-
CoDetect: cooperative anomaly detection with privacy protection towards UAV swarm Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-22 Teng Li, Weiguo Lin, Ruichen Ma, Zhuo Ma, Yulong Shen, Jianfeng Ma
In this study, we introduce a novel framework for cooperative anomaly detection in UAV swarms. The scheme integrates an anomaly detection model, consensus algorithm, and lightweight communication authentication algorithm. Tailored to address external eavesdroppers and malicious Byzantine nodes, it effectively manages and mitigates Byzantine behavior while safeguarding internal communication. Simultaneously
-
Unleashing potentials with deep learning: decoding the complex events for distributed fiber optic sensing applications Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-22 Yujiao Li, Liqin Hu, Kuanglu Yu
Addressing the classification performance challenge in Φ-OTDR real-world applications due to the difficulty in obtaining enough labeled samples, we introduced and researched semi-supervised learning models tailored for Φ-OTDR event classification. Specifically, the XM-based models exhibit notable improvements in classification performance compared with the ST model based on pseudolabeling and the MT
-
Perception field based imitation learning for unlabeled multi-agent pathfinding Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-22 Wenjie Chu, Ailun Yu, Wei Zhang, Haiyan Zhao, Zhi Jin
This paper proposes an imitation learning method to learn a universal agent policy for unlabeled multi-agent pathfinding (unlabeled MAPF) in grid environments. The method transforms the unlabeled MAPF problem into a series of temporal-independent homogeneous classification problems for each agent. Based on this transformation, a neural network is designed to imitate a distance-optimal expert algorithm
-
Performance improvement of β-Ga2O3 SBD-based rectifier with embedded microchannels in ceramic substrate Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-19 Wen Hong, Chao Zhang, Fang Zhang, Xuefeng Zheng, Xiaohua Ma, Yue Hao
This study proposed and fabricated a β-Ga2O3 SBD-based rectifier with embedded microchannels in a ceramic substrate for active cooling for the first time. Experimental results demonstrate that this technique can increase the output power from 3.2 to 21.3 W, consuming only 0.9 mW of pump power. The achievements in this work indicate that embedded cooling offers a powerful technique to suppress the thermal
-
Global adaptive output-feedback tracking with prescribed performance for uncertain nonlinear systems Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-19 Yuan Wang, Yungang Liu
At present, one typical control strategy for guaranteeing transient and steady-state performance is funnel control and prescribed performance control. The strategy features completely discarding the system nonlinearities, even if they are completely known and available. Such an intrinsic feature requires the controller to produce a larger control effect to eliminate the negative impact caused by the
-
Mitigating set-stuck failure in 3D phase change memory: substituting square pulses with surge pulses Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-19 Ninghua Li, Wang Cai, Jun Xiang, Hao Tong, Weiming Cheng, Xiangshui Miao
In the devices that integrate phase change memory (PCM) and ovonic threshold switching (OTS), the OTS threshold voltage often surpasses the RESET operation voltage of PCM. The conventional application of square pulses hinders the successful completion of the SET operation in these integrated devices. To address this challenge, a novel pulse called the surge pulse is introduced, which comprises a high
-
Cooperative control for heterogeneous multi-agent systems: progress, applications, and challenges Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-18 Bing Yan, Peng Shi, Jonathon Chambers
This study provides an overview of the advancements, applications, and challenges in the field of heterogeneous MASs with a focus on cooperative control. It summarizes the existing secure control methods under cyber-attacks and safe control approaches in physical threats. Additionally, we discuss the potential applications of heterogeneous MASs and future research directions to address remaining challenges
-
Finite-time bearing-only formation of first-order multi-agent systems under pinning control Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-15 Chenjun Liu, Wei Zhu, Fenglan Sun
The finite-time bearing-only formation problem of first-order MASs under pinning control has been discussed in this study. Considering the situation of tracking moving formation in finite time, the validity of the pinning controller is verified by Lyapunov stability theory and numerical simulations. Besides, using the time-varying function with certain properties, a finite-time control mechanism is
-
A novel graph oversampling framework for node classification in class-imbalanced graphs Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-15 Riting Xia, Chunxu Zhang, Yan Zhang, Xueyan Liu, Bo Yang
Graph neural network (GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the
