As the scale of wireless sensor networks (WSNs) continues to expand, challenges such as excessive network energy consumption and load imbalance have become increasingly severe. Existing non-uniform clustering protocols rely on fixed parameters and local information, lack the ability to dynamically perceive global energy differences, and are thus difficult to adapt to the dynamic changes of large-scale networks for balancing energy consumption and load. To address this issue, this paper proposes an adaptive cluster radius multi-hop routing protocol (ACRM) suitable for large-scale WSNs. The protocol provides a decision-making basis for the adjustment of nodes’ personalized competition radii and auction-based cluster head selection through an energy disparity factor quantified based on the Gini coefficient. On this basis, cluster head selection is modeled as a static game with incomplete information. Through an auction mechanism, cluster head seats are allocated according to the principle of maximizing bid prices, and a price decay strategy is introduced to prevent overloading of low-energy nodes. In the routing phase, intra-cluster routing employs hierarchical decision-making to select a subset of nodes for multi-hop communication to reduce energy consumption; while inter-cluster routing establishes multi-hop paths based on a direction-aware scoring mechanism that integrates node direction and energy, effectively avoiding path detours and reverse transmissions. Additionally, unlike existing non-uniform clustering protocols, ACRM effectively addresses the issues of cluster head overload near the base station and excessive energy consumption from frequent clustering through directly connected node offloading and adaptive periodic reconfiguration. Simulation results show that in a 500m×500m network scenario, the network stability period of ACRM reaches 636 rounds, which is over 100% higher than that of protocols such as LEACH, LEACH-OR, EEUC, and DEBUC, approximately 61.8% higher than PUAG, and 18.4% higher than UCRTD; significant improvements are also observed in the overall network lifetime and the number of data packets received by the base station.

The Internet of Things (IoT) environment contains many different types of devices, each with different functionalities, communication protocols, and security capabilities, which makes the IoT a complex challenge for security protection. Therefore, network intrusion detection (NID) is needed to detect intrusions in the network to secure the IoT. In recent years, deep learning (DL)-based intrusion detection systems have achieved excellent results, but they tend to require high-computational resources and storage space, which is not feasible for most IoT devices. In this article, we propose a lightweight intrusion detection model based on self-knowledge distillation (SKD), namely, tied block convolution lightweight deep neural network (TBCLNN), which improves the detection accuracy while also reducing the number of model parameters and computational cost. Specifically, we use the binary Harris Hawk optimization algorithm (bHHO) for dimensionality reduction of traffic features. We use lightweight convolution, such as tied block convolution (TBC), to design lightweight neural network (LNN) models with residual and inverse residual structures. Moreover, we propose an improved SKD loss function to solve the sample imbalance problem and compensate for the performance degradation caused by lightweight neural networks. The multiclassification accuracy of our proposed method exceeds 99% on all three publicly available IoT datasets. The experimental results show that our method has a small model size and requires only low-computational resources, making it suitable for resource-constrained IoT intrusion detection.

The disperse structure distributions (discreteness) and variant scattering characteristics (variability) of SAR airplane targets lead to special challenges of object detection and recognition. The current deep learning-based detectors encounter challenges in distinguishing fine-grained SAR airplanes against complex backgrounds. To address it, we propose a novel physics-guided detector (PGD) learning paradigm for SAR airplanes that comprehensively investigate their discreteness and variability to improve the detection performance. It is a general learning paradigm that can be extended to different existing deep learning-based detectors with ”backbone-neck-head” architectures. The main contributions of PGD include the physics-guided self-supervised learning, feature enhancement, and instance perception, denoted as PGSSL, PGFE, and PGIP, respectively. PGSSL aims to construct a self-supervised learning task based on a wide range of SAR airplane targets that encodes the prior knowledge of various discrete structure distributions into the embedded space. Then, PGFE enhances the multi-scale feature representation of a detector, guided by the physics-aware information learned from PGSSL. PGIP is constructed at the detection head to learn the refined and dominant scattering point of each SAR airplane instance, thus alleviating the interference from the complex background. We propose two implementations, denoted as PGD and PGD-Lite, and apply them to various existing detectors with different backbones and detection heads. The experiments demonstrate the flexibility and effectiveness of the proposed PGD, which can improve existing detectors on SAR airplane detection with fine-grained classification task (an improvement of 3.1% mAP most), and achieve the state-of-the-art performance (90.7% mAP) on SAR-AIRcraft-1.0 dataset. The project is open-source at https://github.com/XAI4SAR/PGD.

