Search

Object detection plays a vital role in the fields of computer vision, machine learning, and artificial intelligence applications (such as FUSE-AI (E-healthcare MRI scan), face detection, people counting, and vehicle detection) to identify good and defective food products. In the field of artificial intelligence, target detection has been at its peak, but when it comes to detecting multiple targets in a single image or video file, there are indeed challenges. This article focuses on the improved K-nearest neighbor (MK-NN) algorithm for electronic medical care to realize intelligent medical services and applications. We introduced modifications to improve the efficiency of MK-NN, and a comparative analysis was performed to determine the best fuse target detection algorithm based on robustness, accuracy, and computational time. The comparative analysis is performed using four algorithms, namely, MK-NN, traditional K-NN, convolutional neural network, and backpropagation. Experimental results show that the improved K-NN algorithm is the best model in terms of robustness, accuracy, and computational time.

Position awareness is very important for many sensor network applications. However, the use of Global Positioning System receivers to every sensor node is very costly. Therefore, anchor based localization techniques are proposed. The lack of anchors in some Wireless Sensor Networks lead to the appearance of multi-hop localization, which permits to localize nodes even if they are far from anchors. One of the well-known multi-hop localization algorithms is the Distance Vector-Hop algorithm (DV-Hop). Although its simplicity, DV-Hop presents some deficiencies in terms of localization accuracy. Therefore, to deal with this issue, we propose in this paper an improvement of DV-Hop algorithm, called Regularized Least Square DV-Hop Localization Algorithm for multi-hop wireless sensors networks. The proposed solution improves the location accuracy of sensor nodes within their sensing field in both isotropic and anisotropic networks. We used the double Least Square localization method and the statistical filtering optimization strategy, which is the Regularized Least Square method. Simulation results prove that the proposed algorithm outperforms the original DV-Hop algorithm with up to 60%, as well as other related works, in terms of localization accuracy.

Educational data generated through various platforms such as e-learning, e-admission systems, and automated result management systems can be effectively processed through educational data mining techniques in order to gather highly useful insights into students’ performance. The prediction of student performance from historical academic data is a highly desirable application of educational data mining. In this regard, there is an urgent need to develop an automated technique for student performance prediction. Existing studies on student performance prediction primarily focus on utilizing the conventional feature representation schemes, where extracted features are fed to a classifier. In recent years, deep learning has enabled researchers to automatically extract high-level features from raw data. Such advanced feature representation schemes enable superior performance in challenging tasks. In this work, we examine the deep neural network model, namely, the attention-based Bidirectional Long Short-Term Memory (BiLSTM) network to efficiently predict student performance (grades) from historical data. In this article, we have used the most advanced BiLSTM combined with an attention mechanism model by analyzing existing research problems, which are based on advanced feature classification and prediction. This work is really vital for academicians, universities, and government departments to early predict the performance. The superior sequence learning capabilities of BiLSTM combined with attention mechanism yield superior performance compared to the existing state-of-the-art. The proposed method has achieved a prediction accuracy of 90.16%.

The COVID-19 disease has spread all over the world, representing an intriguing challenge for humanity as a whole. The efficient diagnosis of humans infected by COVID-19 still remains an increasing need worldwide. The chest X-ray imagery represents, among others, one attractive means to detect COVID-19 cases efficiently. Many studies have reported the efficiency of using deep learning classifiers in diagnosing COVID-19 from chest X-ray images. They conducted several comparisons among a subset of classifiers to identify the most accurate. In this paper, we investigate the potential of the combination of state-of-the-art classifiers in achieving the highest possible accuracy for the detection of COVID-19 from X-ray. For this purpose, we conducted a comprehensive comparison study among 16 state-of-the-art classifiers. To the best of our knowledge, this is the first study considering this number of classifiers. This paper’s innovation lies in the methodology that we followed to develop the inference system that allows us to detect COVID-19 with high accuracy. The methodology consists of three steps: (1) comprehensive comparative study between 16 state-of-the-art classifiers, (2) comparison between different ensemble classification techniques, including hard/soft majority, weighted voting, Support Vector Machine, and Random Forest, and (3) finding the combination of deep learning models and ensemble classification techniques that lead to the highest classification confidence on three classes. We found that using the Majority Voting approach is an adequate strategy to adopt in general cases for this task and may achieve an average accuracy up to 99.314%.