-
Distribution of polarization squeezed light through a 20 km fiber channel Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-12 Chao Li, Siyu Ren, Yanru Yan, Yalin Li, Meihong Wang, Xiaolong Su
We prepared and distributed the polarization squeezed light through a 20 km fiber channel. After this distribution, a polarization squeezed light with −0.57 dB squeezing is still observed. We demonstrate that the quantum variance of Ŝ3 and Ŝ2 decreases with the increase in the fiber length, while the variance of Ŝ1 increases, because of the increase in the loss and excess noise. By introducing the
-
Maximizing conditional independence for unsupervised domain adaptation Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-01 Yiming Zhai, Chuanxian Ren, Youwei Luo, Daoqing Dai
Unsupervised domain adaptation (UDA) studies how to transfer a learner from a labeled source domain to an unlabeled target domain with different distributions. Existing methods mainly focus on matching marginal distributions of the source and target domains, which probably leads to a misalignment of samples from the same class but different domains. In this paper, we tackle this misalignment issue
-
Granger causal representation learning for groups of time series Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-01 Ruichu Cai, Yunjin Wu, Xiaokai Huang, Wei Chen, Tom Z. J. Fu, Zhifeng Hao
Discovering causality from multivariate time series is an important but challenging problem. Most existing methods focus on estimating the Granger causal structures among multivariate time series, while ignoring the prior knowledge of these time series, e.g., the group of the time series. Focusing on discovering the Granger causal structures among groups of time series, we propose a Granger causal
-
Span-based joint entity and relation extraction augmented with sequence tagging mechanism Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-04-03 Bin Ji, Shasha Li, Hao Xu, Jie Yu, Jun Ma, Huijun Liu, Jing Yang
Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in a text span form. However, since previous span-based models rely on span-level classifications, they cannot benefit from token-level label information, which has been proven advantageous for the task. In this paper, we propose a sequence tagging augmented span-based network (STSN), a span-based
-
CPT: a pre-trained unbalanced transformer for both Chinese language understanding and generation Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Hang Yan, Fei Yang, Zhe Li, Hujun Bao, Xipeng Qiu
In this paper, we take the advantage of previous pre-trained models (PTMs) and propose a novel Chinese pre-trained unbalanced transformer (CPT). Different from previous Chinese PTMs, CPT is designed to utilize the shared knowledge between natural language understanding (NLU) and natural language generation (NLG) to boost the performance. CPT consists of three parts: a shared encoder, an understanding
-
Hybrid stochastic control strategy by two-layer networks for dissipating urban traffic congestion Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Xiaojing Zhong, Bin Pang, Feiqi Deng, Xueyan Zhao
This work proposed stochastic network control strategies for traffic congestion on roads from the perspectives of internal guidance and external intervention. Using three steps: establishing the controlled model, analyzing control effects theoretically, and conducting simulation experiments, the effectiveness of information guidance and random guidance is verified from both the theoretical and simulation
-
Improved RF power performance via electrostatic shielding effect using AlGaN/GaN/graded-AlGaN/GaN double-channel structure Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Chunzhou Shi, Ling Yang, Meng Zhang, Hao Lu, Mei Wu, Bin Hou, Xuerui Niu, Qian Yu, Wenliang Liu, Wenze Gao, Xiaohua Ma, Yue Hao
The direct current and radio frequency of DCGC-HEMT and DCTB-HEMT were systematically investigated. Owing to the utilization of a graded-AlGaN bottom barrier to provide more carriers and shield traps in the buffer, DCGC-HEMT exhibited greater saturated drain current and suppression in drain lag, enabling it to show greater output performance than DCTB-HEMT. The improvement in the former’s superior
-
Quantum key distribution over a mimicked dynamic-scattering channel Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Qi-Hang Lu, Fang-Xiang Wang, Wei Chen, Hai-Yang Fu, Yin-Jie Lu, Shuang Wang, De-Yong He, Zhen-Qiang Yin, Guang-Can Guo, Zheng-Fu Han
Free-space quantum key distribution (QKD) plays an important role in the global quantum network. However, free space channels suffer from the atmospheric turbulence and scattering effects of haze, fog, and dust, which significantly weaken the performance of QKD or even block the secure quantum link. Here, we prove the performance of QKD over a dynamic scattering channel can be enhanced significantly
-
Fixed-time stabilization of output-constrained stochastic high-order nonlinear systems Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Ruiming Xie, Shengyuan Xu
