Publication Search

This research aims to develop a multiclass flower image classification system using the Convolutional Neural Network (CNN) algorithm with the EfficientNet architecture. The main problem addressed is the difficulty of manual identification of flower species that share high visual similarity. The research stages include collecting 17,299 flower images across 19 classes, performing data preprocessing such as image resizing, pixel normalization, and augmentation, followed by model training using the EfficientNet transfer learning approach. The model was trained for 10 epochs with an 80:20 training-validation data split. The evaluation results show that the model achieved a validation accuracy of 98.05% with a loss value of 0.0968, and an average precision, recall, and F1-score of 0.98. The trained model was then implemented into a web-based application built using the Next.js framework, enabling users to upload flower images and obtain real-time classification results via the Hugging Face API. The system successfully identified flower species with a confidence level of 99.87%. These findings demonstrate that combining a modern CNN architecture with transfer learning provides efficient and highly accurate flower classification performance, which can be effectively implemented for educational and digital conservation purposes.

The development of renewable energy, particularly Solar Power Plants (PV), requires a reliable, real-time, and easily accessible electrical energy monitoring system to ensure optimal system performance. This study aims to design and implement an Internet of Things (IoT)-based electrical energy monitoring system for PV using the NodeMCU ESP32 microcontroller, the PZEM-004T sensor for measuring electrical parameters, and the Node-RED platform as the data visualization interface. The developed system is designed to monitor voltage, current, power, energy, frequency, and power loss in real time, and then display the data in the form of numerical values, graphs, and indicators on a dashboard accessible through a local network. The research method includes hardware design, software development (sensor reading, data processing, and communication), integration with Node-RED, and system testing on a small-scale PV installation. The test results show that the system is capable of monitoring electrical parameters in a stable and responsive manner. Variations in sunlight intensity were found to affect the current and power produced by the solar panels, whereas the inverter output voltage tended to remain within normal operating ranges. The Node-RED dashboard display was considered informative and helpful for users in monitoring and analyzing PV performance. Based on these results, it can be concluded that the IoT-based electrical energy monitoring system designed in this study functions well and is feasible for application in residential or educational-scale PV installations. The system still has the potential for further development through cloud service integration, the addition of environmental sensors, and enhancements to data analysis features and user interface design.

Relational databases store information in interconnected tables and are widely used for data management and retrieval. However, in certain environments, the original values stored in a relational database cannot be exposed during data retrieval. This limitation creates a challenge because common encryption methods only transform data for storage and do not support mathematical operations needed for value matching. Partially Homomorphic Encryption is a cryptographic approach that allows specific mathematical operations to be performed directly on transformed data without restoring it to its original form. This study proposes the use of Partially Homomorphic Encryption to enable value-based data retrieval while keeping all stored values in their transformed form throughout the entire process. The method relies on homomorphic properties that allow mathematical comparison to be conducted on encrypted data, making the retrieval process possible without revealing the original values. The results show that this approach can perform data retrieval operations in a relational database while preserving the transformed structure of the stored data. The proposed method offers an alternative for environments that require data retrieval without exposing original values and demonstrates the potential of homomorphic techniques in supporting secure and functional data processing in relational database contexts.

Indonesian Sign Language (BISINDO) serves as a primary communication medium for the deaf community; however, limited public understanding often creates barriers during daily interactions. This study aims to develop a real-time BISINDO word-level translation system using hand landmark extraction and temporal modeling with Long Short-Term Memory (LSTM). The system employs MediaPipe Hands to detect 21 hand landmarks per frame, which are then processed as sequential motion patterns to classify five BISINDO words: saya, terima kasih, maaf, nama, and kamu. A total of 250 gesture samples were recorded under controlled lighting conditions as the primary dataset. The processed sequences were used to train the LSTM model, which was subsequently integrated with an ESP32 microcontroller and a DFPlayer Mini module to produce direct audio output. Experimental results show that the model achieved an average accuracy of 86%, with precision and recall values ranging from 0.81 to 0.94. The confusion matrix analysis indicates that most gestures were correctly classified, although some errors occurred in gestures with similar initial motion trajectories. Integration testing demonstrated an average system latency of 3.8 seconds and an audio output success rate of 85%. These findings indicate that the proposed system is capable of translating BISINDO word-level gestures accurately, responsively, and consistently in real-time conditions. This study provides a strong foundation for the broader development of sign language translation systems, with potential enhancements in vocabulary expansion, multi-user datasets, and hardware optimization for deployment in real-world environments.

