Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
Dance Gesture Recognition Using Laban Movement Analysis with J48 Classification
Get PDFThis study describes the introduction of classical dance movements using the Laban Movement Analysis (LMA) method which consists of 3 main components, namely Body, Space, and Shape. How to carry out the classical motion recognition process using Kinect which is then read by the screen using the Brekel Kinect and produces dance motion pictures in different formats (. * BVH). After that, it is calculated using the LMA method by obtaining the results obtained in the form of numerical data from each joint from the direction of the axis (xyz), then classification is carried out using the J48 classification method provided at WEKA tools after 50 training data is carried out. 96% truth is recognized, because it guarantees those who meet the requirements, 12 data tests are carried out apart from training data, which can be 92% accurate on average, so it is very possible that this method can be used in dance preparation, especially in classical dance
Machine Learning based Stream Selection of Secondary School Students in Bangladesh
Get PDFIn the Bangladeshi education system, there are three stages up to the secondary school certificate (SSC)- the primary (Primary Education Completion Certificate, or PEC), middle school (Junior School Certificate, or JSC), and SSC. A separate stream has to be chosen after the eighth grade, which could be any of the following streams: Science, Business Studies, and Humanities. The selection of a stream is very important for their future higher studies and career planning. Usually, students take the decision of selecting a stream based on PSC and JSC results only. To address this challenge, we have collected a dataset from different Bangladeshi schools, which consists of PSC and JSC students' records. There are 26 data for each student record including subject-wise student results, parent’s academic qualification, parent’s profession, parent’s monthly income, sibling information, district, etc. In the experimental analysis, a series of machine learning regression algorithms have been utilized. Moreover, we have employed various performance metrics in order to validate our model’s performance. The experimental results demonstrate that among the regressors, extreme gradient boosting algorithm’s performance were superior in both science and humanities streams. In the business stream however, Support Vector Machine’s performance is considerably better. It is expected that the analysis will help prospective students and stakeholders in their future decisions. Moreover, we have utilized Local Interpretable Model Agnostic Explanations that helps to increase the interpretability of the model
Efficient Dual Mode Arbitration Scheme for Multiprocessor Hardware Interface in System-on-Chip
Get PDFA processor transforms human needs into hardware operations in any SoC. The single processor was ubiquitous in previous systems. But as chip size, complexity, and speed increase, several processors are used nowadays to handle concurrent operations. To manage requests from several processors, a central hardware block will conduct the arbitration among the processors and allow a processor to access the bus. This paper addresses the multiprocessor arbitration in any System on Chip or ASIC. There are several arbitration algorithms available in the realm of technology, and any system can choose a specific arbitration to implement in hardware based on its own demands. Instead of using one type of arbitration in hardware, this research combined and used two schemes and implemented both possibilities in a hardware dual-mode arbiter system to be used in SoC. The proposed dual-mode arbiter was initially hardware modeled using Verilog HDL, then functionalities were verified using industry simulator Cadence and Modelsim, and finally synthesized and implemented using Xilinx XST EDA tool and FPGA device. The AMBA, the industry-standard bus protocol, is being considered for the master processors and the proposed dual-mode arbiter to ensure an efficient hardware interface and to use with any off-the-shelf macro available for the high-tech industry
Neurorehabilitation Robot-Assisted for Stroke Recovery: Hybrid Exoskeleton Assistive Limb (HEAL)
