Deception detection plays a crucial role in criminal investigation. Videos contain a wealth of information regarding apparent and physiological changes in individuals, and thus can serve as an effective means of deception detection. In this paper, we investigate video-based deception detection considering both apparent visual features such as eye gaze, head pose and facial action unit (AU), and non-contact heart rate detected by remote photoplethysmography (rPPG) technique. Multiple wrapper-based feature selection methods combined with the K-nearest neighbor (KNN) and support vector machine (SVM) classifiers are employed to screen the most effective features for deception detection. We evaluate the performance of the proposed method on both a self-collected physiological-assisted visual deception detection (PV3D) dataset and a public bag-of-lies (BOL) dataset. Experimental results demonstrate that the SVM classifier with symbiotic organisms search (SOS) feature selection yields the best overall performance, with an area under the curve (AUC) of 83.27% and accuracy (ACC) of 83.33% for PV3D, and an AUC of 71.18% and ACC of 70.33% for BOL. This demonstrates the stability and effectiveness of the proposed method in video-based deception detection tasks.

The intensive application of deep learning in medical image processing has facilitated the advancement of automatic retinal vessel segmentation research. To overcome the limitation that traditional U-shaped vessel segmentation networks fail to extract features in fundus image sufficiently, we propose a novel network (DSeU-net) based on deformable convolution and squeeze excitation residual module. The deformable convolution is utilized to dynamically adjust the receptive field for the feature extraction of retinal vessel. And the squeeze excitation residual module is used to scale the weights of the low-level features so that the network learns the complex relationships of the different feature layers efficiently. We validate the DSeU-net on three public retinal vessel segmentation datasets including DRIVE, CHASEDB1, and STARE, and the experimental results demonstrate the satisfactory segmentation performance of the network.

Handheld ultrasound devices are known for their portability and affordability, making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening. However, the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size, which hinders accurate diagnoses by doctors. At the same time, paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated. Therefore, we propose a modified cycle generative adversarial network (cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training. We introduce an ultrasound image pre-training method that does not require paired images, alleviating the requirement for large-scale paired datasets. We also propose an enhanced block with different structures in the pre-training and fine-tuning phases, which can help achieve the goals of different training phases. To improve the robustness of the model, we add Gaussian noise to the training images as data augmentation. Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.

The synchronous monitoring of cerebral blood flow and blood oxygen levels plays a pivotal role in the prevention, diagnosis, and treatment of cerebrovascular diseases. This study introduces a novel noninvasive device utilizing inductive sensing and near-infrared spectroscopy technology to facilitate simultaneous monitoring of cerebral blood flow and blood oxygen levels. The device consists of modules for cerebral blood flow monitoring, cerebral blood oxygen monitoring, control, communication, and a host machine. Through experiments conducted on healthy subjects, it was confirmed that the device can effectively achieve synchronous monitoring and recording of cerebral blood flow and blood oxygen signals. The results demonstrate the device’s capability to accurately measure these signals simultaneously. This technology enables dynamic monitoring of cerebral blood flow and blood oxygen signals with potential clinical applications in preventing, diagnosing, treating cerebrovascular diseases while reducing their associated harm.

This paper proposed a deep-learning-based method to process the scattered field data of transmitting antenna, which is unmeasurable in inverse scattering system because the transmitting and receiving antennas are multiplexed. A U-net convolutional neural network (CNN) is used to recover the scattered field data of each transmitting antenna. The numerical results proved that the proposed method can complete the scattered field data at the transmitting antenna which is unable to measure in the actual experiment and can also eliminate the reconstructed error caused by the loss of scattered field data.

This paper proposed a method to generate semi-experimental biomedical datasets based on full-wave simulation software. The system noise such as antenna port couplings is fully considered in the proposed datasets, which is more realistic than synthetical datasets. In this paper, datasets containing different shapes are constructed based on the relative permittivities of human tissues. Then, a back-propagation scheme is used to obtain the rough reconstructions, which will be fed into a U-net convolutional neural network (CNN) to recover the high-resolution images. Numerical results show that the network trained on the datasets generated by the proposed method can obtain satisfying reconstruction results and is promising to be applied in real-time biomedical imaging.

Three dimensional (3-D) imaging algorithms with irregular planar multiple-input-multiple-output (MIMO) arrays are discussed and compared with each other. Based on the same MIMO array, a modified back projection algorithm (MBPA) is accordingly proposed and four imaging algorithms are used for comparison, back-projection method (BP), back-projection one in time domain (BP-TD), modified back-projection one and fast Fourier transform (FFT)-based MIMO range migration algorithm (FFT-based MIMO RMA). All of the algorithms have been implemented in practical application scenarios by use of the proposed imaging system. Back to the practical applications, MIMO array-based imaging system with wide-bandwidth properties provides an efficient tool to detect objects hidden behind a wall. An MIMO imaging radar system, composed of a vector network analyzer (VNA), a set of switches, and an array of Vivaldi antennas, have been designed, fabricated, and tested. Then, these algorithms have been applied to measured data collected in different scenarios constituted by five metallic spheres in the absence and in the presence of a wall between the antennas and the targets in simulation and pliers in free space for experimental test. Finally, the focusing properties and time consumption of the above algorithms are compared.

A high-sensitivity magnetic sensing system based on giant magneto-impedance (GMI) effect is designed and fabricated. The system comprises a GMI sensor equipped with a gradient probe and an signal acquisition and processing module. A segmented superposition algorithm is used to increase target signal and reduce the random noise. The results show that under unshielded, room temperature conditions, the system achieves successful detection of weak magnetic fields down to 2 pT with a notable sensitivity of 1.84×10⁸ V/T (G = 1 000). By applying 17 overlays, the segmented superposition algorithm increases the power proportion of the target signal at 31 Hz from 6.89% to 45.91%, surpassing the power proportion of the 2 Hz low-frequency interference signal. Simultaneously, it reduces the power proportion of the 20 Hz random noise. The segmented superposition process effectively cancels out certain random noise elements, leading to a reduction in their respective power proportions. This high-sensitivity magnetic sensing system features a simple structure, and is easy to operate, making it highly valuable for both practical applications and broader dissemination.

In this paper, an induced current learning method (ICLM) for microwave through wall imaging (TWI), named as TWI-ICLM, is proposed. In the inversion of induced current, the unknown object along with the enclosed walls are treated as a combination of scatterers. Firstly, a non-iterative method called distorted-Born backpropagation (DB-BP) is utilized to generate the initial result. In the training stage, several convolutional neural networks (CNNs) are cascaded to improve the estimated induced current. In addition, a hybrid loss function consisting of the induced current error and the permittivity error is used to optimize the network parameters. Finally, the relative permittivity images are conducted analytically using the predicted current based on ICLM. Both the numerical and experimental TWI tests prove that, the proposed method can achieve better imaging accuracy compared to traditional distorted-Born iterative method (DBIM).

Convolutional neural network (CNN) has excellent ability to model locally contextual information. However, CNNs face challenges for descripting long-range semantic features, which will lead to relatively low classification accuracy of hyperspectral images. To address this problem, this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification. Firstly, the low-level spatial-spectral features are extracted by multi-scale residual structure. Secondly, an attention module is introduced to focus on the more important spatial-spectral information. Finally, high-level semantic features are represented and learned by a token learner and an improved transformer encoder. The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images. The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.