Given the great benefits of electrical energy, the availability of electrical energy sources is limited. Currently, the availability of electrical energy sources is not able to meet the increasing demand for electricity in Indonesia. The high use of electrical energy in daily life will have a negative impact on the environment. Therefore, to maintain the sustainability of energy sources, it is necessary to pursue strategic steps that can support the provision of electrical energy optimally and affordably, This study aims to find out how much total energy is used by the Energy Consumption Index (IKE) on electrical energy from the influence of electrical power and the length of time of use of electrical energy at SMK Negeri 2 Lubuk Basung, Lubuk Basung District, Agam Regency. This study aims to determine the value of energy consumption used or Energy Consumption Index (IKE) and energy saving opportunities at SMK Negeri 2 Lubuk Basung, Lubuk Basung District, Agam Regency. The results of this study are for the IKE value of the first floor which is 1.71 kWh/m2, for the IKE value of the second floor which is 0.03 kWh/m2, for the IKE value of one building, which is with a value of 1.74 kWh/m2, for the annual IKE of 0.022 kWh/m2/year and for the value of energy-saving opportunities of IDR 651 646/month IDR 7 819 755/year.

This study presents a machine learning approach for predicting the dimensions of microstrip antenna slots based on antenna performance parameters such as frequency, gain, directivity, return loss (S11), radiation efficiency, and VSWR. A two-phase methodology was employed. In the first phase, ten regression algorithms were evaluated, and Random Forest was identified as the most effective model based on Mean Absolute Error (MAE) and R-squared (R²) scores. In the second phase, hyperparameter tuning was conducted using Grid Search to further improve the model’s performance. The optimized Random Forest model demonstrated consistent improvements in predictive accuracy, with R² values increasing across all output variables. These results indicate that the combination of regression-based modeling and systematic hyperparameter tuning is effective for capturing complex relationships in antenna design tasks. The proposed approach offers a promising data-driven alternative for geometric prediction in microstrip antenna development, particularly when analytical models are insufficient.

The Message Queue Telementary Transport (MQTT) protocol is able to adjust the sending and receiving of messages to monitor in accordance with the user's preferences because the sending and receiving of messages is topic based on a specified topic, making it necessary to routinely monitor the condition of patients who have been diagnosed with heart problems from a distance. With the aim to perform a Quality of Service (QoS) analysis with throughput, delay, and packet loss parameters using Unshielded Twisted Pair internet transmission media (UTP) and Wireless, the goal of this research is to design and implement (MQTT) a heart rate monitoring device with an EKG module as a sensor and ESP32 as a microcontroller. On the Ubidots website, EKG signals are transmitted over the internet and shown in real time. QoS analysis is performed using the Wireshark application. Data was collected on two scenarios at intervals of 30 minutes, 1 hour, 2 hours, 5 hours, 8 hours, 12 hours, 18 hours, and 23 hours. The throughput, latency, and packet loss metrics used in this study's results cause different value variations; these are influenced by the weather, internet bandwidth, computer, and router specifications. According to testing, the tool is portable and has a 3000mAh battery, but it has the restriction that it can only be used with reliable internet and bandwidth.

This research aims to be able to meet the water supply of lettuce plants automatically by using three sensors such as soil moisture, water level, and water discharge. The goal is to provide water needs to plants automatically and regularly. The developed tool uses YL-96 sensor for soil moisture, HC-SR04 for water level and YF-S201 for water discharge. Sensor data is sent to the arduino to be processed using the fuzzy mamdani method so that these three data values affect the movement of the tap servo motor that flows to the lettuce plant. Fuzzy logic here as a decision maker from the value of 3 sensor data and then processed automatically by arduino using fuzzy mamdani to determine how many degrees the servo motor moves. The result is that the Lettuce Plant Water Needs Analysis System Automation Tool is able to maintain the water supply of lettuce plants and soil moisture ideally at 76% with a servo motor movement system success rate of 100%.

The election of the OSIS chairman at SMK Al-Ikhlas Losari often influences subjectivity, so a goal-oriented system is needed to select the best candidate. This study applies the WASPAS method in a Decision Support System to broadcast OSIS chairman candidates based on criteria such as attendance, integrity, academic achievement, and health. Data were collected through observation, interviews, and literature studies, then processed using Microsoft Excel. The results of the WASPAS calculation yield a Qi preference value, which determines the ranking of candidates transparently. This system reduces subjectivity, increases efficiency, and ensures the selection of competent leaders, supporting the OSIS vision.

