Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Efficient PAPR reduction technique in OFDM system using amplitude clipping and selective filtering
Get PDFOne of the most important transmission methods for the next generation of wireless communication systems is orthogonal frequency division multiplexing (OFDM). Transmitting an OFDM signal in a noisy environment with a low bit error rate (BER) is the primary goal. High peakto-average power ratio (PAPR) at the transmitter, which lowers the transmission peak power, is one of OFDM's biggest drawbacks. In this paper, we propose efficient PAPR reduction technique in OFDM system using amplitude clipping and selective filtering. The efficient multiefficiency PAPR reduction strategies with pulse amplitude modulation (PAM) and quadrature amplitude modulation (QAM) modulation are employed with selective filtering and evaluated in terms of percentage reduction level to lowest PAPR of 3.841 db. It is observed that QAM modulation produces better results compared to PAM modulation with less BER of 0.003 for signal-to-noise ratio (SNR) of 20 db
QV finder: an accurate Quran verse finder system
Get PDFA voice-based search is becoming increasingly important for accessing information across various domains. One of the most challenging areas is Quranic verse search, where precise recitation rules (Tajweed), dialectal variations, and background noise affect accuracy. In this work, we present QV finder, an artificial intelligence (AI)-powered system that utilizes a finetuned whisper-based automatic speech recognition (ASR) model specifically trained on diverse Quranic recitations for the whole Quran. In this paper, we present a robust pipeline for Quranic verse retrieval that bridges the gap between ASR technology and domain-specific linguistic complexity. The model supports both professional and normal reciters, even under noisy conditions. To enhance the localization of verses from partial recitations, we integrated tokenization and advanced string-matching algorithms such as Levenshtein distance and FuzzyWuzzy. For normal reciters, the proposed model achieves a word error rate (WER) of 10.1% and character error rate (CER) of 3.3%, outperforming Google ASR, which exhibits a WER of 27.04%, and a CER of 7.13%. The model also achieves 100% verse retrieval accuracy with a 2.5% false positive rate. Our best fine-tuned model is uploaded here: https://huggingface.co/basharalrfooh/whisper-small-quran
Internet of things meteorological station for climate monitoring and crop optimization in Carabayllo-Perú
Get PDFIn the agricultural sector, monitoring environmental variables such as temperature, humidity, and atmospheric pressure is crucial for efficient and sustainable agriculture. However, conventional monitoring systems are expensive and need more autonomy, making their implementation difficult in small- and medium-scale agricultural operations. This study presents the design, implementation, and evaluation Internet of things (IoT)-based autonomous for watch remote critical climate variables in the Carabayllo region, Peru. The system uses a data acquisition, processing, and transmission architecture based on the ESP32 microcontroller, DHT22 sensors for measure climatic aspects, BMP180 for detection barometric, and the ThingSpeak cloud platform for data storage and visualization. Results show that the proposed system achieves accuracy comparable to commercial weather stations, making it accessible to small farmers. The implementation demonstrated the system’s ability to detect feasible local microclimates to monitor and predict weather patterns for proper crop growth. This approach enables farmers to monitor conditions in real time, receive early alerts on adverse weather events, and optimize agricultural practices such as irrigation and fertilization. The study concludes that the proposed IoT weather station represents a viable and cost-effective solution to improve agricultural decision-making in developing regions, potentially contributing to increasing crops
Jellyfish optimized deep learning framework for cache pollution attack detection in NDN environment
