Integrating the Internet of Things (IoT) in SPA Medicine: Innovations and Challenges in Digital Wellness

Computers, Journal Year: 2024, Volume and Issue: 13(3), P. 67 - 67

Published: March 6, 2024

Integrating modern and innovative technologies such as the Internet of Things (IoT) Machine Learning (ML) presents new opportunities in healthcare, especially medical spa therapies. Once considered palliative, these therapies conducted using mineral/thermal water are now recognized a targeted specific therapeutic modality. The peculiarity treatments lies their simplicity administration, which allows for prolonged treatments, often lasting weeks, with progressive controlled effects. Thanks to technologies, it will be possible continuously monitor patient, both on-site remotely, increasing effectiveness treatment. In this context, wearable devices, smartwatches, facilitate non-invasive monitoring vital signs by collecting precise data on several key parameters, heart rate or blood oxygenation level, providing perspective detailed treatment progress. constant acquisition thanks IoT, combined advanced analytics ML collection analysis, allowing real-time personalized adaptation. This article introduces an IoT-based framework integrated techniques tailored customer management more effective results. A preliminary experimentation phase was designed implemented evaluate system’s performance through evaluation questionnaires. Encouraging results have shown that approach can enhance highlight value significant contribution healthcare.

Language: Английский

---

An ensembled method for predicting dissolved oxygen level in aquaculture environment

Ecological Informatics, Journal Year: 2024, Volume and Issue: 80, P. 102501 - 102501

Published: Jan. 29, 2024

Dissolved oxygen (DO) level is an important indicator aquaculture quality. This study proposes ensembled method, WTD-GWO-SVR, combining wavelet threshold denoising (WTD), grey wolf optimization (GWO), and support vector regression (SVR) for accurately predicting DO levels. Addressing challenges such as high noise, poor data quality, non-linearity non-stationary properties of time series data, our method integrates SVR regression-based estimation, WTD denoising, GWO optimizing the parameters Gaussian kernel's radial basis function. We collected a dataset using variety low-cost sensors in real setting. Our comprehensive evaluation on demonstrates that WTD-GWO-SVR achieved mean squared error, absolute R2 values 0.38%, 3.81%, 99.73%, respectively. It also consistently outperformed back-propagation neural network long short-term memory model. superior computational performance compared to these methods. The throughput accuracy make it potential choice prediction water quality monitoring systems.

Language: Английский

---

AquaYOLO: Advanced YOLO-based fish detection for optimized aquaculture pond monitoring

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 20, 2025

Abstract Aquaculture plays an important role in ensuring global food security, supporting economic growth, and protecting natural resources. However, traditional methods of monitoring aquatic environments are time-consuming labor-intensive. To address this, there is growing interest using computer vision for more efficient aqua monitoring. Fish detection a key challenging step these vision-based systems, as it faces challenges such changing light conditions, varying water clarity, different types vegetation, dynamic backgrounds. overcome challenges, we introduce new model called AquaYOLO, optimized specifically designed aquaculture applications. The backbone AquaYOLO employs CSP layers enhanced convolutional operations to extract hierarchical features. head enhances feature representation through upsampling, concatenation, multi-scale fusion. uses precise 40 × scale box regression dropping the final C2f layer ensure accurate localization. test model, utilize DePondFi dataset (Detection Pond Fish) collected from aquaponds South India. contains around 50k bounding annotations across 8150 images. Proposed performs well, achieving precision, recall mAP@50 0.889, 0.848, 0.909 respectively. Our ensures affordable fish small-scale aquaculture.

Language: Английский

---

Enhancing Water Quality Management: Predictive Insights Through Machine Learning Algorithms

Environmental earth sciences, Journal Year: 2025, Volume and Issue: unknown, P. 171 - 180

Published: Jan. 1, 2025

Language: Английский

---

Anomaly Detection on Multivariate Sensing Time Series Data for Smart Aquaculture

Springer proceedings in business and economics, Journal Year: 2025, Volume and Issue: unknown, P. 273 - 283

Published: Jan. 1, 2025

Language: Английский

---

Enhancing Agricultural Practices Through Iot And Decision Tree Analytics: A Case Study On Autonomous Irrigation Management

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 233 - 242

Published: Jan. 1, 2025

Language: Английский

---

Deep learning applications in the Internet of Things: a review, tools, and future directions

Evolutionary Intelligence, Journal Year: 2024, Volume and Issue: unknown

Published: June 8, 2024

Language: Английский

---

Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China

Ecological Informatics, Journal Year: 2024, Volume and Issue: 84, P. 102854 - 102854

Published: Oct. 16, 2024

Language: Английский

---

Advancing Brain Tumour Detection and Classification: Knowledge Distilled ResNeXt Model for Multi-Class MRI Analysis

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Dec. 22, 2024

Accurate and timely diagnosis of brain tumors is crucial for optimal patient outcomes. Despite advancements in medical imaging deep learning, the accurate classification remains a significant challenge. Existing methods, including CNNs VGG16, often struggle to differentiate between tumor types capture subtle radiological features. To address these limitations, we propose novel Knowledge Distilled ResNeXt architecture. By transferring knowledge from complex teacher model, our model effectively learns discriminative features improves accuracy. Our comprehensive experiments demonstrate superiority classifying (glioma, meningioma, pituitary tumor, no tumor) compared state-of-the-art methods. This research contributes development more effective diagnostic tools improved care.

Language: Английский

---

Water Quality Index Prediction and Classification using Hyperparameter Tuned Deep Learning Approach

Global NEST Journal, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 8

Published: April 21, 2024

<p>Water quality (WQ) is hugely important for animals, humans, plants, industries, and the environment. In past few years, WQ has been compressed by pollution contamination. Usually, assessed utilizing costly laboratory arithmetical processes, making real observation ineffective. Whereas, poor wants a more cost-effective resolution. Water critical problem, so, it vital to generate method that estimates in order manage water notify users on occasion of recognition superiority. For effectual management, precisely estimate type. We use advantage machine learning (ML) models build model proficient forecasting index class. Therefore, this paper presents an automated Quality Index Prediction Classification using Hyperparameter Tuned Deep Learning (WQIPC-HTDL) Approach. The purpose WQIPC-HTDL technique WQI classify into multiple levels. technique, linear scaling normalization (LSN) approach used. Besides, long short-term memory (LSTM) employed prediction classification process. To enhance efficacy LSTM model, grasshopper optimizer algorithm (GOA) can be point out enhanced performance detailed simulation analysis was made. obtained values inferred rule when equated other models.</p>

Language: Английский

---