AI-Assisted Disease Monitoring Using Stretchable Polymer-Based Sensors

Unraveling the neural dynamics of mathematical interference in english reading: A novel approach with deep learning and fNIRS data

English has emerged as the predominant global language, driving efforts to optimize its acquisition through interdisciplinary cognitive research. While behavioral studies suggest a link between English learning and mathematical cognition, the neural mechanisms underlying this relationship remain poorly understood. To bridge this gap, the present study employs functional near-infrared spectroscopy (fNIRS) to construct a novel dataset on mathematical interference in English acquisition. Utilizing this dataset, a novel deep learning model named AC-LSTM is proposed, amalgamating Transformer and LSTM architectures to identify residual mathematical cognition during the English learning process. The AC-LSTM model achieves an exceptional accuracy rate of 99.8 %, surpassing other machine learning and deep learning models. Moreover, a multi-class classification experiment is conducted to discern algebra, geometry, and quantitative reasoning interference, with the AC-LSTM model achieving the highest accuracy of 75.9 % in this classification task. Furthermore, crucial brain channels for interference detection are pinpointed through grid search, and alterations in vital brain regions (R-Broca and L-Broca) are unveiled via association rule analysis. By integrating fNIRS, deep learning, and data mining techniques, this study delves into cognitive interference in English learning, providing valuable insights for educational neuroscience and data mining research.

Artificial intelligence in the management of metabolic disorders: a comprehensive review

This review explores the significant role of artificial intelligence (AI) in managing metabolic disorders like diabetes, obesity, metabolic dysfunction-associated fatty liver disease (MAFLD), and thyroid dysfunction. AI applications in this context encompass early diagnosis, personalized treatment plans, risk assessment, prevention, and biomarker discovery for early and accurate disease management. This review also delves into techniques involving machine learning (ML), deep learning (DL), natural language processing (NLP), computer vision, and reinforcement learning associated with AI and their application in metabolic disorders. The following study also enlightens the challenges and ethical considerations associated with AI implementation, such as data privacy, model interpretability, and bias mitigation. We have reviewed various AI-based tools utilized for the diagnosis and management of metabolic disorders, such as Idx, Guardian Connect system, and DreaMed for diabetes. Further, the paper emphasizes the potential of AI to revolutionize the management of metabolic disorders through collaborations among clinicians and AI experts, the integration of AI into clinical practice, and the necessity for long-term validation studies. The references provided in the paper cover a range of studies related to AI, ML, personalized medicine, metabolic disorders, and diagnostic tools in healthcare, including research on disease diagnostics, personalized therapy, chronic disease management, and the application of AI in diabetes care and nutrition.

Hepatitis nursing robot based on RP-lidarA1 sensor

BACKGROUND

To alleviate the workload of medical staff and provide personalized care for hepatitis patients, this study focuses on developing a hepatitis care robot.

OBJECTIVE

The objective of this study is to integrate the RP-lidarA1 sensor into a hepatitis care robot to achieve high-precision environmental perception, mapping, and navigation, thereby improving healthcare services.

METHODS

The RP-lidarA1 sensor was utilized for environmental scanning, and the MPU6050 chip was used to collect attitude data. An improved RBPF-SLAM algorithm was employed for high-precision map construction. For positioning and navigation, a combination of the A* algorithm and Dynamic Window Approach (DWA) algorithm was used to optimize path planning and obstacle avoidance.

RESULTS

Simulation experiments demonstrated that the improved algorithm reduced the number of particles to 50 in a 140 m2 area and shortened the map construction time to 1200 s. The A* algorithm effectively planned optimal paths, while the DWA algorithm improved navigation efficiency. Satisfaction surveys indicated that 92.4% of hepatitis patients and 81.8% of nurses were highly satisfied with the robot's performance.

CONCLUSIONS

The hepatitis care robot integrating the RP-lidarA1 sensor showed excellent performance in autonomous navigation, map construction, and obstacle avoidance, significantly enhancing the quality and efficiency of medical services.