In this study, the fixed-time stabilization problem of stochastic high-order nonlinear systems with output constraint and high-order and low-order nonlinearities is addressed. A new coordinate transformation is employed to directly convert output-constrained stochastic systems into an equivalent unconstrained form. By fully extracting the characteristics of system nonlinearities and using the stochastic
-
Online Pareto optimal control of mean-field stochastic multi-player systems using policy iteration Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Xiushan Jiang, Yanshuang Wang, Dongya Zhao, Ling Shi
In this study, the Pareto optimal strategy problem was investigated for multi-player mean-field stochastic systems governed by Itô differential equations using the reinforcement learning (RL) method. A partially model-free solution for Pareto-optimal control was derived. First, by applying the convexity of cost functions, the Pareto optimal control problem was solved using a weighted-sum optimal control
-
Adaptive joint configuration optimization for collaborative inference in edge-cloud systems Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Zheming Yang, Wen Ji, Zhi Wang
In this study, we propose an adaptive edge-cloud collaborative inference framework that can adaptively configure data and model versions according to task requirements, and decide to transfer them to the cloud server or edge server for inference. Considering the complexity of the joint optimization problem, we decompose the original problem into two low-complexity subproblems. We then propose an adaptive
-
A smart hybrid memory scheduling approach using neural models Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Yanjie Zhen, Huijun Zhang, Yongheng Deng, Weining Chen, Wei Gao, Ju Ren, Yu Chen
SmartS is a novel solution for hybrid memory scheduling using neural models. It proposes a novel collective-page prediction approach, effectively reducing training and inference costs. It also proposes a clustering-based approach to address the class explosion problem. Experiments show that SmartS improves hybrid memory effectiveness significantly. It also reduces the cost of neural models to allow
-
Quantum self-attention neural networks for text classification Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Guangxi Li, Xuanqiang Zhao, Xin Wang
An emerging direction of quantum computing is to establish meaningful quantum applications in various fields of artificial intelligence, including natural language processing (NLP). Although some efforts based on syntactic analysis have opened the door to research in quantum NLP (QNLP), limitations such as heavy syntactic preprocessing and syntax-dependent network architecture make them impracticable
-
Impact of non-ideal UE hardware on cell-free massive MIMO network with centralized operation Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-27 Ning Li, Pingzhi Fan
This paper investigates the impact of non-ideal user equipment (UE) hardware on a cell-free (CF) massive MIMO (mMIMO) network with centralized operation under spatially correlated channels. The minimum mean-squared error (MMSE) estimator can be derived with the help of the generic non-ideal UE hardware model. It is demonstrated that even if the effective signal-to-noise ratio approaches infinity, pilot
-
Gradient sparsification for efficient wireless federated learning with differential privacy Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-26 Kang Wei, Jun Li, Chuan Ma, Ming Ding, Feng Shu, Haitao Zhao, Wen Chen, Hongbo Zhu
Federated learning (FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy
-
Continuous variable quantum teleportation and remote state preparation between two space-separated local networks Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-26
Abstract Implementing quantum communication between space-separated local networks is essential for designing global quantum networks. In this study, we propose quantum teleportation and remote state preparation schemes between users of two space-separated local networks established by continuous-variable multipartite entangled states. In the proposed schemes, the quantum nodes belonging to the two
-
On the size generalizibility of graph neural networks for learning resource allocation Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-26 Jiajun Wu, Chengjian Sun, Chenyang Yang
Size generalization is important for learning resource allocation policies in wireless systems with time-varying scales. If a neural network for learning a wireless policy is not generalizable to the size of its input, it has to be re-trained whenever the system scale changes, which hinders its practical use due to the unaffordable training costs. Graph neural networks (GNNs) have been shown with size
-
What can we learn from quality assurance badges in open-source software? Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-26 Feng Li, Yiling Lou, Xin Tan, Zhenpeng Chen, Jinhao Dong, Yang Li, Xuanzhi Wang, Dan Hao, Lu Zhang
