INTI Nusa Mandiri

DETEKSI RUPIAH EMISI 2022 UNTUK DISABILITAS NETRA MENGGUNAKAN YOLOV5M DENGAN OUTPUT SUARA

2024-08-01T09:03:05+00:00

People with visual disabilities have difficulty recognizing rupiah denominations using blind codes due to differences in paper size for each denomination, wrinkled paper, and variations in blind codes for different emission years.. The proposed method uses the YOLOv5m algorithm as well as Google Text to Speech (GTTS) as voice output. The aim of the research is to find a model with the best precision value from YOLOv5m in detecting the 2022 emission rupiah and integrate it into GTTS to produce nominal rupiah sounds. The model was trained with the main image dataset, namely 700 images of rupiah emissions in 2022 taken at an angle of 120⁰. Next, the model was tested to recognize seven nominal amounts, namely IDR 1,000, IDR 2,000, IDR 5,000, IDR 10,000, IDR 20,000, IDR 50,000, and IDR 100,000. The test results show that the best YOLOv5m model is the one that has been trained using the main dataset (700 images) and supplemented with a multi-class image dataset (250 images) and background images (30 images). This model has a precision value of 82% when testing in real time. This research succeeded in applying the YOLOv5 algorithm which is integrated with Google Text to Speech to detect the image of 2022 emission rupiah banknotes.

K-BEST SELECTION UNTUK MENINGKATKAN KINERJA ARTIFICIAL NEURAL NETWORK DALAM MEMPREDIKSI RANGE HARGA PONSEL

2024-08-01T09:03:07+00:00

Determining the price of a mobile phone that will be released to the market cannot be based on assumptions alone. This problem can be overcome by utilizing machine learning. In this study, what is predicted is not the exact price, but rather the price range of a cellphone based on the specifications that are its attributes. In machine learning, the Deep Learning ANN model will be used to predict the price range of a mobile phone. To understand the relationship between features and labels, the Univariate feature selection method SelectKBest is used which will calculate the correlation value between features and labels. In this study, the best performance was obtained from the ANN model with feature selection and hyperparameter tuning, the evaluation of performance metrics obtained the highest accuracy of 97.5%. Experiments were conducted by building several models to compare until there was one model that performed well in processing training and validation data. Model evaluation is presented using confusion metrics with various types of performance metrics: accuracy, precision, recall and f1-score. This study also aims to evaluate the effectiveness of the SelectKBest feature selection method in improving model accuracy and testing various hyperparameter configurations to obtain the best performance.

KNOWLEDGE MANAGEMENT SYSTEM PENGOLAHAN SAMPAH MENGGUNAKAN SOCIALIZATION, EXTERNALIZATION, COMBINATION, INTERNALIZATION MODEL

2024-08-01T09:03:07+00:00

Garbage is an environmental problem that cannot be avoided, changes in human lifestyles cause an increase in the volume of waste, various ways are carried out to overcome the increase in the volume of waste, one of which is the Reduce, Reuse, Recycle (3R) technique which plays an important role in waste processing and can change waste. to be artistic and economical, to share knowledge about waste management requires a container that can accommodate and share knowledge. In this study, a Knowledge Management System (KMS) was developed using the Knowledge Management Life Cycle (KMSLC) method and capturing knowledge using the Sosialization Externalization Combination Internalization (SECI) model. The results of this study are web-based applications that can accommodate, add and share knowledge in the form of tacit and explicit and change the knowledge formed from the results of individual interactions into documented knowledge which is expected to help organizations manage all knowledge and develop it so that it can improve the abilities and knowledge of members organization for waste management.

SINTESA CITRA DAUN KOPI MENGGUNAKAN GENERATIVE ADVERSARIAL NETWORK PADA DATASET PENYAKIT DAUN KOPI

2024-08-01T09:03:08+00:00

Coffee, as the second most traded commodity after petroleum, faces production challenges, especially due to pest or disease attacks on coffee leaves. Therefore, it is important to carry out early detection of the disease in order to minimize the risk and apply special treatment. Automatic detection of disease can be done through the application of Computer Vision technology. However, one of the main challenges faced is the limited training dataset. Generative Adversarial Networks (GANs) is a Deep Learning method that is capable of modifying images with high quality. This research aims to synthesize coffee leaf images based on the public Coffee Leaf Disease dataset using the GANs method. Testing was carried out using the RMSProp optimizer, the learning rate was 0.0001 and was carried out for 300 epochs. The architecture built uses 26 layers in the generator model and 15 layers in the discriminator model. The results of the test show that the drilled network obtained an MMSE value of 0.1658, which is not too high because the resulting synthesized image is not very good.

