Indoor sensing technologies are gaining increasing attention in the development of smart environments. Wi-Fi-based human activity recognition, which exploits channel state information (CSI), enables accurate detection of human movements by analyzing signal fluctuations caused by activity, even in complex indoor settings. This passive, device-free approach leverages the ubiquity of Wi-Fi signals, eliminating the need for wearable devices and improving user convenience. However, current Wi-Fi-based sensing systems face several limitations, including suboptimal real-time performance, inefficient resource utilization, and the absence of dedicated hardware platforms. To address these challenges, this article presents a wireless sensing device based on printed circuit board technology, integrated with a CSI-driven system for recognizing indoor human behavior. Experimental results across diverse scenarios demonstrate high recognition accuracy, underscoring the proposed system's potential to improve the efficiency and practicality of wireless sensing technologies in smart environments.

Industrial wireless sensor networks (IWSNs) play a critical role in enabling real-time monitoring and intelligent automation in modern industrial applications. However, maintaining reliable communication and efficient data transmission in dynamic and interference-prone environments remains a significant challenge. To address these limitations, this article proposes a graph neural network (GNN)-driven networking approach for IWSNs, designed to enhance communication robustness and optimize data processing. Our approach incorporates a minimum capacity constraint and a trainable slack parameter, enabling adaptive network configuration in response to changing conditions. By modeling the network topology as a graph, we formulate a device-centric joint node selection and power allocation (JNP) strategy, leveraging GNNs for real-time decision-making. Simulations benchmark the proposed method against state-of-the-art methods, showing up to a 70% average increase in fifth percentile rate across various network conditions. These results highlight the effectiveness of the proposed JNP strategy in improving IWSN performance for industrial applications.

Soft-thresholding (ST) has been widely used in deep neural networks. Its fundamental network structure is a deep soft-thresholding fully connected network (ST-FCN). However, training deep ST-FCN to achieve convergence remains time-consuming or even encounters gradient explosion, in part because the convergence behavior is not fully understood. To address this issue, this article proves the relationship between the convergence of deep ST-FCN and the values of network weights and biases. Theoretical analysis shows that, as the number of network layers approaches infinity, deep ST-FCN converges when the network weights tend to an identity matrix, while the biases tend to zero. Following this guidance, we initialize the network weights as the identity matrix, compare it with other representative initialization methods (Gaussian, He, LeCun, Xavier, and Uniform), and quantify their effects on network convergence. Extensive results on a synthetic spectrum dataset and real-world datasets (MNIST and CIFAR-10) demonstrate that initializing the weights to the identity matrix and the bias to zero leads to fast and stable convergence. These conclusions are further supported by additional experiments and statistical analysis on deeper ST networks (with more than ten layers) and other representative architectures (DenseNet-161, ResNet-152, and VGG-19), and more challenging benchmarks (CIFAR-100, STL-10, and Tiny ImageNet). This work provides a theoretical foundation for understanding the convergence of ST neural networks. Furthermore, convergence theory analysis for deep recurrent neural networks (RNNs) with ST is deduced.

MOTIVATION: Proteins carry out most biological processes via interactions with other proteins, known as protein-protein interactions (PPIs). Accurately predicting PPIs is crucial for understanding protein function, yet existing methods often fall short in capturing their complex and hierarchical nature. RESULTS: We propose PF-AGCN, an adaptive graph convolutional network that leverages two distinct graph structures: a function graph representing hierarchical Gene Ontology term relationships and a protein graph modeling direct interactions between proteins. Unlike traditional graph attention networks, PF-AGCN preserves the original biological structures while dynamically learning new relationships, ensuring the retention of essential biological information. Additionally, our framework integrates a protein language model with stacked dilated causal convolutional neural networks, enabling the synergistic fusion of global sequence semantics and local structural patterns. Extensive experiments on a comprehensive protein dataset across three evaluation facets demonstrate PF-AGCN's superior prediction accuracy. AVAILABILITY AND IMPLEMENTATION: The source code is publicly available at https://github.com/smyang107/PFAGCN.

