Neuromorphic computing has endeavored a novel computing paradigm that entails a bio-inspired architecture to reproduce the remarkable functionalities of the human brain, such as massively parallel processing and extremely low-power consumption. However, those promising merits can be greatly canceled by the mismatched communication infrastructure in large-scale hardware implementation, in view of the vast degree of neural connectivity, the unstructured spike dataflow, and the unbalanced model workload assignment. In an effort to tackle those challenges, this work presents NeuroHexa, a network-on-chip (NoC) architecture intended for multi-core neuromorphic design. NeuroHexa adopts a customized intra-chip hexagonal topology, which can be further cascaded in 6 directions by either 2D or 3D chiplet integration. Designed in globally asynchronous, locally synchronous (GALS) methodology, a group of processing nodes can operate in independent work pace to further improve resource utilization. To satisfy the varied requirement of data reuse across the chip, NeuroHexa proposes a flexible multicast routing mechanism to best adapt to the model-defined dataflow. And under a specific congestion scenario, NeuroHexa can switch its routing algorithm between deterministic routing and fully adaptive routing modes. The presented NoC router is evaluated in 28nm CMOS, where we achieve the maximal throughput as 179.2Gbps, and the best energy efficiency as 4.872pJ/packet at the area overhead of 0.0226mm2.

Neuromorphic computing is attracting significant attention due to its bio-mimetic characteristics. Consequently, neuromorphic hardware platforms have emerged as innovative computing architectures for acceleration. However, the fixed nature of data flow and resources leads to considerable inefficiencies in storage and computation, thereby limiting both utilization efficiency and overall performance. This severely hinders the deployment of edge artificial intelligence (AI) models. To address these issues, we present a multi-core neuromorphic accelerator named CROSSCUT. This crossbar-based system supports both spiking neural network (SNN) and artificial neural network (ANN) paradigms and has a capacity of 256K neurons and 288M synapses. By leveraging the Neuron Package Mechanism (NPM) and Synapse Compress Mechanism (SCM), CROSSCUT can increase input data scale by 64 times and reduce wasted resources and computations by 46.7%, ensuring high compatibility with diverse network structures in machine learning models. Additionally, a Tree-Mesh hybrid network on chip (NoC) is constructed for inter-core communication. Implemented on Xilinx XCVU9P FPGA, CROSSCUT can achieve a peak performance of 431.9 GSOPS/s and 121.13 GSOPS/W energy efficiency. The inference accuracy on MNIST is 98.2%.

This paper presents a two-channel time-interleaved (TI) noise-shaping (NS) successive approximation register (SAR) analog-to-digital converter (ADC) with wide bandwidth, high resolution, and low power consumption. A shared loop filter realizes residue filtering between interleaved channels by midway feedback. The error feedback-cascaded integrator feedforward (EF-CIFF) loop filter architecture is adopted to achieve 3rd-order noise shaping with only one residue amplifier. A ring buffer is adopted to provide accurate gain by forming an inner feedback loop. PVT robust biasing and split current source architecture make the ring buffer immune to PVT variation and VCMmismatch. A prototype ADC in 28nm CMOS achieves 62.0 dB SNDR over 75 MHz bandwidth and consumes 5.9 mW, leading to a FoMs of 163 dB.

This paper introduces a hierarchical compilation approach for multi-channel reconfigurable analog-to-digital converter (ADC) systems, motivated by the need for highly flexible and scalable solutions in programmable converter arrays (PCAs). Unlike existing methods that mainly rely on manual circuitlevel adjustments with high complexity, limited scalability, and low flexibility, this method provides a structured and scalable hierarchical mapping scheme. This facilitates flexible and efficient configuration by integrating software and hardware design, making it highly suitable for automation and future expansion. It paves the way for the automatic synthesis, optimization and future expansion of PCAs.

This live demonstration presents a highly programmable analog-to-digital converter (ADC). The ADC is composed of an array of conversion blocks, each of which can be individually programmed. These conversion blocks can collaborate through a flexible bus system to achieve a wide range of functionalities and performance coverage. An interactive online programming system based on Matlab intuitively demonstrates how the ADC chip can be easily programmed. Additionally, the system includes a design rule check function to ensure programming validity, and a simulator to predict the actual performance. The system showcases an ADC performance range of MHz to GHz bandwidth and 30dB to 80dB SNDR.

In order to achieve the brain-like advantages over conservative computers, previous neuromorphic researchers have stretched the hardware explorations of the hybrid artificial neural network (ANN) and spiking neural network (SNN) inference approaches, as well as the efficient bio-plausible and gradient-based SNN training mechanisms. However, a versatile accelerator for both ANN-SNN inference and training is little addressed. In this work, we introduce HyNITA, a neuromorphic processor that supports accelerating both inference and training tasks of hybrid ANN and SNN models. Regarding the similarity and distinction, a pair of working stages are distinguished and distributed to multiple simple cores. The accelerator optimizes the interchange dataflow in a scalable chip design, following a reconfigurable design methodology to integrate the involved equation calculations in the dynamic process of neurons. The evaluation results show it achieves an accuracy of 99.65% and 99.34% on training ANN MNIST and SNN N-MNIST datasets.