IMPLEMENTASI METODE WATERFALL DAN SYSTEM USABILITY SCALE TESTING PADA APLIKASI FISIOTERAPI PASIEN BPJS

2024-08-01T09:03:08+00:00

The background of the problem in this study is that Physiotherapy Services at Permata Hati Hospital for BPJS patients are carried out scheduling or physiotherapy protocol data by writing on the form paper provided and then given to the patient. Besides being given to the patient, the form is also stored by the physiotherapy poly section. The problem that often occurs is that the physiotherapy poly officer must also rewrite the BPJS patient's physiotherapy protocol data in the ledger as data for the next physiotherapy schedule. If you want to find physiotherapy protocol data, it is difficult to do because you have to look one by one in the ledger. The purpose of this research is to make it easier for poly officers to process physiotherapy protocol data in a computerized manner through the design of BPJS patient physiotherapy protocol data applications at Permata Hati Hospital by applying the waterfall method and System Usability Scale (SUS). The results showed that in blackbox testing, the results were obtained in accordance with what was expected starting from the login form test to the patient data input form. Furthermore, testing using the SUS method obtained an average value of 70.75 with a total of 10 respondents and a total of 10 statements. There are 3 components of the System Usability Scale method, namely Acceptable, Grade Scale and Adjective, each component of the results is still at a good value and the level of application is quite comfortable to be used by users.

AUDIT SISTEM INFORMASI MANAJEMEN SEKOLAH MENGGUNAKAN FRAMEWORK COBIT 4.1

2024-08-01T09:03:08+00:00

The School Management Information System (SIMS) has brought many benefits, even though it has been implemented, SMPIT Ajimutu Global Insani Bekasi faces several challenges and problems that require special attention, including limitations in IT Strategic Planning, Less Optimal IT Risk Management, Evaluation of Automation Solutions, Security Information Systems, IT Service Performance Measurement, IT Governance have not been fully implemented in their entirety. This article discusses the application of the COBIT 4.1 framework in conducting SIMS audits at SMPIT Ajimutu Global Insani Bekasi. This research aims to assess the suitability of the information system with the school's strategic objectives, identify strengths and weaknesses in its management, and provide recommendations for improvement. The methodology used includes evaluation of the four main domains in COBIT 4.1: Planning and Organization (PO), Acquisition and Implementation (AI), Delivery and Support (DS), and Monitoring and Evaluation (ME). The audit results show that although SIMS has provided significant benefits, there are several areas that require improvement, such as IT strategic plan documentation, risk management, evaluation of automation solutions, information system security, IT service performance measurement, and IT governance. Based on these findings, recommendations for improvement are provided which include improving documentation and communication, developing formal processes for risk management, routine evaluation of automation solutions, improving security policies, establishing more comprehensive performance metrics, and strengthening IT governance.

PERANCANGAN AUTENTIKASI MULTI FAKTOR DENGAN PENGENALAN WAJAH DAN FIDO (FAST IDENTITY ONLINE)

2024-08-01T09:03:09+00:00

Digital services based online are assets that need to be safeguarded, especially if the application still uses single-factor authentication vulnerable to cyberattacks and potential data leaks and identity theft. The proposed solution is to implement multi-factor authentication (MFA) utilizing facial recognition, particularly through FaceNet technology. Although facial recognition can provide an additional layer of security, the main challenge is to maintain user privacy even if biometric information might leak. This research aims to create a secure, reliable MFA model that protects the privacy of employees at PT Traspac Makmur Sejahtera. The proposed method involves an MFA system with four factors: knowledge factor (password), biometric factor (facial measurements), ownership factor (OTP) and location factor (optional if facial accuracy is insufficient). The implementation of this MFA model enhances security, reliability, and protects employee privacy. Considering the specific needs of the company, this research can assist the company in monitoring the locations of employees working from home (WFH).