Visible light communication (VLC) technology has emerged as a promising solution to address the stringent requirements of indoor industrial communication scenarios, such as the dynamic capacity requirements of smart factory. However, the inevitable deployment of ultra-dense VLC access points introduces new challenges for VLC user equipments, including difficulties related to interference control, resource allocation, and intercell handover. Motivated by these, this article proposes a user-centric networking strategy tailored for indoor VLC systems. The proposed algorithm initiates by tackling system-wide interference mitigation through the use of spectral clustering to partition the network, thereby minimizing intersubnetwork interference. Subsequently, orthogonal subchannel allocation within each subnetwork is employed, along with subchannel multiplexing across subnetworks. Simulations demonstrate the efficacy of our proposed methods, showcasing superior performance in terms of achievable rates compared to benchmarks.

CT report generation (CTRG) aims to automatically generate diagnostic reports for 3D volumes, relieving clinicians' workload and improving patient care. Despite clinical value, existing works fail to effectively incorporate diagnostic information from multiple anatomical views and lack related clinical expertise essential for accurate and reliable diagnosis. To resolve these limitations, we propose a novel Multi-view perception Knowledge-enhanced TansfoRmer (MvKeTR) to mimic the diagnostic workflow of clinicians. Just as radiologists first examine CT scans from multiple planes, a Multi-View Perception Aggregator (MVPA) with view-aware attention is proposed to synthesize diagnostic information from multiple anatomical views effectively. Then, inspired by how radiologists further refer to relevant clinical records to guide diagnostic decision-making, a Cross-Modal Knowledge Enhancer (CMKE) is devised to retrieve the most similar reports based on the query volume to incorporate domain knowledge into the diagnosis procedure. Furthermore, instead of traditional MLPs, we employ Kolmogorov-Arnold Networks (KANs) as the fundamental building blocks of both modules, which exhibit superior parameter efficiency and reduced spectral bias to better capture high-frequency components critical for CT interpretation while mitigating overfitting. Extensive experiments on the public CTRG-Chest-548 K dataset demonstrate that our method outpaces prior state-of-the-art (SOTA) models across almost all metrics.

Soft-thresholding has been widely used in neural networks. Its basic network structure is a two-layer convolution neural network with soft-thresholding. Due to the network's nature of nonlinear and nonconvex, the training process heavily depends on an appropriate initialization of network parameters, resulting in the difficulty of obtaining a globally optimal solution. To address this issue, a convex dual network is designed here. We theoretically analyze the network convexity and prove that the strong duality holds. Extensive results on both simulation and real-world datasets show that strong duality holds, the dual network does not depend on initialization and optimizer, and enables faster convergence than the state-of-the-art two-layer network. This work provides a new way to convexify soft-thresholding neural networks. Furthermore, the convex dual network model of a deep soft-thresholding network with a parallel structure is deduced.

Given the exponential surge in data traffic and the proliferation of connected smart devices, traditional radio frequency (RF)-based wireless communication systems have to confront mounting challenges of spectrum scarcity and access congestion, particularly for networks operated in low-frequency bands. Visible light communication (VLC) technology has emerged as a promising solution, but it has own limitations, including coverage constraints and limited uplink capability, necessitating hybrid systems that leverage VLC and RF. This paper focuses on an indoor hybrid VLC-RF system extending VLC to Wi-Fi’s public spectrum, enabling VLC’s uplink via RF while enhancing system capacity. Yet, integrating VLC-RF with Wi-Fi introduces new challenges due to the coexistence of VLC-RF with existing Wi-Fi systems. To address these challenges, we propose an intelligent coexistence approach, dynamically adjusts duty cycles to ensure fairness and performance optimization between VLC-RF and Wi-Fi. Moreover, a spectrum multiplexing algorithm is introduced in the coexistence approach to enable the hybrid VLC-RF system’s multiplexing transmission on public spectrum, while preserving Wi-Fi system transmission integrity without interference, thereby further optimizing resource utilization. Extensive simulations on a meticulously constructed system-level platform validate our approach, showcasing its efficacy in enhancing system performance while maintaining equitable transmission between hybrid VLC-RF and Wi-Fi systems.

