Computer Science and Information Technologies (E-Journal)
Not a member yet
149 research outputs found
Sort by
Sentiment analysis of online licensing service quality in the energy and mineral resources sector of the Republic of Indonesia
Full text linkThe Ministry of Energy and Mineral Resources of the Republic of Indonesia regularly assessed public satisfaction with its online licensing services. User rated their satisfaction at 3.42 on a scale of 4, below the organization's average of 3.53. Evaluating public service performance is crucial for quality improvement. Previous research relied solely on survey data to assess public satisfaction. This study goes further by analyzing user feedback in text form from an online licensing application to identify negative aspects of the service that need enhancement. The dataset spanned September 2019 to February 2023, with 24,112 entries. The choice of classification methods on the highest accuracy values among decision tree, random forest, naive bayes, stochastic gradient descent, logistic regression (LR), and k-nearest neighbor. The text data was converted into numerical form using CountVectorizer and term frequency-inverse document frequency (TF-IDF) techniques, along with unigrams and bigrams for dividing sentences into word segments. LR bigram CountVectorizer ranked highest with 89% for average precision, F1-score, and recall, compared to the other five classification methods. The sentiment analysis polarity level was 36.2% negative. Negative sentiment revealed expectations from the public to the ministry to improve the top three aspects: system, mechanism, and procedure; infrastructure and facilities; and service specification product types
Machine learning-based anomaly detection for smart home networks under adversarial attack
Full text linkAs smart home networks become more widespread and complex, they are capable of providing users with a wide range of applications and services. At the same time, the networks are also vulnerable to attack from malicious adversaries who can take advantage of the weaknesses in the network's devices and protocols. Detection of anomalies is an effective way to identify and mitigate these attacks; however, it requires a high degree of accuracy and reliability. This paper proposes an anomaly detection method based on machine learning (ML) that can provide a robust and reliable solution for the detection of anomalies in smart home networks under adversarial attack. The proposed method uses network traffic data of the UNSW-NB15 and IoT-23 datasets to extract relevant features and trains a supervised classifier to differentiate between normal and abnormal behaviors. To assess the performance and reliability of the proposed method, four types of adversarial attack methods: evasion, poisoning, exploration, and exploitation are implemented. The results of extensive experiments demonstrate that the proposed method is highly accurate and reliable in detecting anomalies, as well as being resilient to a variety of types of attacks with average accuracy of 97.5% and recall of 96%
Deep learning technique for plant disease detection
Full text linkA nation's economy is primarily reliant on agricultural growth. However, several plant diseases seriously impair crop growth, both in terms of quantity and quality. Due to a lack of subject matter specialists and low contrast data, accurate diagnosis of many diseases by hand is highly difficult and time-consuming. The farm management system is therefore looking for a method for automatically detecting early illnesses. To overcome these challenges and correctly classify the different diseases, an efficient and small deep learning-based framework (E-GreenNet) is proposed. A MobileNetV3Small model is used as the foundation of our end-to-end architecture to produce finely tuned, discriminative, and noticeable features. Furthermore, the new plant composite (PC), plantvillage (PV), and data repository of leaf images (DRLI) datasets are used to independently train our proposed model, and test samples are used to evaluate its actual performance. The suggested model achieved accuracy rates of 1.00 percent, 0.96 percent, and 0.99 percent on the given datasets after a rigorous experimental study. Additionally, a comparative investigation of our proposed technique against the state-of-the-art (SOTA) reveals extremely high discriminative scores
Implementation of automation configuration of enterprise networks as software defined network
Full text linkSoftware defined network (SDN) is a new computer network configuration concept in which the data plane and control plane are separated. In Cisco system, the SDN concept is implemented in Cisco Application Centric Infrastructure (Cisco ACI), which by default can be configured through the main controller, namely the Application Policy Infrastructure Controller (APIC). Conventional configuration on Cisco ACI creates problems, i.e.: the large number of required configurations causes the increase of time required for configuration and the risk of misconfiguration due to repetitive works. This problem reduces the productivity of network engineers in managing Cisco system. In overcoming these problems, this research work proposes an automation tool for Cisco ACI configuration using Ansible and Python as an SDN implementation for optimizing enterprise network configuration. The SDN is implemented and experimented at PT. NTT Indonesia Technology network, as a case study. The experimental result shows the proposed SDN successfully performs multiple routers configurations accurately and automatically. Observations on manual configuration takes 50 minutes and automatic configuration takes 6 minutes, thus, the proposed SDN achieves 833.33% improvement
Predicting students' success level in an examination using advanced linear regression and extreme gradient boosting