Wearable bioelectronics based on emerging nanomaterials for telehealth applications

Nanomaterial-driven, soft wearable bioelectronics are transforming telemedicine by offering skin comfort, biocompatibility, and the capability for continuous remote monitoring of physiological signals. The devices, enabled by advanced zero-dimensional (0D), one-dimensional (1D), and two-dimensional (2D) nanomaterials, have achieved new levels in electrical stability and reliability, allowing them to perform effectively even under dynamic physical conditions. Despite their promise, significant challenges remain in the fabrication, integration, and practical deployment of nanoscale materials and devices. Critical challenges include ensuring the durability and stability of nanomaterial-based bioelectronics for extended wear and developing efficient integration strategies to support multifunctional sensing modalities. Telemedicine has revolutionized healthcare by enabling remote health monitoring. The integration of nanomaterials within wearable devices is a central factor driving this breakthrough, as these materials enhance sensor sensitivity, durability, and multifunctionality. These wearable sensors leverage various operating principles tailored to specific applications, such as intraocular pressure monitoring, electrophysiological signal recording, and biochemical marker tracking.

Intelligent Gesture Recognition Gloves for Real-Time Monitoring in Wireless Human-Computer Interaction

Flexible sensors mimic the sensing ability of human skin, and have unique flexibility and adaptability, allowing users to interact with intelligent systems in a more natural and intimate way. To overcome the issues of low sensitivity and limited operating range of flexible strain sensors, this study presents a highly innovative preparation method to develop a conductive elastomeric sensor with a cracked thin film by combining polydimethylsiloxane (PDMS) with multiwalled carbon nanotubes (MCNT). This novel design significantly increases both the sensitivity and operating range of the sensor (strain range 0-50%; the maximum tensile sensitivity of this sensor reaches 4.97), marking a breakthrough in flexible sensor technology. The sensor can also be fabricated easily and inexpensively which is suitable for large-scale production, indicating its significant application potential. Combined with a dedicated hardware and software system, the sensors enable real-time monitoring of the finger status and accurate gesture recognition. Furthermore, machine-learning algorithms were used to identify American Sign Language gestures with an accuracy of up to 97%. This innovative human-machine interface provides important support for the future development of intelligent interactive systems, and is of great significance in promoting the progress of advanced human-computer interaction technologies.

Portable Mini-Electrochemical Cell: Integrating Microsampling and Micro-Electroanalysis for Multipurpose On-Site Nitrite Sensing

In modern analytical chemistry, one of the primary goals is to develop miniaturized, easy-to-use sensing tools, particularly those with multitasking capabilities. In this work, we designed a mini-voltammetric cell that integrates a modified Au microelectrode (Au/Au NPs as the working electrode) and an Ag/AgCl reference electrode installed within a micropipette tip. This combined tool not only enables portable and on-site microvolume sampling─requiring only a microvolume (around 20-40 μL) or a single droplet─but also facilitates direct micro-electroanalysis in a short time. To evaluate its capabilities, the mini-voltammetric cell was optimized for trace analysis of nitrite ions and demonstrated linear responses in the ranges of 20-150 and 150-1200 μM, with an acceptable limit of detection (LOD) of 18.40 μM, meeting both WHO and EPA standards for nitrite levels. Furthermore, it exhibited high selectivity, stability (up to 36 continuous measurements with only a 3.24% signal drop), and acceptable repeatability (RSD of 2.98%, n = 15). The analytical performance of this miniaturized tool was further assessed through the sampling and detection of nitrite ions in various real samples with different matrixes: (1) urine samples, for the fast diagnosis of urinary tract infections (UTIs), where nitrite ions are detected as biomarkers of UTIs; (2) river water polluted with agricultural waste, where nitrite ions serve as pollutants from nitrogen fertilizers; and (3) on the hands and in forensic investigations, where nitrite ions are detected as indicators of gunshot residue, crucial in crime scene examinations. All real samples were analyzed using the standard addition method and recovery tests, yielding acceptable results. Additionally, the proposed mini-analytical tool was evaluated for its sustainability and applicability using two recognized metrics: The Green Analytical Procedure Index (GAPI) and the Blue Applicability Grade Index (BAGI). The results confirmed that this method can be classified as both a green analytical method and highly applicable. Finally, the practical results demonstrated that the proposed miniaturized electroanalytical tool exhibits reliable performance, high sensitivity and selectivity, and fast response in the on-site microanalysis of nitrite, without the need for any reagents or complex sampling steps, across different real samples (such as clinical, forensic, and environmental samples). We believe the proposed mini-voltammetric cell could be used as an alternative to current detection methods, and with suitable modifications, it could be adapted for the microanalysis of other applications and (bio)targets with small volumes in the near future.

