Human Detection Research Articles

Ultralow limit human IgG detection with 2H-MoS2/L-cysteine based plasmonic fiber-optic spectral combs

The detection of human immunoglobulin G (human IgG) provides crucial evidence in diagnosis of infectious diseases and monitoring of therapeutic effects. Here, we propose a plasmonic fiber-optical surface plasmon resonance (SPR) based sensor to realize the ultralow limit human IgG detection. The proposed sensor is fabricated by attaching a mixture of 2H-MoS2 nanosheets with L-cysteine on a gold-coated tilted fiber Bragg grating. The 2H-MoS2 possesses a large specific surface area, where the L-cysteine can enhance the stability of antibody modification. The composite membrane of 2H-MoS2 and L-cysteine can adsorb more probe rabbit anti-human IgG, which can improve sensitivity of the proposed sensor. The experimental results show that the proposed sensor exhibits a response time of approximately 220 s and a sensitivity of 0.11 dB/(ng/ml). The limit of detection of 0.87 ng/ml of the proposed sensor is one order of magnitude lower than those of other fiber-optic SPR human IgG sensors.

High strength, high sensitivity, hydrophobic and conductive vegetable oil-based composites for human motion detection

The vulnerability of infants and young children due to their fragile bodies and inability to effectively express physical discomfort has raised widespread of concern in the society. As it continues to be difficult to develop sensors with superior mechanical qualities and response sensitivity for use in health monitoring and recognition. Here, a polymer known as, Polyurethane Thermoplastic Elastomer, enhanced by crosslinking which is prepared from Isophorone Diisocyanate (IPDI), soybean oil polyol ED, and polycaprolactone triol (PCT-L) also referred to as PTIED, was prepared based on previously prepared soybean oil polyol ED and polycaprolactone triol (PCT-L) as soft segments, with IPDI as hard segments. This was followed by the preparation of the PTIED-CNT sensor by using PTIED as a matrix and hydroxyl carbon nanotubes (CNT) as a conductive filler. The mechanical properties of the obtained PTIED-CNT sensor have been enhanced, with a tensile strength of approximately 5 MPa. The sensitivity GF of the PTIED-CNT7 % can reach up to 805.67 and remains stable after 4500 seconds of continuous operation at 10 % strain. Moreover, the device can support high stability in a simulated sweat environment and exhibit antibacterial and hydrophobic, which could be used to check for small movements, such as those of the face and throat, and could also recognize sound. Therefore, its potential applications in respiratory monitoring of infants as well as other health monitoring applications are expected.

Magnetron sputtering preparation of flexible ZnO/AlN thin-films sensors with hybrid piezoelectric effect for broad-range human motions detection

Wearable sensors with excellent comfort, flexibility and fast response are widely applied in human-machine interactions, artificial skin, motion detection and healthcare monitoring. However, preparation processes of the most of current piezoelectric sensors are relatively expensive and complicate, limiting their mass productions in the applications. This work demonstrates the superior piezoelectric performance and stability of ZnO/AlN flexible thin films prepared by magnetron sputtering for broad-range human motions detection, and first-principles calculation are applied to reveal the complicate piezoelectric effect of the hybrid system. The ZnO/AlN hybrid thin films sensor exhibits superior piezoelectric performance and excellent reliability, with presenting high outputs voltage (3.63 V), high degree of response speed (42.33 ms), water stability and robust performance upon 10000 cycles. First-principles calculations reveal that formation of the ZnO/AlN interface facilitates charge transport and improves efficiency of carrier transport, and results in reduced in band gap and enhanced electrical conductivity. By applying the sensors in human health monitoring, the underlying behaviors can be determined by output voltage of the sensor in real-time. This work offers a sensitive, simple structured and robust solution for human motion detection.