Get PDFNamed data networking (NDN) is a promising paradigm that replaces the traditional connection-based model with a content-based approach for future Internet infrastructures, allowing data retrieval by unique names. However, NDN faces threats like cache pollution attacks (CPA) which can lead to increased cache misses and data retrieval delays, and pose significant risks to its efficiency and security. In this paper, a novel jellyfish optimized deep learning (DL) framework for cache pollution attack detection in NDN environment (DSODAL) technique has been proposed to detect the CPA attack with high accuracy. To detect CPA in NDN, a dual-gate attention-based long short-term memory (LSTM) (DA-LSTM) network is used which is optimized using the jellyfish search optimization (JSO) algorithm. The DA-LSTM analyzes request sequences to identify malicious patterns, enhancing cache pollution detection. Nodes manage these requests using the content store (CS) for caching frequently accessed data, optimizing retrieval efficiency, and the pending interest table (PIT) to track and process incoming requests. The DA-LSTM analyzes request sequences to identify malicious patterns and detect CPA attacks. The DSODAL approach performance is evaluated using accuracy, precision, recall, F1-score, average delay time, and mean square error (MSE). The DSODAL model advances the overall accuracy by 1.74%, 2.34%, and 2.7%, over existing HCDLP, ACISE, and AHISM techniques
Automating electronic document management design: a model-driven approach using business process
Get PDFModel-driven architecture (MDA) is a useful approach for designing enterprise information systems through structured models. This study applies MDA to electronic document management (EDM) systems, which are essential for improving document workflows and ensuring regulatory compliance. Organizations often face difficulties when converting business process models into software-ready designs. Current transformation methods are complex, involving multiple intermediate steps that increase effort and risk of errors. The objective of this work is to create a direct transformation from business process model and notation (BPMN) diagrams to unified modeling language (UML) class diagrams. This aims to improve automation, reduce modeling effort, and maintain consistency. The proposed methodology uses MDA principles and query/view/transformation (QVT) to automatically map BPMN elements to UML classes based on predefined rules. The approach is implemented within the eclipse modeling framework (EMF) and validated through a case study on EDM systems. The transformation successfully generates UML class diagrams that accurately represent BPMN-based business processes. The results demonstrate: increased automation, reducing manual effort in software modeling, improved model consistency, eliminating errors associated with multi-step transformations and enhanced business-IT alignment, providing a structured approach for business professionals and developers
OPT-TMS: a transport management system based on unsupervised clustering algorithms
Get PDFTransportation management within modern logistics has become increasingly complex, particularly with the expansion of industrial zones outside urban centers. This paper introduces OPT-TMS, a cutting-edge transportation management system (TMS) designed to optimize employee transportation using advanced machine learning techniques, specifically unsupervised learning and clustering algorithms. OPT-TMS integrates a comprehensive dataset that includes employee locations, entry times, bus capacities, and other critical parameters to enhance resource utilization, reduce costs, and improve overall efficiency. The proposed system follows a systematic workflow encompassing data collection, preparation, and adaptive clustering using the K-means algorithm with constraints. The innovative approach leverages real-time data integration through the open route services (ORS) API to optimize bus routes and collection points. Extensive validation, involving both data verification and physical testing, confirms the system’s accuracy and effectiveness across multiple Moroccan cities, including Casablanca, Kenitra, and Marrakech. The development of OPT-TMS into a user-friendly web application further demonstrates its practical utility, offering decision-makers a dynamic tool for real-time adjustments and efficient transportation management. This paper concludes that OPT-TMS represents a significant advancement in transportation logistics, enhancing both employee satisfaction and operational efficiency through data-driven optimization
A centroid-based algorithm for measuring and tracking vehicle speed from a monocular camera using the YOLOv8 object detector
Get PDFAccurate real-time vehicle speed measurement is crucial for enhancing road safety and advance intelligent transportation systems (ITS). This paper proposes a centroid-based tracking algorithm that integrates YOLOv8, a state-of-the-art object detector, with DeepSORT for robust multi-object tracking. By leveraging YOLOv8’s anchor-free detection and DeepSORT’s appearance-based association, the proposed method effectively mitigates occlusions and minimizes identity switches. Evaluations on the VS13 benchmark dataset reveal a 2–5% improvement in measurement accuracy as compared to existing solutions, while maintaining real-time performance at 30 FPS. The method demonstrates consistent reliability across different vehicle models, speeds, and lighting conditions, underscoring its adaptability to real-world traffic scenarios. Moreover, larger bounding boxes enhance tracking stability, reducing false detections. Overall, the approach’s low computational overhead and high accuracy position it as a practical solution for ITS applications in constrained environments
