Semantic segmentation is a key technology for remote sensing image analysis widely used in land cover classification, natural disaster monitoring, and other fields. Unlike traditional image segmentation, there are various targets in remote sensing images, with a large feature difference between the targets. As a result, segmentation is more difficult, and the existing models retain low accuracy and inaccurate edge segmentation when used in remote sensing images. This paper proposes a multi-attention-based semantic segmentation network for remote sensing images in order to address these problems. Specifically, we choose UNet as the baseline model, using a coordinate attention-based residual network in the encoder to improve the extraction capability of the backbone network for fine-grained features. We use a content-aware reorganization module in the decoder to replace the traditional upsampling operator to improve the network information extraction capability, and, in addition, we propose a fused attention module for feature map fusion after upsampling, aiming to solve the multi-scale problem. We evaluate our proposed model on the WHDLD dataset and our self-labeled Lu County dataset. The model achieved an mIOU of 63.27% and 72.83%, and an mPA of 74.86% and 84.72%, respectively. Through comparison and confusion matrix analysis, our model outperformed commonly used benchmark models on both datasets. Full article

“Extended Reality (XR)” refers to a unified platform or content that supports all forms of “reality”—e.g., 2D, 3D virtual, augmented, and augmented virtual. We explore how the mobile device can support such a concept of XR. We evaluate the XR user experiences of multi-mode and multitasking among three mobile platforms—(1) bare smartphone (PhoneXR), (2) standalone mobile headset unit (ClosedXR), and (3) smartphone with clip-on lenses (LensXR). Two use cases were considered through: (a) Experiment 1: using and switching among different modes within a single XR application while multitasking with a smartphone app, and (b) Experiment 2: general multitasking among different “reality” applications (e.g., 2D app, AR, VR). Results showed users generally valued the immersive experience over usability—ClosedXR was clearly preferred over the others. Despite potentially offering a balanced level of immersion and usability with its touch-based interaction, LensXR was not generally received well. PhoneXR was not rated particularly advantageous over ClosedXR even if it needed the controller. The usability suffered for ClosedXR only when the long text had to be entered. Thus, improving the 1D/2D operations in ClosedXR for operating and multitasking would be one way to weave XR into our lives with smartphones. Full article

The combination of blockchain and internet of things (IoT) technology realizes reliable storage of IoT data. However, the data stored on the blockchain (on-chain) face the problem of poor scalability and inefficient retrieval. In this paper, the on-chain data scalability schemes based on transactions and smart contracts are first proposed. Subsequently, on the basis of the above on-chain data scalability scheme based on transactions, an on-chain data index based on skip lists is proposed to improve the retrieval efficiency. The experimental results show that both the on-chain data scalability schemes achieve on-chain data scalability while reducing storage overhead. Meanwhile, the on-chain data index based on skip lists has significantly improved dynamic range retrieval efficiency and reduced the time complexity of single data retrieval to O(log(n)). Full article

As multimedia technology has advanced in recent years, the use of enormous image libraries has dramatically expanded. In applications for image processing, image retrieval has emerged as a crucial technique. Content-based face image retrieval is a well-established technology in many real-world applications, such as social media, where dependable retrieval capabilities are required to enable quick search among large numbers of images. Humans frequently use faces to recognize and identify individuals. Face recognition from official or personal photos is becoming increasingly popular as it can aid crime detectives in identifying victims and criminals. Furthermore, a large number of images requires a large amount of storage, and the process of image comparison and matching, consequently, takes longer. Hence, the query speed and low storage consumption of hash-based image retrieval techniques have garnered a considerable amount of interest. The main contribution of this work is to try to overcome the challenge of performance improvement in image retrieval by using locality-sensitive hashing (LSH) for retrieving top-matched face images from large-scale databases. We use face soft biometrics as a search input and propose an effective LSH-based method to replace standard face soft biometrics with their corresponding hash codes for searching a large-scale face database and retrieving the top-k of the matching face images with higher accuracy in less time. The experimental results, using the Labeled Faces in the Wild (LFW) database together with the corresponding database of attributes (LFW-attributes), show that our proposed method using LSH face soft biometrics (Soft BioHash) improves the performance of face image database search and retrieval and also outperforms the LSH hard face biometrics method (Hard BioHash). Full article

Massive multiple-input multiple-output (MIMO) is a profitable technique to greatly boost spectral efficiency, which has been embraced by the fifth-generation (5G) and sixth-generation (6G) mobile communication systems. By exploiting appropriate downlink precoding algorithms, base stations (BSs) equipped with a large number of antennas are able to provide service to multiple users as well as several cells at the same time and frequency. However, the mutual coupling effect due to the compact antenna array gives misleading results in massive MIMO communication systems. In this paper, we focus on the mutual coupling effect for massive MIMO systems with maximal ratio transmission (MRT), zero-forcing (ZF), regularize ZF (RZF), and minimum mean square error (MMSE) precoding to solve the mutual coupling problem. Additionally, we construct the closed-form expressions of the spectral efficiency (SE) to evaluate the effect of mutual coupling on system performance. Simulation results validate the effectiveness of the proposed mutual coupling effect assessment method and demonstrate the significant impacts of mutual coupling on massive MIMO system performance. Full article

