International Journal of Advances in Applied Sciences
Not a member yet
668 research outputs found
Sort by
Battery temperature monitoring system using Arduino
Get PDFEnergy storage technologies are playing a key role in the modern world. The energy storage technologies are battery and ultracapacitors. This paper presents designing and implementing an Arduino-based battery temperature monitoring system for real-time battery temperature monitoring in a variety of applications, including industrial equipment, renewable energy systems, and electric cars. An Arduino microcontroller, temperature sensors, and optional display and communication modules make up the system. The Arduino receives temperature data from the sensors and processes it to provide information, send out alerts, and log data for further analysis. The technology provides an affordable and adaptable way to guarantee both the safety and best possible performance from batteries
Enhanced skin cancer classification via Xception model
Get PDFSkin cancer is a prevalent and deadly cancer, and early detection is crucial for improving treatment success. Intelligent technologies are currently being used to classify skin lesions. The fundamental goal of this experimental research is to investigate biomedical skin cancer datasets to develop an effective approach for determining whether a cancer is malignant or benign. Well-known deep learning classification models (convolutional neural network (CNN) (sequential), ResNet50, InceptionV3, and Xception) are employed to train and categorize the dataset images. Two large and balanced datasets are collected and employed in this research. One is used to compare the performance of the employed model algorithms. Next, the selected model(s) are again trained on the second dataset for validation and generalization purposes. It turns out that the performance of the Xception model is superior and can be generalized. The performance results obtained from various simulations are tabulated and graphed. Comparative results are also presented
Li-Fi technology for automated transport
Get PDFIndia is now one of the countries that is growing quickly worldwide. Today, practically for everything, a vehicle is necessary. Vehicle production is growing rapidly. One of the downsides of this enormous increase is the ineffective management of traffic. The well-planned expansion of transport organizations has resulted in a variety of challenges with travel. It is detrimental to both mankind and the economy when emergency vehicles like ambulances and fire engines are late in arriving. Smart transport is the most effective strategy to lower vehicle accidents and communicate with other cars to open a way for emergency vehicles. Here, the preliminary ideas and findings of a small-scale model of an automated transport system are presented using an innovative discovery known as Li-Fi, also known as light-fidelity. Full duplex communication is accomplished with Li-Fi, in which light is modified at speeds that are too rapid for the eye to follow. Li Fi may be used to create intelligent transportation systems since it offers various advantages over other communication protocols
Unveiling anomalies in industrial control systems: a kernel SHAP-based approach with temporal convolution autoencoder
Get PDFIndustrial control systems (ICS) are often the target of cyber-attacks, leading to undesirable consequences. ICSs operate without human supervision, making them vulnerable to adversaries. In recent years, numerous deep learning-based solutions have demonstrated their efficiency in detecting anomalies in ICSs. However, there is a lack of ability to pinpoint the sensors and actuators that contributed to the anomaly. In this research work, we use kernel Shapley additive explanations (SHAP) to explain anomalies detected by a temporal convolution autoencoder (TCAE). The proposed TCAE model handles the long-term dependency effectively and is computationally effective on a large dataset. A comprehensive explanation is provided, focusing on the feature that contributed to the anomaly for each identified attack. The SHAP values are extracted for each identified attack and visually depict the feature that contributed to the anomaly for each attack, helping the expert to handle the attack and build user trust
Generative adversarial network for intelligent haze removal from high quality images
Get PDFSuspended atmospheric particulates like haze, mist, and fog greatly degrade captured images, creating considerable challenges for computer vision applications operating in safety-sensitive areas such as autonomous driving, surveillance, and remote sensing. In this paper, we treat the important challenge of single-image haze removal by proposing a novel and robust conditional generative adversarial network (cGAN)-based framework. The proposal utilizes a U-Net-based generator with self-attention and skip connections to preserve spatial fidelity, and a PatchGAN discriminator to enforce local realism. At the heart of our contribution is a carefully weighted multi-component loss function that applies reconstruction, perceptual, edge, structural similarity (SSIM), and adversarial losses to optimize pixel-level accuracy and perceptual quality. We trained and evaluated our proposal on the large-scale real-world LMHaze dataset. Experimental results demonstrate state-of-the-art performance with a peak signal-to-noise ratio (PSNR) of 33.42 dB and SSIM of 0.9590. Our qualitative and comparative analyses further support our claims by assessing our proposed model's capacity to recover clear and artifact-free images from hazy images - outperforming the existing methods on this challenging real-world benchmark
Implementation of XGBoost for diabetes mellitus risk prediction based on health history
Get PDFDiabetes mellitus (DM) is a chronic disease with a growing global burden and specific challenges for early management, particularly in regions with limited access to healthcare. This study develops a web-based system to classify diabetes risk from medical history using extreme gradient boosting (XGBoost), an ensemble model of decision trees. The dataset comprised 520 respondents (320 DM, 200 non-DM) and underwent labeling, standardization, and an 80:20 train–test split, followed by hyperparameter selection via grid search and 5-fold cross-validation (CV). On the test set, the model achieved an accuracy of 0.9888, precision of 1.0000, recall of 0.9718, and an F1-score of 0.9857; discriminative performance was also strong with an area under the receiver operating characteristic curve (AUC ROC) of 0.839. These findings confirm that XGBoost effectively handles complex or imbalanced medical data while providing probabilistic outputs that are clinically meaningful. Deployed as a web application, the system can support early screening, triage, and clinical decision-making, thereby expediting referrals and personalizing interventions in primary care and hospital settings, especially in resource-constrained environments. This work lays the groundwork for further development, including the integration of explainable artificial intelligence (XAI) techniques to enhance clinical transparency