MENGUKUR KEPUASAN MAHASISWA DALAM MENGGUNAKAN APLIKASI MUSIC STREAMING MENGGUNAKAN METODE AHP

2024-08-01T09:03:09+00:00

Online streaming applications are currently very popular among the public, especially students. Because of this user interest, the author wanted to conduct research. This research uses the AHP method to measure students' level of satisfaction with the use of music streaming applications. The research evaluation criteria included quality, service, price and payment. Questionnaires are used to determine student preferences and assessment of related criteria. The collected data was analyzed using the AHP method and the application priorities were compared. These findings will help developers and users improve quality and user experience. The research was conducted using the Analytical Hierarchy Process (AHP) methodology on students in the Bekasi City area with a population of 7058 people and obtained a sample size of 379 respondents using the Slovin formula. The research results show that Spotify is the most popular music streaming application among users, especially students. Followed by applications such as Joox and YouTube.

PENERAPAN HYPERPARAMETER MACHINE LEARNING DALAM PREDIKSI GAGAL PINJAM

2024-08-01T09:03:09+00:00

Loans or credit are one of the key factors in advancing the economy. One of them is encouraging business expansion which will have a direct impact on a country's economic growth. Banks and other financing institutions must be able to evaluate the borrower's ability to pay their debts based on the inherent risks to reduce the possibility of default. To this end, machine learning (ML) has emerged as a revolutionary tool in using advanced prediction methods to examine historical data based on customer behavior. This research investigates the application of ML in predicting loan outcomes by optimizing parameters in the Machine Learning algorithm. The ML algorithms examined in this research are Logistic Regression (LR), K-Nearest Neighbor (KNN), Random Forest (RF), Decision Tree (DT), and XGBoost (XGB). Meanwhile, the technique used in hyperparameter tuning is Grid Search Cross Validation (CV). The results show that the algorithm's performance is more optimal than before, it can be seen that the LR algorithm experienced an increase in accuracy of 5%, KNN by 4%, RF by 3%, DT by 3%, and XGB by 2%. By including a default dataset based on customer behavior and optimized algorithm parameters, apart from being able to answer the alignment in previous literature in providing a deeper understanding of loan estimation, this research can also provide an understanding that hyperparameter techniques are worth trying to improve the performance of ML algorithms. So, it will be easier for financing institutions to determine the right loan scenario.

PERBANDINGAN PENERAPAN ALGORITMA DEEP LEARNING DALAM PREDIKSI HARGA EMAS

2024-08-02T05:11:16+00:00

Digital investment is trending because advancements in information technology make access easy through smartphones. Various digital investment instruments attract much interest from the public. Post COVID-19 pandemic, the economic impact of the pandemic is still felt until the end of 2022, requiring people to be smart in managing their finances. Gold investment is considered profitable due to its high value and tendency to increase, unlike the fluctuating stocks. Although easily accessible, investments carry risks, so investors must have sufficient knowledge to maximize profits. This research aims to predict gold prices using several deep learning models, namely Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). The dataset used was taken from the Kaggle website, which includes historical gold price data. In this research, various deep learning models were applied and evaluated to determine the best model for predicting gold prices. The results show that the CNN model with Adam optimization and Mean Squared Error (MSE) loss function provides the best performance. The CNN model achieved the lowest Mean Absolute Error (MAE) of 0.004848717761305338, the lowest MSE of 4.3451079619612133, and the lowest Root Mean Squared Error (RMSE) of 0.006591743291392053. These results indicate that the CNN model is more effective in predicting gold prices compared to the ANN, RNN, and LSTM models on the used dataset.

ANALISIS SENTIMEN PERKEMBANGAN MOTOR LISTRIK MENGGUNAKAN SUPPORT VECTOR MACHINE DAN OPTIMASI PARTICLE SWARM OPTIMIZATION

2024-08-02T07:57:17+00:00

Innovation in electric motor technology such as increased range, speed, and battery endurance can attract interest from individuals fascinated by the latest advancements. Sentiment analysis enables a profound understanding of consumer perceptions towards electric motors. In this study, Support Vector Machine (SVM) is employed as a classification tool to evaluate opinions on current developments in electric motors. SVM seeks an optimal hyperplane that maximizes the distance between sentiment categories. The development of sentiment analysis methods utilizes SVM with Particle Swarm Optimization (PSO) to successfully achieve an accuracy of 80.33% and obtain a Good Classification category based on ROC Curve results. This research provides insights into consumer perceptions of electric motor technology, offering valuable feedback for manufacturers in the development of superior electric motor products. Leveraging sentiment analysis, manufacturers can enhance product improvements, increase quality, and expand functionality to meet the evolving market demands.

