One of the most reliable information sources is video, and in recent years, online and offline video consumption has increased to an unprecedented degree. One of the main difficulties in extracting information from videos is that unlike images, where information can be gleaned from a single frame, a viewer must watch the entire video in order to comprehend the context. In this work, we try to use various algorithmic techniques, such as deep neural networks and local features, in conjunction with a variety of clustering techniques, to find an efficient method of extracting interesting key frames from videos to summarize them. Video summarization plays a major role in video indexing, browsing, compression, analysis, and many other domains. One of the fundamental elements of video structure analysis is key frame extraction, which pulls significant frames out of the movie. An important frame from a video that may be used to summarize videos is called a key frame. We provide a technique that leverages convolutional neural networks in our suggested model, static video summarization, and key frame extraction from movies.

This paper presents a comprehensive exploration of the synergistic relationship between User-Centered Design (UCD) and Artificial Intelligence (AI) within the context of the AI-UCD Algorithm Framework. With the growing influence of AI in digital interfaces, the need to prioritize user needs and preferences has become paramount. The AI-UCD Framework, consisting of nine pivotal steps, acts as a structured guide for integrating AI into user interfaces while ensuring a user-centric, data-driven, and ethical approach. The exploration begins by highlighting the importance of understanding user needs and context through robust user research and contextual inquiry. It then delves into the process of defining AI integration objectives and brainstorming AI-enhanced solutions, emphasizing the creative aspects of UCD in tandem with AI capabilities. Subsequently, the paper discusses the critical role of designing AI-driven interfaces, from information architecture to user flow design, ensuring seamless integration of AI features.Implementation and testing of AI features are addressed, highlighting the collaboration between UI/UX designers and AI developers. The paper emphasizes the iterative nature of the framework, relying on usability testing and user feedback to drive continuous improvements. Moreover, it considers user training and assistance, a vital aspect of introducing users to AI features.The framework's data-driven aspect is covered by discussing data collection, analysis, and performance monitoring to ensure AI features are meeting objectives and KPIs. Additionally, the exploration addresses AI's role in personalization, adapting to user behavior and preferences. It recognizes the ethical dimensions of AI, promoting transparency, fairness, and accessibility.The paper then presents a five-step AI-UCD Validation Model, designed to verify the framework's effectiveness in real-world applications. These validation steps encompass user testing and feedback, data analysis, ethical audits, iterative improvements, and compliance with industry standards. Examples of how these steps work in practice are provided.

The aim of our investigation is to personalize bilateral recommendation of job-related proposals based on existing professional social networks. In a context where the points of view of job seekers and employers can be contradictory, our approach consists in trying to bring the both in a best possible matching. To this end, we propose an integration system that gives a minimum of credit to the users’ data in order to facilitate the discovery of relevant proposals based on the users’ behaviors, on the characteristics of the proposals and on possible relationships. The main contribution is the proposal of an architecture for the recommendation of profiles and job offers including social and administrative factors. The particularity of our approach lies in the freedom from the recommendation problem by using metrics proven in the literature for the estimation of similarity rates. We have used these metrics as default values to appropriate data dimensions. It emerges that, the user’s behavior is exclusively responsible for the recommendations. However, the cross-analysis of randomly generated behaviors on real profiles collected on Cameroonian sites dedicated to job offers, shows the influence of the most active users. But, for requests via the search bar (interface with the script respecting the path of our architecture) the central subject remains the user. Our current work is limited by a data set that is not very representative of changing socio-economic conditions.

In the field of medical imaging, breast ultrasound has emerged as a crucial diagnostic tool for early detection of breast cancer. However, the accuracy of diagnosing the location of the affected area and the extent of the disease depends on the experience of the physician. In this paper, we propose a novel model called UGGNet, combining the power of the U-Net and VGG architectures to enhance the performance of breast ultrasound image analysis. The U-Net component of the model helps accurately segment the lesions, while the VGG component utilizes deep convolutional layers to extract features. The fusion of these two architectures in UGGNet aims to optimize both segmentation and feature representation, providing a comprehensive solution for accurate diagnosis in breast ultrasound images. Experimental results have demonstrated that the UGGNet model achieves a notable accuracy of 78.2\% on the "Breast Ultrasound Images Dataset."