The increasing model size and computation load of convolutional neural networks (CNN) pose a grand challenge to deploy CNN models on edge computing devices. To further improve performance without significant accuracy loss, this paper developed a neural architecture search (NAS) method to achieve a layer-wise mixed-precision-and-sparsity (LAMPS) CNN. However, this optimization cannot be fully utilized and directly mapped to existing AI accelerators due to the irregu- lar computation of sparse and multi-precision data. To tackle this challenge, this work proposed a LAMPS vector systolic accelerator and demonstrated state-of-the-art results. Experi- mental results show that the LAMPS accelerator on Xilinx ZCU102 achieves an average performance of 756.83 GOPS and 470.25 GOPS when accelerating the NAS-optimized VGG16 and Resnet18, respectively, leading to 1.3-6.0x speed-up over the state- of-the-art accelerators on FPGA.

Cluster head (CH) nodes near the base station (BS) die prematurely due to the need to perform more communication tasks, which can lead to disruption of network connectivity and makes it difficult to achieve the goal of load balancing in Wireless Sensor Networks (WSNs), this problem is known as hot spot problem. To solve this problem, non-uniform clustering strategies have been proposed. However, all the current related non-uniform clustering protocols have some drawbacks, such as the lack of a theoretical basis for the value of the multi-hop threshold distance between clusters, the limited attention to the data transmission process, and the insufficient load balancing of the protocols in the face of complex and variable networks. Based on the above problems, we propose an unequally clustered routing protocol based on multi-hop threshold distance (UCRTD) for WSNs. First, this paper analyzes the energy-saving threshold distance for multi-hop communication in conjunction with the energy consumption model of WSNs, and based on the multi-hop energy-saving threshold distance, a strategy for selecting the best energy-saving relay node is proposed. In intra-cluster communication, considering that medium-sized networks form larger clusters, cluster members (CMs) within the cluster that are farther away from the CH take multi-hop communication. For inter-cluster communication, to maximize the network lifetime, the most energy-efficient CH node with the highest residual energy is selected in the routing phase for alternate multi-hop transmission, and this strategy effectively prolongs the network lifetime and also ensures the load balance of the network. Simulation results show that the proposed UCRTD effectively prolongs the network lifetime and maintains good load balancing under multiple network environments when compared with four existing EEUC, EBUC, EADUC, and EAUCA unequal clustering protocols as well as LEACH protocol.

Abstract OpenMP supports the use of target offloading compile guidance instructions to invoke heterogeneous-platform accelerators to compute core code segments; however, unreasonable use of target offloading instructions can make the data transfer process time-consuming. The problem of unused array transfer and unused data segment transfer arises when the amount of data transferred from the host side to the device side exceeds the amount of data required for the core computation on the device side. For the transmission of unused arrays, the use of the transmitted arrays is guided by adding a filter to eliminate the transmission of redundant data; for the transmission of unused data segments, the use of arrays is quickly determined on the basis of the filter, and valid data are transmitted by optimizing Clang’s code generation strategy after obtaining the lengths of the data segments in core computation. Experiments are performed using the Polybench benchmark; the optimized speedup for unused array transfer reaches 7%, and the optimized speedup for unused data segment transfer reaches 10%. The experimental results show that data transfer optimization for target offloading characteristics can help improve program performance.

In the field of intrusion detection, existing deep learning algorithms have limited capability to effectively represent network data features, making it challenging to model the complex mapping relationship between network data and attack behavior. This limitation, in turn, impacts the detection accuracy of intrusion detection systems. To address this issue and further enhance detection accuracy, this paper proposes an algorithm called the Fourier Neural Network (FNN). The core of FNN consists of a Deep Fourier Neural Network Block (DFNNB), which is composed of a Hadamard Neural Network (HNN) and a Fourier Neural Network Layer (FNNL). In a DFNNB, the HNN is responsible for sampling the network intrusion data samples in different time domain spaces. The FNNL, on the other hand, performs a Fourier transform on the samples outputted by the HNN and maps them to the frequency domain space, followed by a filtering process. Finally, the data processed by filtering are transformed back to the time domain space for subsequent feature extraction work by the DFNNB. Additionally, to enhance the algorithm’s detection accuracy and filter out noise signals, this paper also introduces a High‐energy Filtering Process (HFP), which eliminates noise signals from the data signal and reduces interference on the final detection result. Due to the ability of FNN to process network data in both the time domain space and the frequency domain space, it possesses a stronger capability in expressing data features. Finally, this paper conducts performance evaluations on the KDD Cup99, NSL‐KDD, UNSW‐NB15, and CICIDS2017 datasets. The results demonstrate that the proposed FNN‐based IDS model achieves higher detection rates, lower false alarm rates, and better detection performance than classical deep learning and machine learning methods.

