Detection of heart rate and heart rate variability (HRV) is highly important in health monitoring and medical diagnosis, especially under the exercise state. Currently, the main detection techniques include photoplethysmographic volumetric tracing (PPG), electrocardiography (ECG), and ballistocardiogram (BCG). However, ECG and BCG are not suitable for application during exercise, and the accuracy of PPG during exercise is greatly affected by motion artifacts, requiring complex analysis algorithms. Therefore, this paper proposes a novel dynamic-state HRV detection method for a gyrocardiography (GCG)-based chest band with a MEMS inertial measurement unit (IMU). The GCG signals are acquired under three states: resting, jogging, and running. Considering that the actual motion is diverse and may lead to different interference, a novel filter method is proposed after detailed interference measurement and analysis. In addition, the fine peak detection method is proposed to avoid the missed peaks and advance the detection accuracy. The HRV indexes obtained by GCG are compared with those obtained by ECG in the resting state for verification. Meanwhile, the heart rate and HRV indexes obtained by GCG in the jogging and running states are also compared. Experimental results indicate that in the resting state, the accuracy of heart rate measured by GCG is more than 95%, the average accuracy of the HRV indexes is about 92% and the average accuracy in jogging state is 89%. To sum up, the proposed dynamic-state HRV detection method based on a chest band with a MEMS IMU is effective and feasible.

MEMS gyroscopes are widely used in Internet of Things (IoT) products to achieve attitude control or combined inertial navigation. However, temperature is a key factor affecting the system stability and performances, therefore temperature compensation is very important. This paper proposes a novel narrow-band force rebalance control method based on a band pass filter (BPF) and temperature self compensation for a MEMS gyroscope. A three-dimensional adaptive filter demodulator and scalable fuzzy controller are utilized for the closed loop control of the drive mode. Besides, the BPF is used as a controller to achieve the narrow-band force rebalance control without modulation or demodulation. The center frequency of the BPF is adjusted in real time to match the sense-mode resonant frequency. Meanwhile, its gain is tuned based on the sense-mode quality factor. The real-time sense-mode resonant frequency, sense-mode quality factor, mode-matching voltage, and demodulation phase can be obtained with the polynomial fitting formulas and drive-mode resonant frequency. Experimental results demonstrate that over the full temperature range from -40°;C to 80°;C, the closed loop control systems of the mode-splitting and mode-matching gyroscopes without and with self compensation are very robust, and the bandwidth drifts are all less than 5Hz. For the mode-splitting gyroscope, the temperature drifts of the zero bias and scale factor are improved by a factor of 3 and 1.9 respectively. However, for the mode-matching gyroscope, the temperature drifts of the zero bias and scale factor are improved by a factor of 80 and 8 respectively. Thus, the proposed self-compensation method is effective and promising.

Currently, many people around the world, especially children and youth, are facing the problem of attention deficit. Neurofeedback training is proved to be an effective method for improving the attention level. However, current neurofeedback training typically requires the use of computers or other nonportable devices, which limits the application scenarios of this technique. Therefore, a portable neurofeedback training system based on high-performance edge AI accelerator is proposed in this paper. More specifically, the real-time single-channel EEG and ECG signals of the trainees are first collected by the wearable flexible headband and patch. The wavelet packet decomposition algorithm is adopted to decompose and denoise the collected signals. The processed signals are classified by a convolutional neural network model, and an AI accelerator is designed to run this model for portability. The classification results are fed back to the trainees in real-time with a serious game to achieve the closed-loop regulation of their attentions. Finally, a single-blind controlled experiment is conducted to verify the effectiveness of the proposed system. The experimental results indicate that the attention levels of subjects trained with the proposed system are significantly improved (p < 0.05), and the attention-related EEG indicator theta/beta ratio decreased by an average of 21.85%.