A review on ischemic heart disease prediction frameworks using machine learning
Get PDFIschemic heart disease (IHD) is a leading cause of mortality worldwide, calling for advanced predictive models for timely intervention. Current literature reviews on machine learning (ML)-based IHD prediction frameworks often focus on predictive accuracy but lack depth in areas like dataset diversity, model interpretability, and privacy considerations. Existing IHD prediction frameworks face limitations, including reliance on small, homogenous datasets, limited critical analysis, and issues with model transparency, reducing their clinical utility. This review addresses these gaps through a systematic, comparative analysis of popular ML models, such as random forest (RF) and support vector machines (SVM), noting their strengths and limitations. Key contributions include a qualitative examination of prevalent tools, datasets, and evaluation metrics, identification of gaps in dataset diversity and interpretability; and recommendations for improving model transparency and data privacy. Major findings reveal a trend toward ensemble models for accuracy but highlight the need for explainable artificial intelligence (AI) to support clinical decisions. Future directions include using federated learning to enhance data privacy, integrating unstructured data for comprehensive prediction, and advancing explainable AI to build trust among healthcare providers. By addressing these areas, this review aims to guide future research toward developing robust, transparent ML frameworks that can be more effectively deployed in clinical settings
Susceptibility of Aedes aegypti to malathion and permethrin insecticides in Enrekang Regency: an experimental study
Get PDFInsecticide resistance in Aedes mosquitoes can undermine arbovirus control efforts. Malathion and permethrin insecticides belong to the group of insecticides used for control and if used continuously will cause immunity of target mosquitoes. This study aims to assess the level of susceptibility of Aedes aegypti to insecticides commonly used in public health in the Enrekang Regency. The type of research used was experimental research. Female Aedes aegypti were collected from rearing results with a total sample size of 240 mosquitoes which were divided into 120 mosquitoes each in 4 treatments and 2 controls on malathion 0.8% and permethrin 0.25% insecticides. The results obtained from the research on insecticide susceptibility test results using malathion 0.8% in 60 minutes of exposure averaged 55% dead and exposure for 24 hours averaged 90% mosquito death, while permethrin 0.25% insecticide in 60 minutes of exposure averaged 90% dead mosquitoes and 24 hours exposure averaged 100% mosquito death, while for the control all live. The conclusion of the study was the susceptibility test of Aedes aegypti mosquitoes to malathion 0.8% insecticide in the category of moderate resistance while permethrin 0.25% insecticide in the category of susceptible
Sentiment analysis of vaccine data using enhanced deep learning algorithms
Get PDFThis paper investigates and experiments with an approach to improve sentiment analysis on vaccine datasets with deep learning. It evaluates random forest (RF), naïve Bayes (NB), and recurrent neural network (RNN) models across a variety of configurations, i.e., vector dimensions, pooling techniques, as well as evaluation methods, hierarchical SoftMax vs negative sampling. The results show that the model we proposed prevailed with an accuracy of 99.05% on a learning rate equal to 0.001, outperforming all other models based on metrics including precision, recall, and F1-score for benign/malignant cases. The results suggest that higher vector dimensions, average pooling, lowering the dropout rate, and employing hierarchical SoftMax for output significantly improve model performance. Hierarchical SoftMax performs better than negative sampling, whereas a lower dropout rate decreases overfitting and leads to improved generalization. Our results demonstrate the necessity to apply more sophisticated deep-learning tools around capturing nuances of public vaccine-related sentiment, which may be crucial for informing communication strategies and supporting decision-making in a real-world health emergency. The findings indicate that the performance of sentiment analysis with regard to COVID-19 vaccine deployment policy design and public monitoring could be enhanced by advanced deep learning algorithms
Enhancing artificial neural network performance for energy efficiency in laboratories through principal component analysis
Get PDFThis study investigates energy efficiency challenges during laboratory activities. Inefficient energy use in the practicum phase remains a critical issue, prompting the exploration of innovative forecasting models. This research employs artificial neural network (ANN) models integrated with principal component analysis (PCA) to predict energy consumption and optimize usage. The findings reveal that PCA components, including eigenvalues, eigenvectors, and matrix covariance values, significantly influence the ANN model's performance in forecasting energy production. The ANN training achieved a high correlation coefficient (R=1) with a mean squared error (MSE) of 0.045931 after 200,000 epochs, demonstrating the model's robustness. While testing results showed a moderate correlation (R=0.46169), the models demonstrated potential for refinement and scalability. This integration of ANN and PCA models provides a reliable framework for accurately forecasting energy usage, offering an effective strategy to enhance energy efficiency in laboratory settings. By optimizing energy consumption, this approach has the potential to reduce operational costs and environmental impact. The strong performance metrics highlight the practical utility of these models in educational contexts, contributing to sustainable energy management and better resource allocation. Furthermore, the reduction in energy-related environmental impacts underscores the broader applicability of these models for fostering sustainable development in similar contexts