In order to achieve efficient and accurate breast tumor recognition and diagnosis, this paper proposes a breast tumor ultrasound image segmentation method based on U-Net framework, combined with residual block and attention mechanism. In this method, the residual block is introduced into U-Net network for improvement to avoid the degradation of model performance caused by the gradient disappearance and reduce the training difficulty of deep network. At the same time, considering the features of spatial and channel attention, a fusion attention mechanism is proposed to be introduced into the image analysis model to improve the ability to obtain the feature information of ultrasound images and realize the accurate recognition and extraction of breast tumors. The experimental results show that the Dice index value of the proposed method can reach 0.921, which shows excellent image segmentation performance.

• Breast Cancer Diagnosis
• Image Segmentation
• U-Net framework

Overweight and obesity pose public health concerns, linked to disease risks, morbidity, and mortality. This study employs machine learning for predictive modeling of obesity or overweight based on physical condition and eating habits data. Various algorithms were tested, with the best performer, random forest, achieving 78% accuracy, 79% precision, 78% recall, and 78% F1-score. This research underscores the potential of machine learning in identifying individuals at risk and aiding healthcare decision-making.

• Obesity Prediction
• Random Forest Algorithm

Facial expression emotion recognition is an intuitive reflection of a person’s mental state, which contains rich emotional information, and is one of the most important forms of interpersonal communication. Facial expression emotion recognition does the task of classifying the expressions on facial images into various categories such as anger, fear, surprise, sadness, happiness and so on. It analyses facial expressions from both static images and videos in order to reveal information on one’s emotional state. FER analysis comprises three steps: a) face detection, b) facial expression detection, and c) expression classification to an emotional state. Emotion detection is based on the analysis of facial landmark positions (e.g. end of the nose, eyebrows). Furthermore, in videos, changes in those positions are also analysed, in order to identify contractions in a group of facial muscles.

• Emotion Recognition
• Facial Analysis
• Video Emotion Analysis

The “Real-Time Face Mask Detection System” addresses the imperative need for enforcing face mask usage in indoor locations. Manual checks are impractical and risky. This innovative system employs real-time image recognition, distinguishing masked and unmasked faces with high accuracy. It operates in real time, conserving resources and ensuring immediate compliance. This technology reinforces safety measures in public spaces, enhancing overall public health. By providing swift, reliable feedback, it plays a crucial role in promoting and enforcing face mask regulations in indoor settings, safeguarding lives and operational efficiency.

• Face Mask Detection
• Real-Time Image Recognition

The AI Virtual Mouse is an innovative leap in HCI technology, replacing traditional mice, batteries, and dongles. Utilizing computer vision and machine learning, it interprets hand gestures and tip movements through webcams or built-in cameras. This system enables users to execute computer functions like left-click, right-click, scrolling, and cursor control without physical input devices. Powered by deep learning for precise hand detection, it’s not only cutting-edge but also addresses health concerns by reducing device dependency, minimizing physical touchpoints, and mitigating the spread of diseases such as COVID-19.

• AI Virtual Mouse
• HCI Innovation

 Credit card fraud is a serious criminal offense. It costs individuals and financial institutions billions of dollars annually. According to the reports of the Federal Trade Commission (FTC), a consumer protection agency, the number of theft reports doubled in the last two years. It makes the detection and prevention of fraudulent activities critically important to financial institutions. Machine learning algorithms provide a proactive mechanism to prevent credit card fraud with acceptable accuracy. In this paper Machine Learning algorithms such as Logistic Regression, Naïve Bayes, Random Forest, K- Nearest Neighbor, Gradient Boosting, Support Vector Machine, and Neural Network algorithms are implemented for detection of fraudulent transactions. A comparative analysis of these algorithms is performed to identify an optimal solution.

• Credit Card Fraud Detection
• Machine Learning Algorithms