Full text linkThis research employs a hybrid approach, integrating advanced linear regression and extreme gradient boosting (XGBoost), to forecast student success rates in exams within the dynamic educational landscape. Utilizing Kaggle-sourced data, the study crafts a model amalgamating advanced linear regression and XGBoost, subsequently assessing its performance against the primary dataset. The findings showcase the model's efficacy, yielding an accuracy of 0.680 on the fifth test and underscoring its adeptness in predicting students' exam success. The discussion underscores XGBoost's prowess in managing data intricacies and non-linear features, complemented by advanced linear regression offering valuable coefficient interpretations for linear relationships. This research innovatively contributes by harmonizing two distinct methods to create a predictive model for students' exam success. The conclusion emphasizes the merits of an ensemble approach in refining prediction accuracy, recognizing, however, the study's limitations in terms of dataset constraints and external factors. In essence, this study enhances comprehension of predicting student success, offering educators insights to identify and support potentially struggling students
Development of learning videos for natural science subjects in junior high schools
Full text linkThe purpose of this study was to determine the development procedure and the feasibility of learning media for whiteboard animation in Natural Sciences subjects at SMP Padindi, Tangerang Regency. This study uses a research and development (R&D) approach. The development model in this study is the analysis design development implementation evaluation (ADDIE) model. The feasibility test is carried out by means of individual testing (one to one) on 3 experts, namely material experts, learning experts, and media experts, as well as 3 students. In addition, a small group test was also carried out on 9 students. The results showed that: i) the material expert test was 87.5%, the learning expert was 85%, the media expert was 84.44%, 3 students were 88.84%, and the small group was 90%; and ii) this whiteboard animation learning media is suitable for use based on the results of media trials by experts and students
Unraveling Indonesian heritage through pattern recognition using YOLOv5
Full text linkThis research focuses on three iconic Indonesian batik patterns-Kawung, Mega Mendung, and Parang-due to their cultural significance and recognition. Kawung symbolizes harmony, Mega Mendung represents power, and Parang signifies protection and spiritual power. Using the YOLOv5 deep learning model, the study aimed to accurately identify these patterns. Results showed mean average precision (mAP) scores of 77% for Kawung, 80% for Parang, and an impressive 99% for Mega Mendung. The highest precision results were 91% for Kawung, 88% for Parang, and 77% for Mega Mendung. These findings highlight the potential of pattern recognition in preserving cultural heritage. Understanding these designs contributes to the appreciation of Indonesia s culture. The research suggests applications in cultural studies, digital archiving, and the textile industry, ensuring the legacy of these patterns endures
Generalization of linear and non-linear support vector machine in multiple fields: a review
Full text linkSupport vector machines (SVMs) are a set of related supervised learning methods used for classification and regression. They belong to a family of generalized linear classifiers. In other terms, SVM is a classification and regression prediction tool that uses machine learning theory to maximize predictive accuracy. In this article, the discussion about linear and non-linear SVM classifiers with their functions and parameters is investigated. Due to the equality type of constraints in the formulation, the solution follows from solving a set of linear equations. Besides this, if the under-consideration problem is in the form of a non-linear case, then the problem must convert into linear separable form with the help of kernel trick and solve it according to the methods. Some important algorithms related to sentimental work are also presented in this paper. Generalization of the formulation of linear and non-linear SVMs is also open in this article. In the final section of this paper, the different modified sections of SVM are discussed which are modified by different research for different purposes
National archival platform system design using the microservice-based service computing system engineering framework
Full text linkArchives play a vital function concerning the dynamics of people and nations as an instrument to treasure information in diverse domains of politics, society, economics, culture, science, and technology. The acceleration of digital transformation triggers the implementation of a smart government that supports better public services. The smart government encourages a national archival system to facilitate archive producers and users. The four electronic-based government system (SPBE) factors in the archival sector and open archival information system (OAIS) as a data preservation standard are the benchmarks in developing this study's national archival platform system. An improved service computing system engineering (SCSE) framework adapted to the microservice architecture is used to aid the design of the national archival platform system. The proposed design met the four-factor service design validation of coupling, cohesion, complexity, and reusability. Also, the prototype suggests what resources are needed to put the design into action by passing the performance test of availability measurement
A preliminary empirical study of react library related questions shared on stack overflow
Full text linkReact is a JavaScript library to develop user interfaces for single-page applications. Developers utilize react to build large web apps that allow users to update data without refreshing the page. Despite its benefits, many developers face react-related issues in the implementation. To find a solution, developers commonly shared and discussed their issues on stack overflow (SO). Although recent studies have demonstrated the benefits of utilizing react in web development, the trends of the users’ attentions remain unknown. In this study, we conducted a preliminary empirical study of react library-related questions shared on SO. We applied an exploratory data analysis technique to investigate the distribution of problems shared by the developers. The findings reveal that although the quantity of react-related topics on SO has risen over time, community interest is beginning to decrease. This is shown by the increase of the unsolved questions and the decrease of the number of views per year. Regarding the react users’ activity, most of them are more active in providing answers rather than commenting and providing scores. The findings of this study might point to future research that recommends approaches to assist the react community in overcoming issues while using react in the early phases