Detecting small floating targets on the sea surface has long been a major challenge in radar signal processing. Recently, deep learning (DL) has attracted considerable attention for its potential to improve detection probability. However, its performance heavily relies on the availability of sufficiently labeled datasets, which are often difficult to acquire in complex sea clutter environments. Therefore, this letter introduces the Complex-Valued Hybrid Spatio-Temporal Network (CVHSTNet), a novel maritime radar target detection method designed for low-data scenarios that utilizes time-frequency (TF) representations of radar echoes as inputs. To mitigate the overfitting issue, CVHSTNet is intentionally designed with a shallow architecture, integrating a three-layer complex-valued convolutional neural network (CV-CNN) with a one-layer complex-valued bidirectional long short-term memory network (CV-BiLSTM). Unlike existing real-valued models that overlook phase information, our method operates directly on complex-valued data to capture the complete signal representation. More importantly, this hybrid architecture enables the network to effectively exploit both spatial and temporal characteristics, thereby further enhancing feature representations. Comprehensive experiments on 40 datasets from the IPIX database demonstrate that, with only 50 samples per range cell for training, the proposed method achieves a detection probability exceeding 90% in 37 out of 40 datasets, with a false alarm rate (FAR) of 10−3. To the best of our knowledge, this is the first time a DL-based approach has demonstrated the ability to distinguish between small floating targets and sea clutter under limited labeled radar data conditions.

This work presents a new analog-to-digital converter (ADC) architecture named programmable converter array (PCA) for multi-standard signal acquisition. Unlike prior reconfigurable ADCs that are mainly configured at the circuit level, PCA is highly flexible at the architecture level and can process multiple input signals simultaneously for mode concurrency. The elemental units in the converter array are Conversion Blocks (CBs) based on successive approximation register (SAR) ADCs. Multiple CBs can interleave or run synergically through a bus system to form sophisticated architectures. Fabricated in 28nm CMOS, the prototype converter array can be configured as over 16 modes, with an SNDR range from 30dB to 82dB and an aggregate bandwidth from sub-MHz to 1000MHz. The prototype achieves a peak Schreier figure of merit (FoMs) of 176dB while maintaining FoMs over 165dB in most configurations, and occupies only 0.1mm2 of silicon area.

Spiking neural networks (SNNs) are a promising alternative to traditional artificial neural networks (ANNs) due to their biologically inspired and event-driven characteristics. Similar to ANN, the weights in SNN also exhibit significant sparsity. How to make full use of the weight sparsity in SNN and coordinate hardware design to optimize resource utilization has become a challenge. In this brief, a multicore SNN accelerator named Cactus, based on a fine-grained and programmable structured pruning strategy is proposed. It is a balanced block pruning strategy, which achieves high accuracy in image and speech classification tasks while ensuring high processing elements (PEs) utilization. To increase flexibility, the block size can be configured as$8\times 8$,$16\times 16$,$32\times 32$,$64\times 64$in Cactus. Implemented on Xilinx Kintex UltraScale XCKU115 FPGA board, Cactus can operate at 200 MHz frequency, achieving 198.59GSOP/s peak performance and 56.47GSOP/W energy efficiency at 75% weight sparsity and 0% spike sparsity.

In various domains such as surveillance and smart retail, pedestrian retrieval, centering on person re-identification (Re-ID), plays a pivotal role. Existing Re-ID methodologies often overlook subtle internal attribute variations, which are crucial for accurately identifying individuals with changing appearances. In response, our paper introduces the Attribute-Guided Pedestrian Retrieval (AGPR) task, focusing on integrating specified attributes with query images to refine retrieval results. Although there has been progress in attribute-driven image retrieval, there remains a notable gap in effectively blending robust Re-ID models with intra-class attribute variations. To bridge this gap, we present the Attribute-Guided Transformer-based Pedestrian Retrieval (ATPR) framework. ATPR adeptly merges global ID recognition with local attribute learning, ensuring a co-hesive linkage between the two. Furthermore, to effectively handle the complexity of attribute interconnectivity, ATPR organizes attributes into distinct groups and applies both inter-group correlation and intra-group decorrelation regularizations. Our extensive experiments on a newly estab-lished benchmark using the RAP dataset [32] demonstrate the effectiveness of ATPR within the AGPR paradigm.

Convolutional neural networks require a huge amount of computation in video applications. For some specific tasks, such as surveillance, differential frame convolution reuses inter-frame data and significantly reduces multiplication and accumulation. However, there are still some challenges in improving energy efficiency of differential frame convolution on chips. Firstly, differential frame convolution brings additional on-chip storage for reusing inter-frame data. Secondly, in post-processing of differential frame convolution, there are more memory accessing and arithmetic logic operations. Therefore, sparse working mode is of vital importance for the post-processing. In response to these challenges, this work proposes an on-chip fusion storage architecture for energy-efficient differential frame convolution and a pixel-level pipeline data flow that supports the sparsity of features. The simulation of our accelerator implemented in 28nm CMOS can achieve energy efficiency by 3.09× compared with other state-of-the-art works

This work proposes a dithered-digital-mixing background timing-skew calibration method for time-interleaved (TI) analog-to-digital converters (ADCs). Unlike prior digital-mixing methods that limit the input bandwidth or lead the calibration process to a limit cycle, the proposed method enhances the input bandwidth to the Nyquist frequency and guarantees the convergence. This is achieved by a pseudo-random binary sequence generator that produces a dither signal. Practical considerations including thermal noise and the step size of variable delay lines are discussed. Behavioral simulation results demonstrate the effectiveness of the proposed method with an improvement of signal-to-noise-and-distortion ratio from 26.3dB to 52.6dB for a 5GS/s 9b 16-channel TI ADC.