Sleep disorders and the associated physical and mental illnesses are becoming increasingly prominent, affecting people’s quality of life and work-learning efficiency. Accurate sleep monitoring and efficient sleep-aid interventions are still world challenges. In recent years, there have been significant advances in monitoring the in-and-out-of-bed state, heart rate, HRV, respiratory rate, snoring event, body movement, and sleep stage, including the development and use of multimodal sensors for data acquisition and the adoption of AI techniques such as feature extraction and pattern recognition for sleep parameter identification. Common sleep-aid methods can be categorized into two main groups: pharmacologic and non-pharmacologic. However, in the long run, it seems that the effect of a single sleepaid method is limited, and the integration of multiple sleep-aid intervention methods is the trend. Microneedle sleep-aid techniques that integrate herbal sleep aids, acupoint acupuncture sleep aids, and transcranial current stimulation sleep aids have emerged. However, there is a lack of summarization and review of the latest research on sleep monitoring and sleep interventions in recent years, and this paper hopes to point out the limitations of the current technology and suggest under-explored research paths through the investigation of the latest studies. In this paper, relevant studies in the last 5-10 years have been well researched, and expertise in neuroscience, clinical medicine, biomedical engineering, computer science, mobile health, and humancomputer interaction is utilized to discuss sleep monitoring and sleep-aid techniques from an interdisciplinary perspective. The principles of state-of-the-art sleep monitoring techniques, multidimensional sleep parameter recognition techniques, and physical, medical, and microneedle sleep-aid techniques are presented. In addition, the advantages and limitations of these techniques, as well as the opportunities and challenges of emerging techniques, are discussed.

Underwater hyperspectral imaging systems are essential tools for observing marine geology, seabed minerals, and marine reptiles. However, the complex underwater imaging environment and the high cost of equipment present unpredictable challenges for underwater hyperspectral image acquisition. Consequently, this limits the widespread application of hyperspectral images in underwater survey missions. To address these challenges, this study first explores spectral reconstruction technology to indirectly assist in acquiring underwater hyperspectral images through data-driven deep learning methods. Specifically, a Multi-Scale Large Kernel Spectral Reconstruction Network (MSL-SRN) was designed, which leverages available public RGB and hyperspectral image pairs to train the network to learn hyperspectral information from a single underwater RGB image. To validate the feasibility and effectiveness of this approach, spectral reconstruction experiments were conducted on a real underwater hyperspectral dataset. Experimental results indicate that the proposed method closely approximates underwater hyperspectral images. The concept presented in this study provides a novel approach to overcoming the cost and accessibility limitations of underwater hyperspectral imaging.

Spectral super-resolution technology, which reconstructs 31-band hyper-spectral images from RGB natural scene images within the 400-700nm bands, has seen rapid growth. However, its fixed spectral resolution and spectral coverage limit its application in remote sensing imaging, particularly for aerial images with multi-band information. The lack of corresponding high-spectral image pairs has hindered research progress, leaving the potential spectral information of these remote sensing images untapped. In this study, we explore a hybrid transformer architecture for multispectral images that carry visible light and near-infrared informations to achieve spectral super-resolution. This network integrates both intra-row and intra-column attention mechanisms, along with a cross inter-row and inter-column attention mechanism, to precisely capture and process the spatial and spectral features in spectral images. In the case of two simulated datasets, the experimental results demonstrate favorable outcomes. In classification experiments using multimodal Pavia University datasets, the reconstructed hyper-spectral images exhibit superior performance with higher average accuracy (95.30%), overall accuracy (95.70%), and Kappa coefficient (93.50%).

More and more people around the world suffer from insomnia, hence sleep-aid methods are very important and urgent. In this article, a flexible sleep-aid eye mask based on acupoint electric pulse stimulation (AEPS) combined bioelectrical signal feedback is proposed. Besides, the massage sleep-aid principle of Yintang and Anmian acupoints is described. Afterwards, AEPS circuit, bioelectrical signal acquisition (BSA) circuit, and a smart flexible sleep-aid eye mask are put forward. The sleep-aid effect evaluation methods based on the key features of EEG and ECG signals, as well as the real-time sleep-aid control method, are presented in detail. Experimental results demonstrate that the BSA circuit and feature extraction method with discrete wavelet transform (DWT) analysis are effective. After four kinds of experimental tests with ten subjects, compared with the results of no stimulation (NS), the values of HRMEAN and$E_{\mathrm{ betam}}$of AEPS of Yintang acupoint (AEPS-Y), AEPS of Anmian acupoint (AEPS-A), and AEPS of Yintang and Anmian acupoints (AEPS-YA) decrease, while the values of RRMEAN, SDNN, RMSSD, LF, HF, RLH,$E_{\mathrm{ alpham}}$, and RAB of AEPS-Y, AEPS-A, and AEPS-YA increase, which verifies that the sleep-aid controls of AEPS-Y, AEPS-A, and AEPS-YA are all effective. In addition, the sleep-aid effect of AEPS-Y is better than that of AEPS-A or AEPS-YA. Compared with that without AEPS-Y, the median sleep latency with AEPS-Y of the flexible eye mask is reduced by about 43.08%. To sum up, this flexible eye mask can be widely used for sleep-aid control at home, which is low cost and comfortable.