In rotating machinery fault diagnosis, domain adaptation (DA) transfer learning-based framework has been attracting great attentions to tackle the problem of inconsistent feature distribution and insufficient labeled fault feature data. However, most of the existing approaches mainly focus on either the cross-domain distribution alignment or manifold subspace learning, which faces two critical limitations: 1) it is hard to overcome the feature distortions when aligning the distribution in the original feature space and 2) subspace learning is insufficient to decrease the distribution divergence. To address the above limitations, this work proposes an intelligent fault diagnosis scheme based on supervised DA with manifold embedding and key features selection. It first applies maximal overlap discrete wavelet packet transform (MODWPT) to process the vibration signals and performs the statistical feature extraction. In order to ensure that the selected key features are conductive to domain adaption, the fault discriminative ability and domain invariance of the features are investigated based on the domain differences and Laplacian score. Then, it presents a new supervised domain adaption with manifold embedding for the distribution alignment in manifold subspace by taking the class information and neighboring relationships into account. Finally, an intra classifier is learned to predict the unlabeled target domain. The proposed fault diagnosis scheme is evaluated using a set of practical data sets of motor and bearing. The extensive experimental results demonstrate that it significantly outperforms the comparative models and achieves much more effective fault diagnosis under different working conditions.

In clinics, a radiology report is crucial for guiding a patient's treatment. However, writing radiology reports is a heavy burden for radiologists. To this end, we present an automatic, multi-modal approach for report generation from a chest x-ray. Our approach, motivated by the observation that the descriptions in radiology reports are highly correlated with specific information of the x-ray images, features two distinct modules: (i) Learned knowledge base: To absorb the knowledge embedded in the radiology reports, we build a knowledge base that can automatically distill and restore medical knowledge from textual embedding without manual labor; (ii) Multi-modal alignment: to promote the semantic alignment among reports, disease labels, and images, we explicitly utilize textual embedding to guide the learning of the visual feature space. We evaluate the performance of the proposed model using metrics from both natural language generation and clinic efficacy on the public IU-Xray and MIMIC-CXR datasets. Our ablation study shows that each module contributes to improving the quality of generated reports. Furthermore, the assistance of both modules, our approach outperforms state-of-the-art methods over almost all the metrics. Code is available at https://github.com/LX-doctorAI1/M2KT.

Session-based travel packages recommendation aims to predict users’ next click based on their current and historical sessions recorded by Online Travel Agencies (OTAs). Recently, an increasing number of studies attempted to apply Graph Neural Networks (GNNs) to the session-based recommendation and obtained promising results. However, most of them do not take full advantage of the explicit latent structure from attributes of items, making learned representations of items less effective and difficult to interpret. Moreover, they only combine historical sessions (long-term preferences) with a current session (short-term preference) to learn a unified representation of users, ignoring the effects of historical sessions for the current session. To this end, this article proposes a novel session-based model named STR-VGAE, which fills subtasks of the travel packages recommendation and variational graph auto-encoders simultaneously. STR-VGAE mainly consists of three components: travel packages encoder , users behaviors encoder , and interaction modeling . Specifically, the travel packages encoder module is used to learn a unified travel package representation from co-occurrence attribute graphs by using multi-view variational graph auto-encoders and a multi-view attention network. The users behaviors encoder module is used to encode user’ historical and current sessions with a personalized GNN, which considers the effects of historical sessions on the current session, and coalesce these two kinds of session representations to learn the high-quality users’ representations by exploiting a gated fusion approach. The interaction modeling module is used to calculate recommendation scores over all candidate travel packages. Extensive experiments on a real-life tourism e-commerce dataset from China show that STR-VGAE yields significant performance advantages over several competitive methods, meanwhile provides an interpretation for the generated recommendation list.