Inspired by the brain, Spiking Neural Network (SNN) applies temporally sparse spiking communication to gain more bio-mimetic and highly energy efficient computing. The current mainstream platforms for SNN applications are typically the combination of Host+FPGA+Chip Array, which requires an efficient host to preprocess and encode data. It’s not suitable for end-to-end tasks in edge due to its high system power consumption of host and non-negligible high latency of protocol conversion on FPGA. In addition, Convolutional Neural Network (CNN), exhibits strong feature extraction capabilities. Like the brain's visual system, a hierarchical CNN-SNN hybrid network, in which SNN can make use of CNN’s feature extraction capabilities during encoding, can achieve better performance. In this study, we design a 64Neural-Core Array and integrate it with a CNN encoder and a low-power RISC-V CPU within a System-on-Chip (SoC) to enable comprehensive end-to-end hybrid network application support. The proposed heterogeneous SoC is implemented on a Virtex UltraScale+ XCVU9P FPGA, featuring 32.8K neurons, 37.7M synapses and 578GOPS/s peak performance. It processes MNIST classification with a peak throughput of 2022 images per second at frequency of 250MHz. This design gains a balance between high throughput and recognition accuracy simultaneously.

Achieving energy-efficient massive ultrareliable and low-latency communications (E2-mURLLC) is a promising application prospect for sixth-generation (6G) mobile communication networks. However, there are some insurmountable obstacles, such as a large number of potential users, complex and diverse small-scale and shadow fading, and stringent energy efficiency (EE), reliability, and latency requirements. Considering the above obstacles, we propose a cell-free massive multiple-input–multiple-output (MIMO) architecture based on the$\kappa $-$\mu $shadowed fading model, and maximum-ratio combining (MRC) multiuser detection with simple path-loss decoding (S-PLD) to achieve the simultaneous optimization of EE, latency, and reliability. Furthermore, the finite blocklength information theory is used to uncover the relationship among EE, reliability, latency, and achievable data rate when the packet size is small. Simulation results show that compared with the massive MIMO architecture, using our architecture with MRC multiuser detection and S-PLD can support a threefold increase in the number of access users, reduce transmit power by 90%, achieve a nearly 100 times reliability enhancement, and shorten transmission latency by 23.3%. Consequently, a cell-free massive MIMO system with MRC multiuser detection and S-PLD, as a considerable significant potential to facilitate the advancement from URLLC to E2-mURLLC, is promising to support some time-sensitive applications with massive access, such as unmanned aerial vehicles, the Industrial Internet of Things and vehicle-to-vehicle communications.

Radar emitter classification (REC) plays an important role in modern warfare. Traditional REC methods have difficulty identifying complex radar signals in the present day. Inspired by biology, spiking neural networks (SNNs) have gradually gained widespread attention due to their low power characteristics. Compared with convolutional neural networks (CNNs), SNNs are more suitable for application in the field of REC. The reason is that SNN can not only maintain higher accuracy in the presence of noise interference, but also reduce the power consumption of mobile devices. However, it is challenging to make full use of the input sparsity of radar emitter signals and the weight sparsity of pruned SNN models. In this paper, a 28-nm neuromorphic processor for REC named NeuroREC is proposed. It uses matrix compression algorithms to store sparse weights on chip, and designs corresponding spike detection circuits for this purpose. As a single-core design, we propose a ping-pong running mechanism to alleviate the imbalance between IO throughput and peak performance. Two SNN models for classifying RadioML2016.b and RadioML2018.a datasets are deployed on the chip, achieving competitive accuracy with only 8 timesteps, and demonstrating better robustness than CNN. Fabricated in 28-nm CMOS process, NeuroREC runs at frequencies ranging from 22.5MHz to 744MHz. Under specific sparsity conditions, it can reach an energy efficiency of 7.22TSOP/W for 8-bit weight.

This research investigates the potential of in vivo learning to enhance visual representation learning for image-based person re-identification (re-ID). Compared to traditional self-supervised learning (which require external data), the introduced in vivo learning utilizes supervisory labels generated from pedestrian images to improve re-ID accuracy without relying on external data sources. Three carefully designed in vivo learning tasks, leveraging statistical regularities within images, are proposed without the need for laborious manual annotations. These tasks enable feature extractors to learn more comprehensive and discriminative person representations by jointly modeling various aspects of human biological structure information, contributing to enhanced re-ID performance. Notably, the method seamlessly integrates with existing re-ID frameworks, requiring minimal modifications and no additional data beyond the existing training set. Extensive experiments on diverse datasets, including Market1501, CUHK03-NP, Celeb-reID, Celeb-reid-light, PRCC, and LTCC, demonstrate substantial enhancements in rank-1 precision compared to state-of-the-art methods.