In the development of open-source software (OSS), many developers use badges to give an overview of the software and share some key features/metrics conveniently. Among various badges, quality assurance (QA) badges make up a large proportion and are the most prevalent because QA is of vital importance in software development, and ineffective QA may lead to anomalies or defects. In this paper, we focus
-
Memory-enhanced text style transfer with dynamic style learning and calibration Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-26 Fuqiang Lin, Yiping Song, Zhiliang Tian, Wangqun Chen, Diwen Dong, Bo Liu
Text style transfer aims to rephrase a sentence to match the desired style while retaining the original content. As a controllable text generation task, mainstream approaches use content-independent style embedding as control variables to guide stylistic generation. Nonetheless, stylistic properties are context-sensitive even under the same style. For example, “delicious” and “helpful” convey positive
-
Robust cooperative multi-agent reinforcement learning via multi-view message certification Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-22 Lei Yuan, Tao Jiang, Lihe Li, Feng Chen, Zongzhang Zhang, Yang Yu
Many multi-agent scenarios require message sharing among agents to promote coordination, hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment. Major relevant studies tackle this issue under specific assumptions, like a limited number of message channels would sustain perturbations, limiting the efficiency in complex scenarios. In this
-
Retrieval-and-alignment based large-scale indoor point cloud semantic segmentation Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-25 Zongyi Xu, Xiaoshui Huang, Bo Yuan, Yangfu Wang, Qianni Zhang, Weisheng Li, Xinbo Gao
Current methods for point cloud semantic segmentation depend on the extraction of descriptive features. However, unlike images, point clouds are irregular and often lack texture information, making it demanding to extract discriminative features. In addition, noise, outliers, and uneven point distribution are commonly present in point clouds, which further complicates the segmentation task. To address
-
Linear shallow neural network to accelerate transmitter dispersion eye closure quaternary (TDECQ) assessment Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-21 Junjiang Xiang, Zejun Chen, Yijun Cheng, Hailin Yang, Xuancheng Huo, Meng Xiang, Gai Zhou, Yuwen Qin, Songnian Fu
We have demonstrated a data-driven TDECQ assessment scheme based on L-SNN. In comparison with existing DL-based schemes, the proposed L-SNN can achieve the lowest computation complexity with only 210 multiplications. The MAE of the L-SNN scheme for 25 and 50 Gbaud PAM-4 optical signals is experimentally verified to be 0.13 and 0.15 dB, respectively, over the TDECQ range of 1.5–4.0 dB, which has reached
-
FUSE: a federated learning and U-shape split learning-based electricity theft detection framework Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-21 Xuan Li, Naiyu Wang, Liehuang Zhu, Shuai Yuan, Zhitao Guan
In this study, we propose a novel theft detection framework named FUSE. Firstly, we introduce a new variant of split learning named three-tier U-shape split learning into the local training process. This allows us to migrate the extensive computational overhead to the assisted CSs, while ensuring the sensitive data is preserved in the place where it is generated for privacy-preserving. Furthermore
-
A model reduction approach for discrete-time linear time-variant systems with delayed inputs Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-03-08 Ai-Guo Wu, Guang-Ren Duan, Yu Wang, Jie Zhang
A model reduction approach is presented for discrete-time linear time-variant input-delayed systems. According to this proposed approach, a dynamical variable is constructed by taking advantage of the current state and historical information of input. It is revealed that the behavior of this dynamical variable is governed by a discrete-time linear delay-free system. It is worth noting that the presented
-
Optimizing evasive maneuvering of planes using a flight quality driven model Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-26 Chang Liu, Shaoshan Sun, Chenggang Tao, Yingxin Shou, Bin Xu
This paper investigates the optimal evasive maneuver for a plane to avoid an incoming missile. To accurately model the system dynamics while improving computational efficiency, a simplified plane model based on flight quality is established. A missile model with proportional guidance is also formulated. The problem of determining the optimal evasion plane maneuver is formulated. The Gauss pseudospectral
-
Multi-sensor multispectral reconstruction framework based on projection and reconstruction Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-26 Tianshuai Li, Tianzhu Liu, Xian Li, Yanfeng Gu, Yukun Wang, Yushi Chen
The scarcity and low spatial resolution of hyperspectral images (HSIs) have become a major problem limiting the application of the images. In recent years, spectral reconstruction (SR) has been applied to convert multispectral images (MSIs) with abundant quantities and high spatial resolution into HSIs. With the launch of several new multispectral (MS) satellites with a short repeat period, the simultaneous
