首页期刊导航|International journal of software science and computational intelligence
期刊信息/Journal information
International journal of software science and computational intelligence
IGI Publishing
IGI Publishing
季刊
1942-9045
International journal of software science and computational intelligence/Journal International journal of software science and computational intelligence
Appati, Justice KwameNartey, Prince KofiYaokumah, WinfredAbdulai, Jamal-Deen...
702-718页
查看更多>>摘要：Biometric authentication is gaining ground in security-related issues in business, corporate management, and other settings. A considerable amount of research has been conducted in this area, yet further research into its betterment is still an emerging trend. This article presents a study of the published empirical research on some fingerprint recognition techniques widely in use. The study is limited to articles that explicitly discuss techniques used in recognizing a person's fingerprint. It employs a systematic mapping design, which proposes a categorical system to classify the research results based on the selected articles' topics. The categories include work distribution by year of publication, datasets used, fingerprint recognition approaches, metrics, and evaluation. This study shows the direction of currently performed empirical research on fingerprint recognition by comparing the selected published work to the classification criteria and evaluating them.
查看更多>>摘要：Computation of an optimal coverage and connectivity-aware wake-up schedule of sensor nodes is a fundamental research issue in a 3D-wireless sensor network. Most of the existing metaheuristic-based wake-up scheduling schemes do not make sure optimal solution and occasionally smacked in local minima. This paper proposes a hybrid metaheuristic-based wake-up scheduling scheme (Memtic-Tabu-based-WS) where best feature of memtic algorithm and Tabu Search algorithm is combined. The proposed scheme has considered four parameters such as energy consumption, coverage, connectivity, and optimal size of schedule list. Performance comparison of the proposed Memtic-Tabu-based-WS scheme is performed in different network scenarios and compared with three well-known state-of-the-art schemes in terms of coverage ratio, active sensor nodes, and fitness value. The result analysis validates the superiority of the proposed scheme over the existing schemes with better coverage ratio and derivation of the optimal wake-up schedule.
查看更多>>摘要：Optimization problems are challenging, but the larger challenge is to deal with the energy issue of the cloud, with continuous dynamic load and fluctuating VM performance. The optimization technique aids in efficient task-resource mapping ensuring optimal resource utilization with minimum active hosts and energy consumption. Existing works focused on time-invariant and bounded VM performance with major concentration on minimizing the execution cost and time. A multi-objective adaptive manta-ray foraging optimization (MAMFO) has been proposed in the paper for efficient scheduling with optimum resource utilization and energy consumption. The paper contributes by considering the time-varying VM performance and performance prediction using a dynamic time-series based ARIMA model, filtering out the VMs with larger fluctuating possibility, and employing only the selected VMs to be scheduled using MAMFO to meet the optimization goal with minimum SLA violations. The experimental analysis improves the work efficiency (e.g., energy consumption attained to be 0.405 kWh, and 5.97% of SLA violations).
查看更多>>摘要：The growing number of connected IoT devices and their continuous data collection will generate huge amounts of data in the near future. Edge computing has emerged as a new paradigm in recent years for reducing network congestion and offering real-time IoT applications. Processing the large amount of data generated by such IoT devices requires the development of a scalable edge computing environment. Accordingly, applications deployed in an edge computing environment need to be scalable enough to handle the enormous amount of data generated by IoT devices. The performance of MSA and monolithic architecture is analyzed and compared to develop a scalable edge computing environment. An auto-scaling approach is described to handle multiple concurrent requests at runtime. Minikube is used to perform auto-scaling operation of containerized microservices on resource constraint edge node. Considering performance of both the architecture and according to the results and discussions, MSA is a better choice for building scalable edge computing environment.
查看更多>>摘要：The migration of the banking system to the cloud seems inevitable in the near future like any other industry. By leveraging cloud technology, the personal and financial data of any customer can be accessed and controlled by third-party service providers. However, in order to maintain confidentiality, this information should be kept in an encrypted format, which has an impact on the usefulness and flexibility of fundamental operations like search. Moreover, in a financial institution, a data owner may want to provide the searching capability to the users from diverse domains. Therefore, to provide such flexibility, a system of multi-authority fine-grained search is introduced where each authority manages a single but entirely disjointed domain of attributes. As a result, the proposed system is more scalable. It can handle a large number of users from diverse domains and manage their credentials effectively while most of the schemes in the literature lack this feature and have a performance bottleneck because of a single centralized trusted authority.
