Journal of Information Systems and Informatics (Journal-ISI)
Not a member yet
580 research outputs found
Sort by
IT Governance Assessment at City Revenue Agency Using COBIT 5 Framework
Get PDFThis study assesses the IT governance capability level at the Tangerang City Revenue Agency (BAPENDA) using the COBIT 5 framework to identify capability gaps and provide recommendations for improvement. Employing a qualitative descriptive approach, data were collected through interviews and observations to understand the current IT governance conditions against COBIT standards. The capability assessment revealed uneven levels across various processes. EDM04 (Ensure Resource Optimization) and MEA01 (Monitor, Evaluate, and Assess Performance and Conformance) were rated at Level 2, indicating that these processes are managed and controlled effectively. In contrast, APO07 (Manage Human Resources), BAI09 (Manage Assets), and DSS01 (Manage Operations) were assessed at Level 1, reflecting that these processes are operational but require substantial improvements to meet the target Level 3. The analysis highlights an urgent need to enhance IT governance, particularly in processes with lower capability levels. DSS01 (Manage Operations) was identified as the highest priority for improvement, based on the gap values and effort required for enhancement. The prioritization of process capability improvement in this study is guided by the principles of gap value and effort required for each process. Strategic enhancements in IT governance are crucial for the Tangerang City Revenue Agency to align better with best practices and achieve higher capability levels. Recommendations include implementing electronic-based applications, establishing Standard Operating Procedures related to performance targets and compliance, and improving IT human resources to enhance the effectiveness of IT service delivery and governance
Enhancing Real-time Herbal Plant Detection in Agricultural Environments with YOLOv8
Get PDFThe detection of herbal plants plays a crucial role in the utilization of traditional medicine, particularly in the Toba region of Indonesia. This study aims to develop an Android application capable of real-time detection of herbal plants using the YOLOv8 algorithm. The five types of herbal plants targeted in this study are tempuyung, rimbang, papaya leaves, turmeric leaves, and aloe vera. The research methodology includes the collection of a dataset of herbal plant images, which were then labeled using the Roboflow platform. The YOLOv8 model was trained with this dataset to detect herbal plant objects. After training, the model was exported to TensorFlow Lite and integrated into an Android application. Testing was conducted to evaluate the accuracy and real-time detection performance of the application. The results show that the YOLOv8 model achieved a mean Average Precision (mAP) of 92.4%, with optimal real-time detection capabilities on Android devices. The developed application can quickly and accurately detect and identify herbal plants, providing a practical solution for users to recognize herbal plants. This study indicates that the YOLOv8 algorithm is effective for herbal plant recognition applications in a mobile context, opening up opportunities for further development in the integration of AI technology into everyday applications
Enhancing Service Delivery through an Online Complaints System for Northern Ghana’s Tertiary Institutions
Get PDFThis study investigated the factors hindering the successful implementation of online complaints system in tertiary institutions in Northern Ghana, and developed an effective complaint system to enhance service delivery, using iterative waterfall models with CSS, MYSQL, JavaScript, HTML, and visual studio codes. To identify the factors hindering the successful implementation of online complaints system, a structured questionnaire was administered to a sample of 308 participants to ascertain the factors that influence the implementation of online complaints system. The findings revealed that lack of education and training, and inadequate resources are the key factors hindering the implementation of online complaint system. Consequently, a new complaint system was developed from this study which incorporated speech-to-text, and text-to-speech features to cater for the needs of diverse users, unlike the previous ones. This new complaint system was found to be cost effective since students only need access to internet connectivity to lodge complaints, unlike previous ones where students have to travel to school before lodging complaint. Finally, the new complaint system equally efficiently handles students’ complaints by keeping a record of all previously lodged complaints of the user, this particular feature provides educational institutions with insights on the frequency of complaints lodged by users. Based on the results, it is evident that tertiary institutions which are looking forward to adopting and implementing students’ complaints system, should consider educating and training for both staff and students on its usefulness. Also, tertiary institutions are encouraged to adopt and implement this system since it is less frustrating and cost effective
