cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
-
Journal Mail Official
jurnal.bits@gmail.com
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
Building of Informatics, Technology and Science
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. This journal is managed by Forum Kerjasama Pendidikan Tinggi (FKPT) published 2 times a year in Juni and Desember. The existence of this journal is expected to develop research and make a real contribution in improving research resources in the field of information technology and computers.
Arjuna Subject : -
Articles 889 Documents
Optimizing Quantum Neural Networks for Predicting the Effectiveness of Drug Compounds as Corrosion Inhibitors Mawaddah, Lubna; Rosyid, Muhammad Reesa; Santosa, Akbar Priyo; Akrom, Muhamad
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5318

Abstract

Corrosion, caused by electrochemical reactions in corrosive environments, can degrade the quality and lifespan of materials, potentially leading to significant losses in various industrial sectors. One common strategy to reduce corrosion rates is by using corrosion inhibitors. A significant challenge in this field is the time-consuming and costly process of testing new corrosion inhibitors in the laboratory. Consequently, there is a need for more efficient and cost-effective methods to predict the effectiveness of potential corrosion inhibitors using machine learning techniques. This research addresses this problem by applying a quantum machine learning (QML) approach with quantum neural network (QNN) algorithms to evaluate the effectiveness of drug compounds as corrosion inhibitors. The study aims to optimize QNN models by investigating three different quantum circuit configurations to identify the most effective design. The results showed that Model-01, consisting of three layers, demonstrated the best performance with an MSE of 38.81, an RMSE of 6.23, and an MAE of 6.19, along with the shortest training time of 32 seconds, indicating an optimal balance between complexity and generalizability. Overall, this QML approach provides new insights into the predictive ability of QNN models in assessing the effectiveness of drug compounds as corrosion inhibitors, demonstrating the potential of quantum computing to enhance predictive accuracy and efficiency in investigating anti-corrosion materials
Implementasi Algoritma Convolutional Neural Network (CNN) Untuk Klasifikasi Kecacatan Pada Proses Welding di Perusahaan Manufacturing Saefulloh, Nandang; Indra, Jamaludin; Rahmat, Rahmat; Juwita, Ayu Ratna
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5321

Abstract

Manufacturing industry has become one of the largest sectors in Indonesia, driven by increasing demand from the public. A primary concern to meet both local and international market needs is product quality. In ensuring high-quality standards, production processes require strict quality control. One common issue in quality control is defects occurring during the welding process, which significantly affects inspection cycle times. To address this, the Convolutional Neural Network (CNN) approach with VGG-16 architecture can help classify defects in the welding process. This method not only expedites the defect classification process but also enhances the accuracy of identifying product defects. The stages of implementing this method include dataset preparation, data preprocessing, CNN model design, model training, and performance evaluation. Evaluation results demonstrate that the use of automatic defect detection technology, especially with balanced data scenarios, can significantly improve quality control performance. Accuracy, precision, recall, and F1-score achieve excellent levels, reaching 92%. Thus, this research provides a significant contribution to enhancing production efficiency and improving product quality in the motorcycle manufacturing industry in Indonesia. It is hoped that the use of this technology will assist manufacturing companies in identifying and addressing production defects more effectively, thereby enhancing the overall competitiveness of Indonesia's manufacturing industry.
Implementasi Algoritma Convolutional Neural Networks Untuk Klasifikasi Jenis Cat Tembok Menggunakan Arsitektur MobileNet Carlos, Daniel; Herwindiati, Dyah Erny; Lubis, Chairisni
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5322

Abstract

The development of image recognition technology has made significant advancements, particularly with the emergence of Convolutional Neural Networks (CNN) algorithms. One of the CNN architectures that is efficient and effective for mobile devices is MobileNet. This study aims to implement the CNN algorithm using the MobileNet architecture for classifying types of wall paint. The main problem addressed is the accurate identification of wall paint types based on images, requiring a model that performs well even on devices with limited resources. MobileNet was chosen as the solution due to its ability to reduce computational complexity without sacrificing performance. The methodology used in this research involves two approaches: classification with feature extraction using GLCM and histogram, and classification without feature extraction directly using MobileNet. The training and testing process was conducted using the early stopping technique to prevent overfitting, with the model trained for 50 epochs. The final results show that classification without feature extraction using MobileNet yields excellent results. The model achieved a training accuracy of 89.68% and a testing accuracy of 88.86%, with low loss values (0.0111 for training and 0.0117 for testing). These results indicate that MobileNet is effective in recognizing and classifying types of wall paint and can operate efficiently on devices with limited resources. Therefore, this research demonstrates that using the MobileNet architecture for classifying wall paint types is an effective and efficient solution, opening opportunities for similar applications on various mobile devices in the future.
Prototype Pengukuran Kadar Alkohol dan Co Pada Ruangan Laboratorium Pendidikan Kimia Berbasis IoT Al Aziz, Vindy Rova Dwiki; Zarory, Hilman; Son Maria, Putut; Faizal, Ahmad
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5328

