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 926 Documents
Komparasi Deteksi Single Shot Detector (SSD) Dengan YouLook (Yolov8) Menggunakan GhostFaceNet Untuk Pengenalan Wajah Pada Dataset Terbatas Salsabila, Pramesya Mutia; Luthfiarta, Ardytha; Nugraha, Adhitya; Muttaqin, Almas Najiib Imam; Zarifa, Yasmine
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6225

Abstract

Face recognition has become a crucial topic in image processing and computer vision, particularly in university environments. This study explores the use of GhostFaceNet and YOLOv8 models to address the challenges of face recognition with a limited dataset, consisting of only one formal photo per individual. By applying image augmentation techniques, we improved the system's accuracy to 85%. GhostFaceNet excels in generating precise and detailed face embeddings, which are essential for accurate recognition. Meanwhile, YOLOv8 demonstrates superior speed in detecting faces under various lighting conditions and angles. Comparative results reveal that YOLOv8 achieves an accuracy of 81%, outperforming SSD, which only reaches 76%. Despite challenges related to the low quality of original images, the findings highlight the significant potential of deep learning-based face recognition systems. This research aims to compare SSD and YOLOv8 detection models using GhostFaceNet and contribute to the development of more effective and reliable face recognition methods in academic settings.
Penerapan Teknologi IoT dan Ragam Sensor Dalam Sistem Monitoring Gelombang Laut sebagai Peringatan Dini Hadad, Sitna Hajar; Safi, Mudar; Turuy, Seh; Rumaf, Nurdin; Ismail, Risandi J
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6234

Abstract

North Maluku has an archipelago so that community activities are mostly related to the sea, such as fishermen and people who use sea routes as a mode of transportation. Uncertain weather conditions resulting in heavy rainfall and high sea waves can threaten the safety of the community, especially the fishing community and people who use sea transportation modes. As happened some time ago, namely the sinking of KM Cahaya Arafa. KM Cahaya Arafa sank because it was hit by high sea waves so that it had an accident, namely drowning in the waters of Tokaka Village, South Halmahera Regency, North Maluku Province which resulted in the death of dozens of people. The purpose of this research is to apply IoT Technology and Various Sensors to design a Sea Wave Monitoring System as an Early Warning on Marine Transportation Modes which if bad weather occurs can threaten safety when doing activities at sea. The monitoring system prototype was developed to provide early information on the high danger of sea waves both through sound, sirens, and widely accessed using mobile phones and the internet. The test results of the IoT-based sea wave notification system show that this technology is effective in detecting certain wave heights, ranging from half a meter to two meters, and providing early warning quickly and accurately. The sensors integrated in the system are capable of measuring changes in wave height with high precision, and IoT technology enables stable data transmission to various communication platforms, including mobile apps and instant messaging systems. With the ability to detect various wave heights, this system can be a reliable and efficient disaster mitigation tool, and can be further developed to support better preparedness for coastal communities against the potential threat of high waves and tsunamis.
Analisis Sentimen dan Pemodelan Topik pada Ulasan Pengguna Aplikasi myIM3 Menggunakan Support Vector Machine dan Latent Dirichlet Allocation Prastyo, Priyo Agung; Berlilana, Berlilana; Tahyudin, Imam
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6268

Abstract

In the current digital era, mobile applications play a crucial role in enhancing user experience. This study analyzes user sentiment towards the myIM3 application and identifies key topics discussed in user reviews using Support Vector Machine (SVM) and Latent Dirichlet Allocation (LDA). The dataset comprises 1,000 user reviews from the Google Play Store, including review text, star ratings, review dates, and application versions. Data preprocessing involved cleaning, normalization, stop word removal, and lemmatization. Text data was transformed using Term Frequency-Inverse Document Frequency (TF-IDF). The dataset was split into training and testing sets (80:20 ratio). The SVM model, optimized with a linear kernel, achieved an accuracy of 84.65%, with a precision of 85% for negative sentiment, 84% for positive sentiment, and challenges in classifying neutral sentiment. Cross-validation ensured model robustness. LDA identified five primary topics: general user experience, application usability and purchase experience, positive feedback and functionality, general application evaluation, and network issues and pricing concerns. Techniques like oversampling, undersampling, and hybrid methods addressed imbalanced datasets to enhance model performance. The results revealed that 43% of reviews were positive, 42% were negative, and 15% were neutral. The key topics indicated that network issues and pricing were significant user concerns. These findings provide valuable insights for developers and stakeholders to improve user experience and refine application features based on user feedback.
Robusta Coffee Plant Disease Identification using Dempster Shafer Method in Expert Systems Sidauruk, Acihmah; Miftakhurrokhmat, Miftakhurrokhmat; Pujianto, Ade; Salmuasih, Salmuasih
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6272

