Jurnal Informatika: Jurnal Pengembangan IT
Not a member yet
437 research outputs found
Sort by
Efficient Weather Classification Using DenseNet and EfficientNet
No full textClassifying images of weather conditions using deep learning models is a challenging task due to the computational intensity and resource requirements. To deploy AI models on resource-constrained devices like smartphones and IoT devices, compact and computationally lightweight models are necessary. Efficient deep learning models for weather classification are essential to reduce energy consumption and costs, making AI more accessible and sustainable. To the best of our knowledge, there are limited studies comparing MobileNet, DenseNet, and EfficientNet as efficient models and did not report any hyperparameter optimization. Our study contributes by investigating efficient models with hyperparameter optimization. Firstly, we measured the inference speed of 14 models, namely MobileNet, MobileNetV2, MobileNetV3, EfficientNetB0, EfficientNetV2B0, NASNetMobile, DenseNet121, VGG16, Xception, InceptionV3, ResNet50, ResNet50V2, ConvNeXtTiny, and InceptionResNetV2. Then, the top-7 fast models, which are MobileNet, MobileNetV2, MobileNetV3, EfficientNetB0, EfficientNetV2B0, NASNetMobile, and DenseNet121, were benchmarked for their accuracy. The models were compared by a small dataset having four classes: cloudy, rain, shine, and sunrise. Batch size and learning rate for each model were optimized by grid search method. It turns out that DenseNet121 achieved the best and the most balanced validation and testing accuracy, 0.9821 and 0.9837, followed by EfficientNetB0 with 0.9821 and 0.9740 respectively. This study is important to find efficient models with optimal comparison
Campus Market Segmentation Through the Binary Logistic Regression and GIS Technology
No full textUnderstanding and targeting specific consumer segments has become paramount in the evolving marketing landscape. Within the confines of a university campus, a unique characteristic of potential consumers with distinct preferences and behaviors exists. The aim of this research is to model of interest in choosing UIN Sulthan Thaha Saifuddin Jambi. This research uses primary data, data from high school students of XII students in Jambi Province. The sample used 1205 students from six districts/cities in Jambi Province. Binary Logistic Regression analysis is employed for the analysis. The findings indicate that the variables of gender, region of origin, and majors of high school students have a significant influence on the interest in choosing UIN Sulthan Thaha Saifuddin Jambi. The regional origin variables, Merangin Regency and East Tanjung Jabung Regency did not have a significant effect on the interest in choosing UIN Sulthan Thaha Saifuddin Jambi. Meanwhile, Jambi City, Kerinci Regency, Tebo Regency, and Bungo Regency influenced the interest in choosing UIN Sulthan Thaha Saifuddin Jambi. The variables from school majoring in science and social studies have a significant influence on the intention to choose UIN Sulthan Thaha Saifuddin Jambi
Monitoring System for Website-Based Micro Hydro Power Plant using Firebase
No full textThe use of electrical energy is a basic need for everyone. Micro Hydro Power Plant is one of the technologies that has developed recently. This technology has little adverse impact on the environment. This plant utilizes flowing water, discharge from water, and water pressure. The highlands or mountainous areas where there is flowing water. This water flow can be used as a driving force to drive a turbine, which is the driving force for this power plant because the generator uses a generator that requires motion power to generate electricity. Because this plant utilizes flowing water as a power source to drive a turbine and turn a generator. So basically, where there is running water, there is electricity. Moreover, micro Hydro does not need to build large reservoirs like hydropower. The purpose of making this system is to make it easier to check the condition of the MHP equipment and record the data obtained from the sensors that have been installed. This Website was successfully implemented using HTML, PHP, Firebase Database, CSS, JavaScript, JSON, etc. This Website will use the waterfall method, which consists of observation and needs analysis, system design, modeling, implementation and coding, testing, and maintenanc
Analisis Opini Publik Tentang Boikot Produk Pro-Israel di Twitter Berbahasa Indonesia Menggunakan Metode SVM
