Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Robust k-NN approach for classifying Aquilaria oil species by compounds
Get PDFAccurate classification of Aquilaria oil species is essential for ensuring the quality and authenticity of agarwood oils, which are widely used in perfumes and traditional medicine. This study investigated the effectiveness of the k-nearest neighbours (k-NN) machine learning model for classifying Aquilaria oil species based on four significant chemical compounds: dihyro-βagarofuran, δ-guaiene, 10-epi-γ-eudesmol, and γ-eudesmol. The dataset comprised 480 samples of Aquilaria oil, which were analyzed using gas chromatography-mass spectrometry (GC-MS) and gas chromatography-flame ionization detector (GC-FID). The k-NN model, with an optimal k-value of 10 and using euclidean distance as the distance metric, achieved 100% accuracy, sensitivity, specificity, and precision in both training and testing datasets. These results demonstrate the robustness of k-NN in species identification, highlighting the discriminative power of the selected compounds. This study verifies that the integration of chemical profiling with machine learning offers a scalable solution for accurate species identification in the essential oil industry. Future work could explore hybrid models and data expansion techniques to further enhance the classification performance in more complex environmental conditions
Enhancing urban cyclist safety through integrated smart backpack system
Get PDFThe increasing adoption of bicycles as a sustainable mode of urban transportation has underscored the urgent need for enhanced safety measures for cyclists. This paper presents the development and implementation of an integrated smart backpack system designed to improve the safety and visibility of urban cyclists. The system leverages advanced technologies, including the ESP32 microcontroller, GPS modules, proximity sensors, and LED lighting, to create a semiautomatic solution that adapts to environmental conditions and cyclist behavior in real-time. Extensive testing under various conditions, including low visibility and adverse weather, demonstrated the system’s reliability in enhancing cyclist visibility and reducing accident risks. The smart backpack also features a userfriendly mobile application, providing real-time data on speed, distance, and location, which further contributes to rider safety. The results indicate significant potential for this technology to be widely adopted, offering a practical and effective solution to the growing safety concerns of urban cyclists. This work not only advances the field of wearable safety technologies but also sets the foundation for future innovations in smart transportation systems, contributing to safer and more sustainable urban mobilit
Effective vocabulary learning through augmented and virtual reality technologies
Get PDFThis study investigates the role of augmented reality (AR) and virtual reality (VR) technologies in enhancing vocabulary learning achievement among students. It addresses the need for innovative instructional methods that improve engagement and retention compared to traditional approaches. Utilizing a survey-based quantitative design supplemented by qualitative interviews, the research involved 220 participants from diverse educational backgrounds, providing a robust dataset for analyzing the impact of these immersive technologies on vocabulary acquisition. Structured questionnaires assessed engagement levels, learning outcomes, and user experiences with AR and VR applications designed explicitly for vocabulary enhancement. The findings reveal that 75% of participants reported improved vocabulary retention, highlighting the interactive nature of AR and VR as a significant factor influencing student attitudes toward vocabulary learning. The study concludes contextualized learning scenarios with interactive features are more effective than passive learning environments. Additionally, it suggests future research directions, including developing personalized learning paths and integrating collaborative features to enhance group learning experiences. The implications for educators emphasize the potential of AR and VR technologies to transform vocabulary instruction and foster deeper engagement among learners
Design and analysis for robotic arm position for automatic electric vehicle
Get PDFNowadays electric vehicles (EV) utilization is increasing. Because of charging issues, EVs are troubling people at the time of the journey because of the lack of charging stations. Therefore, to overcome these issues, robotic arm position for automatic electric vehicle is introduced in this analysis. This vehicle is operated through solar, so charging issues are overcome. The robotic arm position for automatic electric vehicle is fully automated by 4 infrared radiation (IR) sensors, which are placed in variations, back and other sides with particular speed limit variations, so that accidents can be avoided. The Flux in hand gloves can operate without manual operation while driver is sleeping. This analysis uses Raspberry Pi, python software with machine learning (ML) algorithm (support vector machine). Hence, this robotic arm position for automatic electric vehicle shows better results in terms of charging issues, accident ratio and driver presence
IoT-enabled smart healthcare system with machine learning for real-time vital sign monitoring and anomaly detection
Get PDFThis paper presents an innovative IoT-enabled smart healthcare system that combines real-time vital sign monitoring with machine learning-based anomaly detection. The system utilizes a MAX30102 photoplethysmography sensor interfaced with an ESP-32 microcontroller to collect heart rate and blood oxygen saturation (SpO2) data. MQTT protocol ensures efficient data transmission to a cloud database. A long short-term memory (LSTM) neural network architecture is employed for time-series prediction of vital signs and anomaly detection. The system demonstrates high accuracy, with mean squared errors of 0.3% in offline testing and over 90% accuracy in real-time prediction. This affordable and scalable solution offers continuous monitoring capabilities, making it viable for widespread adoption in healthcare settings. The integration of IoT and machine learning techniques provides a robust framework for early detection of health anomalies, potentially improving patient care and outcomes in various medical scenarios
Detection of the Tajweed rules in the Qur’anic recitations