Use of synthetic data has provided a potential solution for addressing unavailable or insufficient training samples in deep learning-based magnetic resonance imaging (MRI). However, the challenge brought by domain gap between synthetic and real data is usually encountered, especially under complex experimental conditions. In this study, by combining Bloch simulation and general MRI models, we propose a framework for addressing the lack of training data in supervised learning scenarios, termed MOST-DL. A challenging application is demonstrated to verify the proposed framework and achieve motion-robust [Formula: see text] mapping using single-shot overlapping-echo acquisition. We decompose the process into two main steps: (1) calibrationless parallel reconstruction for ultra-fast pulse sequence and (2) intra-shot motion correction for [Formula: see text] mapping. To bridge the domain gap, realistic textures from a public database and various imperfection simulations were explored. The neural network was first trained with pure synthetic data and then evaluated with in vivo human brain. Both simulation and in vivo experiments show that the MOST-DL method significantly reduces ghosting and motion artifacts in [Formula: see text] maps in the presence of unpredictable subject movement and has the potential to be applied to motion-prone patients in the clinic. Our code is available at https://github.com/qinqinyang/MOST-DL.

Abstract Nuclear magnetic resonance with diffusion‐ordered spectroscopy (DOSY) serves as an important analytical tool to non‐destructively separate a molecule from a compound in medicine and chemistry. However, the data acquisition time increases rapidly for multidimensional DOSY. To enable fast DOSY, partial data are acquired with non‐uniform sampling, and the spectrum can be reconstructed with a proper constraint, such as sparsity in the state‐of‐the‐art method. However, the reconstructed spectrum is observed to have isolated artefacts, which can be easily recognised as fake peaks and affect the estimated diffusion coefficients severely. The authors introduce the low‐rank constraint as an effective remedy to remove these artefacts and derive a fast algorithm to solve the reconstruction problem. Results on both synthetic and realistic DOSY spectra show that a better spectrum and more accurate diffusion coefficients can be achieved.

Quantitative magnetic resonance imaging (MRI) is of great value to both clinical diagnosis and scientific research. However, most MRI experiments remain qualitative, especially dynamic MRI, because repeated sampling with variable weighting parameter makes quantitative imaging time-consuming and sensitive to motion artifacts. A single-shot quantitative T2mapping method based on multiple overlapping-echo acquisition (dubbed MOLED-4) was proposed to obtain reliable T2mapping in milliseconds. Different from traditional MRI acceleration methods, such as compressed sensing and parallel imaging, MOLED-4 accelerates quantitative T2mapping via synchronized multisampling and then deep learning to map the complex nonlinear relationship that is difficult to solve by traditional optimization-based methods. The results of simulation, phantom, and in vivo human brain experiments show the great performance of the proposed method. The principle of MOLED-4 may be extended to other ultrafast quantitative parameter mappings and potentially lead to new dynamic MRI with high efficiency to catch quantitative variation of tissue properties.

Conventional sparse coding based super-resolution (SR) methods obtained promising performance by learning overcomplete dictionaries for low-resolution (LR) and high-resolution (HR) feature spaces, and assuming that the sparse representation of a HR feature vector was identical or linear to the sparse representation of the corresponding LR one. However, in fact, the relationship between LR and HR sparse domains is nonlinear due to the complicated degradation of the observed image. To learn the relation more precisely, an assumption called “the same-support constraint” is adopted in our proposed method, which forces LR/HR image patches to activate the atoms lying in the same locations of the LR/HR dictionaries. Under the same-support constraint, our approach first learns LR dictionary, and then obtains HR dictionary and a nonlinear mapping between LR/HR sparse domains by training them iteratively. LR/HR dictionaries learned individually can explore structural characteristics of their corresponding feature spaces well, while the mapping learned iteratively can reveals accurately the intrinsic non-linear relationship between LR and HR sparse domains. Experimental results show that the proposed method outperforms the compared sparse learning based single image super-resolution methods.

Compressed sensing has shown great potential in reducing data acquisition time in magnetic resonance imaging (MRI). Recently, a spread spectrum compressed sensing MRI method modulates an image with a quadratic phase. It performs better than the conventional compressed sensing MRI with variable density sampling, since the coherence between the sensing and sparsity bases are reduced. However, spread spectrum in that method is implemented via a shim coil which limits its modulation intensity and is not convenient to operate. In this letter, we propose to apply chirp (linear frequency-swept) radio frequency pulses to easily control the spread spectrum. To accelerate the image reconstruction, an alternating direction method of multipliers (ADMM) algorithm is modified by exploiting the complex orthogonality of the quadratic phase encoding. Reconstruction on the acquired data demonstrates that more image features are preserved using the proposed approach than those of conventional compressed sensing MRI.