Get PDFConventional rehabilitation techniques that require manual intervention and the use of devices are identified as having several drawbacks. These include limited features, fatigue for both patients and therapists during prolonged rehabilitation sessions, time-consuming procedures, high operational and maintenance costs for devices, a lack of motivation for patients, limited accessibility, and challenges in measuring or monitoring rehabilitation progress. In response to these challenges, the Hybrid Exoskeleton Assistive Limb (HEAL) is introduced as a tailored solution with distinctive features. These features include real-time electromyographic (EMG) monitoring, a therapist-friendly graphical interface, and advanced techniques in the rehabilitation process. HEAL utilizes robotics-assisted rehabilitation for repetitive, precise, and controlled movements, enhancing brain-muscle motor function, developing muscle strength, and providing a wide range of motion. The system focuses on upper limb robotic rehabilitation and consists of an EMG to read muscle responses, an Arduino microcontroller for signal processing, and a high-torque precision servo motor for controlling limb movements. HEAL emphasizes the Brain-Muscle-Computer control process rather than passive rehabilitation, which relies on external forces to move the muscles, as demonstrated by the therapist. HEAL is particularly suitable for neurorehabilitation, emphasizing recovery and improvement of function in individuals with neurological disorders or injuries, especially in stroke patients. HEAL's ability to tailor rehabilitation programs individually offers personalized rehabilitation, considering each patient's unique needs, goals, and abilities. It utilizes advanced technologies for targeted and efficient rehabilitation. The HEAL device is cost-saving with a compact design, positioning it as a promising and comprehensive solution in stroke neurorehabilitation
Efficient Medical Image Compression Based on Wavelet Transform and Modified Gray Wolf Optimization
Get PDFThe use of medical images in diagnostic procedures is increasing, leadning to a significant rise in the memory and bandwidth requirements for preserving and transmitting these images. To address this issue, image compression techniques have garnered significant attention. These techniques are capable of reducing the data size necessary to represent an image, allowing for more efficient utilization of storage space and communication bandwidth by eliminating unnecessary information. Numerous research directions have focused on compressing medical images, but past approaches have been time-consuming and risked information loss. To trounce these limitations, this paper introduces an effiective method for reducing the size of medical images in telemedicine applications. The method utilizes Integer Wavelet Transform (IWT) and sophisticated algorithm. Primarily, input images undergo pre-processing with a circular median filter to eliminate noise and improve image quality. Subsequently, the pre-processed images are divided into multiple sub bands using IWT.Then, these sub bands are furhter divided into n X n non-overlapping matrices, and optimal coefficients are chosen by employing a modified grey wolf optimizer algorithm. Finally, the selected coefficients are encoded using Huffman coding for transmission. During decompression, the reverse process of image compression is applied. The introduced method is tested on various medical images, and the findings demonstrate its superior performance compared to previous methods, generating visually similar images with a smaller data size
Factors Influencing the Adoption of Cloud-based Village Information System: A Technology-Organization-Environment Framework and AHP–TOPSIS Integrated Model
Get PDFCloud-based service is a key area for growth in Indonesia, but there are still very few villages that have adopted a village information system based on cloud computing. This study investigates the factors influencing OpenSID adoption in cloud computing. The research was informed by the Technological Organizational Environmental (TOE) and combined two multi-criteria decision analysis methods, namely, AHP and TOPSIS to analyze the acceptance of cloud computing-based village information systems, the driving factors for adoption, and the selection of forms of OpenSID. The research focuses on the analysis of four dimensions namely organization, trust, innovation, and vendor. The sub-dimensions of each dimension include the organization (the technological readiness of actors, top management support, and firm size), Trust (security and privacy factors), innovation (compatibility, complexity, trialability, and relative advantage factors), and Vendor (vendor reputation, perceived price, and external support factors). Primary data was collected using a questionnaire and semi-structured interviews with respondents from the village government apparatus in Indramayu. The results of the study showed an open-source cloud-based village information system is the most suitable alternative solution for government at the village level in Indramayu, West Java Province. The results highlighted that the enablers that are critical for cloud adoption include Technology readiness, trust, technological innovation, and vendor. The barriers that are hindering cloud adoption are infrastructure readiness, understanding the use of cloud computing technology, low technical skills and knowledge, data integration issues, and data security. This research is a reference for developing a village information system based on cloud computing
Implementing Pseudo-Random Control in Boost Converter: An Effective Approach for Mitigating Conducted Electromagnetic Emissions
