International Journal of Computer (IJC - Global Society of Scientific Research and Researchers, GSSRR)
Not a member yet
459 research outputs found
Sort by
Virtual Training in the Police Domain
Get PDFDubai Police has employed cutting-edge video game technologies to create innovative virtual incidents ranging from crime scenes to traffic accidents to hostage scenarios in an engaging way that mimics real-life situations to allow the trainee to learn-by-doing to harness his skills in a safe and practical environment. The importance of such an innovative approach has been realized early on to enhance and support the traditional methods employed for learning and awareness. Over many years, Dubai Police researched and developed many virtual environment prototypes with a large portfolio of virtual environment products to reach the current state. These products have been replicated in different fields and are shaping up a technological transformation for the methods used in learning and awareness in the Police domain and beyond. Additionally, these products have been used and recommended nationally, regionally, and internationally. It is essential to highlight that all of these products have been developed in-house using Dubai Police personnel within the Virtual Technology Centre in Dubai Police and cover the four strategic goals of Dubai Police
Predicting DDoS Attacks Preventively Using Darknet Time-Series Dataset
Get PDFThe cyber crimes in today’s world have been a major concern for network administrators. The number of DDoS attacks in the last few decades is increasing at the fastest pace. Hackers are attacking the network, small or large with this common attacks named as DDoS. The consequences of this attack are worse as it disrupts the service provider’s trust among its customers. This article employs machine learning methods to estimate short-term consequences on the number and dimension of hosts that an assault may target. KDD Cup 99, CIC IDS 2017 and CIC Darknet 2020 datasets are used for building a prediction model. The feature selection for prediction is based on KDD Cup 99 and CIC IDS 2017 dataset; CIC Darknet 2020 dataset is used for prediction of impact of DDoS attack by employing LSTM (Long Short Term Memory) algorithm. This model can help network administrators to identify and preventively predict the attacks within five minutes of the commencement of the potential attack
A Review of Question Answering Systems: Approaches, Challenges, and Applications
Get PDFQuestion answering (QA) systems are a type of natural language processing (NLP) technology that provide precise and concise answers to questions posed in natural language. These systems have the potential to revolutionize the way we access information and can be applied in a wide range of fields including education, customer service, and health care.There are several approaches to building QA systems, including rule-based, information retrieval, and machine learning-based approaches. Rule-based systems rely on predefined rules and patterns to extract answers from a given text, while information retrieval systems use search algorithms to retrieve relevant information from a large database. Machine learning-based systems, on the other hand, use training data to learn to extract answers from text.One of the main challenges faced by QA systems is the need to understand the context and intent behind a question. This requires the system to have a deep understanding of the language and the ability to make inferences based on the given information. Another challenge is the need to extract relevant information from a large and potentially unstructured dataset.Despite these challenges, QA systems have a wide range of applications, including education, customer service, and health care. In education, QA systems can be used to provide personalized learning experiences and help students learn more efficiently. In customer service, QA systems can be used to handle a high volume of queries and provide quick and accurate responses to customers. In health care, QA systems can be used to assist doctors and patients by providing timely and accurate information about medical conditions and treatments.Overall, this review aims to provide a comprehensive overview of QA systems, their approaches, challenges, and applications. By understanding the current state of development and the potential impact of QA systems, we can better utilize these technologies to improve various industries and enhance the way we access information
Effectiveness of Awareness and Willingness to Use EFDs in Sealing Corruption Loopholes in Tanzanian Tax Collection System: A Case of Mbeya City
Get PDFThis study aimed to investigate the effectiveness of awareness and willingness to use Electronic Fiscal Devices (EFDs) in sealing corruption loopholes in the Tanzanian tax collection system. The study used a case study strategy to achieve this goal, involving a sample of 152 EFD users selected from a population of 1500 EFD registered taxpayers in Mbeya city. A validated questionnaire was used to collect respondents’ data using a systematic random sampling technique. It also used Cronbach’s Alpha coefficient tests to examine the reliability of the scales. Data analyses were done with the help of SPSS, from which descriptive statistical outputs such as percentages were interpreted into meaningful results. The study discovered a statistically significant relationship between taxpayers’ awareness and willingness to use EFDs and sealing corruption loopholes in the Tanzanian tax collection system. The study’s findings generally show that a high level of taxpayers’ awareness of EFDs and their greater willingness to use EFDs aid in sealing corruption loopholes in the Tanzanian tax collection system. Therefore, the study recommends that the Tanzania Revenue Authority (TRA) enhance taxpayers’ awareness of EFDs and their willingness to use EFDs to seal corruption loopholes in the Tanzanian tax collection system. This awareness and willingness will increase tax revenue collection, which is vital for the country’s social-economic development
Survey Analyses of The Specific Impacting Factors in Devising a Machine Learning Prediction model for The General Election Process in Kosovo
Get PDFThe focus of the research study was analyses of impacting factors and later to incorporate those insights into variables to be measured for devising a machine learning predictive model for prognosis and prediction of the general election turnout in Kosovo. We have developed a novel method for recognizing the main impacting factors in elections. Our method shows that finding out whether different ways of collecting different data of election voters can lead to much better prediction and understanding of the election process. In order to do that we needed to analyze the specific impacting factors in the election process in Kosovo are investigated during the study. The data has derived from an originally collected survey dataset that contains the impacting factors previously identified and assessed regarding the general parliamentary elections in Kosovo has been realized. Insights and recommendation has been discussed and argumented