Advanced 3D Artistic Image Generation with VAE-SDFCycleGAN
Get PDFGeneration of a 3-dimensional (3D)-based artistic image from a 2-dimensional (2D) image using a generative adversarial network (GAN) framework is challenging. Most existing artistic GAN-based frameworks lack robust algorithms lack suitable 3D data representations that can fit into GAN to produce high-quality 3D artistic images. To produce 3D artistic images from 2D image that considerably improves scalability and visual quality, this research integrates innovative variational autoencoder signed distance function, cycle generative adversarial network (VAE-SDFCycleGAN). The proposed method feeds a single 2D image into the network to produce a mesh-based 3D shape. The network encodes a 2D image of the 3D object into latent representations, and implicit surface representations of 3D images corresponding to those of 2D images are subsequently generated. VAE extracts feature from the two-dimensional input image and reconstructs a voxel-type grid using a signed distance function. Cycle GAN produces improved and high-quality 3D artistic images from 2D images. The publicly available COCO dataset was used to evaluate the proposed advanced 3D-VAE-SDFCycleGAN. The model produced a peak signal noise ratio (PSNR) of 31.35, mean square error (MSE) of 65.32, and structural similarity index measure (SSIM) of 0.772 which indicates the improved quality of the generated images. The results are compared with other traditional GAN methods and the results obtained show that the proposed method outperforms the others in terms of quantitative and qualitative evaluation metrics
Analysis of Labeling and Class-Balancing Effects on Clash of Champions Sentiment Using LSTM and BERT
Get PDFAdvances in digital technology have changed the way people interact and access information, including in education. One educational event that has caught the public's attention is Clash of Champions by Ruangguru, designed to increase young people's interest in learning through an interactively presented competition. The purpose of this study is to use posts on X social media to examine public opinion on the event. Using TweetHarvest, 1,891 tweets were gathered and preprocessed (cleaning, case folding, normalization, tokenization, stopword removal, stemming, and English translation). A total of 12 experimental scenarios were created by combining VADER and TextBlob labeling strategies with class balancing techniques (undersampling and SMOTE), and the LSTM and BERT models were evaluated for each scenario. The best results were achieved by combining VADER, SMOTE, and BERT, yielding an accuracy of 97.73%, with precision, recall, and F1-scores of 98%, 98%, and 96% (positive), 99% (neutral), and 98% (negative), respectively. These findings highlight the efficacy of transformer-based models like BERT in addressing class imbalance and improving sentiment classification. The integration of SMOTE effectively mitigated class imbalance, providing consistent and accurate performance across all sentiment categories
Optimizing Zakat Distribution with GIS and Data Mining in Community Empowerment at BAZNAS Deli Serdang
Get PDFThis research aims to develop an information system that utilizes Geographic Information System technology to map and analyze the distribution of zakat effectively in Deli Serdang Regency. The methods used include collecting data on zakat recipients and applying the K-means grouping method to identify distribution patterns in 22 districts. The results of the study show that there are three groups of zakat recipients: High Recipients, Medium Recipients, and Low Recipients. Tanjung Morawa was identified as the district with the highest number of zakat recipients, namely 239 people, which shows a significant need. The K-Means algorithm plays an important role in identifying areas that need help, so this Geographic Information System-based grouping is proven to improve the efficiency of zakat resource allocation. This allows BAZNAS to target assistance more precisely and strategically. This study recommends the use of this approach to optimize zakat management and support community economic empowerment, as well as reduce social inequality in the region
Evaluating YOLOv5 and YOLOv8: Advancements in Human Detection
Get PDFThe YOLO (You Only Look Once) method is a state-of-the-art approach in real- time object detection, known for its high-speed image processing capabilities. Recently YOLO versions have differed in performance, particularly in terms of detection accuracy and computational efficiency. The objective of this study is to assess the effectiveness and performance of YOLOv5 and YOLOv8 in real-time human detection applications using the SEMMA (Sample, Explore, Modify, Model, and Assess) methodology also. The dataset was processed through the Roboflow platform, which facilitated both the dataset management and the labeling process. Roboflow's tools streamlined the annotation of images, ensuring consistent labeling for deep learning model training and evaluation. F1 score, recall score, and precision score are compared both YOLOv5 and YOLOv8 to evaluate the performance of these architectures. The result of the evaluations shows that the performance of the YOLOv8 is better than the YOLOv5 which, YOLOv5 achieved F1-score equal 0.5865 (58%), recall score equal 0.83 (83%), and precision score of 0.4535 (45%). Meanwhile, YOLOv8 demonstrated better performance, with F1-score of 0.7921 (79%), recall score of 0.8289 (82%), and precision score of 0.7585 (75%). Base on the evaluations, we concluded that the performance of the YOLOv8 model is greater than the YOLOv5 model for Precision, and F1-Score, while YOLOv5 has slightly better score on recall. The contribution of this study is going to implemented into Audio guidance for the blind’s prototype that have been developing in previous study