Recent studies have seen significant advancements in the field of long-term person re-identification (LT-reID) through the use of clothing-irrelevant or insensitive features. This work takes the field a step further by addressing a previously unexplored issue, the Clothing Status Distribution Shift (CSDS). CSDS refers to the differing ratios of samples with clothing changes to those without clothing changes between the training and test sets, leading to a decline in LT-reID performance. We establish a connection between the performance of LT-reID and CSDS, and argue that addressing CSDS can improve LT-reID performance. To that end, we propose a novel framework called Meta Clothing Status Calibration (MCSC), which uses meta-learning to optimize the LT-reID model. Specifically, MCSC simulates CSDS between meta-train and meta-test with meta-optimization objectives, optimizing the LT-reID model and making it robust to CSDS. This framework is designed to prevent overfitting and improve the generalization ability of the LT-reID model in the presence of CSDS. Comprehensive evaluations on seven datasets demonstrate that the proposed MCSC framework effectively handles CSDS and improves current state-of-the-art LT-reID methods on several LT-reID benchmarks.

Brain-inspired spiking neural network (SNN) has recently attracted widespread interest owing to its event-driven nature and relatively low-power hardware for transmitting highly sparse binary spikes. To further improve energy efficiency, some matrix compression algorithms are used for weight storage. However, the weight sparsity of different layers varies greatly. For a multicore neuromorphic system, it is difficult for the same compression algorithm to adapt to all the layers of SNN model. In this work, we propose a weight density adaptation architecture with hybrid compression method for SNN, named Marmotini. It is a multicore heterogeneous design, including three types of cores to complete computation of different weight sparsity. Benefiting from the hybrid compression method, Marmotini minimizes the waste of neurons and weights as much as possible. Besides, for better flexibility, a reconfigurable core that can be configured to compute convolutional layer or fully connected layer is proposed. Implemented on Xilinx Kintex UltraScale XCKU115 field-programmable gate array (FPGA) board, Marmotini can operate at 150-MHz frequency, achieving 244.6-GSOP/s peak performance and 54.1-GSOP/W energy efficiency at 0% spike sparsity.

Spiking neural networks (SNNs) have attracted widespread interest due to their event-driven and low-power nature. Compared to Artificial Neural Networks (ANNs), SNNs have time dimension information and present more realistic brain-inspired computing models. However, it is challenging to deploy sparse spiking neuron network models on dense neuromorphic processors. In this paper, a spiking neural network accelerator with sparse spike and weight is presented, using ping-pong architecture to improve system data throughput. To reduce the inference delay, the proposed accelerator supports the decoupling of calculation of membrane potential and leaky integrate-and-fire (LIF) dynamics computing in the feedforward neural networks. Implemented on Xilinx Kintex UltraScale FPGA, the accelerator can achieve the peak performance of 65.7 GSOP/s and the energy efficiency of 41.7 GSOP/W in the task of classifying MNIST dataset. Under the full load, the whole system can run ping-pong when more than 43 time steps are calculated at a time.

Gesture recognition based on WiFi has recently attracted wide attention from academia and industry. However, the position-independent sensing is still a challenging problem. Existing work has made a breakthrough by extracting position-independent features through multiple transceiver pairs. We explore the position-independent gesture recognition methods that maintain accuracy and robustness while providing only one transceiver pair. Due to the limited information access and spatial resolution in that scenarios, noise cannot be effectively eliminated and gesture features are easily confused. Therefore, we propose a subcarrier selection method to select the subcarrier with less interference by noise. We extract dynamic phase as features for gesture recognition, which is position-independent. In addition, we split the dynamic phase variations of different gestures into a series of segments code based on the actions (traverse, approach and away). The easily confused gesture features are transformed into distinguishable gesture code. We developed a prototype on a Commercial Off-The-Shelf WiFi device. Extensive experimental results show that our system achieves position-independent gesture recognition using only one transceiver pair within an acceptable error range, achieving a maximum recognition accuracy of 94.33% and an average recognition accuracy of 87.25% in different positions.

Recent research has demonstrated the great potential of leveraging existing WiFi infrastructure for ubiquitous non-invasive respiration monitoring. Although this WiFi-based approach opens up a new direction for respiratory rate detection, existing studies are limited as only some simple scenarios have been considered. Consequently, the feasibility of using this technology in realistic scenarios needs to be further verified, especially for ensuring the detection performance in the following two cases: (1) long-distance and (2) different body postures. To address above two complex case studies, this paper presents several selection mechanisms to enable a robust WiFi-based respiration detection system. Firstly, a double-variance antenna links selection strategy is proposed to select the most sensitive link for breathing movements. Moreover, three subcarrier selection combining solutions are developed, where secondary selection is conducted to obtain the optimal respiration pattern in diverse situations. We conduct extensive experiments in two typical scenes. The evaluation results demonstrate that the detection error of our system is less than 0.7 bpm in each scene. More importantly, it outperforms compared with state-of-the-art systems.

