International Journal of Computer (IJC - Global Society of Scientific Research and Researchers, GSSRR)
Not a member yet
459 research outputs found
Sort by
Survey on Emotion Recognition Using Facial Expression
Get PDFAutomatic recognition of human affects has become more interesting and challenging problem in artificial intelligence, human-computer interaction and computer vision fields. Facial Expression (FE) is the one of the most significant features to recognize the emotion of human in daily human interaction. FE Recognition (FER) has received important interest from psychologists and computer scientists for the applications of health care assessment, human affect analysis, and human computer interaction. Human express their emotions in a number of ways including body gesture, word, vocal and facial expressions. Expression is the important channel to convey emotion information of different people because face can express mainly human emotion. This paper surveys the current research works related to facial expression recognition. The study attends to explored details of the facial datasets, feature extraction methods, the comparison results and futures studies of the facial emotion system
An Architecture for Misconfiguration Patching of Web Services: A Case Study of Apache Server
Get PDFServices are usually left configured by default and therefore subjects to vulnerabilities because they are not security enforced. Web services are so popular that they are targets of attacks to intrusions related to vulnerabilities discovered by attackers. This work proposes an architecture for patching Web service misconfigurations related to existing vulnerabilities. The approach underlying this architecture first retrieves and structures anti-vulnerability measures published by the official service manufacturers. Second, it evaluates the risk level using Common Vulnerability Scoring System (CVSS) on the current state of configurations. The proposed approach has been applied on Apache server on four vulnerabilities: version discovery, XSS, SQL injection and deny of service. Experimental results on a vulnerable environment demonstrate that the proposed approach considerably reduces vulnerabilities compared to similar solutions
Distributed Denial of Service Attack Challenges in Cloud Computing: A Review
Get PDFCloud computing as an ever-evolving technology has appeared to be a new discovery, with a history that can be traced to the 1960s, yet the computing paradigm has not been fully adopted till date. This is due to the security and trust management issues associated with the paradigm. Studies so far have shown remarkable efforts in the area of cloud computing security but has paid little attention to the area of application-based denial of service and its distributed variant. To this end, this paper highlights the Extensive Mark-up Language Denial of Service (XDoS) and the Extensive Mark-up Language Distributed Denial of Service (XDDoS) as one of the security challenges that inhibit the adoption of cloud computing. So many researchers in this field have proposed different solutions to this issues, however, it was observed that there is a need for an efficient and more effective counter-measures solution against XDoS and its distributed variant XDDoS which are application based denial of service that can be found in software as a service (SaaS) cloud computing service model
Decision Support Systems for the Efficiency Social Networks of Small and Medium Enterprises
Get PDFThe objective of this literature review article was to develop a framework of reference for the use of social networks as a decision support systems tool for the efficiency of small and medium enterprises. Twenty (20) research articles were reviewed from 2011 to 2017 that were associated with the topics of decision support systems, strategic decisions, and social networks. The research findings suggest that the use of decision support systems help the organization gain a competitive advantage, improve performance by analyzing the data obtained, and the data extracted from social networks add value to the company with low investment. Social networks have transformed the availability of information for their customers, making available a set of tools for searching, debugging, and validating data from both: individuals and organizations [19]. The use of social media is an effective modality for the development of relationships with clients and employees [10]
Responding to and Preventing Threats to Cybersecurity When Utilizing the Internet of Things
Get PDFThe Internet of Things has the potential to connect billions of devices and is developing at a tremendous rate. Billions of people will be able to connect through it. However, this system increases the vulnerability of each device, as a breach in the security of a single connected device will compromise the rest of the system’s safety. A hacker or virus may be able to get access to multiple connected devices by targeting just one of the many devices online. Therefore, such attacks will have a much larger reach compared to the attacks on individual systems. Preventing or being able to react to this issue is important, as the safety and privacy of people must be protected. Society needs a proper protocol that can protect these connected devices from cyber-attacks. This paper aims to propose solutions that will either prevent or respond to these cyberattacks, thus making systems more secure
Improvement of an Interoperable and Adaptable Middleware using IoT Semantic Web Technologies