With the proliferation of low-Earth-orbit (LEO) satellites, existing satellite networks need to be enhanced to better handle time-sensitive flows (TSFs). However, the migration of time-sensitive network (TSN) technology to satellite networks is challenged by the large space–time range and limited on-board resources, particularly in providing differentiated quality-of-service guarantees for multilevel TSFs. To address this issue, we propose a multilevel queue-based TSN technique that uses latency requirements as an indicator for traffic scheduling. This approach improves the time-sensitive transmission capability of services with different requirements in LEO satellite networks. We conducted a simulation evaluation under a Walker constellation, and the results demonstrate that our proposed method could significantly improve network throughput, and reduce the packet loss ratio by 90% and the time-out ratio by 14.5%. Additionally, our proposed mechanism could accommodate more TSFs with acceptable latency requirements. Full article

The premise of vehicle intelligent decision making is to obtain vehicle motion state parameters accurately and in real-time. Several state parameters cannot be measured directly by vehicle sensors, so estimation algorithms based on filtering are effective solutions. The most representative algorithm is the Kalman filter, especially the standard unscented Kalman filter (UKF) that has been widely used in vehicle state estimation because of its superiority in dealing with nonlinear filtering problems. However, although the UKF assumes that the noise statistics of the system are known, due to the complex and changeable operating conditions, sensor aging and other factors, these noises vary. In order to realize high-precision vehicle state estimation, a noise-adaptive UKF algorithm is proposed in this article. The maximum a posteriori (MAP) algorithm is used to dynamically update the noise of the vehicle system, and it is embedded into the update step of the UKF to form an adaptive unscented Kalman filter (AUKF). The system will dynamically update the noise when noise statistics are unknown and prevent filter divergence by adjusting the mean and covariance of the estimated noise to improve accuracy. On this basis, the proposed method is verified by the joint simulation of CarSim and Matlab/Simulink, confirming that the AUKF performs better than the standard UKF in estimation accuracy and stability under different degrees of noise disturbance, and the estimation accuracy for the yaw rate, side slip angle and longitudinal velocity is improved by 20.08%, 40.98% and 89.91%, respectively. Full article

With the continuous development of digital agriculture and intelligent forestry, the demand for three-dimensional modeling of trees or plants using agricultural robots is also increasing. Laser radar technology has gradually become an important technical means for agricultural robots to obtain three-dimensional information about trees. When using laser radar to scan trees, incomplete point cloud data are often obtained due to leaf occlusion, visual angle limitation, or operation error, which leads to quality degradation of the subsequent 3D modeling and quantitative analysis of trees. At present, a lot of research work has been carried out in the direction of point cloud completion, in which the deep learning model is the mainstream solution. However, the existing deep learning models have mainly been applied to urban scene completion or the point cloud completion of indoor regularized objects, and the research objects generally have obvious continuity and symmetry characteristics. There has been no relevant research on the point cloud completion method for objects with obvious individual morphological differences, such as trees. Therefore, this paper proposes a single-tree point cloud completion method based on feature fusion. This method uses PointNet, based on point structure, to extract the global features of trees, and EdgeConv, based on graph structure, to extract the local features of trees. After integrating global and local features, FoldingNet is used to realize the generation of a complete point cloud. Compared to other deep learning methods on the open source data set, the CD index using this method increased by 21.772% on average, and the EMD index increased by 15.672% on average, which proves the effectiveness of the method in this paper and provides a new solution for agricultural robots to obtain three-dimensional information about trees. Full article

In exploring the flight delay problem, traditional deep learning algorithms suffer from low accuracy and extreme computational complexity; therefore, the deep flight delay prediction algorithm is difficult to directly deploy to the mobile terminal. In this paper, a flight delay prediction model based on the lightweight network ECA-MobileNetV3 algorithm is proposed. The algorithm first preprocesses the data with real flight information and weather information. Then, in order to increase the accuracy of the model without increasing the computational complexity too much, feature extraction is performed using the lightweight ECA-MobileNetV3 algorithm with the addition of the Efficient Channel Attention mechanism. Finally, the flight delay classification prediction level is output via a Softmax classifier. In the experiments of single airport and airport cluster datasets, the optimal accuracy of the ECA-MobileNetV3 algorithm is 98.97% and 96.81%, the number of parameters is 0.33 million and 0.55 million, and the computational volume is 32.80 million and 60.44 million, respectively, which are better than the performance of the MobileNetV3 algorithm under the same conditions. The improved model can achieve a better balance between accuracy and computational complexity, which is more conducive mobility. Full article