The 2019–2020 coronavirus pandemic had far-reaching consequences beyond the spread of the disease and efforts to cure it. Today, it is obvious that the pandemic devastated key sectors ranging from health to economy, culture, and education. As far as education is concerned, one direct result of the spread of the pandemic was the resort to suspending traditional in-person classroom courses and relying on remote learning and homeschooling instead, by exploiting e-learning technologies, but many challenges are faced by these technologies. Most of these challenges are centered around the efficiency of these delivery methods, interactivity, and knowledge testing. These issues raise the need to develop an advanced smart educational system that assists home-schooled students, provides teachers with a range of smart new tools, and enable a dynamic and interactive e-learning experience. Technologies like the Internet of things (IoT) and artificial intelligence (AI), including cognitive models and context-awareness, can be a driving force in the future of e-learning, opening many opportunities to overcome the limitation of the existing remote learning systems and provide an efficient reliable augmented learning experience. Furthermore, virtual reality (VR) and augmented reality (AR), introduced in education as a way for asynchronous learning, can be a second driving force of future synchronous learning. The teacher and students can see each other in a virtual class even if they are geographically spread in a city, a country, or the globe. The main goal of this work is to design and provide a model supporting intelligent teaching assisting and engaging e-learning activity. This paper presents a new model, ViRICTA, an intelligent system, proposing an end-to-end solution with a stack technology integrating the Internet of things and artificial intelligence. The designed system aims to enable a valuable learning experience, providing an efficient, interactive, and proactive context-aware learning smart services.

Web applications (WAs) are constantly evolving and deployed at broad scale. However, they are exposed to a variety of attacks. The biggest challenge facing organizations is how to develop a WA that fulfills their requirements with respect to sensitive data exchange, E-commerce, and secure workflows. This paper identifies the most critical web vulnerabilities according to OWASP Top Ten, their corresponding attacks, and their countermeasures. The application of these countermeasures will guarantee the protection of the WAs against the most severe attacks and prevent several unknown exploits.

This paper shows the importance of automated scoring (AS) and that it is better than human graders in terms of degree of reproducibility. Considering the potential of the automated scoring system, there is further a need to refine and develop the existing system. The paper goes through the state of the art. It presents the results concerning the problems of existing systems. The paper also presents the semantic features that are indispensable in the scoring system as they have complete content. Moreover, in the present research, a huge deviation has been exhibited by the system which has been shown later in performance analysis of the study, and this clearly indicates the novelty and improved results of the system. It explains the algorithms included in the methodology of this proposed system. The novelty of our work consists in the use of its own similarity function and its notation mechanism. It does not use the cosine similarity function between two vectors. This paper describes and develops a more accurate system which employs a statistical method for scoring. This system adopts and integrates rule-based semantic feature analysis.

In response to the researchers need in the bio-medical domain, we opted for automating the bibliographic research stage. In this context, several classification models of supervised machine learning are used. Namely the SVM, Random Forest, Decision Tree, KNN, and Gradient Boosting. In this paper, we conduct a comparative study between experimental results of full article classification and abstract classification approaches. Furthermore, we evaluate our results by using evaluation metrics such as accuracy, precision, recall and F1-score. We observe that the abstract approach outperforms the full article approach in terms of learning time and efficiency.

Pilgrimage represents the most important Islamic religious gathering in the world where millions of pilgrims visit the holy places of Makkah and Madinah to perform their rituals. The safety and security of pilgrims is the highest priority for the authorities. In Makkah, 5000 cameras are spread around the holy for monitoring pilgrims, but it is almost impossible to track all events by humans considering the huge number of images collected every second. To address this issue, we propose to use artificial intelligence technique based on deep learning and convolution neural networks to detect and identify Pilgrims and their features. For this purpose, we built a comprehensive dataset for the detection of pilgrims and their genders. Then, we develop two convolutional neural networks based on YOLOv3 and Faster-RCNN for the detection of Pilgrims. Experiments results show that Faster RCNN with Inception v2 feature extractor provides the best mean average precision over all classes of 51%., Accepted in ATSIP'2020

This work tackles the issue of the protection of confidential private data. Special attention is given to online banking. We made profit random functions to produce unpredictable results for intruders. By creating a list of passwords and by encrypting each word in two different steps based on random functions we obtain efficient double protection. Additional security is offered by biometrical data such as fingerprints. The fingerprints are watermarked in a well-chosen image which serves a shared key between the bank and its customer. This image is merged in the customer's fingerprints by using the mathematical principle of singular value decomposition (SVD). As a result we get a blurred image that is only understandable by the bank.

