HighTech and Innovation Journal
Not a member yet
317 research outputs found
Sort by
Analysis of Seasonal Wind Energy Potential on Zanzibar Coastal Island
Full text linkThe main objectives of this research were to numerically analyze the potential for seasonal wind power (WP), assess wind direction, and select the most effective wind turbine (WT) for installation at the research site. Wind data were collected half-hourly from a branch of the Tanzania Meteorological Authority nearest to the research site. The collected data were analyzed using a double-parameter Weibull distribution (WD) model, where the standard deviation (SD) method was used to fit the WD. The results revealed that the site experienced strong winds within the range of 4.5–7 m/s between the hours of 05:00 - 20:00, with the most likely seasonal wind speed (WS) ranging from 5–7 m/s, while the mean seasonal WS was 9.07–12.14 m/s. The highest possible wind energy density (wED) of 23.3 GWh/m2 at a hub height of 10 m occurred during winter, followed by spring, autumn, and summer, with 6.39, 6.32, and 3.33 GWh/m2, respectively. The annual wED was > 13.52 GWh/m2, with a typical month-to-month energy of 1.13 GWh/m2. Finally, the study concluded that the recommended WT model (POLARIS P62-1000) was the best choice for installation at the study site due to its sustainable WS and WP potential. Based on the findings of this research, which show that the site has sustainable seasonal wind resources, it is suggested that future wind research be carried out to extend the dataset to ensure the long-term seasonal wind pattern at the site. Doi: 10.28991/HIJ-2024-05-02-08 Full Text: PD
A Novel Classification Model Based on Hybrid K-Means and Neural Network for Classification Problems
Full text linkWe propose a new classification model”a new classification model for clustering overlapping problems based on K-Means and neural networks. K-means clustering algorithm belongs to unsupervised learning. It is a classic algorithm for solving clustering problems. Since this algorithm calculates its categories based on distance, the results tend to converge to the local optimal solution and have poor boundary clustering properties. The K-Means classification algorithm defines clusters by the distance between the cluster center value and the target object, and the optimal result is obtained through continuous iteration. Therefore, clustering results are overlapped, and there are often outliers that do not belong to the current cluster, resulting in unsatisfactory clustering results. Our model offers a new method to segment non-ideal data in overlapping regions. Since clustering algorithms cannot effectively identify and classify this part of the data, we split this part of the data and train it using a neural network. The results are then integrated into the clustered data. In the experiment, the k-fold cross-validation method ensures the model stability of the results. We used the accuracy to evaluate the quality of the model, and we used standard deviation and mean deviation to detect clustering results. Five sets of experimental data from the cross-experiment show that compared with the K-Means classification model, the accuracy of our model is effectively improved. Doi: 10.28991/HIJ-2024-05-03-012 Full Text: PD
Innovative Metal Powder Production Using CFD with Convergent-Divergent Nozzles in Wire Arc Atomization
Full text linkThis study aims to enhance the production of metal powders using a novel approach that integrates computational fluid dynamics (CFD) with convergent-divergent (C-D) nozzles in wire arc spraying atomization (WASA). The primary objective is to investigate the influence of nozzle design on particle size distribution and production efficiency. Utilizing the ANSYS CFD Fluent program, simulations were conducted to analyze the effects of various parameters, including throat diameter and divergent angles, on gas dynamics and metal droplet behavior. The findings reveal that C-D nozzles facilitate the acceleration of gas flow to supersonic speeds, significantly improving the shear force acting on the molten metal, thereby promoting the fragmentation of droplets into smaller particles. Notably, the optimized nozzle configuration achieved a median particle size (D50) of 44.42 µm, suitable for additive manufacturing applications. The novelty of this work lies in its comprehensive simulation framework that allows for rapid virtual testing, potentially leading to significant improvements in the efficiency and quality of metal powder production processes. This research addresses critical gaps in the existing literature and provides a robust foundation for future studies in the field of metal powder manufacturing. Doi: 10.28991/HIJ-2024-05-03-02 Full Text: PD
Social Media Data Privacy Related to Security Awareness and Student Trust Regarding Data on Instagram