Get PDFIn today changing world, Internet of Things (IoT) is creating a new world, where people and businesses can make more timely and better informed decisions about what they want or need to do. Over the last years, agriculture industry in few countries has been expended to smart agriculture. Nevertheless, the agricultural industry in Myanmar needs to be modernized with the involvement of IoT technologies for crops’ growth monitoring, irrigation decision and harvesting system. However, due to the complexity of IoT middleware, most of the middleware frameworks are designed to be used by IT experts. To allow non-IT experts (e.g. farmers, plant scientist) to configure the sensor devices easier and faster, without knowing the background knowledge of technical details, sensor-level configuration of heterogeneous devices needs to be fully interoperable (network, syntactic, and semantic interoperability) due to the huge number of sensor devices integrated and their diversity in term of data formats, communication protocols, nature of components etc. In this work, we propose a fully interoperable middleware framework that incorporates semantic web technologies with the existing Global Sensor Network middleware to solve the above challenges. The proposed system supports horizontally semantic interoperability which addresses the challenge of adaptability of our approach to different domains. Performance of the proposed system will be implemented and evaluated mainly in crops’ growth of agriculture area of Myanmar
Comparative Study of Machine Learning Algorithms to Measure the Students’ Performance
Get PDFStudents’ performance in the continuous assessments needs to be monitored to identify the students who may not perform well in the final examination. The aim of the research is to predict the students at risk those who will not complete the course. In order to predict the students at risk, Machine Learning algorithms can be applied to the students’ data at hand to construct a model from the training data set. With the prediction model, testing data can be applied to identify the students at risk. In this paper, two Machine Learning Algorithms namely C4.5, and Naïve Bayes Algorithm are used to analyze the training data set to build the prediction models and tested on the testing data set. The accuracy level of the two algorithms were also computed and compared to identify the algorithm which yields results at higher accuracy
Performance and Security of Group Signature in Wireless Networks
Get PDFA Group signature protocol is a cryptographic scheme that decouples a user identity and location from verification procedure during authentication. In a group signature scheme, a user is allowed to generate signatures on behalf of other group members but identity and location information of the signer is not known by a verifier. This ensures privacy, authentication and unlinkability of users. Although group signature is expensive to implement, its existential anonymity, non-repudiation and untraceablility properties make it attractive especially for resources-constrained devices in wireless network. A general group signature scheme usually contains six basic phases: setup (or key generation), join, message signing (or signature generation), signature verification, open and user revocation. In this paper, an evaluation of the performance of group signature based on three of the phases mentioned above is considered and its security in wireless networks examined. The key generation, signing and verification algorithms are implemented in Java 8. A proof of security of group signature by implication is also presented
Comparative Study of Image Denoise Algorithms
Get PDFDenoising is a pre-processing step in digital image processing system. It is also typical image processing challenges. Many works proposed to solve problem with new approaching. They can be divided into two main categories: spatial-based or transform-based. Some denoising methods apply in both spatial and transform domains. The goal of this paper focuses on reviewing denoise methods, classifying them into different categories, and identifying new trends. Moreover, we do experiments to compare pros, cons of methods in survey
Automated Geophysical Field Calculator Using Schlumberger Electrode System
Get PDFThe aim of this paper is to present a fast and direct approach for solving the geometric factor (k) and the Apparent Resistivity (?a) for the Schlumberger electrode configurations in geo-electric field surveys, using the measured quantities of the current electrode and potential electrode spacing respectively. The program is a web-based development based on scripting. Swish script is the major driver alongside the hypertext markup language (html), developed and housed in flash-java containers. The main features are the potential electrode spacing (M,N), current electrode spacing (A,B), the instant resistance reading (V/I (?)) (is the reading from the measuring device, usually a resistivity meter), the Geometric factor (k) and the Apparent Resistivity ( ).The ability of the program to modify basic quantities like current electrode spacing, the potential electrode spacing and the V/I to suit individual field practice with respect to the lateral and vertical variations in the inhomogeneous media made it a unique program. On execution of the program, it was found that both the geometric factor (k) and the apparent resistivity ( ) values are automatically displayed once the respective field data were inputted and the execute button clicked accordingly. It was tested for values of L = 1.0, 1.47,…,100 and l = 0.5, …,500. Finally a standard field sheet was incorporated into the program to reduce the monotony of numbering