Abstract

Robusta coffee is one type of coffee that can grow well in Indonesia. Robusta coffee has 2.2% more caffeine and less sugar than Arabica coffee. This coffee may be a more interesting coffee variety from different levels of taste and thickness. In addition, Robusta coffee is very accommodating to the economy of several coffee-producing countries around the world, including Indonesia. A number of factors, especially pests and diseases, can reduce the productivity and quality of coffee plants. This is also confirmed by coffee experts who conducted research on pests and diseases in Robusta coffee plants. This study aims to develop an expert-based system that can identify problems and diseases in Robusta coffee plants using the Dempster Shafer method, and developed in a web-based platform. From the data collected from literature studies, dialogue with farmers, and consultation with an expert, 13 types of pests and diseases were obtained, and 27 symptoms of the disease. The results of this study are the development of a web-based expert system that can diagnose pests or diseases from several symptom inputs filled in by users or coffee farmers. The results of the trial of 13 test cases on the diagnosis of pests and diseases of Robusta coffee plants obtained an average accuracy value of 94%. This shows that this expert system can analyze the types of pests or diseases in Robusta coffee plants very well using the Dempster Shafer method.
Citra Sitentik Untuk Klasifikasi Buah Menggunakan Algoritma SIFT Descriptor, Bag of Features dan Support Vector Machine Lukman, Achmad; Seniwati, Erni; Riswanto, Eko
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6296

Abstract

Recognizing specific objects assigned to a computer using artificial intelligence of course goes through a training and testing process using machine learning methods, the limited number of datasets makes it difficult for deep learning methods to carry out classification, so to overcome this, other methods are needed, including Scale Invariant Features Transform ( SIFT) which is a method of image processing to extract features from a limited amount of data and combined with a method in machine learning. To overcome the inability of deep learning to use limited datasets, this research uses a combination of SIFT and bag of features to extract features and support vector machine (SVM) to carry out classification. In this study, the aim is to observe the effect of synthetic images on the performance of the combination of SIFT descriptor, Bag of Features and Support Vector Machine algorithms in classifying real fruit images. The dataset involved is a synthetic image in the form of a 3D image that is made into a complete object, then taking random views to make an image that represents the object as training data. Furthermore, for testing data, real images taken from the dataset link in previous research will be used. The number of synthetic datasets that can be collected for each fruit is 150 images, so that the total is 450 images, while the real fruit images consist of 148 apple images, 152 banana images, and 166 orange images, so that the total real images are 466 images. The results of this research show that the highest accuracy was 65.45% with an F1-score reaching 58.45%.
Analisis Sentimen Traveloka Berdasarkan Ulasan Google Play Store Menggunakan Algoritma Support Vector Machine dan Random Forest Rohimah, Siti; Afdal, M; Mustakim, Mustakim; Novita, Rice
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6300

Abstract

The internet has become a key element in supporting technological and information advances in various sectors of human activity. In the trade and tourism sector, the Traveloka application is the favorite choice of Indonesian people. Reviews or reviews from users play an important role for the Company to understand the level of customer satisfaction. However, currently there are several users who give high ratings but contain negative reviews. Based on these problems, this research aims to understand more deeply user opinions, so that they can be used to improve services and features as well as test and compare the accuracy of the two algorithms in classifying user sentiment. In this research, the Support Vector Machine and Random Forest classification methods were used. The research results show that Random Forest has superior and stable performance compared to SVM, with higher average accuracy for most features, such as Traveloka (71% & 67%) and Airplanes (75% & 74%). Evaluation with k-fold cross validation supports these results, with higher average Random Forest accuracy on features such as Traveloka (70% & 66%) and Airplanes (75% & 74%).
A Hybrid CNN-LSTM Model with SMOTE for Enhanced Sentiment Analysis of Hotel Reviews Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6301

