Recent progress in dielectric elastomers has been remarkable. As an actuator, it is now possible to lift an 8 kg weight by more than 1 mm at a speed of 88 ms with a dielectric elastomer of only 0.15 g. As a sensor, it is capable of measuring from 0.01 N to 1,400 N with a very thin and small device, and can also use moisture sensors, stretch sensors, and tactile feedback. Therefore, by effectively combining these sensors, it is possible to create a wearable system with a fairly realistic sensation. In addition, dielectric elastomers are inexpensive, lightweight, have a simple structure, can be multi-layered, and are highly efficient. In the future, they are expected to be applied in various industrial machines. In this study, we analyzed the factors that improve the performance of dielectric elastomers and considered measures for industrialization. Based on this, various systems that can be applied to wearables have been considered.
Breast cancer (BC) is a very common type of cancer in women, and it occurs due to the abnormal growth of breast cells to produce malignant tumors. The early detection of BC is challenging in clinical standards to reduce the fatality rate caused by this disease. Artificial intelligence is helpful in early and automated detection of BC and provides a cost-effective way to assist radiologists in providing better diagnostic decisions. The artificial intelligence (AI) model integrated with the Internet of Things (IoT) provides the framework for real-time analysis of patient data and tele-healthcare monitoring for detecting BC. This paper proposes a novel IoT-enabled deep learning-based approach implemented on an Android device to detect BC using thermal images. A deep convolutional neural network (CNN) architecture with five blocks of cascaded convolutions followed by max-pooling after each block and cascaded dense layers is formulated and trained using the Google Cloud central processing unit. The post-training quantization (PTQ) of deep CNN (DPCNN) is performed using floating-point 16-bit (FP16) and integer 8-bit (INT 8)-based quantization techniques. The reduced-size DPCNN model is deployed on a cloud framework and an Android device for real-time detection of BC using thermal images. The DPCNN model deployed on the Android device provides a portable framework for low latency, enhanced privacy, and offline processing compared to the cloud-based framework for detecting BC using thermal images. The experimental results obtained using a public database reveal that the proposed DPCNN has obtained the accuracy values of 99.63% and 99.27% for FP16 and INT8 cases to detect BC. The proposed DPCNN model has fewer parameters and higher classification performance than transfer learning and existing methods in detecting BC using thermal images.
Wearable technology is rapidly transforming health care by providing unprecedented opportunities for continuous, real-time health monitoring, proactive disease management, and early detection of health issues. This review delves into the diverse landscape of wearable devices, including smartwatches, fitness trackers, medical-grade biosensors, and intelligent textiles, with a particular focus on their role in managing chronic conditions, enhancing remote patient monitoring, and improving preventative care strategies. Unlike existing literature, this paper emphasizes the integration of artificial intelligence (AI) and machine learning (ML) with wearable technologies, offering groundbreaking predictive capabilities for early diagnosis, personalized treatments, and dynamic health interventions. Additionally, the paper addresses critical challenges that hinder widespread adoption, such as data privacy concerns, sensor accuracy, and the integration of wearable data within established healthcare systems. By synthesizing the current state and future trends in the field, this review offers novel insights into the technological, regulatory, and ethical considerations that must be overcome for the successful incorporation of wearables into mainstream health care. The paper concludes by proposing future avenues for innovation, particularly in sensor advancement, energy efficiency, and system interoperability, which will not only improve healthcare delivery but also make it more accessible to underserved populations worldwide.
