Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Skin cancer disease analysis using classification mechanism based on 3D feature extraction
Get PDFDermoscopic image analysis is essential for effective skin cancer diagnosis and classification. Extensive research work has been carried out on dermoscopic image classification for the early detection of skin cancer. However, most of the research works are concentrated on 2D features. Therefore, a 3D lesion establishment mechanism is presented in this work to generate 3D features from the obtained 3D lesions. The objective of this work is to reconstruct 3D lesion image from 2D lesion images and a multispectral reference IR light image. The 3D lesion establishment is achieved by designing an efficient convolutional neural network (CNN) architecture. Details of CNN design architecture are discussed. After reconstruction of 3D lesions, 2D and 3D features are extracted and classification is performed on the obtained 2D and 3D features. Classification performance is evaluated using the images from PH2 database. The mean classification accuracy using K-nearest neighbors (KNN) classifier based on the 3D lesion establishment using the CNN architecture is 98.70%. The performance results are compared against varied classification methods in terms of accuracy, sensitivity, specificity and are proved to be better
Impact of criticality analysis on the operational availability of Scooptrams LH203 in the Huarochirí Mining Industry
Get PDFThis study addresses the decline in the operational availability of low-profile loading equipment used in underground mining, a challenge primarily attributed to shortcomings in the implementation of preventive maintenance strategies. The main objective is to propose a preventive maintenance model based on criticality analysis aimed at improving the availability and operational efficiency of such equipment. Adopting a quantitative approach with a non-experimental, cross-sectional design, the research applies a descriptive method to assess the impact of the maintenance plan on equipment availability, using operational and maintenance data collection and analysis. The results reveal a significant increase in equipment availability from 79.20% to 92.57% following the implementation of the model. This highlights the relevance of maintenance strategies grounded in criticality analysis and real-time monitoring technologies. The findings underscore the success of the proposed model in enhancing both availability and operational efficiency, and demonstrate its potential for replication in other mining sectors to promote safer and more efficient operations
Enhancing the effectiveness of CAPTCHA using an improved visual cryptography scheme
Get PDFTraditional CAPTCHA systems, designed to distinguish humans from bots, are increasingly ineffective due to advancements in artificial intelligence (AI), particularly deep learning and optical character recognition (OCR) technologies, which enable bots to bypass these systems. This paper proposes a new CAPTCHA authentication method that combines enhanced visual cryptography with traditional techniques to improve security. Visual cryptography divides information into visually distinct shares, reinforcing CAPTCHA’s defenses against automated attacks, especially those using deep learning. This approach not only strengthens security but also improves user experience by adjusting the time required to complete CAPTCHA challenges, addressing usability concerns associated with traditional systems. Overall, the proposed method offers a more secure, efficient, and user friendly solution for online authentication
Machine learning approach for cost estimation in software project planning
Get PDFSuccessful organizing and handling of software projects depends extensively on accurate cost estimation. This study explores the effectiveness of machine learning models in estimating software project costs using datasets like Desharnais, Maxwell, and Kitchenham, aiming to prevent project delays and resource misallocation. It shows how model selection has a major impact on forecast accuracy through thorough assessment. An R-squared value (R2) of 0.804 indicates that the support vector machine (SVM) model performs exceptionally well in the Desharnais dataset. On the Maxwell dataset, linear regression (LR) stands out with a minimum mean absolute error (MAE) of 0.483 and the greatest R2 value of 0.607, while SVM has the lowest root mean squared error (RMSE) of 0.537. Similarly, on the Kitchenham dataset, LR and SVM are the top performers, with MAE of 0.201 and RMSE of 0.274, respectively, and R2 values of around 0.929. These findings highlight the importance of tailored model selection for accurate cost prediction, as LR and SVM continuously demonstrate reliability across varied datasets. ML techniques like LR and SVM can enhance software project planning and management by providing accurate cost estimation, with future research exploring ensemble learning and deep learning methodologies
Core machine learning methods for boosting security strength for securing IoT
Get PDFInternet-of-things (IoT) revolutionized the mechanism of larger scale of network system offering more engaged, automated, and resilient data dissemination process. However, the resource-limited IoT devices potentially suffers from security issues owing to various inherent weakness. Artificial intelligence (AI) and machine learning (ML) has evolved more recently towards boosting up the security features of IoT offering a secure environment with higher privacy. Till date, there are various review papers to discuss elaborately security aspect of an IoT; however, they miss out to present the actual gap existing between commercial available products and research-based models. Hence, this paper contributes towards discussing the core taxonomy of evolving security methods using ML along with their research trend to offer better insight to existing state of effectiveness. The study further contributes towards highlighting the potential trade-off between the real-world solution and on-going ML based approaches
Bit-rate aware effective inter-layer motion prediction using multi-loop encoding structure