Affordable energy-saving switch control system for homes with disabled persons

The need for energy conservation has become increasingly urgent in today's world, especially as energy costs continue to rise and the demand for sustainable living grows. For persons with physical disabilities, simple tasks like turning light switches on and off can be challenging, resulting in higher energy usage, increased electricity bills, and increased physical strain. Existing solutions often prioritize energy efficiency but overlook affordability and accessibility, making them impractical for low-income households. To address these issues, this paper proposes an affordable automated energy-saving lighting switch control system using Arduino Uno, ultrasonic sensors for human presence detection, and a relay to control lighting. A person-counter mechanism ensures accurate operation based on room occupancy. Experimental results shows that the proposed system achieves 100% accuracy in detecting human presence in a room, effectively reducing energy consumption from 0.4 kWh to 0.2 kWh per day, which corresponds to 50% energy savings. Additionally, it is 42.41% less expensive than the most affordable system compared in the paper. These findings underscore the system’s potential to offer an affordable, accessible, and energy-efficient solution that enhances the convenience and comfort of disabled persons while contributing to energy conservation efforts.

TCFormer: Visual Recognition via Token Clustering Transformer.

Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token distribution disregards the semantic meaning of different image regions, resulting in sub-optimal performance. To address this issue, we propose the Token Clustering Transformer (TCFormer), which generates dynamic vision tokens based on semantic meaning. Our dynamic tokens possess two crucial characteristics: (1) Representing image regions with similar semantic meanings using the same vision token, even if those regions are not adjacent, and (2) concentrating on regions with valuable details and represent them using fine tokens. Through extensive experimentation across various applications, including image classification, human pose estimation, semantic segmentation, and object detection, we demonstrate the effectiveness of our TCFormer.

Vision-based approach for human motion detection and smart appliance control

This study focuses on the use of computer vision technology and motion detection sensors to create an intelligent system that recognizes human presence in monitored spaces. The system uses a relay module for automation and control of household appliances while sensing motion detection, operated by an ESP32 microcontroller. This innovative solution addresses two major issues in home automation: reliable human presence recognition and seamless appliance control. The research merges a camera-based vision system with motion sensors, comparing motion and vision-based identification. The ESP32 microcontroller improves motion detection precision and context awareness by integrating motion sensors and computer vision technologies. The integration of a camera module allows real-time analysis and recognition of human presence, reducing false alarms. The relay module also enables automated control of home appliances, synchronizing and feedbacking operations with sensed human presence. The dynamic adaptation of the system improves user convenience and energy efficiency.

Human performance in detecting deepfakes: A systematic review and meta-analysis of 56 papers

Deepfakes are AI-generated media designed to look real, often with the intent to deceive. Deepfakes threaten public and personal safety by facilitating disinformation, propaganda, and identity theft. Though research has been conducted on human performance in deepfake detection, the results have not yet been synthesized. This systematic review and meta-analysis investigates human deepfake detection accuracy. Searches in PubMed, ScienceGov, JSTOR, Google Scholar, and paper references, conducted in June and October 2024, identified empirical studies measuring human detection of high-quality deepfakes. After pooling accuracy, odds-ratio, and sensitivity (d') effect sizes (k = 137 effects) from 56 papers involving 86,155 participants, we analyzed 1) overall deepfake detection performance, 2) performance across stimulus types (audio, image, text, and video), and 3) the effects of detection-improvement strategies. Overall deepfake detection rates (sensitivity) were not significantly above chance because 95% confidence intervals crossed 50%. Total deepfake detection accuracy was 55.54% (95% CI [48.87, 62.10], k = 67). For audio, accuracy was 62.08% [38.23, 83.18], k = 8; for images, 53.16% [42.12, 64.64], k = 18; for text, 52.00% [37.42, 65.88], k = 15; and for video, 57.31% [47.80, 66.57], k = 26. Odds ratios were 0.64 [0.52, 0.79], k = 62, indicating 39% detection accuracy, below chance (audio 45%, image 35%, text 40%, video 40%). Moreover, d' values show no significant difference from chance. However, strategies like feedback training, AI support, and deepfake caricaturization improved detection performance above chance levels (65.14% [55.21, 74.46], k = 15), especially for video stimuli.