SISTEM INFORMASI HOME SERVICE DAN PENJUALAN SPARE PARTS MENGGUNAKAN MODEL WATERFALL

2024-08-05T03:41:43+00:00

Yamaha Karya Laba Motor is a company specializing in motorcycle maintenance and parts sales. Despite its services, shortcomings persist such as verbal vehicle inspections upon service intake and manual recording of service queues and parts sales. Issues arise concerning inventory monitoring, particularly when parts are depleted, necessitating time-consuming manual checks that hinder mechanics' efficiency. Additionally, the lack of home service and online parts sales further complicates customer convenience. The development of a Home Service and online parts sales application at Yamaha Karya Laba Motor aims to address these challenges by enhancing operational efficiency and customer satisfaction. The application includes features such as transaction management, user administration, parts inventory, reporting, Home Service requests, and online parts sales. These functionalities empower Yamaha Karya Laba Motor employees to efficiently monitor parts availability and generate transaction reports. Simultaneously, customers benefit from streamlined processes, saving time and ensuring convenience. This study underscores the transformative impact of digital solutions in improving operational workflows and enhancing service.

IMPLEMENTASI TEKNIK SMOTE UNTUK MENGATASI IMBALANCE CLASS DALAM KLASIFIKASI SENTIMEN MENGENAI CHATGPT

2024-08-05T04:01:37+00:00

ChatGPT is a chatbot or computer program in the form of a virtual robot that can simulate human-like conversations. ChatGPT is widely used in various fields in academia. The impact of the use of ChatGPT on academia and public perception of this technology is significant. Sentiment analysis can be used to determine the polarity of a text or opinion that is positive or negative. In this research, social media is used as a data source to collect public opinion regarding ChatGPT instantly. The methods used in this reserach are the KNN algorithm and Naive Bayes algorithm. The aim of this research is to find the best algorithm model for sentiment classification in terms of public opinion for ChatGPT which contains English text. Before testing the algorithm model, a text processing stage was carried out which included the processes of case folding, tokenizing, stopword removal, and stemming. Word weighting using TF-IDF was carried out before the data was ready to be processed. Splitting data used in this research includes 80% of the dataset as training data and 20% of the dataset as testing data. The application of the SMOTE technique to the KNN and Naive Bayes algorithms to overcome the imbalance class of the public opinion dataset regarding ChatGPT. The research results show that combining SMOTE and Naive Bayes algorithm gives the best results with an accuracy value of 85.00%, a precision value of 87.64%, a recall value of 84.78% and an f1-score of 86.18%.

PENERAPAN MODEL WATERFALL DALAM MERANCANG APLIKASI PEMILIHAN SISWA TELADAN MENGGUNAKAN METODE SIMPLE ADDITIVE WEIGHTING

2024-08-07T04:03:38+00:00

By having exemplary students, it is hoped that students at school will have good role models in all aspects. Unfortunately, subjective selection because it is done using voting can lead to unhealthy competition. So far, the selection of exemplary students begins with the selection of students with the highest average scores, then looks at the student's activity and record of violations which culminates in a vote carried out in the exemplary student selection meeting. Voting at the end of the election can cause the selection of exemplary students to no longer be objective and no longer fair. The application design will use the waterfall method by implementing the SAW method as a method used to help make decisions. The criteria used are 7 criteria in accordance with school policy and the results of this analysis, first the system is able to record all students who will be alternative exemplary students and also the criteria set in accordance with school policy. Second, by implementing a decision support system using CBIS, it can minimize the objectivity and complexity of stakeholders in making decisions and can increase data accuracy. Third, based on the management using this decision support application, an alternative ranking of exemplary students was obtained with the first alternative position being Siska Azzahra Shafa with a total score of 19,790, the second alternative being Andrawan Erlang Padana with a total score of 19,654 and the third being Ichsan Sandi with a total score of 19,645.

