HighTech and Innovation Journal
Not a member yet
317 research outputs found
Sort by
Real-Time Intrusion Detection in Power Grids Using Deep Learning: Ensuring DPU Data Security
Full text linkDeep learning technologies have revolutionized the management of energy, energy consumption, and data security within smart grids through non-intrusive load monitoring (NILM). This paper explores the use of deep learning for real-time intrusion detection in power grids with a primary focus on safeguarding the integrity and security of Data Processing Units (DPUs). An evaluation of various machine learning models, including Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), Decision Trees, and Random Forests, is conducted to detect various types of intrusions, including Fault, Injection, Masquerade, Normal, and Replay. Random Forest produced AUC values of 1.00 for all classes and an overall F1-score of 0.99 for all classes. The Decision Tree model also shows robust performance for detecting Fault and Injection intrusions (AUC = 0.98), with an overall F1-score of 0.94. However, the LDA and SVM models do not perform well in detecting Injection intrusions with overall F1-scores of 0.83 and 0.86. Advances in machine learning can be used to improve smart grid security, reliability, and efficiency, according to this study. These findings highlight the potential of advanced machine learning techniques to enhance smart grid reliability and efficiency. Doi: 10.28991/HIJ-2024-05-03-018 Full Text: PD
Exploring Self-Management Practices in SMES: Insights from an Initial Survey
Full text linkSelf-managed teams are perceived as highly productive and have been actively studied in recent times. Considering this, the notion of the utility of establishing and cultivating such teams in small and medium-sized businesses in Kazakhstan has emerged, aiming to enhance their role in the country's economic development. Therefore, the authors of this article have resolved to conduct an empirical study on teams operating within the SMEs sector of Kazakhstan. This study aims to present the findings of an initial survey conducted among employees of small and medium-sized enterprises to characterize their self-management capacities and identify factors influencing their self-management abilities. For this purpose, representatives of teams in small and medium businesses in Kazakhstan were surveyed. The design of the survey questionnaire involved three field experts to validate and refine the questions. Findings reveal that approximately two-thirds of SME teams in Kazakhstan demonstrate characteristics of cross-functionality, diversity, motivation, and co-location, indicative of their self-managing nature. This suggests agile management's potential for organizational goals. To the best of the authors' knowledge, this is the first empirical study aimed to investigate how far the teams in Kazakhstani enterprises are self-managed. Doi: 10.28991/HIJ-2024-05-03-016 Full Text: PD
The Dynamic Capability, Innovation, Competitive Advantage, and Survival of Tech Startups
Full text linkThis study aims to bridge the research gap by exploring the impact of dynamic capability and innovation on startup survival. It tests the mediating roles of competitive advantage and scrutinizes the moderating role of dynamic capabilities in the relationship between innovation and startup survival. The sample group consisted of 170 tech-startups in Thailand. We calculated the sample size based on the estimated parameter ratio for each sample, which was determined using stratified random sampling. We conducted online (Google Forms) and paper (post office) surveys after systematic sampling. The analysis included confirmatory factor analysis (CFA) and structural equation modeling (SEM). The causal relationship model and the empirical data agreed well without adjusting the model, and it was found that dynamic capability did not have a direct effect on the survival of startups. However, the influence of dynamic capability and innovation on the survival of startups through competitive advantage was found to have statistical significance. Furthermore, startups can amplify the impact of innovation on competitive advantage by enhancing their dynamic capabilities. Startups can achieve this by identifying and recognizing opportunities that arise from environmental changes, absorption, and reconfiguration. The implication identified in this research is that startups have a better chance of survival when they have a competitive advantage, employ and encourage innovation, and implement dynamic capability. Doi: 10.28991/HIJ-2024-05-04-08 Full Text: PD
The Development and Evaluation of Homogenously Weighted Moving Average Control Chart based on an Autoregressive Process
