The amount of sensitive data stored on mobile devices has increased. Current mobile device security schemas, such as pins, passwords, patterns, or even physiological biometrics are not secure enough to protect these data. There are several continuous or active authentication approaches that would provide an additional line of defense, designed as a security countermeasure. This paper introduces a Continuous Authentication system based on the swipe gestures as images. Therefore, we designed a Dual Input Model based on MobileNetV2. For training and testing the model, we used the two public Datasets, BioIdent and HMOG. As a result, our model achieved an EER of 10.45
A chatbot (Chatting Robot) is a computer program that enables people to communicate with machines using everyday language. The use of chatbots evolved quickly in the last years for different domains, including education and teaching. This paper presents related research conducted in the past year to contextualize the research. Next, we present the general context of a chatbot, its different intrinsic components, and their general architecture to constitute a solid base for the proposed proper system. Furthermore, we present the architecture of the proposed Chatbot by describing, in-depth, the function of every component and detailing the system's scenario. This study is a solid foundation for the final generative Chatbot for Open Educational Resources (OER) Recommender System. This paper aims to present the first step of developing a OER Chatbot" Recommender designated to the teaching community, which is the general architecture of the global system's first component.
Reducing the amount of data transmitted over the network will reduce energy consumption. One of the key issues facing routing protocols in wireless sensor networks is link breakage. Sometimes it causes the traffic to halt entirely or be temporarily suspended. Due to this, the routing protocol must be designed to allow for link breaks in order to identify an other route or manage the issue locally by offering a local link repair that replaces only the damaged portion of the route with the least amount of routing overhead possible to improve energy efficiency. This work introduces the local repair with various ways to lower the routing overhead in the Lightweight Routing Protocol (LRP).
Knowledge graphs have proven to be effective for modeling entities and their relationships through the use of ontologies. The recent emergence in interest for using knowledge graphs as a form of information modeling has led to their increased adoption in recommender systems. By incorporating users and items into the knowledge graph, these systems can better capture the implicit connections between them and provide more accurate recommendations. In this paper, we investigate and propose the construction of a personalized recommender system via knowledge graphs embedding applied to the vehicle purchase/sale domain. The results of our experimentation demonstrate the efficacy of the proposed method in providing relevant recommendations that are consistent with individual users.
Smart healthcare has become one of the important themes of our time. The growth and heterogeneity of medical data are seen as major challenges, especially in terms of processing, performance, storage, and security, which has made it obvious and essential to use various technologies to make smart healthcare more efficient and convenient, including the Internet of Medical Things (IoMT), big data, and cloud computing. However, these technologies may pose new challenges in terms of bandwidth cost due to the number of transfers to be made between a number of nodes, security of a large amount of medical data, and delay, especially since time is a very important factor in saving patients' lives. Some papers propose the joint use of these technologies to mitigate these challenges. In this paper, we introduce the concept of intelligent healthcare, and then we present the recent solutions to address the mentioned challenges. Finaly, we draw a conclusion and some perspectives for this work.
