The detection of fetal brain abnormalities at an early stage has a significant impact with prenatal health care. The brain abnormalities arise a major concern for the lifelong problem in newborns. Early detection of fetal brain abnormalities helps clinicians to give extra care during pregnancy. They can plan the future treatment based on it. They can go for several tests, like fetal MRI to prepare for the appropriate treatment after birth. If these can be detected early and cure the impact these abnormalities can bring when they are grown-up. These abnormalities include cerebral palsy, developmental delays, and cognitive impairments. The existing methods for the detection of the fetal abnormalities at an early stage have less accuracy and are time consuming complex processes. Here we propose, a feasible multisensory framework-based system that helps to detect preliminary fetal brain abnormalities. The system involves sensors like Doppler Ultrasound, Fetal Electroencephalography (fEEG), Near-Infrared Spectroscopy (NIRS) and other imaging systems combined together with the multimodal approach to provide an insight on the brain growth and status. The Doppler Ultrasound sensor is used to identify fetal heart rate patterns, NIRS is used to measures oxygen levels in the brain, helping to detect low oxygen conditions that may harm brain development. fEEG is used to monitor brain activity non-invasively by capturing magnetic signals from the fetal brain by giving high-resolution insights on the neurological function. Other ultrasound imaging techniques are used to detect the physical abnormalities like ventriculomegaly, corpus callosum agenesis, and hydrocephalus. This proposed system uses AI models that work as an ensembled method which comprises of Convolutional Neural Network (CNN) and Long Short-Term Memory network (LSTM) for identifying the structural brain abnormalities. The system has been validated against sourced sample data sets and proved to provide a comparatively higher accuracy and better performance.

Hysterectomy is a common surgery performed to remove a woman’s womb (uterus). Monitoring health after a hysterectomy is also extremely important, especially if the ovaries are still present. Now, the functioning of the ovaries and their impact on a woman’s metabolism or cardiovascular health are still in question, which is why we proposed this study. The combination of wearable sensors and Artificial Intelligence helps with post-hysterectomy health monitoring, especially for women who retain their ovaries. Ovarian function remains vital for hormone balance, cardiovascular health, and metabolic regularity. As traditional approaches lose effectiveness over time, this novel approach explores data collection and AI-driven analytics to address these challenges.

The analysis of volatile organic compounds emitted by cell cultures provides a non-invasive method for monitoring metabolic and oxidative stress states. However, detection is challenged by low volatile organic compounds concentrations and high sample humidity. This study introduces an integrated system combining a MEMS-based pre-concentrator with an array of n-type metal-oxides chemiresistive gas sensors to analyze emissions from the K562 leukemia cell line. The main goal is to distinguish cellular volatile organic compounds signals from those of the culture medium. To achieve this, the pre-concentrator is used with different temperature-programmed desorption protocols to enhance signal intensity and improve discrimination performance.

The development of wearable devices continues to be a growing trend. Mobile health wearables market is extremely fast-moving since wearable ECG design demands increasingly complex features for manufacturers, such as size reduction, high accuracy, low weight, power efficiency, and good signal quality. The AD823X integrated circuits for ECG miniaturization, as an analog front-end (AFE), provide an amplified and filtered analog signal for subsequent digitization. The aim of this work is the development of expansion boards for portable ECG applications based on the AD823X microchip and the Arduino platform. This study includes three different circuit designs for specific ECG applications: cardiac monitor, ECG fitness and Holter monitor. It also presents designs using both AD823X integrated circuits. After performing tests with analog stage, the Atmega328 microcontroller was used for the analog-to-digital conversion of the ECG signals, and a miniaturized custom breakout board was developed for each ECG application, incorporating a CSR BC417143 chip for Bluetooth connectivity. The digitized signals can be transmitted by serial cable, via Bluetooth to a PC, or to an Android smartphone system for visualization. Other performed tests included measuring the noise induced during the analog-to-digital conversion stage of the Atmega328 microcontroller. This work evaluated, compared and determined the best of the applications proposed by the manufacturer of the AD8232X for a wearable ECG monitor, addressing the current needs of the devices and emerging trends in mobile health.