Passive sensing technology enables Wi-Fi-based human activity recognition (HAR), which has been widely noted in recent years. This letter presents a novel Wi-Fi-based class-incremental human activity recognition system that allows for the gradual addition of new activity categories. To the best of our knowledge, this is the first attempt to recognize all previously learned activities under the constraint of limited samples for both the original and newly added activity classes. It is challenging in 1) how to prevent catastrophic forgetting of old activities and 2) how to leverage as few samples as possible to accurately recognize new activities. Therefore, a phased training and update strategy is proposed to avoid the knowledge-forgetting issue. Furthermore, to alleviate the unsatisfactory performance problem caused by insufficient samples of new categories, we design an amplitude-phase enhanced convolution neural network, which integrates an attention mechanism and dual loss function to enhance the feature discrimination and the generalization capability of the model. Extensive experiments show that our system can operate with promising perceptual accuracy in different datasets.

Spiking neural networks (SNNs) have widely drew attention of recent research. With brain-spired dynamics and spike-based communication, SNN is supposed to be a more energy-efficient neural network than existing artificial neural network (ANN). To make better use of the temporal sparsity of spikes and spatial sparsity of weights in SNN, this paper presents a sparse SNN accelerator. It adopts a novel self-adaptive spike compressing and decompressing (SASCD) mechanism for different input spike sparsity, as well as on-chip compressed weight storage and processing. We implement the octa-core design on field programmable gate array (FPGA). The results demonstrate a peak performance of 35.84 GSOPs/s, which is equivalent to 358.4 GSOPs/s in dense SNN accelerators for 90% weight sparsity. For the single-layer perceptron model in rate coding implemented on the hardware, SASCD reduces the time step intervals from 2.15 $\mu$ s to 0.55 $\mu$ s.

High-speed time-interleaved analog-to-digital converters (TI-ADCs) are sensitive to timing skew mismatch. Autocorrelation-based background timing skew calibration techniques require small hardware overhead as they rely on the TI-ADC input signal for calibration. However, such techniques suffer from a very long convergence time. This paper proposes a new correlation-based technique that boosts convergence speed by orders of magnitude compared to existing autocorrelation-based techniques. The technique uses a digital window detector and calculates the signal correlation funnction around zero-crossings only. Practical design considerations including thermal noise, clock jitter, quantization and offset mismatch are discussed. Behavioral simulation results for two TI-ADCs with different speeds, resolutions and interleaving factors are presented.

This paper presents a second-order VCO-based $\Delta\Sigma$ ADC with a fully digital feedback adder, which is highly digital, area efficient and low power. Both the first and second loop integrator are implemented by VCOs and are free of OTA. A novel digital adder is proposed to realize the secondary feedback, significantly reducing the power and area of the second stage. The proposed ADC is designed in a 28nm CMOS technology under 0.9V supply, consuming only 1.14mW. The simulated SNDR and SFDR are 72.5dB and 84.1dB respectively over a 5MHz signal bandwidth.

Accurate and efficient foliage penetration (FOPEN) target recognition plays a vital role in many mission-critical applications, ranging from civilian to surveillance and military. Recently, device-free sensing (DFS), as an emerging technique, has gained great popularity because it requires no dedicated equipment other than wireless transceivers. Although some DFS-based approaches have been successfully applied in foliage environments, they are vulnerable to climate dynamics and heavily rely on re-labeling large amounts of new data when the weather is altered. To address this issue, a CNN-based weather adaptive target recognition network (WATRNet) is proposed in this paper. Specifically, a lightweight weather conditional normalization (WCN) module is embedded atop each convolutional block to encode inputs under different weather conditions into a shared latent feature space. Under an end-to-end learning manner, the proposed WATRNet first learns knowledge from sufficient labeled data under a certain weather condition to achieve a precise classifier. When applying this model under another weather condition, only the WCN module needs to be retrained using limited new labeled samples to learn weather-invariant features, while the rest convolutional parameters in WATRNet are frozen. Consequently, the domain discrepancy caused by climate variations can be adaptively mitigated with as few relabeled data as possible. Comprehensive evaluations are carried out on a real FOPEN dataset collected under four different weather conditions. Experimental results verify that the presented method can achieve over 90% accuracy, even when it implements from a normal weather condition to another severe weather condition with only small amounts of training samples.

The task of infrared-visible person re-identification (IV-reID) is to recognize people across two modalities (i.e., RGB and IR). Existing cutting-edge approaches normally use a pair of images that have the same IDs (i.e., ID-tied cross-modality image pairs) and input them into an ImageNet-trained ResNet50. The ResNet50 backbone model can learn shared features across modalities to tolerate modality discrepancies between RGB and IR. This work will unveil a Modality Bias Training (MBT) problem that is less discussed in IV-reID, which will demonstrate that MBT significantly compromises the performance of IV-reID. Due to MBT, IR information can be overwhelmed by RGB information during training when the ResNet50 model is pretrained based on a large amount of RGB images from ImageNet. Thus, the trained models are more inclined to RGB information. Accordingly, the cross-modality generalization ability of the model is also compromised. To tackle this issue, we present a Dual-level Learning Strategy (DLS) that 1) enforces the focus of the network on ID-exclusive (rather than ID-tied) labels of cross-modality image pairs to mitigate the problem of MBT and 2) introduces third modality data that contain both RGB and IR information to further prevent the information from the IR modality from being overwhelmed during training. Our third modality images are generated by a generative adversarial network. A dynamic ID-exclusive Smooth (dIDeS) label is proposed for the generated third modality data. In experiments, comprehensive experiments are carried out to demonstrate the success of DLS in tackling the MBT issue exposed in IV-reID.

