International Journal of Computer and Information Technology
Not a member yet
138 research outputs found
Sort by
Research Methods in Machine Learning: A Content Analysis
Get PDFResearch methods in machine learning play a pivotal role since the accuracy and reliability of the results are influenced by the research methods used. The main aims of this paper were to explore current research methods in machine learning, emerging themes, and the implications of those themes in machine learning research. To achieve this the researchers analyzed a total of 100 articles published since 2019 in IEEE journals. This study revealed that Machine learning uses quantitative research methods with experimental research design being the de facto research approach. The study also revealed that researchers nowadays use more than one algorithm to address a problem. Optimal feature selection has also emerged to be a key thing that researchers are using to optimize the performance of Machine learning algorithms. Confusion matrix and its derivatives are still the main ways used to evaluate the performance of algorithms, although researchers are now also considering the processing time taken by an algorithm to execute. Python programming languages together with its libraries are the most used tools in creating, training, and testing models. The most used algorithms in addressing both classification and prediction problems are; Naïve Bayes, Support Vector Machine, Random Forest, Artificial Neural Networks, and Decision Tree. The recurring themes identified in this study are likely to open new frontiers in Machine learning research.
Efficient Dynamic Group Signature Scheme with Verifier Local Revocation and Time-Bound Keys using Lattices
Get PDFRevocation is an important feature of group signature schemes. Verifier Local Revocation (VLR) is a popular revocation mechanism which involves only verifiers in the revocation process. In VLR, a revocation list is maintained to store the information about revoked users. The verification cost of VLR based schemes islinearly proportional to the size of recvocation list. In many applications, the size of revocation list grows with time, which makes the verification process expensive. In this paper, we propose a lattice based dynamic group signature using VLR and time bound keys to reduce the size of revocation list to speed up the verification process. In the proposed scheme, an expiration date is fixed for signing key of each group member, and verifiers can find out (at constantcost) if a signature is generated using an expired key. Hence revocation information of members who are revoked before signing key expiry date (premature revocation) are kept in revocation list, and other members are part of natural revocation. This leads to a significant saving on the revocation check by assuming natural revocation accounts for large fraction of the total revocation. This scheme also takes care of non-forgeability of signing key expiry date
An Effective Service Mechanism to Achieve Low Query Latency along with reduced Negative Acknowledgement in iVANET: An Approach to Improve Quality of Service in iVANET
Get PDFThe Internet Based vehicular ad hoc network (iVANET) combines a wired Internet and vehicular ad hoc networks (VANETs) for developing a new generation of ubiquitous communicating. The Internet is usually applied in vehicle to infrastructure (V2I) solution whereas ad hoc networks are used in vehicle to vehicle (V2V) communication. Since vehicular networks is characterized by High speed dynamically changing network topology The latency is one of the hot issues in VANET which is proportional to the source-&-remote vehicle distance and the mechanism involved in accessing source memory. If the distance between data source and the remote vehicle is wittily reduced by using redefined caching technique along with certain cache lookup mechanism, the latency is likely to be reduced by a significant factor in iVANET. This paper studies and analyzes various cache invalidation schemes including state of art ones and come with a novel idea of fructifying network performance within the purview of query latency and negative acknowledgement in iVANET. In this paper the roles of the mediatory network component are redefined with associative service mechanism which guarantees reduced query latency as well as minimizes negative acknowledgements in iVANET environment
Web and Social Media Presence in the Hospitality Industry: A Greek Island Case
Get PDFThe new opportunities offered by emerging technologies for better tourist services have affected the hospitality sector. Specifically, the use of the Web, in general, and the social media influence travelers’ choices. Therefore, it is important for modern hotel businesses to be actively involved and present on the Web and social media. Moreover, COVID-19 outbreak has highlighted the importance for better choices that guarantee safety that must be made in advance. This study tries to investigate the use of the Web and social media by the hospitality sector in Greece using automated evaluation tools. The case study of the Rhodes island is selected as one of the most popular destinations in Greece for both internal and external tourists. Agritourism was also taken into account. Results show that the websites and Facebook are the most preferred tools for online presence, whereas there is low use of Instagram, LinkedIn and Twitter
Neutrosophic Triangular Fuzzy Travelling Salesman Problem Based on Dhouib-Matrix-TSP1 Heuristic
Get PDFIn this paper, the Travelling Salesman Problem is considered in neutrosophic environment which is more realistic in real-world industries. In fact, the distances between cities in the Travelling Salesman Problem are presented as neutrosophic triangular fuzzy number. This problem is solved in two steps: At first, the Yager’s ranking function is applied to convert the neutrosophic triangular fuzzy number to neutrosophic number then to generate the crisp number. At second, the heuristic Dhouib-Matrix-TSP1 is used to solve this problem. A numerical test example on neutrosophic triangular fuzzy environment shows that, by the use of Dhouib-Matrix-TSP1 heuristic, the optimal or a near optimal solution as well as the crisp and fuzzy total cost can be reached
Using Feature Selection Methods to Discover Common Users’ Preferences for Online Recommender Systems