查看更多>>摘要：In today's digital era, Twitter's data has been the focus point among researchers as it provides specific data in a wide variety of fields. Furthermore, Twitter's daily usage has surged throughout the coronavirus disease (COVID-19) period, presenting a unique opportunity to analyze the content and sentiment of COVID-19 tweets. In this paper, a new approach is proposed for the automatic sentiment classification of COVID-19 tweets using the adaptive neuro-fuzzy inference system (ANFIS) models. The entire process includes data collection, pre-processing, word embedding, sentiment analysis, and classification. Many experiments were accomplished to prove the validity and efficiency of the approach using datasets COVID-19 tweets, and it accomplished the data reduction process to achieve considerable size reduction with the preservation of significant dataset's attributes. The experimental results indicate that fuzzy deep learning achieves the best accuracy (i.e., 0.916) with word embeddings.
Gladston, AngelinSharmaa, Arjun, IBagirathan, S. S. K. G.
814-827页
查看更多>>摘要：Gross domestic product is the main measure used predominantly for assessing the wealth and growth of a country. Previous works used the amount of CO2 emitted by a country in predicting the gross domestic product growth of that quarter. Though it is a valid indicator, there are many other features that can be considered while calculating the gross domestic product of a country. In this paper, an approach to predict gross domestic product utilizing many features is introduced. Macroeconomic data like unemployment rate, gold rate, foreign exchange rate, and other important data to plot the graph are used for linear regression, employing dimensionality reduction to analyze and extract only the important features and thereby increasing the effectiveness of the proposed GDP prediction. Since data has been published in different time intervals, preprocessing like interpolation, reshaping, and dimensionality reduction using PCA are carried out to make the proposed GDP prediction model more precise and accurate, and the maximum accuracy of 95% is obtained.
查看更多>>摘要：Smart cities and smart homes have a larger number of devices requiring continuous electricity. An inverter circuit is often used to cope up with power failures. Such inverters can also be used in the period of high demand for power to reduce the load on the grid. On the other hand, utilizing renewable energy is an important aspect of sustainable development. A solar-powered inverter reduces the usage of grid power and makes efficient utilization of solar energy. Further, the inverter can be integrated with microcontrollers to work on predetermined time slots to substitute the grid power. This paper describes the design of a novel solar-powered smart inverter that automatically switches the power supply from the grid to the inverter during peak hours. It is designed to suit smart home requirements up to 1 kW and a holistic design is presented. The performance of the circuit is analyzed and compared with similar works in literature to show the improvements. Simulations and hardware implementations show that the proposed system ensures an uninterrupted power supply for smart homes.
Srivastava, DeepakChui, Kwok TaiArya, VarshaGarcia Penalvo, Francisco Jose...
849-859页
查看更多>>摘要：Proteins are fundamental compounds in biological processes during the analysis of drug target indication for drug repurposing. The identification of relevant features is a necessary step in determining protein structure. A classification technique is used to identify the most important features in a dataset, which is why feature selection is so important. For protein structure prediction, recent research has developed a wide range of new methods to improve accuracy. The authors use principal component analysis (PCA) with correlation-matrix-based feature selection to analyse breast cancer data. In this paper, they discussed a therapeutic agent that is used to reduce the dataset by reduction-based algorithm and after that applied reduced dataset labelled as Standard Gold Dataset on machine learning model to analyze drug target indication. They get the higher accuracy of 92.8%, 93.9%, and 95.3%, each of the three datasets with 200, 500, and 1000 features with SVM with RBF kernel function. Also they found the best result, 97.8%, with the same classifier.
查看更多>>摘要：The distributed publication and subscription for the internet of things is a model of communication between devices that is simple and powerful. In comparison with other variant problems of ME, the problem considered here is a group mutual exclusion problem. The specificity of an IoT system is that a process can be in more than one group at the same time, which is not the case of the algorithms mentioned in the literature where a process request is one group in advance for each request. In this paper, the authors define formally the notion of group. Furthermore, they propose a distributed algorithm for automatic group generation and show that this problem is maximal cliques problem. This leads to a new kind of distributed maximal cliques algorithm to compute the groups suitable for IoT systems. As an application, they propose an IoT-based intersection traffic light management system for vehicles.
NETL
NSTL
Igi Global