Spiking neural networks (SNNs) have been witnessing the developing trends to reduce the model size and improve the hardware efficiency for area- and energy-based applications, which are processed by model pruning and data compressions. However, it is challenging to exploit the unstructured sparsity of SNNs for the dense neuromorphic processors. In this article, we present an efficient sparse SNN accelerator (ESSA), which leverages both the temporal sparsity of spike events and the spatial sparsity of weights in SNN inference. It provides both the compressed weights for sparse SNNs and the uncompressed weights for compact SNNs. The self-adaptive spike compression is proposed for sparse spike scenarios, leading to the improvement of throughput by$3.2\times $. ESSA executes a flexible fan-in–fan-out tradeoff by using combinable dendrites, which overcomes the fan-in limitation in neuromorphic systems. Furthermore, a low-latency intrachip spike multicast method is adopted to reduce the resource overhead. Implemented on the Xilinx Kintex Ultrascale field-programmable gate array (FPGA), ESSA achieves an equivalent performance of 253.1 GSOP/s and an energy efficiency of 32.1 GSOP/W for 75% weight sparsity at 140 MHz. The implementation of a four-layer fully connected SNN is expected to perform$2.6~\mu \text{s}$per time step and the energy consumption is$14.6~\mu \text{J}$. Our results demonstrate that ESSA outperforms several state-of-the-art application-specific integrated circuit (ASIC) or FPGA neuromorphic processors.

Long-Term person re-identification (LT-reID) exposes extreme challenges because of the longer time gaps between two recording footages where a person is likely to change clothing. There are two types of approaches for LT-reID: biometrics-based approach and data adaptation based approach. The former one is to seek clothing irrelevant biometric features. However, seeking high quality biometric feature is the main concern. The latter one adopts fine-tuning strategy by using data with significant clothing change. However, the performance is compromised when it is applied to cases without clothing change. This work argues that these approaches in fact are not aware of clothing status (i.e., change or no-change) of a pedestrian. Instead, they blindly assume all footages of a pedestrian have different clothes. To tackle this issue, a Regularization via Clothing Status Awareness Network (RCSANet) is proposed to regularize descriptions of a pedestrian by embedding the clothing status awareness. Consequently, the description can be enhanced to maintain the best ID discriminative feature while improving its robustness to real-world LT-reID where both clothing-change case and no-clothing-change case exist. Experiments show that RCSANet performs reasonably well on three LT-reID datasets.

Neuromorphic hardware platforms inspired by human brain have emerged as novel non von Neumann computing architectures. They were proved excellent platforms for spiking neural network (SNN) implementations. However, implementing artificial neural networks (ANNs) on existing neuromorphic hardware platforms is still a daunting task because of critical limitations on coding scheme, maximum of fan-in, and highest weight precision in them. In this paper, we introduce a neuromorphic processor developed for various neural networks implementations including ANNs and SNNs. We employ spatio-temporal coding scheme based on spike events. By combining low-precision dendrites, the chip can implement weight precision between 1 bit and 8 bits and scalable fan-in. The 3.66-mm2chip fabricated in 28-nm CMOS with a maximum fan-in of 72 K per neuron demonstrates unprecedented compatibility with ANN applications compared to previously-proposed neuromorphic chips.

Event-based spiking neural network (SNN) has displayed a promising prospect to realize real-time, efficient and intelligent hardware platforms. Whereas great efforts are still being appealed to explore the possibility of introducing online learning abilities to neuromorphic systems. In this paper, a 28-nm CMOS neuromorphic processor is presented, fulfilling online learning by adopting counter and lookup table (LUT) based spike-timing-dependent plasticity (STDP) rule. Designed to work at high-precision scenarios, the presented processor integrates up to 1024 neurons and 256K signed 9-bit synapses. It also ensures chip array interconnection to fit large neural networks. Moreover, by utilizing the sparse property of spike events to minimize activity rate, the typical power consumption is further reduced to 3.348mW for training MNIST dataset.

WiFi-based human activity recognition technology has attracted widespread attention for its prominent application value and theoretical significance. Existing approaches have made great achievements in the same domain sensing, which means the activity samples applied for training the model have a similar distribution with the testing data. However, in practical application, we hope that the same activity of different people with various states and habits in different locations can be accurately recognized and produce the same reaction. Therefore, cross-domain sensing technology is pretty important. Some studies explore the location-independent and environment-independent methods, but few attempts consider the influence of the initial states of the users, such as standing and sitting, which actually have very different effects on the transmission of the wireless signal. This paper presents a human activity recognition method adapted to different initial states. Meanwhile, we solve the accompanying issue of the small sample size sensing, obviating the need for the cumbersome wok resulting from the massive data collection. We take advantage of the idea of metric learning and few-shot learning to realize cross-domain sensing with very few samples. The experiments demonstrate the feasibility and excellent performance of our method, which could recognize human activities with different initial states as the training data.