Get PDFRecommender systems have taken over user’s choice to choose the items/services they want from online markets, where lots of merchandise is traded. Collaborative filtering-based recommender systems uses user opinions and preferences. Determination of commonly used attributes that influence preferences used for prediction and subsequent recommendation of unknown or new items to users is a significant objective while developing recommender engines. In conventional systems, study of user behavior to know their dis/like over items would be carried-out. In this paper, presents feature selection methods to mine such preferences through selection of high influencing attributes of the items. In machine learning, feature selection is used as a data pre-processing method but extended its use on this work to achieve two objectives; removal of redundant, uninformative features and for selecting formative, relevant features based on the response variable. The latter objective, was suggested to identify and determine the frequent and shared features that would be preferred mostly by marketplace online users as they express their preferences. The dataset used for experimentation and determination was synthetic dataset. The Jupyter Notebook™ using python was used to run the experiments. Results showed that given a number of formative features, there were those selected, with high influence to the response variable. Evidence showed that different feature selection methods resulted with different feature scores, and intrinsic method had the best overall results with 85% model accuracy. Selected features were used as frequently preferred attributes that influence users’ preferences
Developing Hybrid-Based Recommender System with Naïve Bayes Optimization to Increase Prediction Efficiency
Get PDFCommerce and entertainment world today have shifted to the digital platforms where customer preferences are suggested by recommender systems. Recommendations have been made using a variety of methods such as content-based, collaborative filtering-based or their hybrids. Collaborative systems are common recommenders, which use similar users’ preferences. They however have issues such as data sparsity, cold start problem and lack of scalability. When a small percentage of users express their preferences, data becomes highly sparse, thus affecting quality of recommendations. New users or items with no preferences, forms cold start issues affecting recommendations. High amount of sparse data affects how the user-item matrices are formed thus affecting the overall recommendation results. How to handle data input in the recommender engine while reducing data sparsity and increase its potential to scale up is proposed. This paper proposed development of hybrid model with data optimization using a Naïve Bayes classifier, with an aim of reducing data sparsity problem and a blend of collaborative filtering model and association rule mining-based ensembles, for recommending items with an aim of improving their predictions. Machine learning using python on Jupyter notebook was used to develop the hybrid. The models were tested using MovieLens 100k and 1M datasets. We demonstrate the final recommendations of the hybrid having new top ten highly rated movies with 68% approved recommendations. We confirm new items suggested to the active user(s) while less sparse data was input and an improved scaling up of collaborative filtering model, thus improving model efficacy and better predictions
Development of an Android Mobile App for Real Time Maize Stem Borers Monitoring in Precision Farming
Get PDFDevelopment of an Android mobile app for real time maize stem borers’ monitoring in precision agriculture is presented. In farmland, cultivated maize requires farmers’ constant care and monitoring during the developing stage to avoid sudden attack of insect pests such as stem borers in the field. The maize monitoring process taken by farmers to ensure attack free and healthy growth is very strenuous and time consuming. The sudden invasion of the Spodoptera species (stem borers) to maize farm early 2016 caused huge loss to farmers and imposed food scarcity in the land. These species are hardly distinguished from one another by farmers in the farm because they look alike in appearance. Rural farmers do not know the right insecticides to apply for the effective control of these species. These issues kept on lingering and now have become serious concern to farmers. Hence, this work is to bridge the gap by providing android mobile app that would enable farmers to effectively monitor these species remotely. The mobile app architecture consists of various sections such as captured insects, categories of spodoptera species, insect pest population plots, determination of economic injury level (EIL) and economic threshold (ET), and control measure was successfully designed. The mobile app structure and behavior were also designed using Unified Modeling Language (UML). The maize Stem borers App was developed in android studio using Kotlin programming language. The App is linked to the cloud server where all the captured and recognized species are stored for downloading and farmers’ visualization. The Internet of Things (IoT) hardware was setup in the maize farm which captured these targeted insect pests, processed via Nividia Jetson Nano and sent to the cloud server. The mobile App synchronized successfully with the cloud server and could download stored maize insect pests in the farmer’s Android phone
Reuse Alternatives based on the Sources of Software Assets
Get PDF
Abstract— Since the idea of software reuse appeared in 1968, software reuse has become a software engineering discipline. Software reuse is one of the main techniques used to enhance the productivity of software development, which it helps reducing the time, effort, and cost of developing software systems, and enhances the quality of software products. However, software reuse requires understanding, modifying, adapting and testing processes in order to be performed correctly and efficiently. This study aims to analyze and discuss the process of software reuse, identify its elements, sources and usages. The alternatives of acquiring and using software assets either normal or reusable assets are discussed. As a result of this study, four main methods are proposed in order to use the concept of reuse in the software development process. These methods are proposed based on the source of software assets regardless the types of software assets and their usages
A Review on the Methods of Evaluating the New Approaches Proposed in the Agile Context
Get PDFIn the recent years, Agile is being one of the emerging technologies adopted by numerous organizations. The Agile methods have not received a wide acceptance within the software development organizations (SDOs), but they are also being extensively employed in different fields and environments. Accordingly, new approaches have been proposed by researchers and practitioners based on the Agile context, however, there is scarce and – sometimes - absence of describing the evaluation process of these approaches. Therefore, this paper reports the findings of an extensive literature search on how the new proposed approaches are being evaluated. The narrative review methodology was employed to criticize and summarize a body of literature retrieved from various scientific sources. The results reveal that there are various methods used for evaluating the proposed Agile approaches. Nevertheless, this review focuses on explaining the five common methods, which are: (1) case study, (2) survey, (3) interview, (3) focus group, and (5) expert review. Thereafter, the authors discuss the key findings and highlight directions for future researches. This study tends to help researchers and practitioners to select the suitable evaluation methods when constructing new Agile approaches.