The rise and popularization of smartphones resulted in an obvious transition from personal computing to smartphones computing; all while guarding interactivity. Consequently, intelligent instruments can possess a “Facial Emotion Detection” (FED) system and an “Automatic Speech Recognition” (ASR) process. Such performances give new opportunities to develop a variability of software's that would otherwise be impossible. One group that would strongly benefit from the aforementioned applications concerns kids with Autism Spectrum Disorder (ASD). Although most recent educational mobile games targeting autistic children are not emotion-aware, our research laboratory inspects how portable technologies, facial expression recognition, and voice recognition algorithms can help autistic kids learn and improve their academic skills. We have designed a computerized system, “World of Kids” which facilitates the development of behaviour detection software's in portable devices. We aim to identify the mobile user's emotions via facial detection in order to extract the best appropriate and favourable game(s), which may even be a learning game(s). This paper describes the process in designing “World of Kids” and discusses the given results after testing the facial expression recognition application to detect emotion.

In this chapter, various aspects pertaining to the open operating system Android OS such as its history, architecture, features, and utility for business purposes will be introduced, following which the role of Android in enterprise management will be explained. The chapter will be concluded by a detailed report of the BYOD approach that uses Android for industrial control and automation. Since mobile devices have become progressively more powerful and accessible, mobile computing has greatly changed our daily lives. As one of the most popular mobile operating systems, Android provides the tools and API for Android developers to develop Android applications. Android is an open source operating system for mobile devices. Today its primary use is lodged in the mobile phone industry. During the recent past years, many projects have been created, with the objective to elevate Android to other platforms, such as sub-notebooks or embedded systems.

In this chapter, we define Information Security (IS) and elaborate on the different methods and technology used. We proceed to explain some of the IS tools and risks found in private and confidential data. We detail the latest algorithms and systems of security and discuss how to implement those systems in business to upgrade performances and increase profits.

Since the emergence of smartphones, there is a noticeable shift in our daily lives from desktop use to mobile use while maintaining interactivity, improving the use of these devices. Mobile gaming is an area that can provide a very personalized way to enjoy life for smartphone users. Today, while smart devices have the ability to recognize facial expressions, robust recognition of facial expressions in real time remains a challenge due to difficulties in accurately extracting the most pertinent emotional characteristics. A valuable objective is to define a computerized system facilitating the design and implementation of behavior detection on mobile devices for various applications. Our work aims to detect emotions through the face recognition of a smartphone user in order to synthesize his behavior while playing.

Purpose: To implement a user-friendly web based interactive platform to teach subjects requiring voice or audio illustrations such as teaching English or any language, radio animation, music, poetry, Koran recitation or learning by hart, or developing oral communication skills. Method: Several technologies (Php5, Codeigniter, html5, Css3, Jquery, Java, Flex, Ajax,…) are used to implement the web based interactive user-friendly interface for learning by hearing and repeating. The learner may be a naive user in terms of Internet and computer use. He/she needs only to click on a link and to enter as a regular or invited learner. It also may be used by visually impaired people. The teacher conducts the course and gives rights to the learner to talk individually or simultaneously. The platform should be implemented in a modular way so that one can augment it by new modules or by existing tools such as forums. Results: The platform has been conceived for several applications. Particular attention has been given to learning Koran by hart. The teacher pronounces a verse, or a segment of it, once or twice by rigorously respecting the rules of Koran recitation (Tajwid). To help the visually non-impaired learners learn verses by hart, verses are displayed on the screen and then masked progressively until all learners can recite the verses by hart. Discussion: The experiment has been conducted successfully. The platform presents several advantages with respect to VoIP tools which are not dedicated to learning by hearing and repeating.

In this article, we propose an intelligent RFID (Radio Frequency Identification) checkout to facilitate access and payment, to assist visually impaired people and to improve marketing strategy. To avoid saturated queues which we used to see in conventional stores remote identification of the customer and items is used to purchase the latter. Payment is then performed by to online payment or by ATM or credit cards. In addition, to ensure high performance and smooth operation of this checkout, we thought of seven major criteria namely: • Improving marketing strategy by displaying specific advertisement for each customer depending on the history of his previous purchases. • Vocally assisting vocally the visually impaired people (Vocal Messages: welcome, total, confirmation…) • Checking the validity of products during purchase process to avoid sales of expired unhealthy products • Adding a biometric security level by using fingerprints so that the customer can confirm his identity and validate his purchase. This makes steeling others' identity cards useless. • Enabling the customer performing the transaction faster by automatic online payment and sending electronic invoice to his inbox. • Offering to the owner the possibility to check and supervise the history of transactions via internet. • Saving energy by activating the RFID reader only if a user enters or leaves.

