Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
SVM algorithm-based anomaly detection in network logs and firewall logs
Get PDFThe purpose of many advanced forms of cyberattack is to deceive the monitors, and as a result, these attacks often involve several kinds, levels, and stages. Existing anomaly detection systems often examine logs or traffic for indications of attacks, ignoring any additional analysis regarding attack procedures. This is done to save time. For example, traffic detection technologies can only identify the attack flows in a general sense. Still, they cannot reconstruct the attack event process or expose the present condition of the network node. In addition, the logs kept by the firewall are significant sources of evidence; nevertheless, they are still challenging to decipher. This paper introduces support vector machine algorithm-based Anomaly detection (SVMA) in network logs and firewall logs to provide robust security against cyberattacks. This mechanism consists of three modules: preprocessing, feature selection and anomaly detection. The genetic algorithm (GA) selects the better feature from the input. Finally, the support vector machine (SVM) isolates an anomaly powerfully. The investigational outcomes illustrate that the SVMA minimizes the required time to select the features and enhances the detection accuracy
IoT based intrusion detection data analysis using deep learning models
Get PDFIn both the academic and industrial domains, integration of the internet of things (IoT) is now universally accepted as a significant technical achievement. IoT offers a multitude of security issues despite its many advantages, such as protecting networks and devices, handling resourceconstrained network scenarios, and controlling threats to IoT networks. This article gives a state-of-the-art analysis on the application of multiple deep learning (DL) algorithms in IoT intrusion detection systems (IDS), covering the years 2020 to 2024. Moreover, two popular network datasets, NSL-KDD and UNSW-NB15, are used for an experimental evaluation. The study thoroughly examines and assesses the advantages of well-known deep learning algorithms, including DNN, CNN, RNN, LSTM, and FFDNN. The study demonstrates the exceptional performance of the DNN approach on both datasets, with 99.14% accuracy in multiclass classification in NSLKDD and 99.36% accuracy in binary classification. Furthermore, on UNSWNB15, 82.26% of multiclass classifications and 93.96% of binary classifications with a 42-second minimum running time were achieved, along with an excellent performance in reducing false alarms at a rate of 2.19%
War strategy assisted Bi-LSTM for sentiment analysis of customer review
Get PDFSentiment analysis (SA) stands as a valuable tool for categorizing reviews to discern positive or negative sentiments. Satisfaction of customers holds a pivotal role in the realm of customer service. Presently, customer expression entails a significant volume of reviews on online platforms. For extracting useful information from massive reviews, the categorization of reviews into positive or negative SA is essential. For enhancing the efficiency of customer review detection, this work presents a war strategy algorithm (WSA)-bidirectional long short-term memory (Bi-LSTM) for customer review classification using the TripAdvisor dataset. Initially, the preprocessing stage is carried out, and the skip-gram-based word embedding is performed. For categorizing the extracted features, the deep learning model Bi-LSTM-WSA is presented. Accuracy and precision values achieved are 97.1% and 97.5% respectively
Using ResNet architecture with MRI for classification of brain images
Get PDFA strong classification model that can correctly detect abnormalities and neurological disorders in brain images is the main goal. The focus of this research is on improving the accuracy of MRI brain image categorization using residual networks (ResNet) methods. Improving the model's capacity to extract complex characteristics from MRI images and achieving more accurate classification results is the aim of using ResNet architectures. By conducting extensive experiments and validating our results, our project aims to attain top-notch performance in brain image classification tasks. The goal is to help improve medical diagnosis and treatment planning. A secondary goal of the research is to determine if deep learning approaches have any use in radiology, with the hope that this will lead to better medical image analysis pipelines. The main objective is to make it easier to identify neurological problems early on, which will enhance patient outcomes and allow for more calculated treatment decisions. Results proved that the proposed ResNet system achieves 98.8% overall accuracy with 98.6% sensitivity and 99% specificity
Applied differential comparative study of VANET simulators: TrAD protocol study using veins and VNS VANET simulators in both real and standard city maps
Get PDFThis study presents a comprehensive evaluation of vehicular ad-hoc networks (VANETs) by analysing the performance of two leading simulation frameworks: VEINS and VNS. With the increasing demand for efficient vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, understanding the capabilities of data dissemination protocols is crucial for enhancing traffic safety and optimizing route management. We investigate the traffic adaptive data (TrAD) protocol, which dynamically adapts to real-time traffic conditions to ensure reliable communication in high-density vehicular scenarios. Simulations were conducted using OMNeT++ with VEINS and NS-3 with VNS across urban environments in Manhattan and Tlemcen, evaluating TrAD’s effectiveness under diverse traffic conditions. The findings offer valuable insights into the operational strengths of the two simulation frameworks and their implications for advancing vehicular communication systems. This work contributes to the development of robust VANET protocols, supporting innovations in smart and sustainable transportation systems
MQTT live performance on the INA-CBT communication system: a measurement-based evaluation