Abstract

Technological advancements, particularly the Internet of Things (IoT), have significantly impacted various sectors, including chemical laboratories. This research aims to design a device for detecting Alcohol and Carbon Monoxide (CO) levels in the Chemistry Education Laboratory at UIN SUSKA RIAU. The device uses MQ-3 and MQ-135 sensors connected to an ESP32 microcontroller, featuring voice notifications and integration with the Blynk application for real-time monitoring. The design includes key components such as a power supply, buzzer, speaker, DFPlayer Mini, LED, and 16x2 LCD. Hardware and software testing were conducted to ensure the device's reliability and durability. The test results showed variations in CO and Alcohol levels in the laboratory over five days. The MQ-135 sensor indicated a significant increase in CO levels on Tuesday with an average of 55.4 PPM, while the MQ-3 sensor recorded the highest Alcohol levels on Friday with an average of 2%. These variations were due to intensive practicum activities and suboptimal air circulation. The implementation of this device successfully detected and transmitted air quality data accurately and quickly through the Blynk application. The research results emphasize the importance of monitoring and controlling air quality in laboratories to ensure a safe and healthy environment for users. The use of sensors integrated with IoT has proven effective in enhancing monitoring quality and providing real-time data that can be accessed remotely, contributing positively to supporting safer learning activities in chemical laboratories
Analisis Tingkat Ketertarikan Mahasiswa Terhadap Bidang Artifcial Intelligence dalam Penulisan Skripsi dengan Random Forest Anshor, Abdul Halim; Wiyatno, Tri Ngudi
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5332

Abstract

Artificial Intelligence (AI) is an advanced phenomenon of information technology that is currently very fast. With AI human work can be replaced by computers. Universities are superior providers in providing experts in the field of AI. One indicator that can describe how the curriculum in the field of AI is implemented on campus is by assessing how interested students are in taking the field of AI for writing their thesis. In this research, researchers used the Random Forest machine learning method with questionnaire sampling data from 200 students interested and not interested in the field of AI. The results of this research will provide accuracy values for classifying students' interest in the field of AI. Questionnaire data will be classified into two classes, namely interested and not interested classes. Results from classification trials with the WEKA application. It is known that the classification results have an accuracy value of 80.5%, this shows that the random forest algorithm has worked effectively in the process of classifying Pelita Bangsa University student interest data in the field of AI in writing theses
Klasifikasi Sentimen Terhadap Pengangkatan Kaesang Sebagai Ketua Umum Partai PSI Menggunakan Metode Support Vector Machine .Safrizal, Safrizal; Agustian, Surya; Nazir, Alwis; Yusra, Yusra
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5340

Abstract

The appointment of Kaesang Pangarep as the Chairman of the Indonesian Solidarity Party (PSI) has sparked various responses on social media, particularly on Twitter. This research aims to classify public sentiment regarding the appointment using the Support Vector Machine (SVM) algorithm with FastText feature representation. The data used for classification involves a small training dataset. The text preprocessing process includes cleaning, case folding, tokenizing, normalization, stopword removal, and stemming. FastText word embedding is used to convert words into vectors, and an SVM model with Grid Search is used for parameter tuning to obtain the optimal model. The use of external datasets to expand the initially limited training dataset enhances data representation and improves the model's performance in sentiment classification. The Covid dataset was expanded by adding 100, 200, and 300 tweets for each negative, positive, and neutral label. From the experiments conducted, the best accuracy on the test data was found in experiment ID C2 with an F1-Score of 53.59% and an accuracy of 62.73%. In experiment ID C3 with the same dataset, the F1-Score was 50.46% and the accuracy was 60.46%. Finally, in experiment ID C7 with the same dataset, the F1-Score was 47.19% and the accuracy was 53.09%.
Combination of CRITIC Weighting Method and Multi-Attribute Utility Theory in Network Vendor Selection Dwi Satria, M. Najib; Setiawansyah, Setiawansyah; Mesran, Mesran
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5342

