Vibration energy harvesting is a promising solution for powering battery-free IoT systems; however, the instability of ambient vibrations presents significant challenges, such as limited harvested energy, intermittent power supply, and poor adaptability to various applications. To address these challenges, this paper proposes ViPSN2.0, a modular and reconfigurable IoT platform that supports multiple vibration energy harvesters (piezoelectric, electromagnetic, and triboelectric) and accommodates sensing tasks with varying application requirements through standardized hot-swappable interfaces. ViPSN 2.0 incorporates an energyindication power management framework tailored to various application demands, including light-duty discrete sampling, heavyduty high-power sensing, and complex-duty streaming tasks, thereby effectively managing fluctuating energy availability. The platform’s versatility and robustness are validated through three representative applications: ViPSN-Beacon, using an ultra-lowcost structural PZT (ϕ35 mm, <0.002 $) to enable a BLE advertisement from a single transient fingertip press with 100 m line of sight; ViPSN-LoRa, supporting wireless communication powered by wave vibrations in actual marine environments (Bohai Bay) with per-uplink task energy compatible with kilometer-scale field links; and ViPSN-Cam, enabling intermittent image capture and wireless transfer, delivering one frame approximately every 15 s under typical conditions. Experimental results demonstrate that ViPSN 2.0 can reliably meet a wide range of requirements in practical battery-free IoT deployments under energy-constrained conditions.

Human-motion energy harvesting is emerging as a promising solution for wearable electronics and devices, offering a sustainable power source that extends operational longevity and enhances durability. However, current techniques and prototypes have yet to achieve fully interactive, battery-free functionality. This paper presents a battery-free interactive gaming system powered by energy harvested from transient fingertip motion. To ensure the reactivity, interactivity, and stability of the fingertip motion harvester (FMH), we employ a multistable structure. The FMH unit provides a reliable energy solution by utilizing precharged potential energy within dynamically varying potential wells. Additionally, the integration of a bistable screen design facilitates seamless gaming experiences, decouples game logic from user interface mechanics, and ensures rapid system recovery after power interruptions. Beyond advancing fundamental research, this work pioneers a practical battery-free interaction paradigm based on fingertip motion, with potential for broader battery-free user interfaces and low-power interactive systems.

Lead optimization, aimed at improving binding affinity or other properties of hit compounds, is a crucial task in drug discovery. Though deep learning-based 3D generative models showed promise in enhancing the efficiency of de novo drug design recently, less research and attention has garnered for structure-based lead optimization. Herein, we propose a 3D pocket-aware diffusion model named Diffleop, which explicitly incorporates the knowledge of protein-ligand binding affinity and information on covalent bonds to guide the denoising sampling process for lead optimization with enhanced binding affinity and rational properties. Specifically, the bond constraint is achieved through diffusion on fully connected molecular graphs, and the determination of atom positions, atom and bond types in each sampling step is guided by the gradient of the binding affinity that is predicted through fitting with an E(3)-equivariant expert network. The comprehensive evaluations indicated that Diffleop outperforms baseline models on lead optimization with higher affinity and more binding interactions, and can generate more drug-like molecules with more rational structures. Diffleop was further applied to optimize 5-methyl-1H-imidazole, our newly discovered lead compound targeting human glutaminyl cyclases (QCs). Three synthesized compounds exhibit substantially improved inhibitory activities against QCs, with the most effective one showing an IC50 value of 8 nM and 3.5-fold better than clinical candidate PQ912.

Wildfire is a severe natural disaster that poses a significant threat to the natural environment, as well as the safety of human life and property. The timely detection of wildfires plays a critical role in minimizing their detrimental impact. Himawari-8, a geostationary satellite equipped with an advanced Himawari imager (AHI) sensor, can provide full-disk data every 10 min, thus enabling near real-time and large-scale monitoring of wildfires. In this article, a wildfire detection method based on the spatiotemporal features of Himawari-8 data is proposed. First, a temporal convolutional network (TCN) is employed to predict the brightness temperature of the bands related to wildfire detection, achieving prediction results with a mean absolute error (MAE) of 0.28 K, a mean square error (MSE) of 0.30 K2, and a mean absolute percentage error (MAPE) of 0.10%. Then, various feature strategies are devised from spectral, spatial, and temporal aspects, and machine learning models are utilized for wildfire detection research. Among the considered strategies, strategy 4, which integrates spectral, spatial, and temporal features with the random forest (RF) algorithm, exhibits the most effective wildfire detection performance. It achieves a precision of 0.62, an omission of 0.34, and an F1-score of 0.64. Compared with the threshold method, precision increased by 0.05, omission decreased by 0.31, and F1-score increased by 0.21. To further evaluate practical applicability, the combination of strategy 4 and the RF is employed for wildfire detection near power grid transmission lines. In this scenario, out of the 295 real wildfires, 253 are successfully detected, resulting in a recall of 0.86. These experimental results affirm the effectiveness of the proposed method for wildfire detection.

