Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
A tag-based recommender system for tourism using collaborative filtering
Get PDFRecommender systems have garnered significant attention from researchers due to their potential for delivering personalized recommendations in light of the vast amount of information available online. These systems have found applications in various domains, including financial services, movies, and research articles. Their implementation in the tourism industry is particularly promising. Travelers often face the daunting task of selecting the right tourist attractions from a plethora of options, which can consume considerable time and energy. By leveraging personalized recommendation technologies, it is possible to provide highly accurate travel suggestions tailored to individual preferences. This study proposes the development of a customized recommendation system (RS) aimed at assisting travelers in the Qassim region of the Kingdom of Saudi Arabia. By using this region as a case study, the proposed RS consists of two main modules: a user registration and login module and a recommendation technique and tag module. The system will capture users’ interests and prompt them to select from various options, subsequently presenting them with tailored recommendations based on their preferences. This approach aims to enhance the travel experience by offering relevant suggestions that align with the interests of each traveler
CNN-GRU based cyber-attack classification and detection with the CICIDS-2017 dataset using optimization algorithm for honey badger
Get PDFThe sheer volume of data exchanged has grown through information and communications technology (ICT) swiftly growing importance since the attackers benefit from illegal access to network data and introduce possible dangers for data theft or alteration. It is considered a significant barrier to monitor the network traffic for cyber-attack detection and classification with alarm ring to inform to network administrator. With KDD-CUP99, conventional machine learning methods like deep neural network (DNN), a kind of artificial neural network (ANN), cannot detect and classify novel attacks types and lacks clarity regarding accuracy. The CICIDS 2017 dataset, which is improved in this study, serves as training data for the model and useful framework that combines a hybrid convolutional neural network (CNN) with the gated recurrent unit (GRU) technique. The primary aim of this effort is to classify different security attacks and classify cyberthreats with honey badger optimization algorithm (HBOA). To strengthen the performance criteria for various assault types, such as F1-score, recall, precision, and others, the HBOA is utilized to modify the model parameters high-level features ought to be extracted from the network data using the hybrid model assessed and verified by simulation studies. The detection and classification output from the CNN-GRU model, which detects different security threats with greater accuracy of 94%
Phishing URL prediction – two-phase model using logistic regression and finite state automata
Get PDFThe human factor in security is more important when they become the carriers of attacks on enterprises. Phishing attacks can be classified as insider attacks when the employees unintentionally participate in the attack propagation. Since complete user training is a myth, enterprises must implement detection tools for phishing attacks on their network perimeters. This research discusses a two-phase model for phishing URL detection, in which the first phase identifies the properties of URLs that detect phishing and their relative weight using logistic regression. The second phase checks the probability of a new URL being categorized as phishing using the knowledge achieved during the first phase using the dynamically created Finite state machines. The model defines a malicious score (MS), which can be used to check any URL in real-time to identify whether it is phishing or not. The model described in this work has been experimented with different benchmarking datasets to verify the performance. The model provided a decent result in classifying a URL as phishing or naive. The malicious score (MS) defined by this model can be used to evaluate any URL and can be used as a filtering mechanism for end-point phishing URL detection. The key contribution is towards developing a two-phase model which evaluates the URL with the help of self-crafted features without reliance on a feature set. This accommodates the model's hyper-competitive phishing URL detection area in cyber security
A comprehensive analysis of smartphones and tablets in graphic design and digital art
Get PDFThis paper discusses how smartphones and tablets have changed creativity and graphic design. These portable tools and easy apps have transformed the creative process, allowing artists, designers, and students to create high-quality work anywhere. Mobile design apps promote creativity, accessibility, and skill development across broad user groups, according to the study. Unlike desktop tools, it addresses key constraints. Mobile apps sometimes struggle with smaller screens, restricted processing power, and reduced capabilities for complicated tasks like multi-layer editing and advanced graphics. These restrictions may inhibit expert designers working on complex, precise designs. Even Nevertheless, mobile technology like larger screens, stylus support, and cloud-based solutions are making mobile devices more feasible for creative work. The findings emphasise the relevance of integrating mobile technology into education and professional workflows and its complementarity to desktop solutions for resource-intensive jobs. In the developing digital landscape, our dual-platform approach maximizes creativity and flexibility
Measuring political influence during elections using a deep learning approach
Get PDFThis contribution introduces a methodology for measuring political influence on Twitter during the 2020 U.S. presidential election campaign. The approach employs deep knowledge scores, which are generated through sentiment analysis of Tweets from users responding to influential users, coupled with an assessment of the strength of their interactions. The deep knowledge scores enable the categorization of three types of Twitter’s users engaging with influential users: influenced users, distrustful users, and connected users. Our approach, structured around a five-layer framework, effectively constructs networks of trust and distrust, and establishes the relationship between fluctuations in trust or distrust levels and the topics discussed by influential users
Novel prostate cancer detection and classification model using support vector machine
