Journal of Soft Computing Exploration

Squeeze-and-Excitation networks and attention mechanism in automatic detection of coffee leaf diseases based on images

Muhammad Izza Iqbal, Donny Avianto — Wed, 04 Dec 2024 00:00:00 +0000

This research examines the effectiveness of Squeeze-and-Excitation Networks (SENet) combined with Attention Mechanism for automated detection of coffee leaf diseases. The integration of SENet and Attention Mechanism presents a promising technological opportunity as SENet has proven effective in improving CNN performance by modeling channel interdependencies, while Attention Mechanism enables focused feature extraction on crucial leaf areas - a combination that remains underexplored in coffee leaf disease detection. Using a combination of three datasets: Coffee Leaf Diseases, Disease and Pest in Coffee Leaves, and RoCoLe.Original, comprising 3,177 coffee leaf images divided into four classes (Healthy, Miner, Phoma, and Rust), this study compares the performance of SENet against other deep learning architectures such as InceptionV3, ResNet101V2, and MobileNet. Experiments were conducted with variations in epochs (15 and 30), three data split ratios, and three optimizer types. Results demonstrate that SENet with Attention mechanism performs, achieving a peak accuracy of 96% at 30 epochs with an 80:20 data ratio and RMSprop optimizer. InceptionV3 and MobileNet showed competitive performance with 93% accuracy, while ResNet101V2 achieved 81%. Class-wise analysis reveals SENet's proficiency in detecting various coffee leaf diseases, with F1-scores 91% for all classes.

Eye disease classification using deep learning convolutional neural networks

Tue, 10 Dec 2024 00:00:00 +0000

This study begins with the analysis of the growing challenge of accurately diagnosing eye diseases, which can lead to severe visual impairment if not identified early. To address this issue, we propose a solution using Deep Learning Convolutional Neural Networks (CNNs) enhanced by transfer learning techniques. The dataset utilized in this study comprises 4,217 images of eye diseases, categorized into four classes: Normal (1,074 images), Glaucoma (1,007 images), Cataract (1,038 images), and Diabetic Retinopathy (1,098 images). We implemented a CNN model using TensorFlow to effectively learn and classify these diseases. The evaluation results demonstrate a high accuracy of 95%, with precision and recall rates significantly varying across classes, particularly achieving 100% for Diabetic Retinopathy. These findings highlight the potential of CNNs to improve diagnostic accuracy in ophthalmology, facilitating timely interventions and enhancing patient outcomes. For future research, expanding the dataset to include a wider variety of ocular diseases and employing more sophisticated deep learning techniques could further enhance the model's performance. Integrating this model into clinical practice could significantly aid ophthalmologists in the early detection and management of eye diseases, ultimately improving patient care and reducing the burden of ocular disorders.

Implementation of integrated temperature, humidity, and dust monitoring system on building electrical panel

Wed, 04 Dec 2024 00:00:00 +0000

This research aims to develop and implement an electrical power monitoring system at the Sub Sub Distribution Panel (SSDP) in the Building. The system is designed to monitor power usage in real-time, provide accurate information on energy consumption, and detect potential energy waste. The methodology used includes hardware and software design. The hardware consists of current and voltage sensors connected to a microcontroller. The data collected by the sensors is then transmitted via Wi-Fi network to the server for analysis. The software uses an Internet of Things (IoT) platform that displays the data in the form of graphs and tables. The implementation shows that the system is capable of monitoring power usage with a high degree of accuracy. The sensors used, namely PM2100 for voltage, SHT20 for temperature and humidity, and GP2Y101AU0F for dust concentration, proved effective in generating accurate real-time data. Based on the test results, the voltage measurement error with the PM2100 was only 0.035%, while the current measurement resulted in an error of 0.48%. The SHT20 sensor recorded an error of 2.4% for temperature and 1.0% for humidity. Dust measurements with the GP2Y101AU0F sensor had a very small error of 0.02%. These results indicate that the tested device has a sufficient level of precision for electrical power and environmental monitoring applications.

