Authors:Sunday A. Idowu, Adewale O. Adebayo, Chigozirim Ajaegbu, Oluwatofunmi O Adetunji Pages: 1 - 8 Abstract: Consistent access to web application contents is of paramount importance to its end users. Irrespective of a user’s location and the internet condition, there is the desire to interact with web applications, particularly through the use of mobile devices. Attempts have been made by previous researchers to introduce the Hypertext Transfer Protocol (HTTP) caching otherwise known as the browser cache which is automatically enabled by the browser and the Application Cache (AppCache) as an attempt to foster offline accessibility. While these approaches have helped, there still exists the problem of poor memory management and content validity.A systematic Literature Review (SLR) was done on existing techniques, after which an overview of Service Workers (SW) and the identification of various SW caching strategies were proposed. Any of the proposed SW strategies can be adopted by web application developers based on the network condition and the contents of the application as this will help in reducing the loading time of the application, promote efficient mobile memory management, and increase the number of active users PubDate: 2022-04-20 DOI: 10.26483/ijarcs.v13i2.6810 Issue No:Vol. 13, No. 2 (2022)
Authors:Mohammed Hussein Jabardi Pages: 9 - 17 Abstract: Performance factors analysis has recently gained popularity as a method for assessing how students' environments affect their academic performance. However, most of the progress has been made in analyzing student behaviour during the learning process. Machine Learning provides many powerful methods that could improve student performance prediction. Our aim is to examine all features of students' environmental life using the machine learning paradigm to assess how students' environment affects their grades. These features are divided into three categories (personality, family, and education) and their impact factors are calculated. To improve predictive accuracy, different models (Random Forest, AdaBoost, Decision Tree, Naive Bayes, and Multi-Layer perceptron) are used to score the features in each group according to their contribution to the solution. Results show that personality features are a minor effect on students' academic performance with 53%. Concerning the educational factors, outcomes offer the average impact was 60%. Regarding family factors, results indicate that students' family life significantly affects academic achievement with 64%. PubDate: 2022-04-20 DOI: 10.26483/ijarcs.v13i2.6813 Issue No:Vol. 13, No. 2 (2022)
Authors:Nazeer Haider Pages: 18 - 27 Abstract: Recent years have seen a significant increase in interest in object detection, which is considered to be one of the most fundamental and demanding computer vision tasks. It might be called the pinnacle of computer vision history, because of its rapid progress since 2005. If we regard today's object identification to be a kind of deep learning-powered technical aesthetics, then rewinding the clock since 2005 would allow us to observe the wisdom of the cold war period. This study examines studies on object detection since 2005 in the context of technological advancements that have occurred throughout a quarter-century. This article covers a wide range of subjects, including historical milestone detectors, metrics, datasets, speed-up strategies, etc. This article also reviews important traditional object detections (DPM and HOG), single-stage object detection methods (YOLOR, RetinaNet, SSD, YOLO), and two-stage object detection methods (Mask-RCNN, Faster-RCNN, Fast-RCNN, SPPNet, R-CNN). PubDate: 2022-04-20 DOI: 10.26483/ijarcs.v13i2.6804 Issue No:Vol. 13, No. 2 (2022)
Authors:Archana R Thakur Pages: 28 - 31 Abstract: Data mining is the practice of extracting concealed, helpful patterns and information from data. It is a novel technology that assists organizations to forecast future trends and actions, permitting them to make practical, knowledge driven decisions. The present work describes the data mining process and how it can assist decision makers to take better decisions. Practically, data mining is very fruitful for large sized organizations with huge amount of data. It also helps to augment the net profit, as a result of correct decisions taken during the right time. This paper presents the various steps taken during the data mining process and how organizations can get better answer queries from huge datasets. It also presents detailed review on data mining methods and applications. PubDate: 2022-04-20 DOI: 10.26483/ijarcs.v13i2.6807 Issue No:Vol. 13, No. 2 (2022)
Authors:Preetpal Kaur Buttar Pages: 32 - 38 Abstract: India is a country with many cultures and if you travel from one place to another, you might find yourself in totally different culture. This also means the languages change from place to place in India and it gets very difficult to read signboards, shop names and even many other common things written in local languages. This can create problems for not only the travelers travelling from other countries but also the people who move withing the country from different regions. But most of the signboards, shop names or other landmarks mostly use English or Hindi in most of the regions. Here we propose a complete text detection & recognition as well as transliteration system that will help travelers read text written in Hindi on any signboards or shops and then transliterate that detected text into English. The proposed system is capable of detecting text written in Hindi language in natural environment using Progressive Scale Expansion algorithm and then transliterating the detected text into English language. Our proposed system can detect text in tough scenarios, and it can even detect curved text from natural images. Our system after detecting text region, extracts the text from the detected area using PyTesseract OCR engine and then the extracted text is further transliterated into English text with the help of seq2seq MultiRNN LSTM model which gives us accurate transliterations without losing the actual pronunciation of the original Hindi words. We use a synthetic dataset for Hindi Text images containing approx. 100000 for Text Detection and FIRE2013 dataset for transliteration. The overall system is evaluated using BLEU score. PubDate: 2022-04-20 DOI: 10.26483/ijarcs.v13i2.6808 Issue No:Vol. 13, No. 2 (2022)