Steganography has been proposed as a new alternative technique to enforce data security. Lately, novel and versatile audio steganographic methods have been proposed. A perfect audio Steganographic technique aim at embedding data in an imperceptible, robust and secure way and then extracting it by authorized people. Hence, up to date the main challenge in digital audio steganography is to obtain robust high capacity steganographic systems. Leaning towards designing a system that ensures high capacity or robustness and security of embedded data has led to great diversity in the existing steganographic techniques. In this paper, we present a current state of art literature in digital audio steganographic techniques. We explore their potentials and limitations to ensure secure communication. A comparison and an evaluation for the reviewed techniques is also presented in this paper.

Radio Frequency Identification (RFID) has become a popular identification technology in a number of application areas such as supply chain management. A dedicated middleware solution is required to achieve the maximum benefits of RFID technology. The middleware components serve to abstract the communication between the middleware and the different types of sensing devices on one hand, and the middleware and backend applications on the other hand. FlexRFID is a simple and smart RFID middleware which provides device management and monitoring, data processing, filtering, and aggregation, rapid application development, as well as a policy based business rules layer which helps applying rules for accessing and configuring the services provided by the middleware. This layer serves to process some business intelligence rules locally so that the host system is offloaded from those mundane tasks. The paper shows that FlexRFID is a highly scalable and easily deployable middleware in the heterogeneous sites based on different standards and consisting of different hardware. Apart from these, FlexRFID incorporates the mechanisms for supervision, testing, and control of its components, plus handles the security and privacy issues that inhibit the adoption of RFID technology by applying the privacy policies in the business rules layer. FlexRFID middleware is controlling the data flows in and out as well as locally controlling some intelligence.

This paper applies a method to use the access log data to audit Web sites. It studies website auditing by (1) proposing a new fuzzy clustering algorithm that combines standard fuzzy C-means and the artificial fish swarm algorithm; (2) presenting a new measurement index for similarities between user sessions; and (3) providing an experiment on the execution of this new method. The results are encouraging and show the potential of our fuzzy clustering approach to assist in auditing Web site., The Seventh Annual Communications Networks and Services Research Conference(CNSR'09), Moncton, New Brunswick, May 11-13, 2009

Nowadays, Radio Frequency Identification (RFID) is a popular automatic wireless identification technology, and provides promising benefits in a number of application areas such as supply chain management. Though RFID technology has attracted a significant attention due to the convergence of lower cost and increased hardware capabilities, there still exist major hurdles for the practical realization of its benefits. To achieve the maximum benefits of RFID technology, a dedicated middleware solution is required for managing and monitoring RFID readers or other types of sensing devices, as well as processing dynamically generated high volumes of noisy RFID data. Apart from these, such middleware should possess useful contextual characteristics such as implicit semantics, and support rapid RFID based application development. FlexRFID as reported in this paper is a simple and smart RFID middleware which satisfies the requirements mentioned earlier. The paper shows that FlexRFID is a highly scalable and easily deployable middleware in the heterogeneous sites based on different standards and consisting of different hardware. Apart from these, FlexRFID incorporates the mechanisms for supervision, testing, and control of its components, plus handles the security and privacy issues that inhibit the adoption of RFID technology.

In this paper, a robust perceptual audio hashing system is presented. A model of the human auditory system is used to extract robust features from the outputs of a non-linear filter bank that mimics the human basilar membrane. Experiments on various audio excerpts show that this new ear-based front-end processing provides very effective hash values. The proposed audio hashing system performs very satisfactorily in identification and it turned out very resilient to a large variety of severe audio attacks.

In the context of the prodigious growth of network-based information services, messaging and edutainment, we introduce new tools that enable information management through the use of efficient multimodal interaction using natural language and speech processing. These tools allow the system to respond to close-to natural language queries by means of pattern matching. A new approach which gives the system the ability to learn new utterances of natural language queries from the user is presented. This automatic learning process is initiated when the system encounters an unknown command. This alleviates the burden of users learning a fixed grammar. Furthermore, this enables the system to better respond to spontaneous queries. This work investigates how an information system can benefit from the use of conversational agents to drastically decrease the cognition load of the user. For this purpose, Automated Service Agents and Artificial Intelligence Markup Language (AIML) are used to provide naturalness to the dialogs between users and machines.

In our society based on communication, the barrier between the spoken and gestural languages remains a main problem for the deaf-mute. To make this communication possible, we propose developing an interface with two modules (comprehension and recognition) allowing the recognition and the restitution of the sign language in the form of synthesized words.