Get PDFRecently, there has been a notable increase in the use of video content on the internet, leading for the creation of improved codecs like versatile-video-coding (VVC) and high-efficiency video-coding (HEVC). It is important to note that these video coding techniques continue to demonstrate quality degradation and the presence of noise throughout the decoded frames. A number of deep-learning (DL) algorithm-based network structures have been developed by experts to tackle this problem; nevertheless, because many of these solutions use in-loop filtration, extra bits must be sent among the encoding and decoding layers. Moreover, because they used fewer reference frames, they were unable to extract significant features by taking advantage from the temporal connection between frames. Hence, this paper introduces inter-layer motion prediction aware multi-loop video coding (ILMPA-MLVC) techniques. The ILMPA-MLVC first designs an multi-loop adaptive encoder (MLAE) architecture to enhance inter-layer motion prediction and optimization process; second, this work designs multi-loop probabilistic-bitrate aware compression (MLPBAC) model to attain improved bitrate efficiency with minimal overhead; the training of ILMPA-MLVC is done through novel distortion loss function using UVG dataset; the result shows the proposed ILMPA-MLVC attain improved peak-singal-to-noise-ratio (PSNR) and structural similarity (SSIM) performance in comparison with existing video coding techniques
Optimization signal writing with machine learning assisted control
Get PDFThe high-precision signal writing machine, experiencing a 0.1% failure rate due to discrete fourier transform (DFT) of position error signal (PES) exceeding control limits, can be improved with an appropriate controller gain. This paper combines machine learning (ML) classification and controller optimization to determine the suitable gain for the hard disk drive (HDD) signal writing process. The result from machine classification has a high potential for position error improvement, distinguishing them from those with obvious degradation. The identified machine classes with high potential for signal write quality improvement undergo controller optimization using a genetic algorithm (GA). The objective function considers gain crossover frequency, phase margin, and PES DFT at low frequencies. Experimental results demonstrate that the new controller gain enhances signal write quality of class 0 and class 3 by 14.68% and 17.18%, respectively, leading to a reduced failure rate down to 0.05%
Innovative virtual reality solutions for technical training in heavy construction equipment repair and maintenance
Get PDFThe construction industry is significantly impacted by heavy construction equipment, including bulldozers, excavators, and vehicles. This equipment speeds up building, moves supplies, and builds infrastructure. Using heavy construction equipment correctly can boost productivity and shorten project timelines. Due to their complexity and scale, this equipment must be maintained and repaired. Poor maintenance and repair of heavy construction equipment can reduce performance, damage, and even cause accidents. Due to these problems, this study focuses on the design and development of a simulation training application to enhance the technical skills of workers in maintaining and repairing heavy construction equipment using virtual reality (VR) technology, the development of this application will be carried out using Unreal Engine 5 and thereafter tested and implemented at PT Menara Indonesia or M-Knows Consulting, Indonesia. At the end of this study, the design and development of a VR training simulation application for heavy equipment repair has been successfully completed. After testing the VR application and conducting user acceptance tests, it was concluded that the created VR application greatly assists M-Knows Consulting in training workers to perform maintenance and repair on heavy equipment, with a user acceptance rate of 84%
Seasonal meat stock demand used comparison of performance smoothing-average forecasting
Get PDFSeasonal patterns significantly influence the demand for beef stock, especially in rural areas that rely on natural feed. Accurate forecasting is essential for managing this demand due to beef's status as a government-regulated nutritional commodity. Food production, consumption, and income levels affect the demand for beef stocks. This research aims to identify the most precise forecasting method for predicting future beef stock needs. We evaluated multiple techniques, including single exponential smoothing (SES), double exponential smoothing (DES), single moving average (SMA), and double moving average (DMA), using the mean absolute percentage error (MAPE) metric, focusing specifically on beef supplies in Pemalang. The results indicated that the DMA method achieved the highest accuracy with a MAPE value of 5.993% at the 4th -order parameter. Additionally, increasing the data volume improved forecasting accuracy, demonstrating the effectiveness of the DMA method for beef stock prediction
Enhancing hyperspectral image object classification through robust feature extraction and spatial-spectral fusion using deep learning
Get PDFHyperspectral imaging (HSI) has gained significant attention in recent years due to its broad applications across agriculture, environmental monitoring, urban planning, infrastructure management, and defense and security for object detection and classification. Despite its potential, current methodologies face challenges such as insufficient feature extraction, noise interference, and inadequate spatial-spectral fusion, limiting classification accuracy and robustness. This study reviews advancements in HSI object detection and classification methodologies, emphasizing the role of machine-learning (ML) and deep-learning (DL) techniques. Hence, this work proposes a novel framework to address these challenges, prioritizing robust feature extraction, effective spatial-spectral fusion, and comprehensive noise removal mechanisms. By integrating DL techniques and training with HSI noisy data, this framework aims to enhance classification accuracy and robustness. The findings suggest that the proposed approach significantly improves the reliability and performance of HSI-based object classification systems. This research provides a pathway for future development in the domain, promising to elevate the effectiveness of HSI applications in real-world scenarios