Get PDFCable-based tsunameters have been deployed in Indonesia under the name of the INA-CBT project. Currently, the system operated at the Labuan Bajo landing station works well and sends aggregated data from the seafloor sensors to a central or read down station in Jakarta for further processing. The current scheme makes use of a publish and subscribe indirect communication among the landing station (LS) as the publisher and various clients as subscribers for the sensor data. Message queue telemetry transport (MQTT) was selected as the application-layer protocol for implementing this communication scheme. This paper presents a measurement-based evaluation of the MQTT live performance by observing the MQTT messages’ latencies received at the subscriber of the INA-CBT’s MQTT broker. The results give insight on the general achievable performance of the INA-CBT communication system in providing reliable data for the tsunami detection system. Furthermore, the results obtained can be used as communication parameters for making a more realistic virtual testbed for designing a more appropriate and scalable CBT system
Hyperparameter optimization of convolutional neural network using grey wolf optimization for facial emotion recognition
Get PDFFacial emotion recognition (FER) is a challenging task in computer vision with wide applications in areas such as human-computer interaction, security, and healthcare. To improve the performance of convolutional neural networks (CNN) in FER, a novel approach combining CNN with grey wolf optimization (GWO) was proposed to optimize key hyperparameters. The CNN-GWO model was fine-tuned by adjusting hyperparameters such as the number of convolutional layers, kernel size, number of filters, and learning rate. This model was evaluated using the CK+ dataset and achieved an accuracy of 90.97%, demonstrating its competitive performance compared to existing methods. The optimized hyperparameters included three convolutional layers, 35 filters, a kernel size of 5, a learning rate of 0.045990, a dropout rate of 0.4988, and a max pooling size of 3. These results confirm that GWO is effective in optimizing CNN for FER tasks, providing an efficient solution to enhance model accuracy. This approach shows promising potential for future FER applications, highlighting GWO as a valuable optimization technique for CNN architectures
Sentiment analysis in Arabic and dialects: a review utilizing a corpus-based approach
Get PDFArabic is one of the most morphologically complex languages, and its numerous dialects render identifying sentiment in digital communication a challenging task. In this study, we conduct a systematic literature review (SLR) to investigate the sentiment analysis (SA) techniques used on modern standard Arabic (MSA) and several Arabic dialects (AD) between 2020 and 2024. A corpus-based analysis of 71 articles indicated that machine learning (ML) and deep learning (DL) algorithms were the dominant methods used. Overall, the most frequently studied dialects are those from Saudi Arabia, Morocco, and to a lesser extent, Algeria, among various algorithms used for text classification, including support vector machines (SVM) and convolutional neural networks (CNN). These techniques emerged as some of the most effective strategies employed for sentiment classification. While new contemporary word embeddings, such as Word2Vec, are gaining traction in the field, traditional feature extraction methods, like term frequency-inverse document frequency (TF-IDF), continue to outperform them. The study highlights the importance of additional labeled datasets and tailored models in navigating the linguistically rich world of AD. Additionally, the results highlight the need for dialect-specific adaptations to improve SA outcomes, and further investigation is needed by leveraging advanced DL methodologies, as well as improved data resources, to address these issues
Adoption of virtual tours for tourism promotion in Tegal Regency: a technology acceptance model analysis
Get PDFTegal Regency has various tourist attractions that have the potential to be increased as a stimulus for the district's economy. So that this potential can have an optimal positive impact, the tourist destination should be promoted to the general public to increase tourism visits. This effort can be carried out by utilizing existing technological developments through virtual tour (VT), but their implementation requires careful consideration. This study explored how perceived usefulness (PU), perceived ease of use (PEU), attitude, behavioral intention (BI), and tourism promotion (TP) relate to each other within the context of virtual tourism. Data were collected from 126 participants via an an online survey developed using the technology acceptance model (TAM) framework. The partial least squares structural equation modeling (PLS-SEM) method was employed for analyzing the data. The result revealed significant relationships between PU and ease of use, user attitudes (AT), and BIs. Furthermore, BI, PU, and PEU were all considerable predictors of TP. However, no significant relationship was found between user AT and BIs
Attention based English to Indo-Aryan and Dravidian language translation using sparsely factored NMT
Get PDFNeural machine translation (NMT) is a sophisticated technique that employs a large, singular neural network to learn and execute automatic translation tasks. Unlike statistical machine translation systems, NMT handles the entire translation process in an end-to-end manner, removing the need for additional components. This approach has shown significant promise in translation quality and has become the prevalent method. In this study, we apply sparsely factored NMT to English and several Indo-Aryan (Hindi, Bengali) and Dravidian (Tamil, Malayalam) language pairs. Specifically, we develop the machine translation system using an attention-based mechanism. A significant problem with traditional transformers is the huge memory requirement. Therefore, a sparsely factored NMT (SFNMT) is used to reduce the memory requirement but also improves the training time, thereby, reducing the computing time. In this paper, take inspiration from Vaswani transformer and modify it to get the best results. The system’s performance was evaluated using the BLEU metric. The proposed model indtrl achieves a BLUE score of 32.13 (en→hi), 29.31 (en→be), 31.21 (en→ta), 21.12 (en→ml) and 32.67 (en→hi), 29.38 (en→be), 31.75 (en→ta), 21.17 (en→ml) without backtranslation and with backtranslation. To evaluate the performance of the system, we compared the results with those of existing systems. The developed system demonstrated a marginally higher BLEU score than both AnglaMT and Google translate