Fast screening and diagnosis are critical in COVID-19 patient treatment. In addition to the gold standard RT-PCR, radiological imaging like X-ray and CT also works as an important means in patient screening and follow-up. However, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists. To reduce the workload of radiologists, we propose DeltaNet to generate medical reports automatically. Different from typical image captioning approaches that generate reports with an encoder and a decoder, DeltaNet applies a conditional generation process. In particular, given a medical image, DeltaNet employs three steps to generate a report: 1) first retrieving related medical reports, i.e., the historical reports from the same or similar patients; 2) then comparing retrieved images and current image to find the differences; 3) finally generating a new report to accommodate identified differences based on the conditional report. We evaluate DeltaNet on a COVID-19 dataset, where DeltaNet outperforms state-of-the-art approaches. Besides COVID-19, the proposed DeltaNet can be applied to other diseases as well. We validate its generalization capabilities on the public IU-Xray and MIMIC-CXR datasets for chest-related diseases.

Optimized model and energy-efficient hardware are both required for deep neural networks (DNNs) in edge-computing area. Neural architecture search (NAS) methods are employed for DNN model optimization with resulted multi-precision networks. Previous works have proposed low-precision-combination (LPC) and high-precision-split (HPS) methods for multi-precision networks, which are not energy-efficient for precision-scalable vector implementation. In this paper, a bit-split-and-combination (BSC) based vector systolic accelerator is developed for a precision-scalable energy-efficient convolution on edge. The maximum energy efficiency of the proposed BSC vector processing element (PE) is up to 1.95× higher in 2-bit, 4-bit and 8-bit operations when compared with LPC and HPS PEs. Further with NAS optimized multi-precision CNN networks, the averaged energy efficiency of the proposed vector systolic BSC PE array achieves up to 2.18× higher in 2-bit, 4-bit and 8-bit operations than that of LPC and HPS PE arrays.

Neural architecture search (NAS) optimized multi-bit-width convolutional neural network (CNN) maintains the balance between network performance and efficiency, thus enlightening a promising method for accurate yet energy-efficient edge computing. In this work, we propose a high throughput three-dimensional (3D) systolic accelerator for NAS optimized CNNs, in which the input feature matrix, weight matrix and output feature matrix are delivering vertically, horizontally and perpendicularly through the systolic array respectively. With 3D systolic data flow, the processing time and logic resources consumption can be both reduced compared to the classical non-stationary systolic array. Besides, Booth-based multi-bit-width (INT2/4/8) multiply-add-accumulation (MAC) unit is developed within the 3D systolic accelerator. Deployed on FPGA platform Xilinx ZCU102, peek performance of the convolutional layer can reach as high as 2775 GOPS for INT2, 1650 GOPS for INT4, and 816 GOPS for INT8 respectively. The average performance on accelerating full NAS VGG16 network is 647 GOPS.

Automatic chest radiology report generation is critical in clinics which can relieve experienced radiologists from the heavy workload and remind inexperienced radiologists of misdiagnosis or missed diagnose. Existing approaches mainly formulate chest radiology report generation as an image captioning task and adopt the encoder-decoder framework. However, in the medical domain, such pure data-driven approaches suffer from the following problems: 1) visual and textual bias problem; 2) lack of expert knowledge. In this paper, we propose a knowledge-enhanced radiology report generation approach introduces two types of medical knowledge: 1) General knowledge, which is input independent and provides the broad knowledge for report generation; 2) Specific knowledge, which is input dependent and provides the fine-grained knowledge for chest X-ray report generation. To fully utilize both the general and specific knowledge, we also propose a knowledge-enhanced multi-head attention mechanism. By merging the visual features of the radiology image with general knowledge and specific knowledge, the proposed model can improve the quality of generated reports. The experimental results on the publicly available IU-Xray dataset show that the proposed knowledge-enhanced approach outperforms state-of-the-art methods in almost all metrics. And the results of MIMIC-CXR dataset show that the proposed knowledge-enhanced approach is on par with state-of-the-art methods. Ablation studies also demonstrate that both general and specific knowledge can help to improve the performance of chest radiology report generation.

Interval type-2 fuzzy sets provide us with additional degrees of freedom to represent the uncertainty and the fuzziness of the real word than traditional type-1 fuzzy sets. Interval type-2 fuzzy numbers ranking has an important role in the decision making analysis. In this paper, the probatilistic mean value and variance of interval type-2 fuzzy numbers are proposed based on the Mellin transform for type-1 fuzzy numbers. The interval type-2 fuzzy number with the higher mean is ranked higher. If the mean values are equal the one with the smaller variance is judged higher rank. On this basis, some new distance measures and possibility degree formula are proposed to comparing interval type-2 fuzzy numbers based on their Mellin mean value and variance. Some benchmarking numerical examples are given, and some interpretation issues are explained.