With the wide application of the Internet of Things technology, the hardware security has attracted more and more attention from users around the world. Hardware Trojan (HT) of integrated circuit (IC) has become a main security threat gradually. Therefore, HT detection is very significant. In this article, a HT automatic test system used for side-channel test combined logic test is constructed with a high-performance oscilloscope, FPGA chips, a NI digital acquisition card and LabVIEW software. Besides, the test flow chart and data processing method are depicted in detail. Spectral feature analysis combined principal component analysis is proposed for feature extraction. Fuzzy C-means clustering combined spectral energy analysis is put forward to distinguish the Trojan category from the golden category. Then Fusion distance (i.e. Mahalanobis distance combined Euclidean distance) is presented for the real-time HT recognition. A 128-bit AES cipher circuit and a 2-bit counter are applied as a golden circuit and a Trojan circuit, respectively. Experimental results demonstrate that the detection accuracy is 100% and the proposed detection method can easily achieve 0.1% HT detection sensitivity, which verifies that the detection method is feasible and effective.

Emotions are complex, and people vary greatly in their accuracy in recognizing their own emotions and those of others. With advances in computer science and neuroscience, there is a desire to use automated techniques to help people identify emotions. Bio-electrical signals have been proven effective for emotion detection, but the acquisition of conventional electrocardiogram (ECG) and EEG requires medical-specific equipment, which is very expensive, uncomfortable, and inconvenient due to the large number of electrodes and the hair-covered scalp. In this article, a novel emotion recognition method based on the feature fusion of single-lead EEG and ECG signals is proposed, using the long short term memory (LSTM)-MLP-based model and the CNN-based model for feature fusion and classification, respectively, with fivefold cross-validation for validation. The ECG and EEG signals of 15 participants were collected in five states: 1) happy; 2) relaxed; 3) calm; 4) sad; and 5) afraid, each of which was stimulated using the participants’ own proposed music. Various time-domain features, frequency-domain features, and nonlinear features were extracted from the ECG and EEG signals. Experimental results demonstrate that the accuracy of emotion recognition and classification of signals captured by the proposed device can reach 92.08% using the CNN model. While using the LSTM-MLP feature fusion model, the accuracy figure can be improved to 95.07%. The results of the ablation experiment indicate that the feature fusion approach does improve the accuracy of recognition. It is demonstrated that the proposed device and emotional recognition approach are effective and feasible.

With the rapid development of economy, science, and technology, the aging issues become more and more serious. People aged above 65 have a risk of 28%–35% to fall. Among them, bedside falls happen most frequently. Therefore, the capability to detect fall events of the elderly is very important. In this article, a novel noncontact fall detector based on a MEMS low-resolution infrared sensor and a low-cost radar sensor is developed to detect bedside fall. Besides, IR image processing algorithms based on the adaptive filter, successive approximation, double boundary scans, and mathematical morphology processing are proposed in detail. Partition processing algorithm is used to suppress the influence of residual or existed heat sources on the bed or ground. Then, the statistical features of the center, area, temperature and duration, as well as stable flag and fall action flag, are extracted for fall recognition. Finally, a three-layer radial basis function neural network is applied to distinguish the fall events from the nonfall events. Considering the influence factors of ambient temperature, brightness, gender, dressing, fall posture, fall location, and scenario, a total of 640 tests are conducted and 5-fold cross validation is used to evaluate the classification performance. Experimental results indicate that the averages of the recall, precision, F1-Score, and detection accuracy are measured to be 91.25%, 94.76%, 92.97%, and 93.13%, respectively, which demonstrates that the proposed fall detection method is effective. Besides, the detection accuracy decreases from 96.88% to 85.94% as the ambient temperature rises. Hence, this noncontact fall detector can be widely applied for bedside fall detection at home, which is low cost, nonwearable, unobtrusive, noninvasive, and privacy preserved.