Full text linkThis research aims to investigate a Homogenously Weighted Moving Average (HWMA) control chart for detecting minor and moderate shifts in the process mean. A mathematical model for the explicit formulae of the average run length (ARL) of the HWMA control chart based on the autoregressive (AR) process is presented. The efficacy of the HWMA control chart is evaluated based on the average run length, the standard deviation of run length (SDRL), and the median run length (MRL). As illustrations of the design and implementation of the HWMA control chart, numerical examples are provided. In numerous instances, a comparative analysis of the HWMA control chart relative to the Extended Exponentially Weighted Moving Average (Extended EWMA) and cumulative sum (CUSUM) control charts with mean process shifts is performed in detail. Additionally, the relative mean index (RMI), the average extra quadratic loss (AEQL), and the performance comparison index (PCI) are utilized to evaluate the performance of control charts. For various shift sizes, the HWMA control chart is superior to the Extended EWMA and CUSUM control charts. This study applies empirical data from the area of economics to validate the explicit formula of ARL values for the HWMA control chart. Doi: 10.28991/HIJ-2024-05-01-02 Full Text: PD
Development of a Technique for Discrete-Logical Decision-Making in Medical Information Systems
Full text linkOne of the urgent directions in solving medical diagnostic tasks is to develop new and improved decision support systems capable of efficiently processing polymodal data. Humans cannot always process large arrays of medical information and determine an accurate diagnosis in complex situations. Thus, improving the functioning of the industry requires implementing a variety of systems capable of supporting decision-making of one kind or another. The presented technique aims to steadily increase the level and speed, and demonstrate the feasibility of integrating non-classical logic into the structure of the decision-making system in medical research by using non-classical logic complexes. The main advantage of the proposed approach is that it achieves the necessary level of information criteria; in particular, it provides the required information quality, high reliability of the decision, its value, preserves the amount of information, and searches and decision-making take relatively small-time intervals. This paper presents an overview of various non-classical logics and, based on the analytical findings, delineates the optimal choice of logic for each stage in the development of a decision support system. The processing and feedforward structures for DSS are presented based on selected types of non-classical logic. The algorithms presented for solving decision-making problems are based on discrete-logic approximations of a priori and actual data, which are optimal or suboptimal, and they use information and value criteria. The abstraction of any problem situation relies on using means operating with frequency and comparative logic to provide logical approximations of the sought characteristics. The accuracy of the diagnostic decisions reached 97% when using the developments presented in this study. Doi: 10.28991/HIJ-2024-05-04-010 Full Text: PD
A Consumer Data Privacy Protection Model Based on Non-Parametric Statistics for Dynamic Data Publishing in e-Commerce Platforms
Full text linkObjectives: Consumer data privacy on e-commerce platforms is increasingly crucial. This study aims to investigate privacy protection mechanisms, particularly focusing on personal and corporate secrets. It seeks to understand individual perspectives on privacy and preferences for data disclosure. The primary objective is to explore methods for safeguarding personal information while maintaining data integrity. Methods/Analysis: We employ non-parametric statistical techniques to analyze consumer behavior and preferences on e-commerce platforms. This involves examining patterns of data disclosure and identifying sensitive information shared by users. By studying communication dynamics and recording practices, we assess the efficacy of current privacy protection measures. Novelty/Improvement: This study contributes to the understanding of consumer privacy protection by emphasizing the importance of non-parametric statistical methods in e-commerce research. Our findings underscore the need for enhanced privacy measures. We advocate for further research and development of innovative privacy-enhancing technologies to address evolving privacy challenges in online commerce. Findings:Our research highlights the significance of personal privacy concerns in e-commerce settings. We identify a spectrum of privacy attitudes among users, ranging from strict confidentiality to selective disclosure. Furthermore, our analysis reveals potential vulnerabilities in current privacy safeguards, particularly regarding the collection and storage of sensitive data on e-commerce platforms. Doi: 10.28991/HIJ-2024-05-02-013 Full Text: PD
Automatic Recognition Technology of Library Books Based on Convolutional Neural Network Model