Full text linkInstagram, as one of the most popular social media sites, has brought many new trends. Many people use Instagram to express themselves or share content through photos and videos. While social media data privacy is important, many people still share their daily activities and personal data. This causes a lot of personal information disclosure, which can lead to the potential for crime or misuse of the scattered data, considering that data is crucial today. Therefore, this research was conducted to determine people's social media data privacy and security awareness on Instagram, especially those with a data-related educational background. This research uses quantitative descriptive methods, distributing questionnaires through Google Forms in group chats, personal chats, or questionnaires to respondents directly. The population in this study is made up of students with a computing program background. It also used purposive sampling to determine the number of 153 samples. From the descriptive analysis, it is known that most respondents are aware of the vulnerability of social media data privacy on Instagram. This can be seen from respondents who know what data is used by Instagram, where they also monitor login activity. Respondents also secure their Instagram accounts by not using the same password as other social media accounts. However, in certain cases, some respondents still need to realize this awareness, so education is still needed regarding the importance of social media data privacy, especially on Instagram. Doi: 10.28991/HIJ-2024-05-02-015 Full Text: PD
Optimization of Microeconomic Models Under Integrated Partial Differential Equations
Full text linkObjectives: This study aims to optimize microeconomic models under integrated partial differential equations, focusing on microeconomics and mathematics. Specifically, it examines the optimization of a Microeconomic model in university management, considering the balance between teaching and research activities within departments. Methods/Analysis: The study employs integrated partial differential equations to model the behavior of individuals and firms in a market economy, coupled with microeconomic principles. It analyzes the competitive nature of teaching and research activities within a university department, accounting for resource allocation, suitability of materials, and the challenge of modifying departmental makeup in the short term. Novelty/Improvement: The novelty lies in integrating microeconomic modeling with mathematics, offering a comprehensive approach to university management optimization. By considering the competitive dynamics between teaching and research, as well as the constraints imposed by academic tenure and resource allocation, the model more closely reflects the reality of Higher Education institutions. Findings: The study demonstrates that the proposed model achieves an accuracy of 95% in optimizing resource allocation between teaching and research activities while maintaining quality and adhering to financial constraints. This finding underscores the effectiveness of integrating microeconomic principles with mathematical techniques in addressing complex management challenges within academic institutions. Doi: 10.28991/HIJ-2024-05-04-09 Full Text: PD
Comparative Analysis of Deep Learning Models for Part of Speech Tagging in the Malay Language
Full text linkDespite the widespread use of Malay, under-resourced languages like Malay face challenges in Natural Language Processing (NLP), particularly in Part-of-Speech (POS) tagging. The scarcity of annotated corpora poses a primary obstacle to POS tagging in Malay. This study aims to enhance the effectiveness and reliability of POS tagging models explicitly tailored for under-resourced languages within the field of NLP, focusing on Malay. Existing models, which rely on Conditional Random Fields and Hidden Markov Models, exhibit limitations, underscoring the need for more robust approaches. The research conducts a comparative analysis of various deep-learning models with different encoders for POS tagging in Malay sentences. The experimental analysis demonstrates that the Bidirectional Long Short-Term Memory (Bi-LSTM) model, leveraging a pre-trained Bidirectional Encoder Representations from Transformers (BERT) embedding model, achieves exceptional accuracy, precision, recall, and F1 scores in predicting tags. Notably, the BERT + Bi-LSTM model, boasting an accuracy of 98.82%, outperforms other models, showcasing superior performance across all evaluated metrics. Additionally, this combined model effectively handles known and unknown words, yielding highly accurate POS tagging results for Malay sentences. Doi: 10.28991/HIJ-2024-05-02-04 Full Text: PD
Stability Assessment of an Ore Mill Electric Drive Using Machine Learning
Full text linkThe relevance of the study is due to the need to improve electric drive systems operated in harsh conditions. The goal of the study is to create a model for assessing the state of stability of the electric drive of an ore mill using machine learning capabilities, which will provide high performance and the ability to work consistently in different systems. Various sustainability assessment models have been developed based on 6 machine learning algorithms. The study and comparison of models built using artificial neural networks (ANN) of different architectures was carried out using various learning methods. The expediency of using the Tree and ANN algorithms to develop a model for assessing electric drive stability is substantiated. The novelty of the results obtained lies in the fact that the model has high accuracy, high speed, and the ability to detect instability in uncertain operating modes of the electric motor of an electric drive, as well as the possibility of coordinated operation with various systems. The practical value is that the model allows, at an intellectual level, to provide effective control and fault diagnosis of complex electric drive systems, which cannot be achieved using the known methods. Doi: 10.28991/HIJ-2024-05-02-01 Full Text: PD