TPU-Supported Ti3C2Tx/TiO2/Ru electrospun mat towards flexible and multi-functional sensors for human motion and NH3 detection

Nowadays, the demand for smart wearable devices has been increasing significantly. Integrating multiple functions into a single sensor has become a continuous challenge for researchers. To address these issues, a novel two-dimensional material, MXene (Ti3C2Tx), is now being utilized to fabricate flexible multifunctional sensors. TPU (thermoplastic polyurethane) fiber mats are prepared through electrospinning. Using TPU fiber mats as the substrate, MXene/TiO2/Ru composites are synthesized through a simple and effective method and loaded onto the fiber mats. Experimental tests have revealed that the TPU/MXene/TiO2/Ru flexible sensor exhibits characteristics such as a large stretching range, good durability, high sensitivity, and excellent breathability. The response of the TPU/MXene/TiO2/Ru flexible sensor can reach up to 80.4 k when it is stretched to 120 % of its original length at a stretching speed of 0.5 mm/s. Moreover, this sensor can be used to detect movements in human wrists, arms, faces, legs, fingers, and even vocal cord vibrations, responding to voice recognition through specific word combinations. Furthermore, this sensor exhibits a maximum response of 15.06 % to 100 ppm NH3 at room temperature, accompanied by high selectivity and stability, indicating its excellent multifunctionality in the fields of human health and environmental protection.

Short-Wave Infrared (SWIR) Imaging for Robust Material Classification: Overcoming Limitations of Visible Spectrum Data

This paper presents a novel approach to material classification using short-wave infrared (SWIR) imaging, aimed at applications where differentiating visually similar objects based on material properties is essential, such as in autonomous driving. Traditional vision systems, relying on visible spectrum imaging, struggle to distinguish between objects with similar appearances but different material compositions. Our method leverages SWIR’s distinct reflectance characteristics, particularly for materials containing moisture, and demonstrates a significant improvement in accuracy. Specifically, SWIR data achieved near-perfect classification results with an accuracy of 99% for distinguishing real from artificial objects, compared to 77% with visible spectrum data. In object detection tasks, our SWIR-based model achieved a mean average precision (mAP) of 0.98 for human detection and up to 1.00 for other objects, demonstrating its robustness in reducing false detections. This study underscores SWIR’s potential to enhance object recognition and reduce ambiguity in complex environments, offering a valuable contribution to material-based object recognition in autonomous driving, manufacturing, and beyond.

Load-and-go molecular diagnostics for human papilloma virus detection

The present study describes analytical and clinical performance of the HPV 16 & 18 assay for the detection of HPV specific DNA with near point-of-care utility. A room temperature compatible real time PCR test was developed for detection and discrimination of HPV 16/18 in a single tube. The test was integrated and validated on Compact series automated platform for analytical performance (sensitivity, specificity, accuracy). The clinical evaluation was performed on cervico-vaginal specimens. The analytical sensitivity data showed dynamic range from 50 IU/mL to 1´106 IU/mL using NIBSC international standard (19/224 for HPV16 and HPV18). The test was found to be highly specific for both the HPV targets with no cross reactivity against other HPV genotypes (high and low risk) and similar pathogens. The clinical performance on cervical sampling indicated up to 100% agreement with a comparator test method. The HPV 16 and 18 detection assay employing an integrated automated system offers low to high-throughput analysis with a cost-effective, pipette-free approach, eliminating the need for molecular infrastructure and technical expertise. This test named “HPV 16 and 18 detection kit” has been approved by Central Drugs Standard Control Organisation (India) for commercial utility, and would have significant implications for mass screening of cervical cancer.