No full textThe century-long Israeli-Palestinian conflict has created diverse opinions in Indonesian society. The escalation of tensions in Gaza triggered calls for boycotts of products suspected of supporting Israel. In this study, a Support Vector Machine (SVM) method is used to analyze sentiment on Twitter related to pro-Israel boycotts. By understanding public opinion, this study evaluates the performance of SVM with linear kernel and RBF. Data collection was done through crawling Twitter with the keyword "Pro-Israel boycott", resulting in 2600 data. Data preprocessing involved case folding, cleaning, stopwords, stemming, and TF-IDF weighting. Manual labeling was done for 1560 support data and 1040 non-support data. Implementation of the SVM model resulted in 92.5% accuracy for the linear kernel and 91.92% for the RBF kernel. Word cloud analysis provided visualization of key words and sentiments related to the boycott. This research shows the dominance of positive sentiment with 1560 positive tweets and 1040 negative tweets. For development, it is recommended to add sentiment analysis methods, use a wider dataset, and consider supporting variables to improve accuracy and understanding of public sentiment on the issue
Rancang Bangun Aplikasi Keuangan Untuk Mengatur Jumlah Pengeluaran Pribadi Berbasis Android
No full textNot everyone is able to manage their finances well. Consumptive lifestyles and lack of awareness about the importance of managing finances make a person unable to escape financial problems. In an effort to reduce the impact of existing problems, everyone should have the awareness and effort to manage their finances by recording their financial expenses regularly. In modern times and the rapid development of technology like today, almost everyone has a mobile device at least one Android device. By utilizing existing technology, various things can be done using only their Android devices such as shopping, communicating with someone even though it is quite far away or even to record financial activities. By identifying and collecting data and interviews from related problems, this research aims to be a solution for someone in managing their finances by recording every financial activity in an existing application and making the use of stationery and books to record and recap every expense can be abandoned. With this application, a person can easily record finances anytime and anywhere without fear of losing the notes that have been made. As a result, it is hoped that eating will become wiser and know how much and where the money is spent so that the record can be used as a picture of a person in controlling their money
Sistem Monitoring Pertumbuhan Tanaman Sawi Menggunakan Artificial Intelligence Pada Aquaponik
No full textModern agriculture increasingly relies on technology to increase efficiency and productivity. Aquaponics, a sustainable farming method that combines fish and plant farming, has emerged as one promising approach. To maximize yield in an aquaponics system, monitoring plant growth becomes very important. In this context, Artificial Intelligence (AI) offers innovative solutions to monitor and optimize plant growth in realtime. AI-based aquaponics technology is designed portably so that it allows people to grow crops inside and outside the home. AIbased aquaponics technology uses a camera that functions to monitor plants in real-time. The data on the camera will be processed and analyzed by the AI system so that automatic monitoring of the plant growth environment in the system can be carried out. Where will output results that show whether the leaves are still fresh, immediately wither Using CNN's deep learning method, this technology contributes to sustainable food production with higher efficiency in managing resources. This system can increase productivity and strengthen food security in the face of future challenges. This aquaponics technology can make a significant contribution to the development of sustainable agriculture and can provide guidance and inspiration for agricultural and food industry players. By optimizing food production through AI-based aquaponics systems, communities can face global food security challenges and move towards more environmentally friendly, efficient, and sustainable solutions for the future
Perbandingan Algoritma Sequential Search dan Binary Search Pada Website E-Tracking Pengajuan Surat
