Video Stimulation and Driving Simulation, to support this study. Based on the collection of data and validation of supervised learning models, Naive Bayes outperforms other classifiers explored in this research. EEG is the most effective signal for predicting personality, although combining other signals may produce similar results. Our method accurately predicts the 17 personality traits, demonstrating significant potential for clinical research.

Read more at:

IEEEXplore Google Scholar ResearchGate

Use of Social Media in Flood Assessment in Bangladesh

• F. H. Shubho et al., "Use of Social Media in Flood Assessment in Bangladesh," 2022 IEEE 11th International Conference on Intelligent Systems (IS), Warsaw, Poland, 2022, pp. 1-8, doi: 10.1109/IS57118.2022.10019640.

Abstract: Widespread floods are one of the most destructive natural phenomena that frequently occur in Bangladesh. It devastates human life, food security, shelter, and social and financial losses. Due to Bangladesh's current economic situation, installing and maintaining comprehensive flood gauges for national flood assessments will not be viable. Hence, online social media platforms can be a valuable avenue to get real-world data to perform flood assessments. This study investigates whether the abundance of data collected from social media in Bangladesh could be used to achieve a reliable and consistent flood assessment in Bangladesh. The data gathered from online platforms are related to flooding and exist in the form of videos, images, and text. The data collected is analyzed with a Machine Learning approach. The digital data of images and video frames were converted into numeric values using the VGG-16 architecture. A Convolutional Neural Network takes in the numeric data produced by the VGG-16 for classification. The classification made accuracy of 92% for the image-based model and 87% for the text-based model.

Read more at:

IEEEXplore Google Scholar ResearchGate

Real-time traffic monitoring and traffic offense detection using YOLOv4 and OpenCV DNN

• F. H. Shubho, F. Iftekhar, E. Hossain and S. Siddique, "Real-time traffic monitoring and traffic offense detection using YOLOv4 and OpenCV DNN," TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON), 2021, pp. 46-51, DOI: 10.1109/TENCON54134.2021.9707406.

Abstract: This paper presents a computer vision-based system for traffic offense detection. The system detects traffic offenses such as speed limit violations, unauthorized vehicles, traffic signal violations, unauthorized parking, wrong-way driving, and motorbike riders without helmets. The traffic offense detection system consists of a pipeline of four different modules. These are a vehicle detection module, a vehicle classification module, a vehicle tracking module, and a traffic offense detection module. Vehicles on the roads are detected in the vehicle detection module using visual data such as live camera feed. Next, after the vehicles are detected, they are classified into different classes using a vehicle classification module. A vehicle tracking module is developed to track the vehicle as it moves through the traffic. Lastly, we have implemented a traffic offense detection module that analyzes traffic patterns and detects different types of traffic violations in real-time. The entire system is implemented using OpenCV Deep Neural Network (DNN) module. We have used YOLOv4 to detect vehicles on the roads with high accuracy. For motorbike riders without helmets, we have used a fast YOLOv4-tiny model. The DeepSORT algorithm is used to track vehicles in real-time. Obtained accuracies are 86% in YOLOv4 for vehicle detection and 92% in YOLOv4-tiny for helmet detection.

Read more at:

IEEEXplore Google Scholar ResearchGate