-
Event-triggered sliding mode control of linear repetitive processes and its application in metal rolling process Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-26 Xinyu Lv, Yugang Niu, James Lam
This paper investigates the design problem of a sliding mode controller for linear repetitive processes (LRPs) with a finite pass length on each pass. Under limited communication resources, an event-triggered mechanism is implemented from the sensors to the controller, whose triggered sequence is consistent with the evolution direction of LRPs. To periodically orchestrate communication between the
-
Output feedback stabilization of stochastic high-order planar nonlinear systems with stochastic inverse dynamics and output-constraint Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-22 Ruiming Xie, Shengyuan Xu
In this paper, we solve the output feedback control problem of stochastic high-order planar nonlinear systems with output constraint and stochastic integral input-to-state stability (SiISS) inverse dynamics. By employing a key coordinate transformation, a stochastic nonlinear system with output constraint and SiISS inverse dynamics is converted into an unconstrained system. By skillfully constructing
-
Distinct but correct: generating diversified and entity-revised medical response Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-21 Bin Li, Bin Sun, Shutao Li, Encheng Chen, Hongru Liu, Yixuan Weng, Yongping Bai, Meiling Hu
Medical dialogue generation (MDG) is applied for building medical dialogue systems for intelligent consultation. Such systems can communicate with patients in real time, thereby improving the efficiency of clinical diagnosis. However, predicting correct entities and correctly generating distinct responses remain a great challenge. Inspired by actual doctors’ responses to patients, we consider MDG a
-
A FAS approach for stabilization of generalized chained forms: part 2. Continuous control laws Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-21 Guang-Ren Duan
In this paper, continuous time-varying stabilizing controllers for the type of general nonholonomic systems proposed and treated in part 1 are designed using the fully actuated system (FAS) approach. The key step is to differentiate the first scalar equation, and by control of the obtained second-order scalar system, a proportional plus integral feedback form for the first control variable is obtained
-
Gate regulated near-infrared photodetector utilizing interlayer excitons for MoS2/CrPS4 heterojunction Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19 Guoliang Xu, Chao He, Donghong Shi, Danmin Liu, Wenjie Deng, Jingzhen Li, Xingtao An, Yongzhe Zhang
We have demonstrated a highly efficient visible-NIR photodetector based on the interlayer optical transition. Indirect interlayer transitions can occur proved by DFT calculations. In particular, the exciton current is tuned by an external gate field and the cutoff wavelength is increased to 1500 nm. Remarkably, there is a peak of about 2.75 nA at Vg = 5 V around 1075 nm wavelength. Finally, this study
-
Experimental realization of deterministic joint remote preparation of an arbitrary two-qubit pure state via GHZ states Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19 Nachuan Li, Lu Xu, Jin-Ming Liu
By employing two tripartite GHZ states as the entanglement channel, we realized the deterministic JRSP protocol of six unique initial two-qubit states on the Origin Wuyuan 6-qubit chip, with the measured average fidelities exceeding 0.4. Moreover, we employ the Origin NQVM to simulate the JRSP protocol in the presence of four noise environments. To enhance fidelity, we proposed substituting the two
-
Constrained reinforcement learning with statewise projection: a control barrier function approach Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19 Xinze Jin, Kuo Li, Qingshan Jia
Safety is a critical issue for reinforcement learning (RL), as it may be risky for some actual applications if the learning process involves unsafe exploration. Instead of formulating constraints as expectation-based in constrained RL, considering statewise safety in constrained RL is more meaningful. This work aims to address the issue of safe projection in RL by introducing a control barrier function
-
Wearable ultrasensitive and rapid human physiological monitoring based on microfiber Sagnac interferometer Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19 Xin Wang, Hongyou Zhou, Meihua Chen, Yongcheng He, Zhishen Zhang, Jiulin Gan, Zhongmin Yang
High-sensitive and fast-responding flexible strain sensors are essential for the smart wearable devices that precisely and dynamically perceive the weak deformations induced by human physiological signals. Here, a flexible strain sensor via polydimethylsiloxane (PDMS)-encapsulated microfiber Sagnac interferometer was designed and prepared for monitoring the human pulse signals and sound vibrations