Highly breathable and stretchable strain sensors based on porous films for human motion and gas detection

With the rapid development of flexible wearable sensors in the fields of medical detection and environmental monitoring, it is urgent to develop multifunctional sensors with high sensitivity, fast response, wide sensing range, excellent comfort and multi-stimulus response. In this paper, a porous thermoplastic polyurethane (TPU) film with high stretchability and breathability was prepared by facial liquid phase separation, and a flexible wearable sensor was developed through vapor deposition of polypyrrole (PPy) within the porous TPU film matrix. The fabricated sensor can detect pressure, strain and gas, has a wide pressure detection range (up to 98 kPa), fast response speed (100 ms), sensitivity of up to 0.33 kPa−1 and working stability. Furthermore, it has an extremely high tensile strength of 790 % and can operate in the 0–400 % stretch range with a maximum sensitivity of 238.2. Importantly, the flexible porous TPU/PPy multifunctional sensor has excellent breathability and the capability to monitor NH3 gas, and the gas detection limit can reach 10 ppm. This work provides a new route for achieving high-performance and wearing comfortable strain sensors with broad application prospects in human activity detection and NH3 gas monitoring devices.

Flexible pressure sensor based on CNTs/CB/PDMS sponge with porous and microdome structures for sitting posture discrimination

The application fields of flexible pressure sensors are constantly expanding benefiting from their characteristics of being lightweight, flexible, easy to install, etc. Various structures have been developed for the purpose of improving the sensing performances of these sensors. However, the traditional structure designs typically enhance only a single aspect of performance. In this study, a flexible pressure sensor based on carbon nanotubes (CNTs)/carbon black (CB)/polydimethylsiloxane (PDMS) conductive sponge (CCPS) with both porous and microdome dual microstructures is prepared through the double template and swelling ultrasound methods. The introduction of two microstructures leads to the synergistic effect of dual sensing mechanisms, and the dual sensing mechanisms have been discussed according to the changes in microstructure morphology and finite element analysis results. Thanks to the synergistic effect of dual sensing mechanisms, CCPS exhibits comprehensive pressure sensing performances including a wide pressure sensing range of more than 350 kPa, high sensitivity under low pressure (7.10 kPa−1 over 0–25 kPa, 2.96 kPa−1 over 25–135 kPa, 1.09 kPa−1 over 135 kPa), and satisfactory long-term using performance of over 2000 cycles. CCPS is finally demonstrated for applications such as human motion detection, Morse code, and sitting position discrimination, indicating its broad application possibilities.

Human key point detection method based on enhanced receptive field and transformer

The existing key point detection network models have complex structures, so it is difficult to deploy on edge devices. Meanwhile, the convolution is localized and limited by the size of convolution kernels, which cannot effectively capture long-range dependencies. To address this problem, this paper introduces a lightweight Convolutional Transformer network (LHFormer Net) for human pose estimation. Considering that the sampling area of convolution kernels for different dimensional feature maps is fixed and the contextual information is singular, the enhanced receptive field block is designed to extract richer feature information and reduce information loss in feature maps. Based on the global modeling features of Transformer encoder, convolutional position encoding and multi-head self-attention are used to capture the spatial constraint relationship between key points in the deep feature extraction. Finally, a lightweight deconvolution module is used to generate higher resolution features to achieve multi-resolution supervision, which can effectively solve the problem of scale variation in pose estimation, more accurately locate key points of small and medium-sized people, ad further improve the detection accuracy of the network. Compared with other networks, the experimental results on the open access datasets COCO2017 and MPII show that the proposed network achieves a good balance between model complexity and detection performance.

Self-healing and transparent ionic conductive PVA/pullulan/borax hydrogels with multi-sensing capabilities for wearable sensors