Technological advancements have brought fundamental changes in the way we interact with digital images and photography. One significant milestone in this development is the Photoshop Express Photo Editor, which has become a primary platform for image processing and editing. Datasets are used to analyze sentiment and are utilized during the accuracy testing phase. Based on the testing results, the Convolutional Neural Network (CNN) algorithm achieved an average accuracy value of 86.50%, compared to the Naïve Bayes (NB) algorithm, which achieved an average accuracy value of 75%. The results of the research conclude that the choice of sentiment analysis method should be tailored to the needs and limitations of the system. If a fast, light, and easy-to-understand process is required, the Naive Bayes method is the right choice. However, if accuracy and context understanding are the top priorities, then CNN is a superior approach, although it requires more resources. Additionally, based on the Wordcloud data, it is known that the majority of comments are positive, indicating that the reviews or texts analyzed contain many positive expressions related to quality, usability, and ease of use.

The growing demand for affordable transportation has significantly expanded the used car market. This study aims to develop optimal sales strategies by analyzing seller types and vehicle categories through exploratory data analysis and linear regression techniques. Using a cleaned public dataset of over 150,000 used car listings in Germany, key variables such as registration year, mileage, vehicle type, and seller type were examined. Results indicate that individual sellers dominate the market, although dealers set higher and more stable prices. SUVs and limousines typically hold higher market value. The linear regression model achieved an R-squared value of 0.34, suggesting that registration year and mileage account for 34% of the price variance. These findings offer practical insights for stakeholders in the used car business to tailor pricing strategies based on vehicle attributes and seller classification

Milk consumption and the need for beef cattle for food purposes or sacrificial purposes continue to increase from year to year. This increase is in line with the increasing level of the economy and awareness of the need for nutritious food. However, the increase in demand still faces many production constraints due to the difficulties faced by farmers, the decline in cattle production from year to year in Indonesia. This causes Indonesia to have to import beef for 35.95% of the total national beef consumption. With many factors that affect the decline in the production rate of dairy cows or beef cattle every year, one of them is air pollution and poor air quality in cages. Along with the development of technology, a monitoring and detection system for air cleanliness in cattle pens was created, using the MQ-7 sensor as the concentration of carbon monoxide, the MQ-135 sensor as the concentration of ammonia gas, the MQ-2 sensor as the smoke detection, and When the air pollution value of each sensor input is according to the air pollution standard index (ISPU), the outputs namely indicator lights, buzzers and blowers will be on, then there will be temporary air neutralization in the cage. This tool is made easier by internet of things technology, so that it can send notifications via telegram and can see the level of air pollution levels through the web.

The news about the proposal of the government of the Republic of Indonesia regarding the postponement of the 2024 elections is certainly an interesting discussion. In this research, sentiment analysis will be carried out on the issue of postponing the election. In this study, a dataset obtained using the crawling technique was obtained in the amount of 1280 tweet data about the postponement of the 2024 election. Data labeling in this study uses lexicon-based techniques with Indonesian dictionaries. By applying this technique, the details of the data in the positive class are 67.7%, namely 157 opinion data, and 32.3% negative, namely 75 opinion data. The sentiment classification system's training and test data yield a 9:1 ratio when the Naïve Bayes Classifier method is applied, and word weighting using TF-IDF yields an accuracy value of 91.67%, precision of 90.91%, recall of 100%, and f1-score of 95.24%.

E-Learning becomes a platform which supports technology-based learning on many aspects. The usage of E-Learning becomes the main choice especially in education world. SMK TI Bali Global Jimbaran, which is a middle level vocational school, utilizes this platform in its learning process. In its implementation process, there needs to be a precise and thorough supervision to ensure that the system runs according to business goals. This mapping is conducted to know the process used for measurements. This mapping is done by framework with COBIT 5 by applying PAM (Process Assessment Model), which is adjusted with the condition on research place. The activity measurement are derived from several domains on COBIT 5 with mapping process based on the business goals and institution goals. The domains used are EDM03, AP003, BAI07, DSS05 and MEA01. The results of governance measurement process on current capability level is on level 4 (predicable process) and the expected capability level is on level 5 (Optimizing Process) which has gap value of 2 level.