-
High-performance broadband photodetector based on PtSe2/MoS2 heterojunction from visible to near-infrared region Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19 Bin Wang, Jian Yuan, Mengqi Che, Mingxiu Liu, Yuting Zou, Junru An, Fan Tan, Yaru Shi, Nan Zhang, Liujian Qi, Shaojuan Li
Broadband photodetectors based on narrow bandgap 2D materials have garnered considerable interest for application in the field of optoelectronic devices. However, their large dark current hinders device performance. In this work, a PtSe2/MoS2 heterojunction was fabricated for a broadband photodetector operating within the range of visible to near-infrared. The device exhibited suppressed dark currents
-
A deep learning model enabled multi-event recognition for distributed optical fiber sensing Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19 Yujiao Li, Xiaomin Cao, Wenhao Ni, Kuanglu Yu
Fiber optic sensors that utilize backscattered light offer distributed real-time measurements and have been seen tremendous improvements in sensing distance and spatial resolution over the last decades. However, these improvements in sensor capabilities lead to a significant increase in the amount of data that needs to be processed. Traditional processing schemes are no longer adequate, so the development
-
Recent progress in single crystal perovskite X-ray detectors Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19
Abstract Perovskites have attracted extensive attention as radiation detection material due to their long carrier diffusion length and lifetime, high absorption coefficient, and flexible manufacturing process. Compared with polycrystalline structures, single crystal perovskites improve the performance of optoelectronic devices due to their low defect state density, better photoelectric characteristics
-
Experimental demonstration of a photonic spiking neuron based on a DFB laser subject to side-mode optical pulse injection Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-19
Abstract We proposed and experimentally demonstrated a simple and novel photonic spiking neuron based on a distributed feedback (DFB) laser subject to side-mode optical pulse injection (SMOPI). The DFB laser chip is designed and fabricated based on asymmetric equivalent π phase shift (π-EPS) with the reconstruction-equivalent-chirp (REC) technique. Under side-mode continuous-wave (CW) optical injection
-
When debugging encounters artificial intelligence: state of the art and open challenges Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-21 Yi Song, Xiaoyuan Xie, Baowen Xu
Both software debugging and artificial intelligence techniques are hot topics in the current field of software engineering. Debugging techniques, which comprise fault localization and program repair, are an important part of the software development lifecycle for ensuring the quality of software systems. As the scale and complexity of software systems grow, developers intend to improve the effectiveness
-
Density peak clustering using tensor network Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-20 Xiao Shi, Yun Shang
We introduce a density-based clustering algorithm with tensor networks. In order to demonstrate its effectiveness, we apply it to various types of data sets, including synthetic data sets, real world data sets, and computer vision data sets. Results demonstrate that it is an efficient quantum-inspired unsupervised learning algorithm and can recognize clusters of arbitrary shape and size. It can also
-
Lead-free perovskites-based photonic synaptic devices with zero electric energy consumption Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-20 Dandan Hao, Di Yang, Haixia Liang, Jia Huang, Fukai Shan
The von Neumann bottleneck is a critical limitation in synaptic devices. Therefore, artificial synaptic devices resembling biological neuromorphic synapses have been developed to overcome the von Neumann bottleneck. However, synaptic devices require voltages, which results in considerable energy consumption. Here, photonic synaptic devices with the vertical structure of indium tin oxide (ITO)/SnO2/Al2O3/CsBi3I10/Au
-
Blindness-free beam scanning antenna with array of array architecture: principle, design, and experiment Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-20 Jianxu Sun, Yujian Cheng
This paper presents a 66–76-GHz sparsely-excited phased array antenna with the array of array (AoA) architecture for eliminating the blindness and suppressing the grating lobe when scanning. For the array antennas printed on the thick dielectric layers with high relative permittivity, scanning blindness appears and seriously impacts the radiation performance. To address this issue, the AoA topology
-
Segment-wise learning control for trajectory tracking of robot manipulators under iteration-dependent periods Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-20 Fan Zhang, Deyuan Meng, Kaiquan Cai