Device-free human activity recognition based on WiFi signals has become a very popular research field. However, it still has one major problem that is activities of “unseen” humans cannot be accurately classified, which makes it infeasible in real-world application. To tackle this issue, in this paper, we present a human activity recognition (HAR) system based on identity (ID) transfer mechanism named CrossID, which can cross the boundaries of identity by taking the high-level personal characteristics of the source domain and target domain as IDs for training and transferring. Specifically, we employ the margin-based loss function to improve the training speed and accuracy. To fully evaluate the feasibility of the proposed approach for human activity recognition, a variety of the data samples have been taken at 16 locations conducted by six people performing four different types of activities. Through extensive experiments on our dataset, we verify the effectiveness, robustness, and generalization ability of proposed system. Our average recognition rate in the target domain is 95%, which is slightly lower than 98% in the source domain.

Device-free sensing (DFS) is an emerging technology that empowers wireless communication systems with the ability for not only data communication but also smart sensing. By taking advantage of machine-learning technologies, DFS transforms traditional wireless communication networks into intelligent context-aware networks and will open the doors for a myriad of promising 6G-enabled Internet of Things (IoT) applications, ranging from smart home to smart buildings. Although significant progress has been made for human activity recognition at a single location by leveraging this technology, performance at multiple locations has not been fully explored. As far as multilocation activity sensing is concerned, the performance is compromised along with the change of locations and labor-intensive annotation works caused by multilocation. To tackle this issue, an activity decomposition network (ActNet) is presented to decompose the activity information directly from input samples by using the training data from different locations together. Instead of dealing with different locations separately, our ActNet can assemble data from different locations together for training to mitigate the data limitation issue caused by a single location. To achieve this, a multiple-input–multiple-output (MIMO)-orthogonal frequency-division multiplexing (OFDM) technology-based prototype system is utilized to collect data samples at 24 different locations in a cluttered office environment. Especially, for each location, only ten samples of each activity are used for training. Experiments demonstrate that the average classification accuracy is 94.6% across all locations with ensured robustness produced by our method.

Hardware security remains as a major concern in the circuit design ow. Logic block based encryption has been widely adopted as a simple but effective protection method. In this paper, the potential threat arising from the rapidly developing field, i.e., machine learning, is researched. To illustrate the challenge, this work presents a standard attack paradigm, in which a three-layer neural network and a naive Bayes classifier are utilized to exemplify the key-guessing attack on logic encryption. Backed with validation results obtained from both combinational and sequential benchmarks, the presented attack scheme can specifically accelerate the decryption process of partial keys, which may serve as a new perspective to reveal the potential vulnerability for current anti-attack designs.

Current person re-identification (re-ID) works mainly focus on the short-term scenario where a person is less likely to change clothes. However, in the long-term re-ID scenario, a person has a great chance to change clothes. A sophisticated re-ID system should take such changes into account. To facilitate the study of long-term re-ID, this paper introduces a large-scale re-ID dataset called “Celeb-reID” to the community. Unlike previous datasets, the same person can change clothes in the proposed Celeb-reID dataset. Images of Celeb-reID are acquired from the Internet using street snap-shots of celebrities. There is a total of 1,052 IDs with 34,186 images making Celeb-reID being the largest long-term re-ID dataset so far. To tackle the challenge of cloth changes, we propose to use vector-neuron (VN) capsules instead of the traditional scalar neurons (SN) to design our network. Compared with SN, one extra-dimensional information in VN can perceive cloth changes of the same person. We introduce a well-designed ReIDCaps network and integrate capsules to deal with the person re-ID task. Soft Embedding Attention (SEA) and Feature Sparse Representation (FSR) mechanisms are adopted in our network for performance boosting. Experiments are conducted on the proposed long-term re-ID dataset and two common short-term re-ID datasets. Comprehensive analyses are given to demonstrate the challenge exposed in our datasets. Experimental results show that our ReIDCaps can outperform existing state-of-the-art methods by a large margin in the long-term scenario.The new dataset and code will be released to facilitate future researches.

Cross-domain person re-identification (re-ID) is challenging due to the bias between training and testing domains. We observe that if backgrounds in the training and testing datasets are very different, it dramatically introduces difficulties to extract robust pedestrian features, and thus compromises the cross-domain person re-ID performance. In this paper, we formulate such problems as a background shift problem. A Suppression of Background Shift Generative Adversarial Network (SBSGAN) is proposed to generate images with suppressed backgrounds. Unlike simply removing backgrounds using binary masks, SBSGAN allows the generator to decide whether pixels should be preserved or suppressed to reduce segmentation errors caused by noisy foreground masks. Additionally, we take ID-related cues, such as vehicles and companions into consideration. With high-quality generated images, a Densely Associated 2-Stream (DA-2S) network is introduced with Inter Stream Densely Connection (ISDC) modules to strengthen the complementarity of the generated data and ID-related cues. The experiments show that the proposed method achieves competitive performance on three re-ID datasets, i.e., Market-1501, DukeMTMC-reID, and CUHK03, under the cross-domain person re-ID scenario.

This paper considers person re-identification (re-ID) in the case of long-time gap (i.e., long-term re-ID) that concentrates on the challenge of clothes variation of each person. We introduce a new dataset, named Celebrities-reID to handle that challenge. Compared with current datasets, the proposed Celebrities-reID dataset is featured in two aspects. First, it contains 590 persons with 10,842 images, and each person does not wear the same clothing twice, making it the largest clothes variation person re-ID dataset to date. Second, a comprehensive evaluation using state of the arts is carried out to verify the feasibility and new challenge exposed by this dataset. In addition, we propose a benchmark approach to the dataset where a two-step fine-tuning strategy on human body parts is introduced to tackle the challenge of clothes variation. In experiments, we evaluate the feasibility and quality of the proposed Celebrities-reID dataset. The experimental results demonstrate that the proposed benchmark approach is not only able to best tackle clothes variation shown in our dataset but also achieves competitive performance on a widely used person re-ID dataset Market1501, which further proves the reliability of the proposed benchmark approach.