The objective of our study is to recognize the sign language and re-transcribe it into a written or oral language in order to make mobile communication possible between a deaf-mute and people who don't know the sign language. For that, we used a method of correlation based on a multi-decision segmented filter. The latter has been used for a long time to recognize a target image. However an adaptation of this technique is necessary to take into account particular characteristics of gestures and to be able to send it with a high transmission rate. Moreover, in this application the target image to recognize evolves/moves in real time. Thus to take the right decision, it is necessary to carry out a very large number of correlations therefore slowing down the translation process. To reduce this processing time, we propose, in this article, to implement our system by using the multi-station technique. This technique enables us to distribute the required computing effort on various parallel stations using (PVM) a parallel virtual machine. Our Results show that we succeeded in validating our system, using multidecision filtering and multi-station by using real gesture.

This paper presents an automatic user profile building and training (AUPB&T) system for speech recognition. This system uses text-to-speech (TTS) voices to improve the language models and the performance of current commercial automatic speech recognition (ASR) engines. The vocabularies of these systems are usually suited for general usage. Users have no easy means of training these engines. They generally shun the proposed training methods that require long and picky training sessions. Our proposed solution is a system that accepts the user documents and favorite Web pages, and feeds them to a (TTS) module in order to improve the accuracy of spoken information retrieval queries. The results show that AUPB&T considerably improves the recognition engine performance of the Microsoft speech recognition system without having to resort to manual training.

Our global objective is to profit from the technology offered by the computer and/or Internet without being constrained by sitting in front of a computer. As an example of application, we present a method to use Voice over IP (VoIP) computer software remotely. This method targets mainly the population with reduced mobility or the population unfamiliar with computers, who may have difficulty using this type of software on the computer itself. This design allows for the use of a telephone keypad and headset with a microphone wirelessly, away from the computer. The system attempts to mimic the same kind of interface provided by telephones, with the same type of keypad, in an effort to maximize convenience, and reduce the amount of difficulty that someone with reduced mobility may have in using the system. We will describe the implementation used, present some results on how well the system works and some possibilities for the future.

One of the most important vehicles for providing dynamic learning is interaction combined to animation. We designed a dynamic e-learning environment for teaching optics. In spite of the fact that the teacher and the learner do not share neither space nor time, dynamic teaching is implemented aiming at reducing passivity, engaging and motivating the learner, empowering him with responsibility for his own learning experience, allowing collaborative learning, popularizing complex aspects in optics, and enabling the learner to easily access and interact with the environment content at his own pace, in his own time and from wherever he might be. Audio-visual tools are used for real-time assistance. The degree of complexity is customized by supervising and interpreting the interactions of the learner so that laypeople can readily follow the course. The course is adapted to people with a modest background in physics such as clinicians, optometrists and ophthalmologists. However, the learning environment is useful for advanced topics in optics as well as for research. Index — E-learning, dynamic teaching, interaction, optics.

An ad hoc network is a set of wireless mobile nodes that communally form a network without specific user administration or configuration. There are several scenarios that do not have an available network infrastructure and could benefit from the creation of an ad hoc network as rescue/emergency operations, law enforcement activities, tactical/military missions, commercial projects, educational classrooms.

A multimedia teaching aid based on animated Java applets can help users visualize the behavior of complex optical systems.

This paper introduces an alternative fuzzy clustering method that does not require fixing the number of clusters a priori and produce reliable clustering results. This newly proposed method empowers the existing Improved Artificial Fish Swarm algorithm (IAFSA) by the simulated annealing (SA) algorithm. The hybrid approach can prevent IAFSA from unexpected vibration and accelerate convergence rate in the late stage of evolution. Computer simulations are performed to compare this new method with well-known fuzzy clustering algorithms using several synthetic and real-life datasets. Our experimental results show that our newly proposed approach outperforms some other well-known existing fuzzy clustering algorithms in terms of both accuracy and robustness.

The rapid spread in digital data usage in many real life applications have urged new and effective ways to ensure their security. Efficient secrecy can be achieved, at least in part, by implementing steganograhy techniques. Novel and versatile audio steganographic methods have been proposed. The goal of steganographic systems is to obtain secure and robust way to conceal high rate of secret data. We focus in this paper on digital audio steganography, which has emerged as a prominent source of data hiding across novel telecommunication technologies such as covered voice-over-IP, audio conferencing, etc. The multitude of steganographic criteria has led to a great diversity in these system design techniques. In this paper, we review current digital audio steganographic techniques and we evaluate their performance based on robustness, security and hiding capacity indicators. Another contribution of this paper is the provision of a robustness-based classification of steganographic models depending on their occurrence in the embedding process. A survey of major trends of audio steganography applications is also discussed in this paper.