Electronic Engineering Polytechnic Institute of Surabaya

Battery management systems are essential in electric vehicles and renewable energy applications, especially in terms of ensuring optimal battery health and performance and regarding the state of charge (SOC) in batteries consisting of many cells. The lifetime and efficiency of the battery depend on the accuracy of the SOC parameter estimation. Moreover, systems that apply active balancing technology are able to move cells with high SOC data to cells with low SOC. Many methods have been developed, but their long execution time makes them less optimal when applied. High-speed SOC estimation is required in active balancing technology, in addition to high accuracy. Therefore, this study proposes the estimation of SOC parameters using a statistical and metaheuristic approach from voltage and current input data in each battery cell. The experimental results showed that the metaheuristic-based method (ANFIS) had better RSME and R2 values compared with the polynomial and linear regression or even the machine learning-based method (recurrent neural network) for training data.

Hypoxemia is a serious condition that requires oxygen transfusion. Indiscriminate oxygen administration is a poor strategy that can increase organ damage and even death. This paper describes a system for automatically controlling airflow of an oxygen tubes to a patient based on blood oxygen saturation and respiratory rate measurements. The MAX30102 sensor is used to measure oxygen saturation levels, and the MAX9814 module is used to determine respiratory rate. Both sensor outputs are processed by an STM32F411 microcontroller, and then sent wirelessly to an Arduino Uno microcontroller, which implements the fuzzy logic controller to control oxygen flow. The fuzzy output is used to activate a motor servo that controls the oxygen tube valve opening. The valve opening width (in degrees) is divided into 5 categories. Communication between the microcontroller and the valve actuator uses a 433MHz wireless RF module. The device test results revealed an MAE of 0.40% for oxygen saturation measurements compared to standard hospital measuring instruments and an MAE of 0.47% for respiratory rate measurements compared to manual measurements. Overall system testing produced a valve opening with an MAE of 0.56% compared to simulation results using MATLAB.

This data article presents a comprehensive dataset of 1,438 sputum smear microscopy images containing 11,447 ground-truth bounding-box labels for the detection of Mycobacterium tuberculosis. To address the scarcity of diverse real-world medical imaging data, the clinical specimens were captured using two distinct digital microscope camera systems (Hayear and Optilab). Instead of utilizing computational enhancements that may introduce synthetic biases, this dataset intentionally preserves the raw illumination and color characteristics of the slides. To facilitate robust model evaluation, the dataset includes a detailed metadata.csv file that categorizes each image based on its natural background color variation (e.g., Greenish, Bluish, Purplish/Pinkish, Yellowish) caused by differences in staining thickness and camera sensor responses. All annotations are natively formatted in the YOLO bounding-box format, making this dataset immediately viable for training, validating, and benchmarking automated object detection models for tuberculosis screening.

Many Indonesian farmers cultivating white-leg shrimp (Litopenaeus vannamei), especially in conventional and semi-conventional systems, depend on visual inspections and empirical knowledge to evaluate pond water quality. These farmers typically lack standardized protocols for quantifying essential parameters, including water temperature, pH, dissolved oxygen, and salinity. To address this issue, this research assessed the feasibility a site-specific water quality classification system as a proof-of-concept for conventional white-leg shrimp ponds in Surabaya, Indonesia, employing a Multi-layer Perceptron (MLP) model to prioritize detection of critical states aligned with regulatory standards. The approach follows standards from the Minister of Marine Affairs and Fisheries Regulation No. 75 of 2016, with Analytic Hierarchy Process (AHP) for parameter weights. Validation used 1075 samples from two ponds. Metrics encompassed accuracy, precision, recall, and F1-score, yielding an overall accuracy of 0.89 (95 % CI: 0.8465-0.9256) and a weighted-average F1-score of 0.89. The model performed for the 'Bad' class (precision: 0.93, 95 % CI: 0.8658-0.9647; recall: 0.95, 95 % CI: 0.8906-0.9780; F1-score: 0.94, approximate 95 % CI: 0.8740-1.0000; support: 106) and 'Good' class (precision: 0.88, 95 % CI: 0.7928-0.9336; recall: 0.84, 95 % CI: 0.7489-0.9024; F1-score: 0.86, approximate 95 % CI: 0.7559-0.9641; support: 87), supporting site-level risk assessment. Class imbalance, however, constrained performance for minority classes like 'Excellent' (precision: 0.74, 95 % CI: 0.5357-0.8753; recall: 0.77, 95 % CI: 0.5627-0.8970; F1-score: 0.76, approximate 95 % CI: 0.5217-0.9983; support: 22) and 'Very Bad' (precision: 0; recall: 0; F1-score: 0; support: 0), resulting in a macro-averaged F1-score of 0.64.

Speech emotion recognition (SER) is a crucial technology for applications such as human-computer interaction, mental health monitoring, and call centre analytics. However, SER research in Indonesia is still limited by a lack of annotated speech emotion datasets. In this study, we provided EEPIS’s Speech Emotion Recognition Audio Video Dataset (E-SERAVD), an Indonesian speech emotion recognition dataset that contains four basic emotions: Happy, Angry, Neutral, and Sad. The data obtained from the Indonesian movies and scenes were trimmed to capture emotional expressions. The dataset creation process was based on a model that has been widely used by previous researchers. In this case, the dataset creation begins with the process of defining the parameters and types of audio recordings to be targeted. The next step is data collection, followed by data cleaning. The data validation stage involved testing by three raters to prepare for the labelling process. The three raters’ observations showed satisfactory performance, with agreement scores of 88.8, 68.8, and 91.4%. The constructed dataset was evaluated using the inter-rater reliability metric, which showed a Fleiss Kappa value of 0.61. Therefore, it was included in the good category and was then determined. The final step is to separate the data for training and testing. The baseline model accuracy was evaluated with a value of 90% and F1 score of 86%. The E-SERAVD Dataset for Indonesian SER was prepared as an open-source dataset, with complete documentation and model benchmarks.