International Journal of Computer (IJC - Global Society of Scientific Research and Researchers, GSSRR)
Not a member yet
459 research outputs found
Sort by
A Survey on Phishing Attacks in Cyberspace
Get PDFPhishing is a type of cyber attack in which cybercriminals use various advanced techniques to deceive people, such as creating fake webpages or malicious e-mails. The objective of phishing attacks is to gather personal data, money, or personal information from victims illegally. The primary aim of this review is to survey the literature on phishing attacks in cyberspace. It discusses different types of phishing attacks, such as spear phishing, e-mail spoofing, phone phishing, web spoofing, and angler phishing, as well as negative consequences they may cause for people. Phishing is typically carried out through different delivery methods such as e-mail, phone calls, or messaging. Victims of phishing are usually either not sensitive to privacy protection or do not have enough knowledge about social engineering attacks to know they are at risk. In addition, this paper introduces different methods for detecting phishing attacks. The last section discusses certain limitations of existing studies on phishing detection and potential future researc
A Dynamic Application Partitioning and Offloading Framework to Enhance the Capabilities of Transient Clouds Using Mobile Agents
Get PDFMobile cloud computing has emerged as a prominent area of research, a natural extension of cloud computing that proposes to offer solutions for enhancing the capabilities of smart mobile devices commonly plagued by resource constraints. As one of its promising models, transient clouds aim to address the internet connectivity shortfall inherent in most solutions through the formation of ad hoc networks by devices in close proximity, then the offloading some computations (Cyber Foraging) to the created cloud. However, transient clouds, at their current state, have several limitations, concerning their expansion on a local network having a large number of devices and the management of the instability of the network due to the constant mobility of the devices. Another issue is the fact code partitioning and offloading are not addressed to fit the need of such networks, thereby rendering the distributed computing mechanism barely efficient for the Transient Cloud. In this study, we propose a transient cloud-based framework that exploits the use of multi-agent systems, enabling a dynamic partitioning and offloading of code, and facilitating the movement and the execution of code partition packets in a multi-hop ad-hoc mesh network. When created and deployed, these intelligent mobile agents operate independently or collaboratively and adapt to the continual entry and exit of devices in the neighbourhood. The integration of these trending concepts in distributed computing within a framework offers a new architecture for resource-sharing among cooperating devices that addresses the varied issues that arise in dynamic environments
Elaboration of Processing Chains for Spatio-temporal Analysis of Rainfall Data Application: Alaotra Mangoro Region, Madagascar
Get PDFThis present study was carried out within the framework of the automation of the processing chains of spatio-temporal data processing of climatological data in Madagascar. Our objective is to develop and automate the processing chains of rainfall data from ERA-Interim re-analyses of the European Meteorological Centre ECMWF to observe and analyze the evolution of precipitation over time and space. The chains are elaborated in a generic way by introducing statistical methods such as spatial interpolation, calculation of temporal and spatial averages, maximum entropy method, and principal component analysis. Then, the elaborated chains are implemented with MATLAB. Thus, the test of these chains has been performed in the Alaotra Mangoro region. The results obtained allowed us to observe, analyze and interpret the evolution of precipitation in this region of Madagascar during 35 years (1979 to 2013)
Fuzzy Logic Based Dam Water Shutter Control System by Using Water Level and Rainfall Condition in Raining Season
Get PDFA robust water shutter management system ensures that the water does not overflow and destroy or damage the dam. During the rainy season, care must be taken when dams conserve water, if the reservoir volume is too high, the risk of dam failure may be increased. So water level control is a special matter in the rainy season. Fuzzy logic sets provide better control than binary logic-based methods because they are used to determine the meaning of qualitative values for controller inputs and outputs, such as small, medium, and large control actions. This system used the fuzzy logic control theory in the water shutter management system to get smoothness motor control values of small, very small, medium, large, and very large. The system uses ultrasonic sensors to detect water levels, rain sensors to detect rain, and fuzzy logic controls to control the PWM duty cycle to the shutter gate motor driver circuit based on the detection of these two sensors. This control strategy is implemented with Arduino Uno
Recognition of West African Indigenous Fruits using a Convolutional Neural Network Model
Get PDFThe. Fruit recognition involves the extraction and processing of relevant features from fruit images in order to deduce the categories of that fruit. Due to its importance to human health and sustainability, various systems exist for recognition of fruits, although none exist for recognition of west Africa\u27s indigenous fruits. This research developed a fruit recognition system using a convolutional neural network (CNN) based model. Five west Africa indigenous fruits were selected, while “images were directly used as input to CNN based model of (3 convolutional layers, 3 max pooling layers and 1 fully connected layer) for training and recognition without features extraction process. The study further presents a transfer learning on visual geometry group 16 and ResNet models for result comparison. Using the optimal training set, the proposed CNN based model produced a recognition rate of 96%
Marigold Blooming Maturity Levels Classification Using Machine Learning Algorithms