Development of an IoT-based temperature and humidity prediction system for baby incubators using solar panels

Thu, 05 Dec 2024 00:00:00 +0000

Baby incubators are crucial medical devices to maintain environmental stability for babies born prematurely or have health problems. This research aims to develop a prediction system for temperature and humidity variables in baby incubators by utilizing Internet of Things (IoT) technology and solar panels as the main energy source. Despite advancements in IoT-based incubator systems, existing solutions often rely on reactive approaches, making them less effective in preventing harmful environmental fluctuations. Addressing this gap, this study focuses on optimizing temperature and humidity predictions using artificial intelligence (AI) for proactive control. Using a DHT22 sensor to measure temperature and humidity, as well as a 1 Wp solar panel, the system is designed to operate autonomously in areas with limited access to electricity. The methods used include data collection, data processing to calculate correlation coefficients, and selection of linear regression models for the analysis of relationships between variables. The results showed that the linear regression model applied had a good temperature and humidity prediction with a Mean Squared Error (MSE) value of 0.45 for the training data and 7.32 for the test data.

Valid and practical integrated monitoring instrument of tahfidz qur'an

Efan Efan, Arie Yandi Saputra, Riduan Syahri, Zulkipli Zulkipli — Mon, 06 Jan 2025 00:00:00 +0000

In implementing tahfidz qur'an learning in Islamic boarding schools, students must face many activities, and they are usually given up to five times a day. Almost all of these activities must be recorded by the teacher in a logbook so that there is the potential for slow and invalid reporting. This study aims to create an integrated monitoring instrument of tahfidz qur'an and reveal its validity and practical values. This study was conducted using a research and development (R&D) approach. The instrument was created by combining the Analysis, Design, Development, Implementation, and Evaluation (ADDIE) development procedure and the Rapid Application Development (RAD) development procedure. Furthermore, the application of the Object-Oriented Programming (OOP) paradigm into the application creation process aims to produce a monitoring instrument that is integrated into various types of devices and can provide data and information on the student's achievement of tahfidz qur'an learning to all interested parties. The results of the validity test revealed an Aiken's V value of 0.81 so it was worthy of being tested at the implementation stage. The implementation resulted in a practicality value of 80.65% from teachers, 79.84 from parents of students, and 78.28% from the management of the boarding school. Overall, both teachers, parents of students, and management stated that this integrated monitoring instrument of tahfidz qur'an was practical during use.

Comparison of supervised machine learning methods in predicting the prevalence of stunting in north sumatra province

Fri, 20 Dec 2024 00:00:00 +0000

Stunting is a growth and development disorder in children caused by chronic malnutrition and repeated infections. Stunting has significant short- and long-term impacts and is one of the major health issues currently faced by Indonesia. The prevalence of stunting in North Sumatra Province is 18.9%, and the provincial government aims to reduce this prevalence to 14% by 2024. This study aims to compare the performance of several supervised machine learning methods in predicting stunting prevalence in North Sumatra Province. The data used is secondary data from 2021 to 2023, covering 33 districts/cities in the province. This study evaluates three machine learning models: Support Vector Regression (SVR), Decision Tree, and Random Forest, using evaluation metrics such as Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The analysis results show that Random Forest provides the most accurate and consistent predictions, with lower MSE, MAE, RMSE, and MAPE values compared to the other models in most areas. Decision Tree yields good results in some regions but tends to produce higher errors in certain cases. SVR exhibits a more varied performance, with some regions showing higher prediction errors. Overall, Random Forest is the superior model for predicting district/city-level data, although model selection should be tailored to the data characteristics and application needs

Design of smart baby incubator for low-birth-weight newborns

Mon, 30 Dec 2024 00:00:00 +0000

The newborns mortality rate in Indonesia is still quite high, indicated by the neonatal mortality rate (AKN) of 15 per 1000 Live Births, where the target is only below 10 per 1000 Live Births. This mortality rate can be caused by Low-Birth-Weight (BBLR) cases that leads to death. One form of handling for these cases is using a Baby Incubator for intensive cares, which requires monitoring manually and requires the presence of a nurse around the baby incubator so that the condition of the baby incubator room remains stable. Several studies have been conducted and produced a smart incubator system to address these shortcomings. However, most of the smart incubators only focused on monitoring the condition of the incubator room without observing the condition of the baby inside. Based on this, a study was conducted that focused to producing a smart baby incubator that is capable of real-time monitoring of of room conditions (temperature, humidity, and oxygen levels) and baby conditions (temperature, heart rate, oxygen saturation, baby crying, and baby visuals) by applying the Internet of Things (IoT). The results of this study have the largest number of parameters monitored compared to previous studies.