Conductive hydrogels as wearable sensors have been used for numerous applications in human motion detection, personal healthcare monitoring and other diverse scenarios. However, it remains a challenge to integrate self-healing ability, multiple sensing capabilities, and transparency in one single unit. In this work, multifunctional polyvinyl alcohol (PVA)/Pullulan/Borax conductive hydrogels were fabricated by introducing borate ester bonds and hydrogen bonds. The described hydrogels showed fast self-healing properties, which could autonomously completely recover within 15 s. The hydrogels possessed high optical transparency (92.9%) in the visible light range and had multi-sensing capabilities, such as strain, temperature and humidity sensing. The assembled hydrogel sensor displayed a high strain sensitivity of 2.74 within the strain range of 300%, and it could be used to monitor human motions such as finger and wrist bending. In addition, the hydrogel sensor could sense temperature variations with a temperature coefficient of resistance of −0.914 °C−1 over 28–46 °C. Besides, the hydrogel sensor demonstrated the humidity sensing ability and can recognize human inhale and exhale. The overall sensing performance of the PVA/Pullulan/Borax hydrogel was satisfactory and repeatable. This conductive hydrogel shows great potential in wearable electronics and personal healthcare and inspires a new generation of multifunctional hydrogel sensors.

Complex Indoor Human Detection with You Only Look Once: An Improved Network Designed for Human Detection in Complex Indoor Scenes

Indoor human detection based on artificial intelligence helps to monitor the safety status and abnormal activities of the human body at any time. However, the complex indoor environment and background pose challenges to the detection task. The YOLOv8 algorithm is a cutting-edge technology in the field of object detection, but it is still affected by indoor low-light environments and large changes in human scale. To address these issues, this article proposes a novel method based on YOLOv8 called CIHD-YOLO, which is specifically designed for indoor human detection. The method proposed in this article combines the spatial pyramid pooling of the backbone with an efficient partial self-attention, enabling the network to effectively capture long-range dependencies and establish global correlations between features, obtaining feature information at different scales. At the same time, the GSEAM module and GSCConv were introduced into the neck network to compensate for the loss caused by differences in lighting levels by combining depth-wise separable convolution and residual connections, enabling it to extract effective features from visual data with poor illumination levels. A dataset specifically designed for indoor human detection, the HCIE dataset, was constructed and used to evaluate the model proposed in this paper. The research results show that compared with the original YOLOv8s framework, the detection accuracy has been improved by 2.67%, and the required floating-point operations have been reduced. The comprehensive case analysis and comparative evaluation highlight the superiority and effectiveness of this method in complex indoor human detection tasks.

Skin‐Like Soft Thermoelectric Composites with a “J‐Shaped” Stress–Strain Behavior for Self‐Powered Strain Sensing

AbstractPolymer thermoelectric (TE) materials present a promising alternative to actuating low‐power wearable electronics without an additional power source, among which poly(3,4‐ethylenedioxythiophene) (PEDOT):poly(styrenesulfonate) (PSS) is a promising candidate. However, it is too hard and brittle to integrate into wearables seamlessly and comfortably. Herein, PEDOT:PSS‐based TE composites with simultaneous softness and stretchability are fabricated by a water‐borne polyurethane (WPU) and PEDOT:PSS mixture containing the judiciously chosen ionic liquid (IL) and subsequent drop casting. The obtained composites show a stable TE voltage, high stretchability (>500%), ultra‐flexibility, and excellent sensitivity (gauge factor = 1251). More importantly, it exhibited “J‐shaped” stress–strain curves resembling human skins after a loading/releasing treatment. The skin‐like nonlinear elastic behavior combines enough softness in the “toe” region, high stretchability, and a strong strain hardening at the late deformation stage, enabling its seamless and comfortable integration with the human body. Given the desired mechanical performance and strain‐sensing capability, the composite is designed to serve as a self‐powered sensor with high sensitivity and accuracy, suggesting a high potential in human motion detection. This work demonstrates the versatility of the developed skin‐like PEDOT:PSS‐based composites in wearable electronics.