AI-Assisted Insole Sensing System for Multifunctional Plantar-Healthcare Applications

The pervasive global issue of population aging has led to a growing demand for health monitoring, while the advent of electronic wearable devices has greatly alleviated the strain on the industry. However, these devices come with inherent limitations, such as electromagnetic radiation, complex structures, and high prices. Herein, a Solaris silicone rubber-integrated PMMA polymer optical fiber (S-POF) intelligent insole sensing system has been developed for remote, portable, cost-effective, and real-time gait monitoring. The system is capable of sensitively converting the pressure of key points on the sole into changes in light intensity with correlation coefficients of 0.995, 0.952, and 0.910. The S-POF sensing structure demonstrates excellent durability with a 4.8% variation in output after 10,000 cycles and provides stable feedback for bending angles. It also exhibits water resistance and temperature resistance within a certain range. Its multichannel multiplexing framework allows a smartphone to monitor multiple S-POF channels simultaneously, meeting the requirements of convenience for daily care. Also, the system can efficiently and accurately provide parameters such as pressure, step cadence, and pressure distribution, enabling the analysis of gait phases and patterns with errors of only 4.16% and 6.25% for the stance phase (STP) and the swing phase (SWP), respectively. Likewise, after comparing various AI models, an S-POF channel-based gait pattern recognition technique has been proposed with a high accuracy of up to 96.87%. Such experimental results demonstrate that the system is promising to further promote the development of rehabilitation and healthcare.

Incorporating Machine Learning Strategies to Smart Gloves Enabled by Dual-Network Hydrogels for Multitask Control and User Identification

Smart gloves are often used in human-computer interaction scenarios due to their portability and ease of integration. However, their application in the field of information security has been less studied. Herein, we propose a smart glove using an iontronic capacitive sensor with significant pressure-sensing performance. Besides, an operator interface has been developed to match the smart glove, which is capable of multitasking integration of mouse movement, music playback, game control, and message typing in Internet chat rooms by capturing and encoding finger-tapping movements. In addition, by integrating machine learning, we can mine the characteristics of individual behavioral habits contained in the sensor signals and, based on this, achieve a deep binding of the user to the smart glove. The proposed smart glove can greatly facilitate people's lives, as well as explore a new strategy in research on the application of smart gloves in data security.

Optical Microfiber Intelligent Sensor: Wearable Cardiorespiratory and Behavior Monitoring with a Flexible Wave-Shaped Polymer Optical Microfiber

With the advantages of high flexibility, strong real-time monitoring capabilities, and convenience, wearable devices have shown increasingly powerful application potential in medical rehabilitation, health monitoring, the Internet of Things, and human-computer interaction. In this paper, we propose a novel and wearable optical microfiber intelligent sensor based on a wavy-shaped polymer optical microfiber (WPOMF) for cardiorespiratory and behavioral monitoring of humans. The optical fibers based on polymer materials are prepared into optical microfibers, fully using the advantages of the polymer material and optical microfibers. The prepared polymer optical microfiber is designed into a flexible wave-shaped structure, which enables the WPOMF sensor to have higher tensile properties and detection sensitivity. Cardiorespiratory and behavioral detection experiments based on the WPOMF sensor are successfully performed, which demonstrates the high sensitivity and stability potential of the WPOMF sensor when performing wearable tasks. Further, the success of the AI-assisted medical keyword pronunciation recognition experiment fully demonstrates the feasibility of integrating AI technology with the WPOMF sensor, which can effectively improve the intelligence of the sensor as a wearable device. As an optical microfiber intelligent sensor, the WPOMF sensor offers broad application prospects in disease monitoring, rehabilitation medicine, the Internet of Things, and other fields.