Predictive Model for Computing Health Insurance Premium Rates Using Machine Learning Algorithms
Get PDFThe health care systems depend heavily on out-of-pocket payments, the mechanism that is a barrier to universal health coverage, as it contributes to inefficiency, inequity and cost. To solve this challenge, people are encouraged to enrol on health insurance schemes to reduce the burden of out-of-pocket payments. There is a strong need for insurance companies to develop models that accurately predict medical expenses for the insured population. The variables; Age, sex, body mass index, number of children and region attributes were used to formulate a predictive model to determine health insurance charges using different Machine learning algorithms techniques. The findings showed that the following variables were significant; age (p = 0.000), BMI (p = 0.001), smoking (p = 0.000) and region (0.046). Therefore, these attributes can be said to be the determinants of health insurance charges. Five (5) models that were used in predictive analysis were evaluated. These models were Multiple Linear Regression (MLR), K-nearest Neighbors (KNN), Least Absolute Shrinkage and Selection Operator (LASSO), Extreme Gradient Boosting (Xgboosting) and Random Forest Regression (RFR) The models’ performance evaluation findings indicated Gradient Boosting and RFR were the best models in prediction with the following values R2 = 85.5%, MAE = 2688.2, RMSE = 4748.7 and R2 = 85.3%, MAE = 2726.4, RMSE = 4783.8 respectively. The insurance companies that seek to develop a model for prediction premiums are recommended to use Extreme Gradient Boosting and RFR for a more accurate mode
Enhanced DNA Encoding Scheme in Honey Encryption
Get PDFNowadays, Security plays a vital role in protecting sensitive data from attackers in many organizations. Many researchers have developed security research to prevent attacks. Password-based encryption (PBE) is used to prevent an attacker from attempting to break into the password file. However, the current PBE is vulnerable because attackers can easily access keys by attempting again and again. The use of weak passwords in PBE is an ongoing problem. At present, Honey Encryption (HE) is an encryption method that overcomes (PBE) vulnerabilities. It is resistant to brute force attacks and allows encryption of data using minimal keys. HE generates a plausible message that looks real when the attacker decrypts with an incorrect key. Deoxyribo Nucleic Acid (DNA) is a new way of computing used in medical research. In this paper, DNA sequences are generated as the key distribution of Honey Encryption. The main idea of the paper is five random data lookup tables in the DNA encoding scheme in order to be more secure. It will be shown as the experimental results the same message encryption with the different passwords and the encryption of the different messages with the same password. In this system, diagnosis symptoms such as Influenza, Toothpaste, etc., will be used as the input messages of the DNA scheme. Compared to the results of only one data lookup table, it can be seen that the result of five data lookup tables in the key generation of DNA encoding sequence is more secure and less execution time. According to the experimental results, the proposed method is more secure than the existing method
Code Writing Problem in Python Programming Learning Assistant System
Get PDFTo advance python programming knowledge of students, Python Programming Learning Assistant System (PYPLAS) is elaborated. Currently, PYPLAS included the element fill-in-blank problem and error debugging problem to improve the student’s python programming skill. Then, students learn python testing techniques such as unit test (PYUNIT), PYTEST and coverage, etc. In this paper, PYPLAS provides the code writing problem so that students can learn the python code testing and write the python code according to test code. So, code writing problem is generated by using Test Driven Development (TDD) method. Teacher gives the test code to students. Students answer the program code according to test code by using unit test (PYUNIT). Teacher checks the answer code according to coverage in TDD method. For evaluations, 100 codes are provided to accurate the code testing and coverage approach in TDD method. 11 problems are generated and asked 5 learners from training center and universities to solve them in offline PYPLAS. Their results are checked by using coverage approach to display their correct rate. The results show the code writing problem is helpful to test the student’s coding quality
Advanced and Secure Online Web-Based Auction System
Get PDFThe advance and secure online auctioning system is a versatile approach for facilitating lot-based online auctioning system. In this paper, we will describe how to build a safe and online advance auction website. The system has been built to be extremely scalable and capable of serving huge groups of bidders in a promotional event. You may browse deals and put bids on a secure server using the online auction system. The service provider is responsible for all shipping costs. The goal is to create a user-friendly auctioning platform where any goods may be auctioned and where bidders and sellers can receive value-added services. The items will be verified, and the site will provide a secure and safe experience for online users. Auction system is further divide into two different easy platforms in which one is special designed for only the developers to maintain and update the system according the current requirements and demands while another is specific for user-end platform. It is very efficient, secure and reliable for all types of bidders, buyer and sellers. Because of its reliability, efficiency and secure platform, it is not wrong to say that this auction system is unique and can differs from all other system which are also developed and designed for the purpose of auctioning
Defensive Cybersecurity Preparedness Assessment Model for Universities
Get PDFWith the recent uptake of fiber connectivity, broadband and internet, access has become readily available to citizens all over the world. General Cyber Security threats like malware attacks, social engineering scams and financial frauds have increased. NIST and ISO standards have proposed numerous security models, but the frightening truth about escalating cyber-attacks is that most organizations/businesses, as well as the cyber security industry itself, are unprepared. This is because most existing security analysis tools focus mainly on detecting attacks. Despite the steady flow of security updates and patches, this scenario has led to a continued rise of attack surface in institutions of higher learning where students and staff sensitive information and valuable assets is of high stake. Therefore, the purpose of this study is to develop a web-based model for assessing cybersecurity preparedness in universities. This was achieved through design science methodology and engineering design process. The model provides the overview of the university’s preparedness level and the appropriate recommendations that need to be considered to remain cyber ready at all times