A health monitoring system plays a crucial role in every life. In the 21st century, advanced technologies like wearable sensors have emerged and make healthcare better overall. These sensors collect massive data about our health over time in many dimensions. In this paper, our objective is to develop and evaluate a machine learning-based clinical decision support system using wearable sensor data to accurately classify users’ physiological states and activity contexts. The most accurate and effective model is for identifying wearable sensor-based physiological signal classification. However, there are serious privacy and security issues with sending raw sensor data to centralized computers. We gathered the multivariate physiological and activity data from wearable technology, including smartwatches and fitness trackers, which make up the dataset. Physiological signals, including heart rate, resting heart rate, normalized heart rate, entropy of heart rate variability, and caloric expenditure, are all included in the dataset. Lying, sitting, self-paced walking, and running at different MET levels are examples of activity context labels. To secure our data, we proposed an architecture based on federated learning that helps machine learning model training across several dispersed devices without exchanging raw data. In this study, we used 8 classifiers, and these are XGBoost, RF, Extra Trees, LightGBM, CatBoost, Bagging, DT, and GB. It has been observed that XGBoost performs well in comparison to the other classifiers with an accuracy of 0.94, a precision of 0.90, a Recall of 0.89, an F1-score of 0.90, and an AUC-ROC of 0.98. This study demonstrates the potential of wearable sensor data, combined with machine learning, to accurately classify activity and physiological conditions. ML boosting family, especially XGBoost, exhibited strong generalization across diverse signal inputs and activity contexts. These results suggest that explainable, non-invasive wearable analytics can support early detection and monitoring frameworks in personalized healthcare systems. The proposed federated learning framework effectively combines privacy-aware computation and accurate classification using wearable sensor data.

The health and productivity of dairy cows are critical factors in sustainable livestock management. Along with the rapid rise in intelligence and technology, applying intelligence in livestock management helps in monitoring and provide precise and effective care for the cattle herd. This research designs an intelligent system that can assist the farmers and predict GIR cows' diseases and a support system powered by Artificial Intelligence (AI). The proposed system integrates Internet of Things (IoT) and sensors to track and monitor critical health parameters of the GIR cow, which includes the step count, lying time, rumination time, heart rate, and various environmental factors contributing to the well-being of the cow. The data points that are gathered from the sensors is then processed and analyzed using Machine Learning (ML) algorithms, including Random Forest (RF), Decision Tree (DT), Logistic Regression, K-Neighbors, and Support Vector Machine (SVM), to predict abnormalities including diseases such as lameness, mastitis, heat stress, and digestive problems. The AI techniques used in the system involve complex data processing and pattern recognition to identify early signs of diseases. The RF and DT ML models achieved the highest accuracy (100%), while SVM demonstrated robust performance with 94% accuracy. Integrating real-time monitoring with predictive analytics enables early detection of health issues, allowing timely interventions and improving overall herd management. The proposed system enhances cow welfare and optimizes farm productivity but also has the potential to revolutionize the dairy industry. The complex intelligent system provides a reliable and efficient platform for disease prediction and herd management, and can significantly contribute to the sustainability and profitability of dairy farming, thereby shaping the future of the industry.