No full textDisposition of a letter is an action taken in response to receiving a letter which is usually of an urgent nature or which must be carried out or followed up immediately. In an agency or organization, the flow of disposition letters usually begins with an incoming letter addressed to superiors or leaders. Based on the problems that occurred in Cilangkap Village, where after submitting letters, residents often felt confused about the disposition of the letters they submitted because there was no information regarding the disposition of computerized letters. This study aims to build a website-based letter submission information system and e-tracking letter disposition to make it easier for residents to know the disposition of their letter. This study uses the Sequential Search Algorithm and the Binary Search Algorithm to find the average time needed to search data using the microtime function and obtain the most optimal results from the two algorithms. The results showed that from a total of 507 data, 100 data searches for letter submissions obtained the average result of the Sequential Search Algorithm search time is 5.35 miliseconds and the Binary Search Algorithm is 6.16 miliseconds. So from the research results it can be seen that the Sequential Search Algorithm is more efficient and optimal in the search for letter submission data
Analisis Risiko IT untuk Pemanfaatan Tools Genogram pada Health care
No full textThis research analysis the genogram tool uses to record a person's health history as a medium for supporting health. This research analyzes the risks that might occur in a polyclinic if a genogram tool is implemented. The analysis process is through a risk identification process then a risk assessment using the COBIT for Risk IT method as IT resource mapping, then qualitative analysis as a method of mapping possibilities and impacts according to FGDs with organizations which can be used as a guide in assessing risks. level. Meanwhile, bow tie analysis is a risk mapping method that allows risk recovery so that it can serve as a guide for recovery. The results of risk analysis using the Genogram tool show several conditions, namely low probability but high level of impact, low probability but medium impact, and high probability of impact
Pengembangan Motor IoT untuk Pemantauan Kecepatan dan Pemeliharaan Melalui Telegram
No full textThis research focuses on developing Motor IoT as an advanced solution for real-time motor speed monitoring and maintenance notifications via Telegram. The research method includes installing a magnetic sensor on the motor to measure wheel rotation and produce accurate speed data. The data is sent to the IoT platform and integrated with Telegram, providing users with speed monitoring information as well as providing timely maintenance notifications. In addition, this system monitors the overall condition of the motorbike. The results of research and testing show that Motor IoT can be used and applied to motorized vehicles with the ability to provide accurate information and efficient maintenance notifications. The use of IoT and Telegram technology provides an effective solution for monitoring motor performance, optimizing maintenance and reducing potential damage. IoT motorbikes not only increase the efficiency of using motorized vehicles, but also contribute to minimizing the risk of damage and increasing the overall service life of motorbikes. In addition, the magnetic sensor was successfully integrated with the motor monitoring and maintenance system via Telegram, providing appropriate responses to predetermined conditions. This system is also able to send notifications to Telegram when the motorbike is started, providing information on the distance traveled by the user, with reminders to change the oil every 1000 kilometers. This research produces innovations that can have a positive impact on the automotive industry and user welfare
Implementasi Metode SVM Pada Sentimen Analisis Terhadap Pemilihan Presiden (Pilpres) 2024 Di Twitter
No full textThe focus of the research is the use of Twitter as a platform to express the political opinions of the Indonesian people regarding the 2024 Presidential Election. By utilizing sentiment analysis using the Support Vector Machine (SVM) method, this research aims to evaluate the accuracy of SVM in classifying tweets and compare the performance of four types of SVM kernels. Visualizations of positive and negative sentiments are also generated to provide a clearer picture. The stages of the research involve Twitter data collection, and pre-processing with steps such as data cleansing, case folding, tokenizing, stemming, and filtering. Labeling is done to identify sentiment, then feature extraction using TF-IDF. SVM implementation with linear, polynomial, RBF, and sigmoid kernels is performed, followed by model evaluation using precision, recall, F-measure, and accuracy metrics. The study used SVM to analyze the sentiment of the 2024 presidential election on Twitter data. As a result, out of 3938 tweets, 1575 were positive and 2363 were negative. The SVM model achieved 95.05% accuracy, superior in predicting negative sentiment. Comparison of SVM kernels shows the highest accuracy in the linear kernel 95.43%. Sentiment analysis on tweets shows a majority of positive support for Ganjar 54.9%, while Anies and Prabowo have support levels of 15.8% and 29.3% respectively