ANALISA DAN PERANCANGAN UI/UX APLIKASI PENJUALAN BESI BETON MENGGUNAKAN METODE DESIGN THINKING

2024-08-07T05:43:04+00:00

The world of technology today greatly affects human life. Technological advances, especially in the field of information technology, are increasing every year. PT Sumber Jaya Maju Gemilang provides a variety of reinforced concrete products to meet the needs of different consumers for projects, factories, and other construction. During the sales process, it is still done manually, which hinders business because it takes a lot of time and causes errors in processing and reporting transaction data. Because of these problems, a new design for the Sales of Reinforced Concrete website must be designed using the design thinking method. The purpose of this study is to assist in creating sales applications that meet user needs and improve user experience. The results of the study show that the empathy stage, namely determining and observing previous cases, one of the problems that can be concluded from the empathize process is the company's low level of awareness of their service users. In the previous stage, the idea was to create an application that could handle the problems of people who wanted to order iron and delivery of goods but did not have much time or did not want to queue for a long time. At this stage, the prototype must rearrange the flow of iron sales and delivery of goods so that it is easier, and create a pattern for creating features in the application. In the final stage, the application trial process is carried out using the digital prototype in the Figma Application.

SISTEM INFORMASI POS PELAYANAN TERPADU BERBASIS WEBSITE MENGGUNAKAN METODE EXTREME PROGRAMMING

2024-08-12T07:34:30+00:00

The problem in this research is that the technical notification of Posyandu schedules is still done verbally by word of mouth among the community and is also only announced via loudspeakers at local mosques. This method makes the dissemination of information related to the Posyandu schedule less effective. The main problem that often arises is that there are still parents who don't know the Posyandu schedule, there are even parents who forget the Posyandu schedule. The aim of this research is to make it easier for cadres to convey information and make it easier for parents to receive information about posyandu activity schedules via WhatsApp Blast. This research uses the Extreme Programming method which consists of 4 stages, namely planning, designing, coding and testing. Extreme Programming is a method that is considered effective in its application because it can produce a system that is fast and responsive to changing needs. The result of this research is a posyandu information system based on WhatsApp Blast which was created based on extreme programming stages. Functional testing using the Black Box method shows that the system has met expectations.

PERANCANGAN APLIKASI INFORMASI PENDAKIAN GUNUNG DI INDONESIA BERBASIS ANDROID DENGAN MENGGUNAKAN METODE PROTOTYPE

2024-08-12T10:40:28+00:00

Nowadays, more and more teenagers and adults are interested in mountain climbing. Climbers are keen to find information about the routes and mountains they will be climbing. However, many mountaineers complain that the information they get about climbing routes is not accurate or complete. The information currently available is only general information and does not have accurate data such as coordinate points, mountain profiles, transportation facilities, and other facilities that help climbing. To solve this problem, Object Oriented Design (OOD) and Prototype system development methods were used to create an Android-based Indonesian mountaineering information application. The application was developed using Android Studio and designed to provide comprehensive information for mountaineers, including paths to the mountain, photo galleries, current news about the mountain to be climbed, climbing posts, and geographical locations. The study resulted in contributions in various aspects that can improve the safety and comfort of mountaineers in Indonesia. With more accurate and complete information and the utilization of modern technology, this application supports mountaineering activities significantly. Climbers not only get better guidance but also feel safer and more comfortable in pursuing their hobby.

PERBANDINGAN ALGORITMA YOLOV3 DAN YOLOV4 DALAM PENGELOMPOKAN UKURAN TELUR AYAM SECARA REAL TIME

2024-08-29T07:44:55+00:00

The common problem currently faced by MSMEs producing chicken eggs is the difficulty in calculating the number of eggs and grouping egg sizes where everything is still done manually so that errors often occur and many entrepreneurs often experience losses. To improve and strengthen productivity, management, and marketing in this business, technological innovation is needed. This study aims to detect the number of eggs and group egg sizes based on their type using the Yolov3 and Yolov4 algorithms. Based on the results of the tests carried out, it shows that the Yolov3 and Yolov4 algorithms are able to detect chicken eggs in real time with the best accuracy value obtained by the Yolov3 algorithm. The comparison was carried out using 10 epoch tests with an F1-Score value of 0.89 where the F1-Score value approaching 1 indicates that the system performance has been running well. The results of this classification can be used to create a real time egg calculation application that can help calculate the number of eggs every day by each MSME.