Website based classification of karo uis types in north sumatra using convolutional neural network (CNN) algorithm

Boy Hendrawan Purba, Hermawan Syahputra, Said Iskandar Al Idrus, Insan Taufik — Mon, 30 Dec 2024 00:00:00 +0000

Indonesia is one of the largest archipelagic countries in the world. It has abundant cultural diversity including nature, tribes. One of the tribes in Indonesia is the Batak Karo tribe. Batak Karo is a tribe that inhabits the Karo plateau area, North Sumatra, Indonesia. Batak Karo has various cultures, one of which is a traditional cloth known as uis. Unfortunately, the Karo Batak community, especially the younger generation, has insufficient knowledge of the types of uis. Thus, a solution that is easily accessible both in terms of time, cost and experts in recognizing Uis is needed. This research aims to build a website-based application that can classify the types of Karo Uis. This research uses Convolution neural network (CNN) using Alex Net architecture, to get the best model this research compares several hyper parameters, namely learning rate of 10-1 to 10-4, and data division with a ratio of 70:30 and 80:20. The best model falls on a ratio of 70:30 and a learning rate of 10-4 with an accuracy of 98%, and a validation accuracy of 99%, then the model is stored in h5 format in this study successfully builds and implements the model into a web-based application.

Utilization of eye tracking technology to control lights at operating room

Asyraf Permana, Diah Rahayu Ningtias — Tue, 31 Dec 2024 00:00:00 +0000

The development of technology for control systems is increasing, especially to help people with disabilities and facilitate the performance of health workers. Where it is required to maintain the level of sterilization of equipment in hospitals. Eye tracking technology in the last few decades has developed very rapidly. This control system using eye tracking technology can be done with eye movements for those who experience mobility problems. This research aims to develop a light control system through eye activity using the Mediapipe framework from Google. In this study, 2 lamps (A and B) were used, each with a light intensity of 10W. In lamp A, the light intensity can be controlled by turning the light on or off using the blink of the right eye and the blink of the left eye, while lamp B can adjust the intensity of the light by opening both eyes (right and left). Research on a lighting control system using the eye tracking method with an image processing system has been successfully carried out. All data generated is based on activity, distance, eye position on the camera and differences in participant backgrounds. Apart from that, a system that can work well means consistent results are obtained. However, based on distance, the system can read with precision at distances of 50 cm and 60 cm.

Comparative study of marker-based and markerless tracking in augmented reality under variable environmental conditions

Mon, 30 Dec 2024 00:00:00 +0000

Augmented reality (AR) technology integrates virtual content into real environments using two main methods: marker-based and markerless tracking. Marker-based tracking relies on printed markers for object placement, while markerless uses environmental features for flexibility and accuracy. This research aims to evaluate the combined impact of environmental factors-distance, angle, and lighting-on these two methods. The Multimedia Development Life Cycle (MDLC) methodology was applied by testing 72 combinations of indicators: distance (5-120 cm), angle (30°, 45°, 90°), and light color (red, blue, green, yellow) using Xiaomi Note 8 and Google Pixel 4. Results show markerless tracking is superior in all conditions, achieving a 94.4% success rate on both devices. In contrast, marker-based tracking only achieved 72.2% (Xiaomi Note 8) and 77.8% (Google Pixel 4). Markerless tracking was optimally performed from 50 cm away and up close, while marker-based tracking degraded in performance at long distances and red lighting. Markerless tracking proved to be more reliable and consistent, suitable for dynamic and diverse environments, while marker-based methods remained relevant for short distances and controlled lighting. These findings provide guidance for AR developers in choosing a tracking methodology according to application needs.