Type 1 diabetes (T1D) management is increasingly enhanced by wearable glucose sensors (WGS) integrated with artificial intelligence (AI) that combine multiple physi-ological parameters—such as heart rate, galvanic skin response, body temperature, and physical activity—to predict glucose fluctuations more accurately. Noninvasive sensor technologies, including optical and sweat-based methods, show promise in reducing patient discomfort but still require further clinical validation to confirm reliability. Recent clinical data demonstrate significant potential for these advanced WGS technologies, with substantial improvements in glycemic control and overall disease management reported among all surveyed patients. Insulin pumps integrated with continuous glucose monitoring form “artificial pancreas” systems that automatically adjust insulin delivery in real time, improving patient convenience and metabolic out-comes. Despite progress, challenges remain related to response latency, device in-teroperability, and adaptation to abrupt physiological changes. According to our results, patient acceptance of WGS-based treatments is high, with nearly all individuals willing to adopt these technologies. Initial reluctance is mostly observed during the first weeks, coinciding with the AI algorithm’s calibration and learning phase; however, adherence increases significantly once this period concludes. In conclusion, these integrated technologies represent a practical shift toward personalized, proactive T1D care. Their successful implementation depends on over-coming technical and ethical challenges while addressing psychological factors such as alert fatigue, particularly in vulnerable populations.

Drones equipped with onboard cameras offer promising potential for modern digital media and remote sensing applications. However, effectively tracking moving objects in real time remains a significant challenge. Aerial footage captured by drones often includes complex scenes with dynamic elements such as people, vehicles, and animals. These scenarios may involve large-scale changes in viewing angles, occlusions, and multiple object crossings occurring simultaneously, all of which complicate accurate object detection and tracking. This paper presents an autonomous tracking system that leverages the YOLOv8 algorithm combined with a re-detection mechanism, enabling a quadrotor to effectively detect and track moving objects using only an onboard camera. To regulate the drone’s motion, a PID controller is employed, operating based on the target’s position within the image frame. The proposed system functions independently of external infrastructure such as motion capture systems or GPS. By integrating both positional and appearance-based cues, the system demonstrates high robustness, particularly in challenging environments involving complex scenes and target occlusions. The performance of the optimized controllers was assessed through extensive real-world testing, involving various trajectory scenarios to evaluate the system’s effectiveness. Results confirmed consistent and accurate detection and tracking of moving objects across all test cases. Furthermore, the system exhibited robustness against noise, light reflections, and illumination interference, ensuring stable object tracking even when implemented on low-cost computing platforms.

Strawberries, a high-value crop with growing demand, face increasing challenges from labour shortages, declining pollinator populations, and the limitations of inconsistent manual pollination. This paper presents an IoT-enabled robotic system designed to automate strawberry pollination in open-field raised-bed environments with minimal human intervention. The system consists of a mobile rover equipped with an ESP32-CAM for image capture and a robotic arm mounted on an Arduino Uno, capable of controlled X, Y, and Z positioning to perform targeted pollination. Images of strawberry beds are transmitted to a locally deployed server, which uses a lightweight detection model to identify flowers. System components communicate asynchronously via HTTP and I2C protocols, and the onboard event-driven architecture enables responsive behaviour while minimizing RAM and power usage, which is an essential requirement for low-cost, field-deployable robotics. The server also manages multi-rover scheduling through a custom priority queue designed for low-end hardware. In controlled load tests, the scheduler improved average response time by 6.9% and handled 2.4% more requests compared to the default queueing system, while maintaining stability. Preliminary field tests demonstrate successful flower identification and reliable arm positioning under real-world conditions. Although full system yield measurements are ongoing, current results validate the core design’s functional feasibility. Unlike previous systems that focus on greenhouse deployments or simpler navigation approaches, this work emphasizes modularity, affordability, and adaptability for small and medium farms, particularly in resource-constrained agricultural regions such as Sri Lanka. This study presents a promising step toward autonomous and scalable pollination systems that integrate embedded systems, robotics, and IoT for practical use in precision agriculture.

Ensuring precise trajectory tracking and stability in unconventional UAVs is a critical challenge in aerial robotics. This paper investigates a three-rotor UAV with complex underactuated dynamics and develops a nonlinear backstepping controller. The UAV model highlights the essential role of onboard sensors, since position and angular velocity measurements are fundamental for feedback and must be continuously exploited by the control law. Using these sensor-based signals in simulation, the proposed controller achieves accurate trajectory tracking, fast convergence, and stable behavior. The study emphasizes that sensor integration is crucial for enabling reliable autonomous flight of unconventional UAVs.