Abstract

The main problems in the selection of network vendors include uncertainty regarding the credibility and reliability of the vendor, which can result in the risk of product or service failure. Choosing a network vendor requires a thorough evaluation of the vendor's credibility and track record to ensure their reliability and experience in the industry. In addition, the technology compatibility and flexibility of the product need to be checked to ensure seamless integration with existing infrastructure and the ability to adapt to evolving needs. The combination of the CRITIC weighting and MAUT methods can result in a robust and holistic approach in the decision support system. CRITIC is used to determine the relative weight of each criterion based on the correlation analysis between the criteria, thus helping to reduce subjectivity and improve the objectivity of the assessment. Once the criterion weights are set using CRITIC, MAUT can be used to calculate the utility score of each alternative based on the weights of that criterion. MAUT allows the integration of decision-maker subjective preferences into the analysis, thus allowing for a more thorough and accurate evaluation of the alternatives being evaluated. The results of the network vendor ranking show that Nusanet gets the first rank with a final score of 0.6214, Zitline gets the second rank with a final score of 0.5317, MMS gets the third rank with a final score of 0.5276, TMS gets the fourth rank with a final score of 0.4147, and JPDN gets the fifth rank with a final score of 0.3677. This combination of the CRITIC and MAUT methods provides a comprehensive approach to network vendor selection, ensuring that decisions are based on structured, transparent, and measurable analysis, resulting in the most optimal vendor selection for the organization's needs.
Analisis Sentimen Terkait Konflik Palestina-Israel Pada Media Sosial X Menggunakan Algoritma Naïve Bayes Classifier Simamora, Silvia Damayanti; Irwiensyah, Faldy; Hasan, Firman Noor
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5344

Abstract

The conflict between Palestine and Israel has been ongoing for approximately 76 years, during which the Zionist movement has attempted to establish a Jewish homeland in Palestinian territory. In October 2023, news about this conflict resurfaced and has continued up until June 2024. This issue has drawn global attention, including from the Indonesian public. On the social media platform X, numerous comments and posts both negative and positive regarding the Palestine-Israel conflict have appeared as a result of the ongoing challenges faced by Palestine. This study aims to analyze the sentiment expressed on the social media platform X regarding the Palestine-Israel conflict. The data collected focuses solely on comments and posts from Indonesia, totaling 1,715 entries. The study employs the Naïve Bayes Classifier algorithm, with an 80% to 20% ratio of training data to test data, following a pre-processing phase. The results of this study indicate an accuracy of 94%, precision of 91%, recall of 100%, and an F1-Score of 95%. The analysis reveals a positive sentiment, suggesting that the Indonesian public's response on the social media platform X predominantly shows positive support towards Palestine
Implementasi Model Convolutional Neural Network (CNN) pada Aplikasi Deteksi Kanker Kulit Menggunakan Expo React Native Yonismara, Arvie Arvearie; Salam, Abu
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5351

Abstract

Skin is the outermost organ of the human body, serving to protect the internal parts from threats such as sunlight exposure. Excessive exposure to sunlight can potentially cause skin cancer. Over the past decade, the number of skin cancer cases in Indonesia has increased. The most common method for detecting skin cancer is biopsy, which is quite expensive and time-consuming. Considering this issue, a skin cancer detection application using Deep Learning technology is needed to identify skin cancer at an early stage. Therefore, this research aims to develop a skin cancer detection application using Expo React Native and implement a CNN deep learning model to classify seven classes of skin lesions based on the HAM10000 dataset. The performance evaluation of the CNN model used shows a high performance score, with an average overall score of 0.98. Given this performance, the model is feasible and ready to be implemented in a mobile application. This study demonstrates that the skin cancer detection application using Expo React Native is capable of implementing the deep learning model and can be used to detect skin cancer. Based on the results of the application testing using the black box testing method, perfect results were obtained with 100% success precentage. From the four parts of the application, namely select image, open camera, predict image, and delete image that were tested, all four parts demonstrated that the functionality and features of the skin cancer detection application work well
The Decision Support System for Cashier Recruitment Implements the Multi-Attribute Utility Theory Method Lubis, Juanda Hakim; Mesran, Mesran; Siregar, Cindy Astika
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5352

Abstract

CV.Sumber Segar Lestari is a five-star supermarket that serves the best products on the market, namely imported products. High quality human resources are very necessary to improve a company. In searching for quality human resources according to the company's needs, CV.Sumber Segar Lestari is still carried out manually, namely the cashier reception process at CV.Sumber Segar Lestari (Brastagi Supermarket) uses a cashier reception system based on the Company's Operational Standards guidelines. Starting from the cashier acceptance process by selecting each incoming job application. Then the process of evaluating prospective cashier employees is carried out, including: examining applications and required documents, conducting written tests, interviews, and deciding whether to accept or reject the prospective cashier employee. This method of assessment takes a long time and is prone to errors. Especially if many applicants submit applications. In addition, the assessment process and results can only be seen by personnel, it is very possible to manipulate test results. To solve this problem, this research uses the Multi Attribute Utility Theory method. The Multi Attribute Utility Theory method is a quantitative comparison method that usually combines measurements of different risk costs and benefits. The Multi Attribute Utility Theory method is used to provide an assessment and consideration of the best alternative from various existing options. Processing values using the death method will produce rankings. The final result obtained was alternative A3 which had the highest final score of 0.595 in the name of Mulia Dinda Ramadani