Information Security Evaluation at Hospital Using Index KAMI 5.0 and Recommendations Based on ISO/IEC 27001:2022
Get PDFBali Mandara Regional Hospital integrates information technology into its healthcare services, but ransomware attacks pose significant risks to data security. In accordance with the 2016 Indonesian Ministry of Communication and Informatics regulation, Electronic System Operators (PSE) are required to ensure information security, emphasizing confidentiality, integrity, and availability. To support this, the National Cyber and Crypto Agency introduced the Index KAMI, an evaluation tool aligned with ISO/IEC 27001 standards. This study evaluates the hospital’s information security using Index KAMI 5.0, yielding a score of 177, which classifies its readiness as “Not Eligible” for ISO 27001 compliance. Recommendations for improvement include establishing clear governance policies, implementing systematic risk management, enhancing asset management with integrated inventories, and strengthening data protection through access control and encryption. Additional measures involve improving physical security with surveillance systems and fostering stronger vendor relationships through binding SLA agreements. By adopting these measures, Bali Mandara Regional Hospital can enhance its security system, protect patient data, and achieve compliance with international standards
Enhancing Public Service Delivery Efficiency through AI: Current Initiatives and Future Prospects in Bangladesh
Get PDFThe integration of Artificial Intelligence (AI) in public service delivery presents a transformative opportunity for Bangladesh, where bureaucratic inefficiencies, resource limitations, and unequal access to services persist as significant challenges. This study investigates the current applications of AI in society, its socio-economic impact, and challenges within major sectors in Bangladesh. Qualitative approaches, such as Key Informant Interviews with AI experts, as well as literature review was conducted to highlight AI innovations such as telehealth platforms, smart agricultural systems, and AI-enabled educational tools that greatly increase efficiency, accessibility, and equity in public services. Findings demonstrate that AI initiatives affected more than 40 million people by paving ways for flood prediction while enabling 2.7 million students for AI-enabled education and saving up to 87.5% costs in helpline servicing. AI-enabled healthcare provides services to over 600,000 pregnant women, while IoT-based farming systems increase profitability and yield for aquaculture. The future shows bright prospects for AI-related applications in predictive healthcare, urban planning, and sustainable agriculture. Some major challenges are infrastructure deficits, data privacy breaches, lack of digital literacy, and unpreparedness of the workforce. Policy frameworks emphasizing ethical AI use, scaling capacity building, and bridging the digital divide would lead to citizen-centered governance
An Evaluation Framework for The Adoption of Big Data Technologies in Higher Educational Institutions
Get PDFThe aim of this study is to develop a framework for the use of Big Data Technology in Higher Educational Institutions (HEIs). The research which employed a mixed method approach, is primarily based on relevant critical analysis and literature review of studies conducted within the Big Data Technology area in higher education institutions. It investigated the processes of monitoring student performance by Namibian HEIs. The challenges faced by Namibian HEIs on the use of BDT. The various methods of data collection by Namibian HEIs and determined the level of readiness to adopt BDT.in Namibian HEIs. The study further undertook quantitative surveys and qualitative interviews with staff of the three (3) higher institutions in Namibia. A sample of 345 participants from International University of Management (IUM), Namibia University of Science and Technology (NUST), and The University of Namibia comprising the study's population (UNAM) were selected for this study using the simple random sampling technique. The Unified Theory of Acceptance and Use of Technology (UTAUT) constructs model was used to analyse to collect and analyse the quantitative data collected in this study. Finally, the study developed a sustainable framework that will guide the use of Big Data Technology in Namibian Higher Educational Institutions (HEIs). The validity of the framework was ascertained by expert reviews to ensure that the framework developed is effective and appropriate in fulfilling the purpose of the study and its objectives