Wildfire is a serious natural disaster that poses a serious threat to the safety of human life and property. Currently, there are many researches related to satellite wildfire detection, but few can achieve near real-time monitoring results. Himawari-8 geostationary satellite can provide full disk data every 10 minutes, making near real-time monitoring of wildfires possible. In this paper, a wildfire detection method based on Himawari-8 for multi-temporal data is proposed. In our method, we use temporal convolutional network (TCN) to predict the brightness temperature and achieve excellent prediction results, the mean absolute error (MAE) is 0.28 K, mean square error (MSE) is 0.30 K2, and mean absolute percentage error (MAPE) is 0.10 %. Then, the predicted values combined with other features as model inputs, and machine learning classification models were used for wildfire detection. The experimental results showed that the combination of multi-layer perceptron (MLP) model and strategy 2 containing brightness temperature predicted values achieved an accuracy of 90.91% in wildfire detection.

In recent years, the number of geological disasters in Sichuan province has significantly increased due to the influence of earthquakes and extreme climate, as well as the disturbance to the geological environment by human activities. In the paper, the interferometric synthetic aperture radar (InSAR) technology was introduced to monitor potential geological hazards in different elevation intervals, taking parts of Dujiangyan City, Wenchuan County, and Mao County in Sichuan Province, China as examples. Firstly, the data such as synthetic aperture radar (SAR) images and precision orbit determination (POD) precise orbit ephemerides from 2018 to 2020, high-resolution optical satellite images and digital elevation model (DEM) were collected. Secondly, the differential InSAR (D-InSAR), persistent scatterer InSAR (PS-InSAR), small baseline subset InSAR (SBAS-InSAR), offset-tracking, and distributed scatterer InSAR (DS-InSAR) algorithms were used to invert the surface deformation of the study area. Finally, the remote sensing interpretation methods were comprehensively combined with the InSAR deformation anomaly monitoring results to monitor the potential geological hazards.

Increasingly serious data security and privacy protection issues make federated learning (FL) gradually evolve to be an important technology in the field of artificial intelligence (AI). Meanwhile, in consideration of the huge demands for network access and computing resources from massive IoT devices, ultra-dense edge computing (UDEC), which integrates mobile edge computing (MEC) and ultra-dense network (UDN), has turned out to be a promising network architecture in the era of 5G and even 6G. Facing requirements on ultra-low processing latency, performing FL for UDEC confronts many challenges, one of which is how to relieve the barrel effect caused by the difference in computing power of local devices while ensuring overall FL efficiency. Nevertheless, little work can be found in this area. Toward this end, the paper takes the lead in studying FL for UDEC, and proposes an inter-server collaborative federated learning method by grouping the servers and clients. Theoretical analysis and numerical results corroborate that our proposed inter-server collaborative method can significantly reduce the waiting time during local training without reducing the learning accuracy, thus improving the overall efficiency.

Due to the outstanding characteristics of unmanned aerial vehicles (UAV), i.e., maneuverability and flexibility, UAV enabled mobile edge computing (MEC) has become a widely attractive research direction. However, single-UAV cannot be qualified for numerous tasks and application scenarios in view of its limited computing capacity, while multi-UAV enabled MEC is still in the initial stage, and most existing work transformed the problem of multi-UAV enabled MEC into multiplied single-UAV. The UAV swarm can make UAVs cooperate intelligently, and accomplish diversified tasks in complex environments at low cost, which is regarded as a promising development direction of UAV technology. Nevertheless, it is inefficient since each UAV node is responsible for both communication and computation, and multi-hop transmission among UAVs may lead to a very high delay. Toward this end, the paper takes the lead in studying the problem of grouping and role division in UAV swarm-based edge computing, and puts forward a grouping and role division algorithm to solve it. Final experimental results corroborate that the complexity of our algorithm is less than that of the traditional algorithm, and role division can maximize the use of communication and computing resources.

Accurate Human Epithelial-2 (HEp-2) cell image classification plays an important role in the diagnosis of many autoimmune diseases. However, the traditional approach requires experienced experts to artificially identify cell patterns, which extremely increases the workload and suffer from the subjective opinion of physician. To address it, we propose a very deep residual network (ResNet) based framework to automatically recognize HEp-2 cell via cross-modal transfer learning strategy. We adopt a residual network of 50 layers (ResNet-50) that are substantially deep to acquire rich and discriminative feature. Compared with typical convolutional network, the main characteristic of residual network lie in the introduction of residual connection, which can solve the degradation problem effectively. Also, we use a cross-modal transfer learning strategy by pre-training the model from a very similar dataset (from ICPR2012 to ICPR2016-Task1). Our proposed framework achieves an average class accuracy of 95.63% on ICPR2012 HEp-2 dataset and a mean class accuracy of 96.87% on ICPR2016-Task1 HEp-2 dataset, which outperforms the traditional methods.

In this paper, a vision-based obstacle avoiding path generation problem is considered for autonomous mobile robots under a top-view workspace. The collision-free path planning problem is converted to a convex optimization problem that can be solved numerically using linear matrix inequalities (LMI). A new optimal (shortest) path cost formulation is given for LMI optimization using a novel Line of Sight Meshing (LSM) method. As compared to the traditional meshing algorithms such as Voronoi and Delaunay, the LSM generates fewer mesh cells which results in reduced computation time. A virtual path diagram (VPD), consisting of all collision-free piecewise straight-line paths, is then found for robot navigation. The LMI optimization method is then used to find the optimal (shortest) collision-free path from the VPD set. In addition to distance, other constraints, such as terrain condition and curvature of the path can be incorporated in the cost function for constrained optimal solution. Finally, a rapid prototyping (RP) environment has been developed, which is used for hardware implementation of the algorithm. The generated paths are then converted to motion commands, which are sent wirelessly from a base-station to mobile robots for motion control.