Authors:P Sudhakara Babu, K Satishkumar, K Chandan Pages: 39 - 44 Abstract: In this study, the process of finding performance measures of N* is the optimal threshold , L is the expected system length and T(N*) is the minimum expected cost for an optimal strategy analysis of N-policy FM / FM / 1 Vacation Queueing system with server Start-up and Time-out, in which the arrival rate and service rate triangular and trapezoidal fuzzy numbers are proposed. By using L-R method the L-R method is smaller and more convenient differentiate to alpha-cuts method. The cogency of the model is study by numerical example. PubDate: 2022-04-20 DOI: 10.26483/ijarcs.v13i2.6811 Issue No:Vol. 13, No. 2 (2022)
Authors:Shweta A.Gudadhe, Dr.Archana O. Vyas Pages: 45 - 48 Abstract: Diabetes retinopathy is a long-term condition that damages the retina and other portions of the diabetic patient's body, including the eyes. The people with Diabetic retinopathy who have been suffering for a long time would go blind even if it reached its extreme. Diabetic retinopathy's devastating effects can be minimised if individuals are diagnosed as soon as possible. Diabetic retinopathy must be detected early if a person is to have a chance of regaining their vision and receiving proper treatment. Diabetic retinopathy can be detected from retinal fundus images using image processing and deep learning, as shown in this work. An extraction phase and a classification phase are both included in the proposed study. By segmenting blood vessels and recognising micro aneurysms in digital fundus images, we were able to extract the most relevant information. After a Convolution Neural Network was used to analyse the images, the classification was carried out. Diabetic retinopathy can be diagnosed from retinal fundus pictures using the proposed method, according to the results. PubDate: 2022-04-20 DOI: 10.26483/ijarcs.v13i2.6812 Issue No:Vol. 13, No. 2 (2022)
Authors:Wumi AJAYI, Obi Ibeto; Taiwo Olomola Mathias Madewa Pages: 49 - 55 Abstract: Modern means of communication have improved the way of life of humans around the world. Never has there been a time of unprecedented innovation in the way we humans communicate and share information with one another. Modern Technology has made it conceivable to keep in contact with our family, companions, and colleagues. Modern applications like Zoom, Google Hangout and Microsoft Teams have seen a geometric increase in new users and this growth has reflected the company’s share price. However, the use of modern technology has brought with it issues and concerns in terms of cyberthreats. This study helps to identify modern cybersecurity threats and how to effectively mitigate against them.The methodology used for this study was based on literature search and analysis, we also used model adaptation from generic ones.Our finding show that Organizations now need to grapple with these unprecedented threats and find effective solutions to protect their data, applications, and people from the risk of cyber-attacks and at the same time ensure they adhere strictly to regulatory requirements. This paper sheds light on the modern cyber security threat and identifies methods of mitigating against these threats. This paper can also be used as a Cyber security survival guide to investigate information and protect against cybersecurity threats in an organization.In conclusion, the aim of this paper review is to explore the more recent Cybersecurity threats and recommend effective method that can be adopted at an organizational level to guards against these persistent threats. PubDate: 2022-04-22 DOI: 10.26483/ijarcs.v13i2.6815 Issue No:Vol. 13, No. 2 (2022)
Authors:Wumi Ajayi, Owolabi Bukola, Ahmed Jolaosho Pages: 56 - 63 Abstract: Software testing is an important step in the creation of software products. Automation is critical in the software industry because it enables software testing firms to increase their test efficiency. Researchers have worked on a variety of automated ways for producing test data to evaluate generated software with various disadvantages. This paper therefore, presented Genetic Algorithm (GA)-based test techniques to automate the development of structural-oriented test data. In this work, random test cases are first generated, then, mutates testing is applied to check it. If satisfied, then process stops. Genetic Algorithms are utilized, since they offered a technique of automatically generating test cases. PubDate: 2022-05-01 DOI: 10.26483/ijarcs.v13i2.6814 Issue No:Vol. 13, No. 2 (2022)
Authors:Hema S, Dr.Kangaiammal A Pages: 64 - 69 Abstract: Steganography is the art of hiding secret information within other information that is digitally concealed. It protects the confidentiality of two communicating parties. Information hiding is a highly strong and adaptable strategy that may be used to protect vital information in a variety of situations. There are several steganography techniques available, each with its own set of advantages and disadvantages. This study presents a new data hiding mechanism that hides file information in text cover messages to safeguard user data from vulnerabilities. It also utilize a deduplication strategy that employs the suggested DSHA algorithm to reduce repeated data storage. This novel technique ensures security while maintaining confidentiality. PubDate: 2022-05-01 DOI: 10.26483/ijarcs.v13i2.6817 Issue No:Vol. 13, No. 2 (2022)
Open Access journal