Get PDFCurrently, pulse width modulation (PWM) is a prevalent technique in the field of DC-DC converter control. Its primary objectives encompass maintaining the regulation of the converter's output voltage and improving the load's performance by mitigating the adverse effects caused by harmonic distortions. Unfortunately, the utilization of PWM is associated with significant levels of residual harmonics, characterized by notable amplitudes and frequencies, which have the potential to induce mechanical vibrations, acoustic disturbances, and electromagnetic interference (EMI).To address this challenge, a method known as pseudo-random modulation (PRM) has been developed. In comparison to traditional PWM, PRM offers ease of implementation and high efficacy in EMI mitigation. PRM achieves this by distributing harmonic power across a broader frequency range, thereby reducing the prominence of high-amplitude harmonics at specific frequencies. Within the context of Spread Spectrum Modulation (SSM), this study extensively explores diverse converter topologies and proposes an innovative hardware implementation using the cost-effective Atmega328p microcontroller. Furthermore, the study scrutinizes the consequences of implementing this randomized control strategy to reduce electromagnetic emissions from a Boost converter, a well-recognized source of significant interference in its operational environment. Ultimately, the aim is to evaluate the effectiveness of these applied methodologies in achieving the maximum dispersion of the power spectrum, thereby enhancing overall electromagnetic compatibility
A Novel Approach for improving Post Classification Accuracy of Satellite Images by Using Majority Analysis
Get PDFIn past one year, due to climatic changes and some anthropogenic activities, the forests of Uttarakhand are burning. To identify the damage caused by the forest fires, an area of Nainital district has been taken for the study. Multi temporal Landsat 7 images were taken from April - 2020 and April – 2021. This paper shows a novel approach to increase the accuracy of the classified image. The Support Vector Machine classification is first done and then to improve the accuracy of the classified image, a post-classification technique called Majority Analysis is applied. This method helps to classify the unclassified pixel and it also smoothens out the boundary of the classified pixels, leading to higher accuracy rate. The classification accuracy has improved significantly for April 2020 and April 2021 images from 89.35% to 98.71% and from 88.52% to 99.76% respectively. The change detection study showed a drastic increase in the barren land due to the forest fires and on the contrary, the forest, scarce forest and the shrub land areas have decreased
Malware Detection Approaches Based on Operation Codes (OpCodes) of Executable Programs: A Review
Get PDFA malicious software, or Malware for a short, poses a threat to computer systems, which need to be analyzed, detected, and eliminated. Generally, malware is analyzed in two ways: dynamic malware analysis and static malware analysis. The former collects features dataset during running of the malware, and involves malware APIs, registry activities, file activities, process activities, and network activities based features. The latter collects features dataset prior and without running the malware, and involves Operational Codes (OpCodes) and text based (Bytecodes) features. However, several previous researchers addressed and reviewed malware detection approaches based on various aspects, but none of them addressed and reviewed the approaches merely based on malware OpCodes. Therefore, this paper aims to review Malware Detection Approaches based on OpCodes. The review explores, demonstrates, and compares the existing approaches for detecting malware according to their OpCodes only, and finally presents a comprehensive comparable envisage about them
Classification of Cassava (Manihot sp.) Leaf Variants Using Transfer Learning
Get PDFThere are several types of cassava leaves with different characteristics, tastes, and nutritional content. Some people use cassava leaves as a vegetable ingredient for daily consumption as a source of fiber and minerals. However, people often have difficulty identifying the different types of cassava leaves, including cassava leaf variants that are locally referred to as gajah, karet, and mentega. This study aims to use transfer learning to identify the variant of cassava leaves. The Inception v3 architecture was selected to build the classification model. To demonstrate the superiority of transfer learning, the Inception v3 architecture was run with two different weights. The first weight was randomly initialized, while the second weight was taken from pre-trained weights from ImageNet. The experimental results show that the classification accuracy rate using the pre-trained weights reached 95.76%. This indicates that the classification model used in this study is promising and can be used for practical purposes in everyday life