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
Deteksi Objek Boneka Korban pada Kontes Robot SAR Indonesia Menggunakan ESP32-cam Taupiq, Arahmad; Pratama, Yovi; Bustami, M Irwan
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.v6i3.5979

Abstract

The 2024 Indonesian SAR Robot Contest demands the ability of robots to differentiate between dummy dolls and victim dolls in emergency situations. This SAR robot has the main goal of rescuing victims and bringing them to a safe zone, so the author explores the implementation of object detection on SAR robots using ESP32-cam to detect victim dolls. The authors used the Edge Impulse platform, a TinyML platform, to train an object detection model using the Faster Objects, More Objects (FOMO) architecture. This model is optimized to run efficiently on resource-limited devices such as the ESP32-cam microcontroller. Training data was obtained by taking pictures of dummy dolls and victim dolls in various angles, lighting conditions and backgrounds using a camera from the ESP32-cam. The confusion matrix results from the model training process showed that the F1 score reached 100% and when testing the model, the object detection model was able to detect the victim doll with adequate accuracy, even though there were challenges such as variations in position and environmental conditions so the researchers used additional algorithms to increase detection accuracy. . The use of FOMO allows faster object detection and is able to detect more objects in one frame. This implementation shows great potential in the development of more efficient and autonomous SAR robots for rescue missions. These findings contribute to improving robotic technology, one of which is in SAR operations and provide a basis for further research in the application of object detection.
Perbandingan Algoritma Klasifikasi Data Mining Dalam Diagnosa Penyakit Arteri Koroner Sudarsono, Bernadus Gunawan; Winarno, Edy
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.v6i3.5981

Abstract

Coronary artery disease is one of the diseases that often attacks humans. The cause of this disease is due to narrowing or blockage of the coronary blood vessels that supply blood to the heart. The diagnosis of coronary artery disease by medical personnel has so far been constrained by the limited number of doctors, in terms of the number of doctors and time, because the number of specialist doctors is limited. The limited number of doctors causes several difficulties for medical personnel who diagnose the patient's disease and over time can become a serious problem. Information technology that can help medical personnel is by applying data mining techniques which are techniques to help diagnose coronary artery disease. Data mining can identify patterns or relationships between disease symptoms and diagnostic results, so that patients with a high risk of developing the disease can be identified. The Naïve Bayes algorithm is one of the algorithms of the Data Mining classification technique, which is based on Bayes' theorem. The C4.5 algorithm is one of the algorithms of the Data Mining classification technique, which uses decision trees in classifying data. Algorithm comparisons are carried out in order to obtain the appropriate or best algorithm for use in diagnosing a disease. The comparison process of the Naïve Bayes algorithm and the C.45 algorithm in diagnosing coronary artery disease, obtained the best algorithm results based on the largest percentage value, namely the C4.5 algorithm, with a value of 46.9%.
Sistem Pengukuran pH, Suhu, dan Kelembaban Tanah Pada Tanaman Jagung Menggunakan Metode Proportional-Integral-Derivative Berbasis Internet of things Mira, Mira; Kusnanto, Kusnanto; Oscarito, Oscarito
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.v6i3.5993

Abstract

West Kalimantan Province experienced a decrease in the harvested area and productivity of corn with an area of 16,371.14 in 2022 with a productivity of 43.81 and a production of 71,717.14 tons. While in 2023 with an area of 15,625.22 with a productivity of 43.54 and a production of 68,028.76 tons. The decline in corn production and the increasing consumption needs every year are challenges for the government and corn farming businesses to answer and meet the availability of corn. Regarding this problem, it is necessary to manage corn plantation land, in order to increase the value of corn production to meet consumption and animal feed needs in West Kalimantan. Measuring pH, temperature and soil moisture is very important to understand the right soil conditions for various types of plants. This study uses a DS18B20 sensor to measure soil temperature, capaltive soil moisture to measure air content in the soil, and a pH sensor to determine the acidity level. The ESP32 microcontroller is used as the main controller connected to the third sensor with IoT technology and the PID method as a control system. The PID constant value was determined using the Ziegler-Nichols method, with a Kp value of 4.31, Ki 0.85, and Kd 4.33 with a setpoint of ph 6.0, a temperature of 26°C and a humidity of 70%. The results showed that the pH value was in the range of 3.03-3.45, falling into the acidic category. Furthermore, the temperature value was at 24.69-28.66, falling into the medium to high category. While the humidity value was between 43-80, falling into the low to high category. The test results showed that the system was able to measure temperature, humidity, and soil pH in real-time with a good level of accuracy. This is supported by the accuracy value of the soil pH sensor of 60.6%, the temperature sensor of 98.65%, and the soil moisture sensor of 98.57%. The accuracy value is obtained from 100% minus the average error value for each measurement.
Model Prediksi Kualitas Air Untuk Budidaya Ikan Lele Dengan Algoritma Extreme Gradient Boosting Maulana, Mokhammad Irvan; Nugraha, Fajar; Setiawan, Arif
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.v6i3.5998