Get PDFImage processing is swiftly progressive in the area of computer science and engineering. Image classification is a fascinating task in image processing. In this study, we have classified the marigold blooming maturity levels like a marigold bud, partial blooming marigold, and fully blooming marigold. To classify the marigold blooming maturity levels are a tough and time-consuming task for human beings. Hence, an automatic marigold maturity levels classification tool is very adjuvant even for experience humans to classify the huge number of marigolds. For the sake of that, we have deliberated a novel system to classify automatically marigold blooming maturity levels image data by using machine learning algorithms. There are three types of machine learning models namely Artificial Neural Network(ANN), Convolutional Neural Network(CNN), and Support Vector Machine(SVM) that are used to automatically classify marigold maturity levels. Hence, we have preprocessed the image at first. Then we extract the various features from the marigold images. After that, these features have fed into Machine Learning(ML) models and classify these images into the category. From the experiment, we observed that the Convolutional Neural Network (CNN) model provides a high accuracy compared to other Artificial Neural Network(ANN) and Support Vector Machine(SVM) algorithms. The Convolutional Neural Network(CNN) models performed the best among all two classifiers with an overall accuracy of 93.9%. Our proposed system is efficiently classifying marigold maturity levels
Peer-to-peer Approach for Distributed Privacy-preserving Deep Learning
Get PDFThe revolutionary advances in machine learning and Artificial Intelligence have enables people to rethink how we integrate information, analyze data, and use the resulting insights to improve decision making. Deep learning is the most effective, supervised, time and cost efficient machine learning approach which is becoming popular in building today’s applications such as self-driving cars, medical diagnosis systems, automatic speech recognition, machine translation, text-to-speech conversion and many others. On the other hand the success of deep learning among others depends on large volume of data available for training the model. Depending on the domain of application, the data needed for training the model may contain sensitive and private information whose privacy needs to be preserved. One of the challenges that need to be address in deep learning is how to ensure that the privacy of training data is preserved without sacrificing the accuracy of the model. In this work, we propose, design and implement a decentralized deep learning system using peer-to-peer architecture that enables multiple data owners to jointly train deep learning models without disclosing their training data to one another and at the same time benefit from each other’s dataset through exchanging model parameters during the training. We implemented our approach using two popular deep learning frameworks namely Keras and TensorFlow. We evaluated our approach on two popular datasets in deep learning community namely MNIST and Fashion-MNIST datasets. Using our approach, we were able to train models whose accuracy is relatively close to models trained under privacy-violating setting, while at the same time preserving the privacy of the training data
Distributed Ledger Technology: Applications and its Convergence in Industrial Revolution 4.0
Get PDFDistributed ledger technology (DLT) has garnered a tremendous amount of attention in recent years due to the popularity of blockchain-related cryptocurrencies. However, layperson will have difficulty cutting through the hype and being objective enough to evaluate the benefits and shortcomings of this technology. This study attempts to provide answer to the following questions: 1) what is DLT, and the difference of its two popular specializations: blockchain and directed acyclic graph (DAG)? 2) how far have the society achieved through DLT applications in the field of healthcare, identity management as well as copyright and intellectual property? 3) how does the general public view the convergence of DLT applications in Industrial Revolution 4.0? Through rightly education and understanding of DLT, the society will value the technology better of its application in different sectors
Supporting Service Differentiation in Multi-domain Multilayer Optical Networks
Get PDFProviding differentiated quality of service became more and more important. This is not only because some service requests a high quality and real time transportation, but also because other services such as the capacity greedy applications request a higher bandwidth. In the meantime, has been the hybrid architecture consists of IP/MPLS domain and ASON/GMPLS optical domain projected as the infrastructure of the future internet. This architecture supports the transportation of the in near future expected data traffic on the ASON/GMPLS over DWDM optical domain, whereas it supports all the IP based service applications using the IP/MPLS domain. However, supporting service differentiation in multi-domain multilayer optical networks require the invention on routing scheme that supports both routing policies, the Physical Topology First (PTF) and Virtual Topology First (VTP), which are used to accommodate traffic in multilayer networks. In this work we use a hierarchical routing algorithm to evaluate the service differentiation schemes that are known in the literature in an IP/MPLS over ASON/GMPLS multi-domain network scenario, these service differentiation schemes are the Routing Policy Differentiation (RPD), Virtual Topology Differentiation (VTD) and Virtual Topology Sharing (VTS). 
Software Construction for the Estimation of the Linguistic Level and Test Difficulty
Get PDFFor this survey a new linguistic level evaluation and test measurement software has been created. This particular software has assisted in detection matters regarding readability and it has also allowed text readability measurement with the use of common grading systems, including readability measurement formulas. This system accepts various examination topics, which are classified according to the level of difficulty and where all kinds of tests are represented and it controls all the linguistic level and difficulty goals. The choice of topics and its inclusion is conducted with the sampling method. During this experimental application of our software, a field survey was conducted during which not only university students but also a lot of internet users were called to evaluate this programme