Abstract Single infrared (IR) image super‐resolution methods can help to reduce the cost and difficulty in manufacturing IR sensors for the imaging system. However, the deep learning‐based image SR methods need to build a complex network and thus consume a lot of computational power, which limits the application of SR technology on devices with low computing resources in practice. To solve this problem, the authors present a lightweight multi‐path feature fusion network (MFFN) for the single infrared (IR) image SR. A multi‐path feature fusion block (MFFB) is developed to extract and fuse multiple and discriminative features in a recursive feedback way. Specifically, the multiple features are refined via the linear feature extraction branch, shared‐source residual feature extraction branch, and channel attention branch in MFFB. Finally, the authors reconstruct the high‐resolution IR images from the low‐resolution counterpart based on the refined multiple features. The experimental results demonstrate that MFFN achieves high‐quality single infrared image SR and shows superiority over previous methods for several scale factors (e.g. ×2, ×3, and ×4). MFFN has potential applications in the mobile infrared imaging system.

Sleep apnea impacts more and more people all over the world, and obstructive sleep apnea of which is the most frequent. Hence, research on snoring detection and related suppression methods is extremely urgent. In this article, a novel low-cost flexible patch with MEMS microphone and accelerometer is developed to detect snore event and sleeping posture, and a small vibration motor embedded in the patch is designed to suppress snoring. Theoretical analyses of short-time energy, piecewise average filtering (PAF), and Mel-frequency cepstral coefficients (MFCCs) processing are described in detail, and the improved MFCCs are put forward and used as the input of the convolutional neural network (CNN). Furthermore, the snore recognition method based on the combination of similarity analysis and CNN analysis is presented, followed by the snoring suppression method. Experimental results demonstrate that the main features of the sound signals can be extracted effectively by PAF and MFCCs processing, and the data compression ratio is about 99.41%. Besides, the locations of the eigenvectors can be found accurately based on short-time energy analysis. The numbers of high similarity of snoring signals within 30 s are larger than 3, while those of non-snoring signals are often less than 3. If the preliminary screening with similarity analysis is passed, CNN analysis will be conducted to judge whether there are snoring events. The accuracy of snore recognition with CNN analysis is calculated to be as high as 99.25%. Finally, the average snoring time measured by the smart patch with snoring suppression is reduced to 15 from 135 min, which indicates that the proposed snore recognition and suppression methods are effective.

Monitoring crop growth is of great significance to obtain crop growth status information for development of smart agriculture. The traditional way to measure the phenotypic parameters of crops is labor-intensive and encounters inconvenient operations. In this study, we propose to obtain the phenotypic parameters of crops from 3-D reconstruction of plants from single RGB images using a data-driven plant phenotypic parameters estimation network (P3ES-Net) deep neural network, which enables to estimate the depth shift and camera focal length used for depth estimation and reconstruction of the 3-D model of plants. Based on the principles of the monocular ranging and pinhole imaging model, crop phenotypic parameters such as height, canopy size, and trunk diameter can then be calculated from the 3-D model. Experiments with four practical plants present that our method is able to achieve acceptable evaluation of the growth status of plants. Of more significance, it achieves particular superior depth estimation performance over a commercial depth camera, which is a very new on-sale depth camera using stereo vision and deep learning network. This potential performance throws light on the low-cost measurement of crop phenotypic parameters using RGB camera in monitoring crop growth.

The abundance of a mixed pixel of certain class can be understood as to get the relative score referring to the pure representative of this class, while not be classified with two absolute and discrete value as ”lor 0”. This is in accordance with the Relative Attribute Learning (RAL) problem in computer vision. In RAL, the concept of “relative attribute” is used to describe the belonging level of an obj ect to certain class with a score which is achieved from a learn-to-rank problem using rankSVM framework. To utilize information between data samples and even of mixed pixels, Relative Attribute based Unmixing (RAU) is proposed first time by using relative attribute to describe the abundance of mixed pixel as relative purity of certain class and learn the abundance with rankSVM. The mixed data sample are used to construct training comparisons set in rankSVM with archetypes generated by the reported Kernel Archetypal Analysis (KAA) unmixing method. In addition, spectral variability is also addressed by constructing comparisons set with synonyms spectrum achieved from KAA. Experiments on both synthetic and real hyperspectral mixed image have demonstrated the potential value of proposed method for mixed pixel analysis.