This paper is concerned with the amplitude boundedness problem of adaptive iterative learning control (AILC) for robot manipulators operating with iteration-dependent periods. By introducing virtual memory slots for storing historical data, a practical AILC method is proposed to achieve the segment-wise learning. This method requires less memory storage for historical information of previous iterations
-
Joint UAV trajectory and communication design with heterogeneous multi-agent reinforcement learning Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-20 Xuanhan Zhou, Jun Xiong, Haitao Zhao, Xiaoran Liu, Baoquan Ren, Xiaochen Zhang, Jibo Wei, Hao Yin
Unmanned aerial vehicles (UAVs) are recognized as effective means for delivering emergency communication services when terrestrial infrastructures are unavailable. This paper investigates a multi-UAV-assisted communication system, where we jointly optimize UAVs’ trajectories, user association, and ground users (GUs)’ transmit power to maximize a defined fairness-weighted throughput metric. Owing to
-
Scene text recognition via dual character counting-aware visual and semantic modeling network Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-05 Ke Xiao, Anna Zhu, Brian Kenji Iwana, Cheng-Lin Liu
In this work, we study character counting in STR from a new viewpoint, giving a principled framework showing that the counting information is involved in both visual decoding and semantic decoding. Based on the principled framework, we propose a novel scene text recognizer with a dual character counting-aware visual and semantic modeling network, where the counting information is fused in both vision
-
Unbalanced private set intersection with linear communication complexity Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-05 Quanyu Zhao, Bingbing Jiang, Yuan Zhang, Heng Wang, Yunlong Mao, Sheng Zhong
The private set intersection (PSI) protocol allows two parties holding a set of integers to compute the intersection of their sets without revealing any additional information to each other. The unbalanced PSI schemes consider a specific setting where a client holds a small set of the size n and a server holds a much larger set of the size m (n ≪ m). The communication overhead of state-of-the-art balanced
-
A survey of decision making in adversarial games Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-04 Xiuxian Li, Min Meng, Yiguang Hong, Jie Chen
In many practical applications, such as poker, chess, drug interdiction, cybersecurity, and national defense, players often have adversarial stances, i.e., the selfish actions of each player inevitably or intentionally inflict loss or wreak havoc on other players. Therefore, adversarial games are important in real-world applications. However, only special adversarial games, such as Bayesian games,
-
Mitigate noisy data for smart IoT via GAN based machine unlearning Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-02-02 Zhuo Ma, Yilong Yang, Yang Liu, Xinjing Liu, Jianfeng Ma
With the development of IoT applications, machine learning dramatically improves the utility of variable IoT systems such as autonomous driving. Although the pretrain-finetune framework can cope well with data heterogeneity in complex IoT scenarios, the data collected by sensors often contain unexpected noisy data, e.g., out-of-distribution (OOD) data, which leads to the reduced performance of fine-tuned
-
A survey on model-based reinforcement learning Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-01-23 Fan-Ming Luo, Tian Xu, Hang Lai, Xiong-Hui Chen, Weinan Zhang, Yang Yu
Reinforcement learning (RL) interacts with the environment to solve sequential decision-making problems via a trial-and-error approach. Errors are always undesirable in real-world applications, even though RL excels at playing complex video games that permit several trial-and-error attempts. To improve sample efficiency and thus reduce errors, model-based reinforcement learning (MBRL) is believed to
-
Investigation and mitigation of Mott neuronal oscillation fluctuation in spiking neural network Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-01-22 Lindong Wu, Zongwei Wang, Lin Bao, Linbo Shan, Zhizhen Yu, Yunfan Yang, Shuangjie Zhang, Guandong Bai, Cuimei Wang, John Robertson, Yuan Wang, Yimao Cai, Ru Huang
Mott devices, featuring low hardware cost and high energy efficiency, have been demonstrated as a key oscillatory element in artificial neurons to enable spiking neural networks (SNNs) such as conversion-based SNNs (CSNNs). However, there will be inevitably non-ideal fluctuation in the oscillation behavior, causing the accuracy degradation of networks. In this paper, we investigate the Mott neuronal
-
Fault-tolerant identity-based encryption from SM9 Sci. China Inf. Sci. (IF 8.8) Pub Date : 2024-01-22 Xiaohong Liu, Xinyi Huang, Zhaohui Cheng, Wei Wu
This paper initiates the formal study of attribute-based encryption within the framework of SM9, the Chinese National Cryptography Standard for Identity-Based Cryptography, by presenting two new fault-tolerant identity-based encryption (FIBE) schemes. Our first scheme uses the same private-key/ciphertext structure as the original SM9 algorithm and operates in a small attribute universe. As a result