Predicting the final grasp tendency at the start of movement in prosthetic hands is crucial for improved control. Biological data, such as 3D movement and muscle activity, have been using by researchers to predict the final grasp. Early prediction of the intended grasp allows the prosthetic device to initiate control actions before the motion is complete, resulting in faster and more intuitive responses. Most machine learning algorithms are trained to predict the gesture of the final grasp. The aim of this study is to accurately estimate the final grasp state using inertial measurement unit (IMU) data. This estimation, based on movement trajectories, will allow prosthetic devices to respond more quickly to user actions. Deep Learning model was trained using movement data collected from a prosthetic hand controlled certain gesture trajectories without any human involvement. Data such as acceleration, angular velocity, and orientation were gathered through IMU sensors to create 3D orientation matrices representing the movement process. A deep convolutional neural network was used for training, with data labeled by the final grasp states. The deep learning algorithm successfully predicted the final hand motion with 93% accuracy. This trained model enables the generation of smooth supervisory trajectories, facilitating faster and more accurate control of the prosthesis. The proposed model demonstrates significant potential in improving prosthetic hand control by predicting the final hand movement at an early stage of motion, contributing to more responsive and effective prosthetic devices.
As robotic technology advances towards autonomy and intelligence, tactile sensing systems have become a key technology for overcoming the bottleneck of environmental interaction. Unlike visual perception, which captures macroscopic information, tactile sensing provides precise mechanical feedback for robotic manipulation by real-time analysis of microscopic physical parameters such as contact force, material properties, and surface morphology. This is particularly important in application scenarios that require high precision in force control, such as minimally invasive surgery and precision assembly, where the sensitivity, multimodal perception capabilities, and environmental adaptability of tactile sensors directly determine the operational performance of the robotic system. However, traditional tactile sensors are limited by rigid structures, limited sensitivity, and a single perception modality, making it difficult to meet the demands of complex interactions. In recent years, breakthroughs in flexible electronic materials, biomimetic microstructure design, and multimodal sensing integration technologies have provided innovative opportunities for tactile sensing systems. This review provides a detailed overview of the key technological advancements in tactile sensors and their applications in robotic surfaces, analyzes the major challenges currently faced, and looks ahead to future development directions, particularly the potential in flexible materials and intelligent algorithms.
This contribution aims to analyze the hostile side effects of electromagnetic fields on living tissues as well as smart health tools that work in proximity to living tissues. These include medical intervention tools, wearable devices, and imaging scanners. The evaluation, control, and protection against these adverse effects are also targeted. The implicated physics and their corresponding ruling mathematics are highlighted and discussed. Mathematical modeling using discretized local 3D numerical tools allowed the design, control, and validation of the durability of the devices. These different themes are supported by illustrated cases and an overview of bibliographic examples. The results of the investigation illustrate that the physical events involved in the origins of radiation and stray fields, as well as their adverse effects on exposed materials and their protection, allow a thorough understanding and control of their management. Moreover, the corresponding mathematical formulations dictating the behaviors of the involved fields allow their assessment according to Responsible Attitude and One Health approaches that enable ecological biodiversity and ecosystem.
Antennas are an important part of the current ecology of wireless communication, particularly as it concerns Wi-Fi data rates. The traditional antennas suffer from the issues of urban bandwidth constraints and material efficiency. These issues lead to bad performance and coverage of services. The proposed work outlines a distinctive rectangular patch antenna designed on the photonic crystal structure and partial ground plane at the frequency of 2.4 GHz Wi-Fi band (2.4–2.48 GHz). The antenna is constructed on 40 mm by 50 mm FR4 substrate with εr = 4.3, tan δ = 0.025, 1.6 mm thick and excite by 50-ohm microstrip inset-feed to provide the optimal impedance matching. It is carried out using CST Microwave Studio Suite 2024 in terms of the design, simulation, and performance assessment. It is remarkable that the antenna has VSWR of 1.039064, returnloss (S11) of −34.26823 dB,andbandwidthof 180.043MHz(2.314581 GHzto 2.494624GHz).It wouldserveas anexcellent choice in many Wi-Fi applications because of its incredible gain of 2.86 dBi, directivity of 4.61 dBi, and a radiation efficiency of 66.88 percent. The compact size, the wide bandwidth, and the effective signal transmission characteristics of the proposed antenna make it easy to incorporate into the smart home systems of consumer electronics and numerous devices of the Internet of Things. This research aims at making the performance and reliability of current wireless communication network in dynamic environment better and reliable through the provision of a scalable solution.