Get PDFTajweed is the science of reciting the Holy Quran, focusing on the clarity and correctness of recitation. This paper aims to accurately detect the spoken Tajweed rules applied during Quranic recitation, providing a well-structured Tajweed rules database for further analysis, Tajweed learning, and the training of advanced classification models. The main contribution of this work is to identify a high-accuracy approach for Tajweed rules detection and analysis. An improved template matching approach is introduced to enhance detection accuracy by matching the Quranic verse audio file with multiple speech patterns of a specific rule and selecting the best match. The Quranic audio file is segmented into smaller patterns by finding the correlation between the adjacent audio frames. Then, the template matching is applied to these segmented patterns to identify the best-matching ones. The template matching technique relies on a Tajweed database of 487 patterns of the Madd, Noon Sakinah, Tanween, and Meem Sakinah rules. An overall detection accuracy of 97.1% is achieved, and the Tajweed-pattern database is expanded to include the newly detected rules, increasing their total count to 2,583. Furthermore, an application based on the detected rules in this study was developed to enhance the performance of new Tajweed learners
Machine learning based strategies for managing employee retention: determining factors in hospitality industry
Get PDFIn order to boost performance and remain competitive, the Indian hospitality industry must recruit and retain employees if it wants to succeed in the long run. In order to do this, it will need to use a number of staff retention initiatives. It is suggested that effective employee retention tactics be analyzed using machine learning (ML) approaches for prediction. The results show that the hotel industry uses tactics to keep its employees, such as competitive compensation and benefits, opportunities for growth and recognition, safe and healthy workplaces, adaptable schedules, employment stability, and ongoing education and development. There is a noticeable disparity between the hotel industry’s demographics and retention tactics. In the hotel industry, there is a modestly negative correlation between employee desire to depart and employee retention methods. Pay and benefits, recognition and gratitude, a safe and healthy workplace, opportunities for professional growth, and development all play a role in how satisfied hospitality workers are with their jobs. The hotel sector has to implement strong welfare initiatives if it wants its workers to have a healthy work-life balance. The hotel business should promote the development of professional connections among its employees
Enhancing acoustic environment classification for hearingimpaired individuals using hybrid CNN and RFE
Get PDFIndividuals who are deaf or hard of hearing experience considerable difficulties in distinguishing sounds in various acoustic environments, which affects their communication ability and overall quality of life. Existing auditory assistive technologies currently face challenges with real-time classification and adaptation to changing noise conditions, underscoring the need for more reliable and accurate classification models. This research bridges the existing gap by creating a hybrid classification framework that integrates convolutional neural networks (CNN) and random forest ensemble (RFE) to enhance the accuracy of environmental sound classification. The study utilizes Mel-frequency cepstral coefficients (MFCCs) for feature extraction and principal component analysis (PCA) for dimensionality reduction, thus facilitating the efficient processing of real-world audio data. The proposed methodology improves classification accuracy across various environmental conditions. Experimental evaluations demonstrate superior performance, achieving a training accuracy of 94.93% and a testing accuracy of 93.41%, thereby exceeding conventional machine learning methods. By overcoming limitations in existing models, this research contributes to the development of adaptive hearing assistance systems with enhanced noise classification capabilities. The results have significant implications for the development of smart hearing aids, real-time noise classification, and auditory scene analysis. Ultimately, this research enhances assistive hearing technologies, promoting greater accessibility, communication, and inclusion for hearing-impaired individuals, thus contributing positively to society
Constructing dynamic XOR charts for block ciphers using hadamard matrices
Get PDFBlock ciphers are vital for modern encryption, ensuring the security of digital communications. Currently, powerful attacks target block ciphers, prompting researchers to propose ideas to enhance their cryptographic strength. One notable concept involves making components dynamic and dependent on a secret key, with limited attention given to the dynamic AddRoundKey operation. In this article, we introduce the definitions of some Hadamard matrix forms like B_had, N_had, and NB_had matrices. Subsequently, we present an algorithm for generating key-dependent XOR charts to create a key-dependent AddRoundKey operation based on these matrices. We then construct a dynamic AES block cipher by applying the proposed AddRoundKey operation to AES. We implement the dynamic AES algorithm, assess its security, and evaluate AES and the advanced AES using NIST’s statistical standards. The dynamic AES algorithm exhibits improved resistance against strong block cipher attacks compared to conventional AES
EMG-based hand gesture classification using Myo Armband with feedforward neural network
Get PDFThis paper presents the development of an electromyography (EMG)-based hand gesture identification system for remote-controlled applications. Even though the Myo Armband is no longer commercially supported, the research discusses its use in EMG data collecting. Open-source libraries were utilized to capture EMG data from this device to solve this problem. Using the developed data acquisition platform, data was collected from 30 participants who performed three (3) gestures - a fist, an open hand, and a pinch. The energy spectral density (ESD) and power ratio (pRatio) were extracted to describe gesture-specific patterns. A feedforward neural network (FFNN) was implemented for classification, initially configured with 10 hidden neurons and later optimized to 40 neurons to improve the performance. The box plot analysis showed channels CH1, CH4, CH5, and CH7 as the most significant for enhancing classification accuracy. The optimized FFNN achieved 80% and 70% for the training and testing accuracies, respectively. However, the results suggest that implementing a systematic protocol during data acquisition to reduce signal overlap between movements could improve classification accuracy. In conclusion, the study successfully developed an open-source EMG data acquisition platform for MYO Armband and demonstrated acceptable hand gesture recognition using an optimized FFNN