Full text linkBackground: The development of technological devices has changed many facets of our lives, particularly the way we engage with information and learning. The advent of automated technology for identification has had a had a revolutionary effect on how we read and organize books within the context of books and data searches. It starts by solving the difficulties in analyzing photos of book pages by using methods such as distortion rectification and book separation. Objective: The research compares the effectiveness of the suggested method with traditional straight-line identification techniques using real-world testing. Methodology: The Skip-Gram model in Word2Vec is used to accurately represent spoken language, allowing word vectors to be generated and input data to be preprocessed for CNN. The results show that the methodology created regarding the present investigation works better than alternatives concerning accuracy and efficiency during line identification. Result:This work advances the field of book suggestion systems by presenting a strong and effective method that leverages CNNs. The findings demonstrate deep learning techniques may be used to optimize system recommendations and improve customer service and happiness in a variety of contexts. This technique creates a bridge between natural language processing and picture evaluation and opens up new possibilities for suggestion advancement along with user satisfaction. Doi: 10.28991/HIJ-2024-05-01-015 Full Text: PD
Powering through Challenges: Analyzing the Energy Crisis in the Western Balkans during the Pandemic Context
Full text linkThis paper examines the current challenges in the energy sector of the Western Balkan countries, focusing on the energy sector of Kosovo as a case study during the pandemic. These countries are at crucial stages of their development, marked by significant achievements but with ongoing challenges in the energy sector as a factor for sustainable development. The region remains highly vulnerable to energy crises and geopolitical tensions, particularly due to its heavy dependence on fossil fuels such as brown coal for energy production. Our research focuses on the energy system in Kosovo, highlighting its historical reliance on a fragile energy sector, particularly characterized by inflexible thermal power plants using outdated technology and a lack of additional, more flexible capacity. The purpose of this study is to examine Kosovo's energy system, assess the challenges it encounters, and identify the factors that have contributed to the energy crisis from 2021 to 2023. Doi: 10.28991/HIJ-2024-05-01-08 Full Text: PD
Seismic Optimization Design and Application of Civil Engineering Structures Integrated with Building Robot System Technology
Full text linkObjective: The seismic data monitoring is important for resource distribution, capacity planning, quality of service analysis, error monitoring and isolation, and safety management. The seismic optimization of building civil engineering structures is effectively improved. Several issues pertaining to seismic optimization monitoring of civil engineering structures have come to light as a result of the ongoing advancements in science, technology, and the internet. Method: The study creates a seismic optimization method for civil engineering structures, identifying hidden hazards and implementing safety management and control based on internet-based characteristics. Regarding the problem that the existing high-rise building installation projects mainly rely on manual work, the relevant technical research on the corresponding intelligent operation equipment for the installation project is carried out, the kinematics analysis of the construction installation robot is performed, and the search for security loopholes is realized under the seismic optimization design method of integrated building civil engineering structures to quickly find the safety adaptability. Results: The optimal safety weights and thresholds are obtained, and random initial thresholds and weights are used for seismic optimization of civil engineering structures for safety monitoring. This paper studies the seismic resistance of the current buildings and explains the seismic problems in civil engineering structures in detail while giving a feasible plan to eliminate potential safety hazards and avoid harm caused by earthquakes. Doi: 10.28991/HIJ-2024-05-04-017 Full Text: PD
Orchestration of Federated Risk for P2P Lending Platforms: A Multi-Agent Systems (MAS) Approach
Full text linkFederated risk management in the context of Peer-to-Peer (P2P) lending should be a collaborative approach with multiple autonomous entities (i.e. agent systems) working together to assess, monitor, and mitigate risks. Orchestration of these agents is crucial in facilitating risk evaluation, surveillance, and mitigation tactics. By employing Multi-Agent Systems (MAS), the orchestration of risk, regulatory compliance, and stakeholders' interests are better protected. The framework of federated risk management in P2P lending aims to address challenges and risks inherent in decentralized platforms. In recent years, the P2P lending industry has experienced significant growth, attracting both borrowers and investors seeking an alternative financial system. However, this growth has exposed the industry to various risks, including credit risk, fraud, and information asymmetry. As a result, the need for a robust risk management framework has become increasingly critical. In this paper, we delve into the role of intelligent agents and their protocol for collaborative dynamics that uses the portfolio's return (Rp) and the risk-free rate (Rf), divided by the standard deviation of the portfolio's excess return (σp) for various investment portfolios. Our framework allows MAS to analyze data from diverse sources, default rates, payback history, and portfolio risks to propose adaptive strategies for risk mitigation. Doi: 10.28991/HIJ-2024-05-04-06 Full Text: PD