Fabric-based strain sensors hold significant potential across various applications, including sports, healthcare, rehabilitation, etc. Nonetheless, their complex performance under large deformation and varying loading rates, arising from material viscoelasticity and textile structure intricacies, remains inadequately understood. The primary constraint in evaluating their performance lies in the absence of electromechanically coupled instrumentation. This paper endeavors to overcome the limitation by developing a synchronized measurement system, which integrates mechanically controlled loading, voltage divider circuits, and visual measurement technologies. This system enables synchronized acquisition of mechanical and electrical signals spanning from 0.01 mm/min to 6 m/s, by employing material testing machines for low-speed loading and split Hopkinson pressure bars for medium-to-high-speed loading, and combining electrical performance measurements with displacement and strain field analyses. Experiments revealed that sensor sensitivity increased linearly with the logarithm of loading rates, while deformation patterns evolved with loading speed, thereby offering valuable insights into design and calibration of fabric-based strain sensors under dynamic conditions.
Numerous industries consider their needs ultra-high accuracy with regard to an artificial intelligence (AI)-detected object and pose a challenge with real-world variations. This study specifically focuses on industrial manufacturing lines, where quality control is critical. The methods we discuss here should be transferable to other industry domains with similar constraints, such as logistics or packaging. The primary objective is to achieve greater than 99.9% accuracy with object detection in real-time industrial environments, without significantly impacting the latency. For that, we worked on an SSD_MobileNet model that was refined to the utmost precision and implemented alongside a dual-model system that used a generalist surrogate trained on blurred synthetic images. To achieve blur efficacy, the second model had to be blur trained, blending contextual depth and resilience. Both models’ outputs are fused through a low-computational-cost, high-confidence detection using Intersection over Union metrics selection (>=0.8) to strike a balance between efficiency and detection reliability. Model fusion has better results compared to model stacking or score-based thresholds because it decides on the best detection by considering the spatial overlap of detections and the agreement of class IDs. On the Nvidia Jetson Orin NX platform, deploying this ensemble achieved 99.8% accuracy and further boosted the system to 99.97% without expanding inference passes. Smart dual-model implementation helps increase precision and fault-tolerant parameters while maintaining streamlined recalibrated embedded systems thresholds, proving non-breach. This work supports the shift toward AI-powered advanced industrial surveillance, and research focuses on multidisciplinary approaches toward precise, reliable object detection.
Guided by such relentless scientific curiosity, the field of wearable diagnostics has evolved from experimental concepts into sophisticated, organ-centric platforms capable of capturing rich physiological and biochemical data in real time. This review encapsulates the interdisciplinary transformation wherein bioelectronics, materials science, and artificial intelligence (AI) converge to create next-generation wearables that intimately interface with organs such as the brain, eyes, heart, skin, and lungs. Graphene-based imperceptible e-skins now enable neuromuscular signal acquisition with angular resolutions approaching ∼4° and signal fidelity exceeding traditional Ag/AgCl electrodes. AI-enhanced electroencephalographic (EEG) headbands decode motor intent with >92% accuracy in under 2 s, paving the way for real-time brain–computer interactions. Simultaneously, noninvasive microneedle arrays and sweat-interfacing chemosensors demonstrate femtomolar sensitivity for glucose, lactate, and even nucleic acids, boasting >80% correlation with gold-standard clinical assays. The domain has experienced a >60% increase in advanced functional materials-PEDOT: PSS hybrids, MXenes, oxide nanosheets-and a >70% rise in mechanical adaptability and miniaturization, dramatically expanding diagnostic possibilities in ambulatory environments. Dry electrode systems in smart eyewear, epidermal patches, and Virtual Reality (VR)-integrated systems now maintain <1.13 μV Root Mean Square (RMS) noise levels, 98–99% classification accuracy, and uninterrupted operation exceeding 12 hours, even in motion-rich conditions. As these intelligent, autonomous devices continue to shrink the gap between biological and digital systems, they are poised not merely to monitor health but to redefine human–machine symbiosis in the era of predictive and personalized medicine.