Hydroponic plant cultivation is booming, but stock and sales are hard to predict. Poor prediction can cause farmers to overstock and lose money. This study suggests a framework that uses several machine learning models, including Linear Regression (LR), Random Forest (RF), Decision Tree (DT), and Extreme Gradient Boosting. "Ensemble Learning," which combines these models, should yield more accurate and generalizable results than a single model. This framework is assessed using historical hydroponic plant sales data and related factors like price, weather, and market trends. The model's performance is measured by the difference between predictions and actual values using RMSE and MAE metrics. This framework should improve hydroponic plant stock and sales predictions. Farmers can make better production, inventory, and harvest distribution decisions. Besides reducing financial losses, this reduces food waste and improves food security.

This research aims to design and simulate a DC motor speed control system using integral state feedback (KISF) control. This control is designed to maintain DC motor speed stability with high accuracy despite disturbances or load changes. The research stages include mathematical modeling of the DC motor, PID control design, integral state feedback control design, simulation implementation and simulation results analysis. The show that althought integral state feedback control has a rise time 273.501 ms, slightly slower than PID 197.604 ms, integral state feedback compensates with higher slew rate of change 6.540 V/ms compared to PID 4.344 V/ms. Integral state feedback offers greater flexibility through pole placement values with Ackerman’s formula J3 = [-12 -100 -600], indicating that this system has good capability in responding to input changes, thus maintaining motor speed stably and efficiently. This indicates that integral state feedback control is superior in system adaptation and handling complex dynamics.

This study aims to develop an automated pipeline for data cleaning using Pandas and Scikit-learn. The data cleaning process is often performed manually, requiring a long time and prone to errors. This study uses a quantitative experimental method with a dataset of 100,000 rows of e-commerce transaction data. The results show that the automated pipeline reduces missing values by 95.7% and outliers by 91.7%, and accelerates processing time by 35% compared to manual methods. The distribution of data after cleaning becomes more stable, allowing for more accurate analysis. This study contributes to the development of a more efficient and accurate automated data cleaning approach.Keywords: Systematic Literature Review, Artificial Intelligence and Marketing Strategy.

Accurate rainfall prediction is needed to improve the performance of land that always uses rainfall data. Data mining or often called knowledge discovery in databases (KDD) is an activity that includes collecting, using historical data to find regularities, patterns or relationships in large data. In predicting rainfall, there are several conditions that can be observed as reference data to predict rainfall, namely wind speed, temperature, and air humidity. In this research, a backpropagation artificial neural network prediction method is developed that can be used in predicting future rainfall. The backpropogation artificial neural network method that was built produced an accuracy value of 95.36%, a precision value of 90.50%, a recall value of 97.50% and an f-measure value of 92.00%

All PT Astra International BMW Semarang transactions are recorded in the database but the problem is that the stock management is  efficientless so  the part stock that buyers are interested is not available. This research aims to conduct a comparative mining results using the association rule with apriori algorithm for year 2021, 2022 and 2023 sales transaction dataset with total of 43.694 records using the Rstudio. Data mining process in each year uses the same parameters for each itemset combination. The best association pattern occurs in 2023 with support value 0.05913841 and confidence value 100%. This can be concluded that the rules formed from each year could be different eventhough using same parameters. The item that always appears in the association rule from 2021 – 2023is Z99000000333 (BMW Engine OIL) which is often purchased with items named “Set fil-oil” so it can be a recommendation for  item stocking  in the warehouse.

The study titled "The Influence of System and Service Quality on User Satisfaction of Silalapbaja Website" aims to evaluate the impact of each independent variable on the dependent variable. There were 51 respondents involved in this research, with data analysis conducted using SPSS version 25. The results indicate that System and Service Quality significantly influence User Satisfaction, as evidenced by the significant value of Fhitung = 0.000 < 0.05. From the t-test, System and Service Quality variables partially affect User Satisfaction, while Information Quality does not have a significant partial effect. For instance, the significant values of thitung X1 = 0.000 < 0.05 and X3 = 0.49 < 0.05, whereas X2 = 0.094 > 0.05. The variables that significantly influence are System Quality with a Standardized Coefficients Beta of 0.552 and Service Quality of 0.220. Based on the research findings, it can be concluded that System, Information, and Service Quality contribute to 59% of User Satisfaction, while other factors beyond this study affect 41%. Therefore, it is recommended for the developers of the Silalapbaja Website to prioritize improvements in System and Service Quality to enhance User Satisfaction.