Abstract

The growth of the aquaculture sector in Indonesia, particularly in catfish farming, has experienced significant increases. However, a major challenge faced is the need for accurate predictions of fish development to optimize production and minimize the risk of losses. This study aims to develop a growth prediction system for catfish based on machine learning using the XGBoost algorithm, which considers critical environmental factors such as water quality (temperature, pH, dissolved oxygen, ammonia, and nitrate). With this system, catfish farmers can monitor water quality in real-time, allowing them to take timely and optimal preventive actions regarding feed provision, thereby improving harvest yields and reducing operational costs. The XGBoost model demonstrates good performance with a Mean Absolute Error (MAE) of 0.073 for fish weight and 14.66 for fish length, a Mean Squared Error (MSE) of 0.123 for fish weight and 1.278 for fish length, and an R² value of 0.998 for both variables, indicating high accuracy in predicting fish growth. It is expected that this research will not only enhance productivity and efficiency in catfish farming but also support digital transformation in Indonesia's fisheries sector, providing a competitive advantage for farmers in facing increasingly complex industry challenges.
Kontrol Navigasi Robot Hexapod berbasis Inverse Kinematic dan Body Kinematic untuk Stabilitas Optimal di Medan Ekstrem Pratama, Yovi; Saputra, Chindra; Toscany, Afrizal Nehemia; Bustami, M Irwan; Taupiq, Arahmad
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.v6i3.6007

Abstract

This study discusses the application of Inverse Kinematics (IK), Body Kinematics (BK), and Bézier Curves in a hexapod robot to efficiently control leg movements in a three-dimensional space. IK is used to calculate joint angles based on the desired target position, while BK enables adjustments to the robot's body posture to maintain stability during movement. Simulations demonstrate that these two approaches can produce accurate and controlled movements. Additionally, Bézier Curves are applied to the foot trajectory, significantly enhancing the smoothness of movements and the robot's stability during transitions from one step to the next. Testing the hexapod robot over a distance of 2.10 meters showed a 70% success rate with an average error of 4.2 cm. Further testing of the robot's stability on an inclined X-axis revealed that the robot could adapt to inclines up to 35 degrees; however, at inclines exceeding 35 degrees, the robot was unable to maintain balance. Based on the results, it can be concluded that the combination of IK, BK, and Bézier Curves effectively supports the hexapod robot's movement with a step accuracy of 70% and high stability when adapting to inclines up to 35 degrees. Improving stability in more extreme terrains and enhancing performance in more diverse environments are the primary focuses for maximizing the hexapod robot's capabilities.
Application of Machine Learning for Dementia Classification through MRI Images using Vertex AI on Google Cloud Services Rinanda, Tiara Disti; Arief Suyoso, Aldo Lovely; Margono, Hendro
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.v6i3.6040

Abstract

Alzheimer's dementia remains a serious global health challenge, particularly in resource-limited countries where early and accurate diagnosis is crucial to reducing morbidity and mortality rates. Despite advances in medical imaging and diagnostic tools, early detection of Alzheimer’s remains a complex and resource-intensive task for healthcare systems worldwide. This study leverages the power of machine learning, specifically Convolutional Neural Networks (CNN), to develop a reliable model for detecting the severity of dementia using brain MRI images. The dataset used consists of four main categories: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented, with a total of 1,561 images obtained from Kaggle. The model was trained using Vertex AI on Google Cloud, which automatically optimized model parameters through AutoML and Hyperparameter Tuning. Techniques such as image segmentation and feature extraction were applied to enhance model accuracy. The results show that this CNN model achieved a precision rate of 93.5% for the Non-Demented category, with classification accuracy consistently between 92% and 93% for various other levels of dementia severity. These findings underscore the potential of machine learning, particularly CNN, in significantly improving dementia detection accuracy even in resource-constrained settings. By utilizing advanced techniques such as image segmentation, feature extraction, and CNN-based automated classification, this model offers a promising solution for real-time dementia diagnosis. The scalability and adaptability of the model built using Vertex AI allow for broader applications in global clinical scenarios, supporting public health efforts to reduce the burden of Alzheimer's disease. While challenges regarding data sensitivity and computational resources are acknowledged, the model’s potential to improve early diagnosis and patient outcomes is highly significant.
Penerapan Metode Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) Dalam Penentuan Media Promosi Terbaik Rajiansyah, Rajiansyah; Rizawanti, Riftika
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.v6i3.6079

Abstract

The development of increasingly sophisticated technology provides a function which assists salespeople in promoting a product using technology. With the existence of technology, a seller can use this technology as a media tool for the promotion of the products they are marketing or selling. Promotional media is a way that is used by entrepreneurs in conveying, spreading, and offering the products or services they sell so that consumers are interested in buying. In helping carry out promotional media, it is necessary to have social media, where social media is useful or one of the tools used to promote goods or services to consumers. However, as an entrepreneur the selection of a promotional media tool can be a consideration for an entrepreneur. And in solving a problem researchers really need criteria including Location, Fisheries, Cost and Target Market. So with that researchers really need tools in making decisions using methods that can produce values ​​that are in accordance with the expectations of the authors. The tool is SPK and the method used is TOPSIS. So from this it can be concluded that the best promotional media falls on alternative A3 on behalf of Facebook with the first rank with the highest score of 0.953
Perbandingan Performa Algoritma NBC, C4.5, dan KNN dalam Analisis Sentimen Masyarakat terhadap Krisis Petani Muda pada Media Sosial Facebook Nurkholis, Nurkholis; Permana, Inggih; Salisah, Febi Nur; Mustakim, Mustakim; Afdal, M
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.v6i3.6082