The reconstruction of MR quantitative susceptibility mapping (QSM) from local phase measurements is an ill posed inverse problem and different regularization strategies incorporating a priori information extracted from magnitude and phase images have been proposed. However, the anatomy observed in magnitude and phase images does not always coincide spatially with that in susceptibility maps, which could give erroneous estimation in the reconstructed susceptibility map. In this paper, we develop a structural feature based collaborative reconstruction (SFCR) method for QSM including both magnitude and susceptibility based information. The SFCR algorithm is composed of two consecutive steps corresponding to complementary reconstruction models, each with a structural feature based l 1 norm constraint and a voxel fidelity based l 2 norm constraint, which allows both the structure edges and tiny features to be recovered, whereas the noise and artifacts could be reduced. In the M-step, the initial susceptibility map is reconstructed by employing a k -space based compressed sensing model incorporating magnitude prior. In the S-step, the susceptibility map is fitted in spatial domain using weighted constraints derived from the initial susceptibility map from the M-step. Simulations and in vivo human experiments at 7T MRI show that the SFCR method provides high quality susceptibility maps with improved RMSE and MSSIM. Finally, the susceptibility values of deep gray matter are analyzed in multiple head positions, with the supine position most approximate to the gold standard COSMOS result.

Compressed sensing (CS) has exhibited great potential for accelerating magnetic resonance imaging (MRI). In CS-MRI, we want to reconstruct a high-quality image from very few samples in a short time. In this paper, we propose a fast algorithm, called projected iterative soft-thresholding algorithm (pISTA), and its acceleration pFISTA for CS-MRI image reconstruction. The proposed algorithms exploit sparsity of the magnetic resonance (MR) images under the redundant representation of tight frames. We prove that pISTA and pFISTA converge to a minimizer of a convex function with a balanced tight frame sparsity formulation. The pFISTA introduces only one adjustable parameter, the step size, and we provide an explicit rule to set this parameter. Numerical experiment results demonstrate that pFISTA leads to faster convergence speeds than the state-of-art counterpart does, while achieving comparable reconstruction errors. Moreover, reconstruction errors incurred by pFISTA appear insensitive to the step size.

We have measured five major mechanisms that govern light-emitting diode (LED) degradation, calculated respective percentages, and identified the most influential mechanism during the time evolution of aging. After 480 h, due to the reduction of phosphor-conversion efficiency, the increase of non-radiative centers, the deterioration of thermal properties, the darkening of silicone resin lenses, and the degradation of Ag reflective layers, approximately 42% of the average optical power has decayed. Within this 42%, Ag degradation contributes approximately 28% (with the remaining 14% contributed by the degradation of silicone resin lenses), primarily because other chemical elements have deposited on the surface of Ag reflective layers, thus lowering the reflectivity of these layers. The present work can help draw the community's attention to lowering LED junction temperatures, and to the optimization of packaging designs.

Undersampling the k-space is an efficient way to speed up the magnetic resonance imaging (MRI). Recently emerged compressed sensing MRI shows promising results. However, most of them only enforce the sparsity of images in single transform, e.g. total variation, wavelet, etc. In this paper, based on the principle of basis pursuit, we propose a new framework to combine sparsifying transforms in compressed sensing MRI. Each transform can efficiently represent specific feature that the other can not. This framework is implemented via the state-of-art smoothed l0norm in overcomplete sparse decomposition. Simulation results demonstrate that the proposed method can improve image quality when comparing to single sparsifying transform.

Main problems of the common communication interface software (CIS) for an industry-control network based on RS485 bus are poor openness, flexibility and stability, so some functions of intelligent meters are limited. A new CIS was designed by the following ways: the RS485 serial communication process was composed of physical and application layers; the interface initializing process related to communication at physical layer was described by normalized communication module; the common parts of order message creation and responsive message transmission were described by a data structure and the special parts of them were described by text files respectively; configuration software was used to interpret these descriptions. The software has characteristics of broad generalization and operational facilitation, and can run on Windows completely. The results in application cases show that the software is effective and feasible