The Coronavirus Disease 2019 (COVID-19) has rapidly spread globally, causing a significant impact on public health. This study proposes a predictive model employing machine learning techniques to distinguish between influenza-like illness and COVID-19 based on clinical symptoms and diagnostic parameters. Leveraging a dataset sourced from BMC Med Inform Decis Mak, comprising cases of influenza and COVID-19, we explore a diverse set of features, including clinical symptoms and blood assay parameters. Two prominent machine learning algorithms, XGBoost and Random Forest, are employed and compared for their predictive capabilities. The XGBoost model, in particular, demonstrates superior accuracy with an AUC under the ROC curve of 98.8%, showcasing its potential for clinical diagnosis, especially in settings with limited specialized testing equipment. Our model's practical applicability in community-based testing positions it as a valuable tool for efficient COVID-19 detection. This study advances the field of predictive modeling for disease detection, offering promising prospects for improved public health outcomes and pandemic response strategies. The model's reliability and effectiveness make it a valuable asset in the ongoing fight against the COVID-19 pandemic.

This approach should indicate some challenges in routing and scheduling for the multi-vehicle system. The proposed method delivers a novel method to generate the free-collision trajectory as well as optimal route from starting point to destination. The estimated time at one node and the classification of load level support vehicle to decide which proper route is and stable movement is reached. From these results, it could be observed that the proposed approach is feasible and effective for many applications. The proposed method for routing and scheduling might be useful in the multi-vehicle system. In the large scale system, some intelligent schemes should be considered to integrate.

INTRODUCTION: The study introduces a novel approach to the design and management of industrial robots using virtual reality technology, enabling humans to observe a wide range of robot behaviors across various environments.OBJECTIVES: Through a simulation program, the robot's movements can be reviewed, and a program for real-world task execution can be generated. Furthermore, the research delves into the algorithm governing the interaction between the industrial robot and humans.METHODS: The robot utilized in this research project has been meticulously refurbished and enhanced from the previously old version robotic manipulator, which lacked an electrical cabinet derived.RESULTS: Following the mechanical and electrical upgrades, a virtual setup, incorporating a headset and two hand controllers, has been integrated into the robot's control system, enabling control via this device.CONCLUSION: This control algorithm leverages a shared control approach and artificial potential field methods to facilitate obstacle avoidance through repulsive and attractive forces. Ultimately, the study presents experimental results using the real robot model.

The COVID-19 pandemic can be considered a human disaster, it has claimed the lives of many people. We only know the number of deaths due to COVID-19 through government statistics, but on days when there are no statistics, how do we know whether people died that day or not? This study aims to predict the number of new deaths per day due to COVID 19 in Vietnam on days when observational data is not available and predict the number of deaths in the future. The study used COVID-19 data from the World Health Organization (WHO). A total of 260 days were collected and the author processed and standardized the data. Based on available data, the author uses Kriging interpolation statistical method to build a forecast model. As a result, the author has selected a prediction model suitable for a highly reliable data set, the regression coefficient and correlation coefficient are close to 1, the error between the model’s prediction results compared to data. There are days when the prediction error is almost zero. The study has built a future forecast map of the number of new deaths per day due to COVID-19. The article concludes that applying the Kriging statistical methodis appropriate for COVID-19 data. This research opens up new research directions for related fields such as earthquakes, mining, groundwater, environment, etc.

Facial emotion recognition technology is used to analyze and recognize human emotions based on facial expressions. This technology uses deep learning models to classify facial expressions, eyes, eyebrows, mouth, and other facial expressions to determine a person's emotions. The application of facial emotion recognition in the field of education is a potential way to evaluate the level of student absorption after each class period. Using cameras and emotion recognition technology, the system can record and analyze students' facial expressions during class. In this paper, we use the Convolutional Neural Network (CNN) algorithm combined with the linear regression analysis method to build a model to predict students' facial emotions over a period of time camera recorded.

Stream-based intrusion detection is a growing problem in computer network security environments. Many previous researches have applied machine learning as a method to detect attacks in network intrusion detection systems. However, these methods still have limitations of low accuracy and high false alarm rate. To improve the quality of classification, this paper proposes two solutions in the data preprocessing stage, that is, the solution of feature selection and resampling of the training dataset before they are used for training the classifiers. This is based on the fact that there is a lot of class imbalanced data in the training dataset used for network intrusion detection systems, as well as that there are many features in the dataset that are irrelevant to the classification goal, this reduces the quality of classification and increases the computation time. The data after preprocessing by the proposed algorithms is used to train the classifiers using different machine learning algorithms including: Decision Trees, Naive Bayes, Logistic Regression, Support Vector Machines, k Nearest Neighbor and Artificial Neural Network. The training and testing results on the UNSW-NB15 dataset show that: as with the Reconnaissance attack type, the proposed feature selection solution for F-Measure achieves 96.31%, an increase of 19.64%; the proposed oversampling solution for F-Measure achieves 6.99%, an increase of 3.17% and the proposed undersampling solution for F-Measure achieves 94.65%, an increase of 11.42%.