Abstract

In Indonesia, young farmers face various challenges and crises that hinder the growth and sustainability of the agricultural sector. They face obstacles such as lack of access to capital, limited technology, climate change, and low selling prices for their crops. In addition, they also often face problems in obtaining accurate and relevant information in an effort to facilitate better decision-making in agricultural businesses, so that the interest of young people today to become farmers is decreasing. The study aims to Compare the Performance of NBC, C4.5, and KNN Algorithms in the Analysis of Public Sentiment towards the Young Farmer Crisis on Facebook Social Media. The application of the K-Fold Cross Validation method is (K = 10). Sentiment analysis is carried out with 3 labels (positive, negative, and neutral). The data used in making the classification model (data from preprocessing the stemming column) using (Google Colab) amounted to 4,878 data with Positive sentiment of 43.13% (2,104), Neutral 39.59% (1,931), Negative 17.28% (843) from the initial data without nested comments, which is 4,981 and the total number of Facebook data is 2,900 likes, 6,700 comments, and 3.3 million viewers. The accuracy of the NBC algorithm is 57.32%, the C4.5 algorithm is 98.42%, and the KNN algorithm (K = 19) is 97.33%. It can be concluded that the results of the comparison of the performance of the three algorithms using (Rapidminer10.3), the C4.5 algorithm gets a higher accuracy of 98.42% and is superior because it produces a decision tree.
Perbandingan Algoritma Support Vector Machine dan Naïve Bayes dalam Menganalisis Sentimen Pinjaman Online di Twitter Ikhsani, Yulia; Permana, Inggih; Salisah, Pebi Nur; Mustakim, Mustakim; Rozanda, Nesdi Evrilyan
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.v6i3.6106

Abstract

Unemployment is one of the poverty factors in society, the large economic needs make it difficult for people to meet their daily needs, thus triggering high demand for loans in society. With the advancement of technology, online loans are now available to help people meet their economic needs. However, over time, many irresponsible parties have taken advantage of this. Marked by the emergence of many illegal online loans, which have triggered negative impacts such as the spread of customer personal data, terror on social media, to debt collection using debt collectors. So that it raises a lot of sentiment in society regarding online loans. For this reason, it is necessary to conduct a sentiment analysis with the aim of public response to online loans, which can be positive, negative or neutral responses. There are two datasets used, namely legal online loans and illegal online loans. This study uses two algorithms, namely SVM and Naive Bayes, the two algorithms will be compared to find out which algorithm is better at analyzing online loan sentiment. In addition, in its use, the two algorithms will also use the SMOTE technique to stabilize the data. The results obtained on legal loan data classification using SVM are quite better than Naive Bayes, with an accuracy rate of 69% with sentiment that often appears is positive sentiment. For illegal loan data, classification using the Naive Bayes algorithm is better than SVM with an accuracy of 75% and sentiment that often appears is neutral sentiment. Based on these results, it can be concluded that in analyzing sentiment using legal loan data, the best algorithm is the SVM algorithm, and for illegal loan data, the best algorithm is the Naive Bayes algorithm.
Implementation of Tesseract OCR and Bounding Box for Text Extraction on Food Nutrition Labels Saputra, The Manuel Eric; Susanto, Ajib; Carmelita, Bastiaans Jessica
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.v6i3.6107

Abstract

This study focuses on implementing Optical Character Recognition (OCR) using the Tesseract engine, integrated with bounding box detection, to extract nutritional information from food nutrition labels. The research addresses the challenge of limited consumer access to and understanding of nutritional data, a factor contributing to health issues such as obesity and related metabolic disorders. Studies indicate that although Indonesian consumers generally have a good level of knowledge and positive attitudes toward nutritional labels, the actual behavior of reading and understanding these labels remains limited. Additionally, packaged foods consumed outside the home constitute a significant portion of daily caloric intake, which can lead to health complications if not properly managed. With obesity levels among adults in Indonesia rising to concerning rates, this study highlights the importance of providing accessible nutritional data. In this work, MobileNetV1 is used as the backbone model for bounding box detection, effectively identifying and isolating label regions to enhance OCR accuracy. Tesseract OCR, known for its LSTM-based architecture, is applied to predict sequential data patterns, such as rows of text on nutrition labels. Preprocessing techniques, including grayscale conversion, brightness adjustment, CLAHE (Contrast Limited Adaptive Histogram Equalization), and denoising, are used to improve text clarity and further refine OCR output accuracy. Post-processing steps involve rule-based and contextual error correction to handle common OCR inaccuracies. Evaluated on 10 different label images, the system achieved a maximum Word Error Rate (WER) of 10% and a Character Error Rate (CER) of 1.6%, demonstrating high accuracy in nutritional information extraction.