Exchanging information and data within smart grids is crucial to improve interoperability among system users. Traditional cloud-based data exchange schemes are centralized on a single trusted third-party platform. The schemes consequently suffer from single-point failure, a lack of data protection, and uncontrolled access. Blockchain enables data exchange in a decentralised and secure manner. A new platform is proposed in this work for exchanging data within smart grids using blockchain. It allows users to securely exchange data without losing ownership. This platform provides solutions to three critical problems: privacy, scalability, and user ownership. Particularly, the blockchain-based smart contract technology gives participants the programmability to access data. All interactions are authenticated and recorded by the other participants in the tamper-resistant blockchain network. Furthermore, the performance of the proposed blockchain platform is enhanced by integrating it with an artificial neural network (ANN). The proposed method is used to predict the network’s throughput and latency, and the network administrator uses these predicted values to change the network’s settings for a high throughput and low latency. Throughout the results, the proposed model achieves performance improvements in blockchain-enabled information and data exchange and adapts well to the dynamics of smart grids. Full article

Co-optimization for memory bank compilation and placement was suggested as a way to improve performance and power and reduce the size of a memory subsystem. First, a multi-configuration SRAM compiler was realized that could generate memory banks with different PPA by splitting or merging, upsizing or downsizing, threshold swapping, and aspect ratio deformation. Then, a timing margin estimation method was proposed for the memory bank based on placed positions. Through an exhaustive enumeration of various configuration parameters under the constraint of timing margins, the best SRAM memory compilation configuration was found. This method could be integrated into the existing physical design flow. The experimental results showed that this method achieved up to an 11.1% power reduction and a 7.6% critical path delay reduction compared with the traditional design method. Full article

Nasopharyngeal carcinoma (NPC) is a malignant tumor, and early diagnosis and timely treatment are important for NPC patients. Accurate and reliable detection of NPC lesions in magnetic resonance (MR) images is very helpful for the disease diagnosis. However, recent deep learning methods need to be improved for NPC detection in MR images. Because NPC tumors are invasive and usually small in size, it is difficult to distinguish NPC tumors from the closely connected surrounding tissues in a huge and complex background. In this paper, we propose an automatic detection method, named MWSR-YLCA, to accurately detect NPC lesions in MR images. Specifically, we design two modules, the multi-window settings resampling (MWSR) module and an improved YOLOv7 embedded with a coordinate attention mechanism (YLCA) module, to detect NPC lesions more accurately. First, the MWSR generates a pseudo-color version of MR images based on a multi-window resampling method, which preserves richer information. Subsequently, the YLCA detects the NPC lesion areas more accurately by constructing a novel network based on an improved YOLOv7 framework embedded with the coordinate attention mechanism. The proposed method was validated on an MR image set of 800 NPC patients and obtained 80.1% mAP detection performance with only 4694 data samples. The experimental results show that the proposed MWSR-YLCA method can perform high-accuracy detection of NPC lesions and has superior performance. Full article

Task scheduling algorithms based on reinforce learning (RL) have been important methods with which to improve the performance of cloud platforms; however, due to the dynamics and complexity of the cloud environment, the action space has a very high dimension. This not only makes agent training difficult but also affects scheduling performance. In order to guide an agent’s behavior and reduce the number of episodes by using historical records, a task scheduling algorithm based on adaptive priority experience replay (APER) is proposed. APER uses performance metrics as scheduling and sampling optimization objectives with which to improve network accuracy. Combined with prioritized experience replay (PER), an agent can decide how to use experiences. Moreover, this algorithm also considers whether a subtask is executed in a workflow to improve scheduling efficiency. Experimental results on Tpc-h, Alibaba cluster data, and scientific workflows show that a model with APER has significant benefits in terms of convergence and performance. Full article

Currently, many Chinese font translation models adopt the method of dividing character components to improve the quality of generated font images. However, character components require a large amount of manual annotation to decompose characters and determine the composition of each character as input for training. In this paper, we establish a Chinese font translation model based on generative adversarial network without decomposition. First, we improve the method of image enhancement for Chinese character images. It helps the model learning structure information of Chinese character strokes to generate font images with complete and accurate strokes. Second, we propose a visual attention adversarial network. By using visual attention block, the network catches global and local features for constructing details of characters. Experiments demonstrate our method generates high-quality Chinese character images with great style diversity including calligraphy characters. Full article

This paper proposes a methodology of delivering the emulation hardware of several step-down converter power stages. The generalized emulator design methodology follows these steps: first, the power stage is described using an ordinary differential equation system; second, the ordinary differential equation system is solved using Euler’s method, and thus an accurate time-domain model is obtained; next, this time-domain model can be described using either general-purpose programming language (MATLAB, C, etc.) or hardware description language (VHDL, Verilog, etc.). As a result, the emulator has been created; validation of the emulator may be carried out by comparing it to SPICE transient simulations. Finally, the validated emulator can be implemented on the preferred target technology, either in a general-purpose processor or a field programmable gate array. As the emulator relies on the ordinary differential equation system of the power stage, it has better behavioral accuracy than the emulators based on average state space models. Moreover, this paper also presents the design methodology of a manually tuned proportional–integrative–derivative controller deployed on a field programmable gate array. Full article