Get PDFProstate cancer (PCa) is one of the most common and deadliest cancers that kill men worldwide with high mortality and prevalence especially in developed countries. PCa is regarded as one of the most prevalent cancers and is one of the main causes of deaths worldwide. Early detection of PCa diseases helps in making decisions about the progressions that should have occurred in high-risk patients decrease their risks. The recent developments in technology and methods have given rise to computer aided diagnosis (CAD). Early cancer detection can greatly increase the chance of survival through the administration of the proper treatment. Due to the emerging trends and available datasets in state-of-art machine learning (ML) and deep learning (DL) techniques, there has been significant growth in recent disease prediction and classification publications. This paper presents a unique support vector machine-based model for PCa detection and classification. This analysis aims to classify the PCa using ML algorithm and to determine the risk factors. Support vector machines (SVM) is used to identify and classify the PCa. Accuracy, sensitivity, specificity, precision, and F1-score are the measurements used to evaluate the performance of the presented method. This model will achieve accuracy, sensitivity, specificity, precision, and F1-score than earlier models
RNN-driven integration of spatial, temporal, features for Indian sign language recognition and video captioning
Get PDFThis paper presents a novel model that integrates spatial features from residual blocks and temporal features from FFT, alongside a sophisticated RNN architecture comprising BiLSTM, gated recurrent units (GRU) layers, and multi-head attention. Achieving nearly 99% accuracy on both WLASL and INCLUDE datasets, this model outperforms standard CNN pretrained models in feature extraction. Notably, the BiLSTM and GRU combination proves superior to other combinations such as LSTM and GRU. The BLEU score analysis further validates the model's efficacy, with scores of 0.51 and 0.54 on the WLASL and INCLUDE datasets, respectively. These results affirm the model's proficiency in capturing intricate spatial and temporal nuances inherent in sign language gestures, enhancing accessibility and communication for the deaf and hard-of-hearing communities. The comparison highlights the superiority of this paper's proposed model over standard approaches, emphasizing the significance of the integrated architecture. Continued refinement and optimization hold promise for further augmenting the model's performance and applicability in real-world scenarios, contributing to inclusive communication environments
Comprehensive secure code review analysis of web application security vulnerabilities
Get PDFA secure code review is a process of software development involves systematic examination of application code. However, web applications evolving of cyber threats makes it challenging to conduct adequate security. Therefore, this paper conducts a comprehensive secure code review analysis to protect any crucial aspect of web security from potential threats and vulnerabilities. The application code is scanned for security issues during the real review and the results are classified according to the areas of vulnerability. As a result, the application code risk level and list of risk categories were defined. This result assists in prioritizing issues for resolution, beginning with the most critical problems to lower risk levels. Next, list of risk categories that give the most significant security vulnerabilities affect to application codes are defined. SQL injection, weak password handling, insecure direct object reference, information exposure, improper session management, missing input validation, deprecated functions, and lack of comments are defined as a risk category. Moreover, the result of application code weakness in the security of the application code is determined based on the level of risk and categories. Thus, analysis result offers the developers a clear perspective on protects the web applications from threats and vulnerabilities
Development of an automatic processing system for predicting the earthquake signals using machine learning techniques
Get PDFEarthquake signals are crucial for minimizing the impact of seismic activities. Current algorithms face difficulties in correctly identifying P-waves and assessing magnitudes, which affects the amount of advance warning given. It is crucial to establish standardized methods for the effective selection and integration of multiple algorithms. Machine learning techniques could considerably enhance detection reliability. The research seeks to rectify this shortfall and strengthen automated detection as well as prediction capabilities. The model's performance is assessed using real earthquake data in simulations compared to individual algorithms. The objective of this research is to develop an optimized multi-algorithm framework that enhances the warning lead times and overall reliability. This framework underpinning this method is shaped by the operational demands inherent in early warning systems. The objective of the work is to contribute to the betterment of seismic risk reduction. An ML methodology, merging several distinct detection algorithms, will be deployed along with a tailored prioritization system. The intention is to strengthen the model's dependability and its overall level of consistency. The ML-based multi-algorithm framework significantly boosts the performance of Early Earthquake Warning Systems, providing a scalable approach to enhance automated detection and public safety, ultimately advancing the effectiveness of seismic hazard reduction through quicker and more accurate warnings
Sentiment analysis of YouTube videos comments for children using machine learning and deep learning
Get PDFNowadays, online connectivity is increasing with the rapid growth of the world wide web. Consequently, content shared across numerous platforms varies in appropriateness. it is necessary to ensure the suitability of the content since children are among the consumers of online content. A lot of children watch videos on YouTube these days, and such platforms can contain useful content. However, such videos can also have a negative impact on children. The suitability of these videos can be determined through sentiment analysis to refine the content for children on YouTube, by classifying the posted comments as either positive or negative. Therefore, this study utilizes natural language processing methods, machine learning classifiers (MLCs) and deep learning models (DLMs) to detect and classify negative user comments using the proposed dataset. Different MLCs such as random forest (RF), logistic regression (LR), multinomial Naïve Bayes (MNB), decision tree (DT), K-nearest neighbour (KNN), AdaBoost, and support vector machine (SVM) have been used. Additionally, DLMs were also used such as artificial neural network (ANN), convolutional neural network (CNN) and long short-term memory (LSTM). Overall, the experimental results showed that the LR, RF, AdaBoost, ANN and LSTM classifiers outperformed all the other classifiers in terms of accuracy