Military surveillance events and rescue activities are vital missions for the Internet-of-Things. To this end, foliage penetration for human detection plays an important role. However, although the feasibility of that mission has been validated, we observe that it still cannot perform promisingly under severe weather conditions, such as rainy, foggy, and snowy days. Therefore, in this paper, experiments are conducted under severe weather conditions based on a proposed deep learning approach. We present an auto-encoder/decoder (Auto-ED) deep neural network that can learn the deep representation and conduct classification task concurrently. Since the property of cost-effective, the device-free sensing techniques are used to address human detection in our case. As we pursue the signal-based mission, two components are involved in the proposed Auto-ED approach. First, an encoder is utilized that encode signal-based inputs into higher dimensional tensors by fractionally strided convolution operations. Then, a decoder is leveraged with convolution operations to extract deep representations and learn the classifier simultaneously. To verify the effectiveness of the proposed approach, we compare it with several machine learning approaches under different weather conditions. Also, a simulation experiment is conducted by adding additive white Gaussian noise to the original target signals with different signal to noise ratios. Experimental results demonstrate that the proposed approach can best tackle the challenge of human detection under severe weather conditions in the high-clutter foliage environment, which indicates its potential application values in the near future.

The well-known Internet of Things (IoT) is recently being considered for critical missions, such as search and rescue, surveillance, and border patrol. One of the most critical issues that these applications are currently facing is how to correctly distinguish between human and animal targets in a cost-effective way. In this paper, we present a relatively low-cost, but robust approach that uses a combination of device-free sensing (DFS) and machine-learning technologies to tackle this issue. In order to validate the feasibility of the presented approach, a variety of data is collected in a cornfield using impulse-radio ultra-wideband (IR-UWB) transceivers. These data are then used to investigate the influence of different statistical properties of the radio-frequency (RF) signal on the accuracy of human/animal target classification. Based on the probability density function of different statistical properties, two distinguishing features for target classification are found, namely, standard deviation and root mean spread delay spread. Using them, the impact on the classification accuracy due to different classifiers, number of training samples, and different values of signal-to-noise ratio is extensively verified. Even with the worst case, the classification accuracy of the system is still better than 91% in terms of distinguishing between human and animal targets (including goats and dogs), which indicates that the presented approach has a great potential to be deployed in the near future.

Foliage penetration (FOPEN) has been found to be a critical mission for a variety of applications, ranging from surveillance to military. Recently, an emerging technology, namely wireless sensor network (WSN)-based device-free sensing (DFS), has been introduced to the domain of FOPEN. This technology only utilizes radio-frequency signals for target detection and classification; thus, no additional hardware is required, just a wireless transceiver. Although the feasibility of using this technology for human detection indoors has been explored to some extent, it is questionable if the same technology can be transferred to outdoors. As far as FOPEN is concerned, the impact of seasonal variations on detection accuracy can be severe. To address this concern, in this paper, an experiment is conducted in four seasons, and how to ensure reasonable detection accuracy with seasonal variations is intensively investigated. To fully evaluate the potential of using the WSN-based DFS for FOPEN, an impulse-radio ultrawideband technology-based prototype is used to collect data samples in different seasons. Unlike the conventional approach based on a combination of statistical properties of received-signal strength and a support vector machine, this approach adopts two special measures for performance enhancement. One measure is to use a higher order cumulant (HOC) algorithm for feature extraction, so that the impact on detection accuracy due to unwanted clutters can be minimized. The other one is to determine the optimal parameters of the classifier by means of a flower pollination algorithm. Consequently, the adverse effects on detection accuracy due to variations of weather conditions in four seasons can be accommodated. According to the experimental result, it is shown that the average classification accuracy of the presented approach can be improved by at least 20% under all seasons with an ensured robustness.

In this letter, the possibility of using device-free sensing (DFS) technology for personnel detection in a foliage environment is investigated. Although the conventional algorithm that based on statistical properties of the received-signal strength (RSS) for target detection at indoor or open-field environment has come a long way in recent years, it is still questionable if this algorithm is fully functional at outdoor with the changing atmosphere and ground conditions, such as a foliage environment. To answer this question, a variety of the measured data have been taken using different targets in a foliage environment. Applying these data along with support vector machine, the impact on detection accuracy due to different classification algorithms is studied. An algorithm that based on the extraction of the high-order cumulant (HOC) of the signals is presented, while the conventional RSS-based one is used as a benchmark. The measurement results show that the classification accuracy of the HOC-based algorithm is better than the RSS-based one by at least 17%. Moreover, to ensure the reliability of the HOC-based approach, the impact on classification accuracy due to different numbers of training samples and different values of signal-to-noise ratio is extensively verified using experimentally recorded samples. To the best of our knowledge, this is the first time that a DFS-based sensing approach is demonstrated to have a potential to distinguish between human and small-animal targets in a foliage environment.