Students' Flow Experience of Using AI-Powered Online English Learning Platforms
Full text linkObjectives: This research aims to explain the impact of flow's antecedents on flow experience. Furthermore, this research explores the intention of students to continue using online AI-powered English learning platforms. Methodology: This study gathered data from 300 online students enrolled in AI-powered English learning platforms in Taiwan, with data collection facilitated by a research company in the country. Findings: According to the findings, flow was significantly associated with continuous intention. In terms of antecedents of flow, information quality, service support quality, and intrinsic motivation were significant, whereas confirmation, service quality, and instructor quality were not significant. Flow was found to have significant associations with perceived usefulness and satisfaction. Furthermore, confirmation significantly impacted perceived usefulness and satisfaction. Moreover, perceived usefulness was significantly associated with satisfaction but had no association with continuous intention. Lastly, both intrinsic motivation and satisfaction were associated with continuous intention. Novelty/Improvement:This research delves into the dynamic interplay between students' experiences and the adoption of AI-powered online English learning platforms. The study employed a comprehensive framework, including flow, a technology acceptance model, motivation, and an expectation confirmation model. Doi: 10.28991/HIJ-2024-05-02-011 Full Text: PD
Boundaries and Future Trends of ChatGPT Based on AI and Security Perspectives
Full text linkIn decades, technology and artificial intelligence have significantly impacted aspects of life. One noteworthy development is ChatGPT, an AI-based model that has created a revolution and attracted attention from researchers, academia, and organizations in a short period of time. Experts predict that ChatGPT will continue advancing, bringing about a leap in artificial intelligence. It is believed that this technology holds the potential to address cybersecurity concerns, protect against threats and attacks, and overcome challenges associated with our increasing reliance on technology and the internet. This technology may change our lives in productive and helpful ways, from the interaction with other AI technologies to the potential for enhanced personalization and customization to the continuing improvement of language model performance. While these new developments have the potential to enhance our lives, it is our responsibility as a society to thoroughly examine and confront the ethical and societal impacts. This research delves into the state of ChatGPT and its developments in the fields of artificial intelligence and security. It also explores the challenges faced by ChatGPT regarding privacy, data security, and potential misuse. Furthermore, it highlights emerging trends that could influence the direction of ChatGPT's progress. This paper also offers insights into the implications of using ChatGPT in security contexts. Provides recommendations for addressing these issues. The goal is to leverage the capabilities of AI-powered conversational systems while mitigating any risks. Doi: 10.28991/HIJ-2024-05-01-010 Full Text: PD
Mobile Service Quality's Impact on Customer Repurchase Intention in Food and Beverage Mobile Applications
Full text linkThis study aims to assess the impact of mobile service quality on customer repurchase intention in Indonesia's food and beverage mobile applications. The research identifies key dimensions such as application design, ease of use, privacy, and customer support and evaluates their influence on customer e-satisfaction and repurchase behavior. A quantitative approach was employed, utilizing purposive sampling to gather data from 401 active users of these applications. The analysis, conducted using Structural Equation Modeling-Partial Least Squares (SEM-PLS), revealed that these dimensions significantly enhance overall mobile service quality, which in turn positively affects customer e-satisfaction and repurchase intention. The findings underscore the importance of a minimalist and user-friendly design, robust privacy measures, and responsive customer support”particularly for Gen-Z users in Indonesia, where privacy concerns are increasingly prominent. This study contributes to the existing literature by providing insights specific to the Indonesian market and offering practical recommendations for the food and beverage industry to improve mobile service quality, thereby fostering stronger customer loyalty and increasing repurchase rates. The novelty of this research lies in its focus on the rapidly growing mobile app market in Indonesia, addressing unique regional challenges and opportunities. Doi: 10.28991/HIJ-2024-05-03-011 Full Text: PD