Utilizing metaheuristic optimization with transfer learning for efficient colorectal carcinoma detection in biomedical imaging
Get PDFColorectal cancer (CRC) is the third most popular cancer across the world. Its morbidity and death are reduced by early screening and detection. The screening outcomes are enhanced by computer-aided detection (CAD) and artificial intelligence (AI) in screening models. Contemporary imaging technologies such as near-infrared (NIR) fluorescence and optical coherence tomography (OCT) are implemented to identify the early-phase CRC of the gastrointestinal tract (GI tract) via the identification of morphological and microvasculature changes. Most recently, deep learning (DL)-based approaches have been used directly on raw data. Nevertheless, they are hampered by biomedical data deficiency. These studies can enhance metaheuristic optimization using the transfer learning to detect colorectal cancer successfully (MHOTL-ECRCD). The MHOTL-ECRCD method concentrates on biomedical imaging of CRC categorization and detection. MHOTL-ECRCD minimizes noise through the process of adaptive bilateral filtering (ABF). In MHOTL-ECRCD methodology, Inception-ResNet-V2 is adopted to learn the inherent and complicated image preprocessing features thus used during feature extraction. To classify CRC and detect it, the gated recurrent unit (GRU) approach is applied. Lastly, parameters of the GRU model are optimized with a human evolutionary algorithm. Good classification results of MHOTL-ECRCD are demonstrated by a number of benchmark dataset trials. MHOTL-ECRCD technology superseded the recent techniques as large volumes of comparison were made
Clustering technique for dense D2D communication in RIS-aided multicell cellular network
Get PDFDevice-to-device (D2D) communication and reconfigurable intelligent surface (RIS) are well-known as two promising technologies for nextgeneration cellular communication networks. D2D users operate on the same spectrum as traditional cellular users, potentially leading to increased interference and reduced efficiency in frequency resource usage. RIS provides a remedy for clearing blocked signals from obstructions by reflecting the desired signals to the intended receiver. However, RIS elements reflect not only the desired signals but also the interference signals. This paper proposes a distance-based clustering method aimed at creating a grouping algorithm for neighboring D2D users using different channels, thereby reducing co-channel interference. The simulation indicates that the proposed clustering method for D2D users' equipment (DUEs) leads to a 0.72 dB increase in signal-to-interference-plus-noise ratio (SINR), enhances throughput to 11.25 Mbps, and reduces the bit error rate by up to 24×10⁻² compared to the baseline system. The study findings also indicate that cellular users' equipment (CUEs) experience satisfactory signal quality, even with the presence of DUEs on the cellular network. Our clustering algorithm is feasible to deploying D2D densely in RIS-aided cellular network without significantly affecting CUE performance
An efficient implementation of credit card fraud detection using CatBoost algorithm
Get PDFTransaction fraud has grown to be an important issue in worldwide, banking and commerce security is easier access to trade information. Every day, there are more and more incidents of transaction fraud, which causes large financial losses for both consumers and financial professionals. The ability to identify transaction fraud is getting closer to reality due to improvements in computer science's machine learning (ML) and data mining areas. So, one of them that is becoming dangerous is credit card fraud (CCF). Millions of people are experiencing financial loss and identity theft as a result of these malicious operations. The CCF of many illegal activities that fraudsters are always using new methods to carry out. One major problem facing financial services sector is CCF. To overcome this, categorical boosting (CatBoost) algorithm is explained as a solution to these problems. Fraud or fraudulent transactions are identified using this effective CatBoost algorithm implementation for identification of CCF. Thus, in terms of accuracy, precision, and detection rate this method gives better performance