Abstract

The growing reliance on online reviews as a critical decision-making tool in the hospitality industry underscores the need for robust sentiment analysis methodologies. Understanding customer feedback is essential for hotels to enhance service quality and maintain a competitive edge in an increasingly digital marketplace. However, traditional sentiment analysis models often encounter difficulties processing unstructured textual data, particularly when faced with class imbalances where positive reviews dominate, overshadowing critical negative feedback. To address these challenges, this study investigates integrating a hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) model with the Synthetic Minority Over-sampling Technique (SMOTE) to improve sentiment classification accuracy. Utilizing a dataset of 665 reviews from THE 1O1 Bandung Dago Hotel, the model leverages CNN’s capability to capture local features and LSTM’s strength in handling sequential dependencies, resulting in a more nuanced analysis of customer sentiments. The application of SMOTE effectively balances the dataset, addressing the class imbalance issue, which often skews sentiment classification. This approach improves predictive accuracy and provides actionable insights to enhance customer satisfaction strategies. The study achieved an overall classification accuracy of 77%, with precision at 78%, recall at 77%, an F1 score of 77.5%, and an AUC score of 0.81, reflecting discriminatory solid capability. Future research could focus on model optimization, multilingual sentiment analysis, aspect-based sentiment insights, and real-time sentiment monitoring to further refine customer feedback analysis and support strategic decision-making in the hospitality sector.
Evaluasi Destinasi Wisata Terbaik di Indonesia Dengan Kombinasi Metode ARAS dan AHP Firmansyah, Ariq; Susanto, Bagus Hadi; Pinem, Agusta Praba Ristadi
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6304

Abstract

The management of tourist destinations in Indonesia strives to enhance the quality and comfort for tourists by considering safety aspects. To evaluate the best tourist destinations based on safety and comfort criteria, this study applied a decision support system using the Analytical Hierarchy Process (AHP) to calculate the weights of each safety criterion, including visitor insurance, safety and security procedures, standard operating procedures, tourism business certification, the number of destinations, and operational permits. The Additive Ratio Assessment (ARAS) method was then used to rank tourist destinations based on the calculated weights. The results of the AHP method provided accurate priority weights, while the ARAS ranking positioned Central Java (A3) as the highest-ranked destination with a score of 0.956, followed by Jakarta (A1) with a score of 0.897, and Yogyakarta (A4) with a score of 0.840. A Spearman correlation test between the AHP-ARAS ranking and visitor numbers resulted in a coefficient of 0.857 with a p-value of 0.014, indicating a very strong and statistically significant positive relationship. This study provides valid recommendations for tourists and decision-makers in selecting tourist destinations that align with prioritized safety criteria, while also supporting the development of data-driven and objective tourism management policies.
Implementasi Metode Holt-Winters dan FP-Growth dalam Melakukan Peramalan Stok Barang Pada Swalayan Berdasarkan Pola Asosiasi Loka, Septi Kenia Pita; Afdal, M; Novita, Rice; Mustakim, Mustakim
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6305

Abstract

At present, competition in the business world is extremely fierce, particularly in the convenience store sector. The development of retail trade is progressing rapidly, accompanied by the emergence of many small markets and online shops. This situation encourages store owners to make wiser decisions, such as managing stock replenishment. If overlooked, this matter way hinder employees from locating the necessary items, thereby increasing the potential risk of goods expiring or being damage before they are sold. Therefore, store owners need to understand consumer behavior and shopping habits to assist iin stock management. Based on this issue, the research aims to analyze consumer purchasing patterns and optimize inventory stock. The result of this experiment identified two best rules, namely biscuit and consumption/food, with a confidence of 53,61%, a support of 15,57%, and a lift ratio of 1,116 the error measurement MAPE shows a value of 6,79 using alpha, beta and gamma values of 0,1. The total predicted stock in 52,086 with an actual value of 72,275, which is close to actual value of data prior to the significant observed in the last three months.
Komparasi Metode BERT, VADER, dan RoBERTa untuk Analisis Sentimen Masyarakat terhadap Keputusan Pasangan Nurdewanti, Debi Safa; Prathivi, Rastri
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6306

Abstract

This research discusses the phenomenon of childfree in Indonesia, which is increasingly being discussed in line with social and economic changes. Although a negative stigma is still attached to a couple's decision not to have children, public awareness of the childfree option continues to increase. This study aims to analyze public sentiment towards childfree decisions using three sentiment analysis methods, namely BERT, RoBERTa, and VADER. The analysis results show that the BERT method has the highest accuracy of 99%, signaling its ability to classify sentiment very accurately. In contrast, the RoBERTa and VADER methods show lower accuracy, at 50% and 41% respectively. Both methods had difficulty in distinguishing the sentiment classes, which resulted in many misclassifications. Evaluation using the confusion matrix shows that RoBERTa and VADER have a significant number of misclassifications, with RoBERTa having 9 FPs and 19 FNs, and VADER having 16 FPs and 84 FNs. Meanwhile, BERT has almost no errors in classification, with a total FP of 0 and FN of 1. These results confirm that the BERT method is superior for sentiment analysis of the childfree phenomenon compared to the RoBERTa and VADER methods. This research provides insight into how people view the childfree phenomenon and finds the best sentiment analysis method among the three methods.