Carbon Quantum Dot/Multiwalled Carbon Nanotube-Based Self-Powered Strain Sensors for Remote Human Motion Detection

Carbon Quantum Dot/Multiwalled Carbon Nanotube-Based Self-Powered Strain Sensors for Remote Human Motion Detection

Sodium-dependent glucose co-transport proteins (SGLTs) are not involved in human glucose taste detection

The sweet taste of saccharides, such as sucrose and glucose, and other sweeteners is known to result from activation of the TAS1R2/R3 receptor expressed in taste receptor cells (TRCs) of the taste bud. Recent reports have suggested the existence of an additional sweet taste signaling pathway for metabolizable saccharides that is dependent on the activity of glucose transporters, especially SGLT1, also expressed in TRCs. We have investigated the potential contribution of SGLT1 to glucose taste signaling in humans. Concentration-response analysis of glucose mediated changes in membrane potential measured in Chinese hamster ovary (CHO) cells transiently expressing the human SGLT1 (hSGLT1) yielded an EC50 value of 452 μM. The SGLT inhibitor phlorizin inhibited the membrane potential response to 10 mM glucose with an IC50 of 3.5 μM. In contrast, EC50 values of 127 and 132 mM were obtained from concentration-response analysis of glucose taste in vehicles of water or 20 mM NaCl, respectively, by rapid throughput taste discrimination with human subjects. Lactisole, an antagonist of TAS1R2/R3, at a concentration of 1 mM completely inhibited taste responses to glucose concentrations of 250 mM and below. Phlorizin (0.2 mM) and the high potency SGLT1-selective inhibitor mizagliflozin (10 μM) failed to inhibit glucose taste detection measured at peri-threshold concentrations in the rapid throughput taste discrimination assay. A Yes/No experiment using the taste discrimination assay revealed that 0.2 mM phlorizin was discriminable from water for some subjects. Taken together the results indicate that agonist activation of TAS1R2/R3 is sufficient to account for all glucose taste without contribution by an alternative SGLT-mediated signaling pathway. Furthermore, the taste of phlorizin could be a confounding variable for studies evaluating a role for SGLTs in taste.

State-of-the-art in human activity recognition based on inertial measurement unit sensors: survey and applications

Human activity recognition systems using wearable sensors is an important issue in pervasive computing, which applies to various domains related to healthcare, context aware and pervasive computing, sports, surveillance and monitoring, and the military. Three approaches can be considered for activity recognition: video sensor-based, physical sensor-based, and environmental sensor-based. This paper investigates the related work regarding the physical sensor-based approaches to motion processing. In this paper, a wide range of artificial intelligence models, from single classifications to methods based on deep learning, have been reviewed. The human activity detection accuracy of different methods, under natural and experimental conditions poses several challenges. These challenges cause problems regarding the accuracy and applicability of the proposed methods. This paper analyzes the methods, challenges, approaches, and future work. The goal of this paper is to establish a clear distinction in the field of motion detection using inertial sensors.

Multi-Dimensionally Functionalized Pressure Sensor for Human Motion Detection Based on 1D AgNWs/2D rGO-Coated 3D Porous Sponge.

This study presents a conductive-type pressure sensor based on a conductive composite of 1D/2D nanomaterials coated onto a 3D nonconductive polymer structure with various pores. A 3D porous elastomer for the substrate was fabricated by using a sugar template, which led to an increased mechanical deformation range. The sugar template enhanced the surface roughness of the polymer, resulting in an improvement in the adhesion of nanomaterials to the polymer surface. Subsequently, it was functionalized by coating with hybrid nanomaterials of 1D silver nanowires (AgNWs) and 2D reduced graphene oxide (rGO) through a dip-coating process. When pressure is applied, the rGO/AgNWs/ecoflex pressure sensor deforms along the direction of the applied force, causing the conductive multidimensional nanomaterials to come into contact. Consequently, the improved networks between the two nanomaterials expanded the current paths, increasing the current detected through the electrodes attached to the sensor. The rGO/AgNWs/ecoflex pressure sensor, with its porous structure within the flexible ecoflex, demonstrated a high sensitivity (up to 2.29 kPa-1) over a wide detection range of 0-120 kPa. This enables the monitoring of a wide range of motions, including small pressures such as subtle touch, respiratory vibrations, and drinking, as well as large pressures such as human bodily movements, finger/arm bending, and foot pressure, making it an excellent candidate for applications requiring precise pressure detection.