ChatGPT: potential, prospects, and limitations

Recently,OpenAI released Chat Generative Pre-trained Transformer(ChatGPT)(Schulman et al.,2022)(https://chat.openai.com),which has attracted considerable attention from the industry and academia because of its impressive abilities.This is the first time that such a variety of open tasks can be well solved within one large language model.To better understand ChatGPT,we briefly introduce its history,discuss its advantages and disadvantages,and point out several potential applications.Finally,we analyze its impact on the development of trustworthy artificial intelligence,conversational search engine,and artificial general intelligence.

Prompt learning in computer vision: a survey

Prompt learning has attracted broad attention in computer vision since the large pre-trained visionlanguagemodels (VLMs) exploded. Based on the close relationship between vision and language information builtby VLM, prompt learning becomes a crucial technique in many important applications such as artificial intelligencegenerated content (AIGC). In this survey, we provide a progressive and comprehensive review of visual promptlearning as related to AIGC. We begin by introducing VLM, the foundation of visual prompt learning. Then, wereview the vision prompt learning methods and prompt-guided generative models, and discuss how to improve theefficiency of adapting AIGC models to specific downstream tasks. Finally, we provide some promising researchdirections concerning prompt learning.

Controllable image generation based on causal representation learning

Artificial intelligence generated content(AIGC)has emerged as an indispensable tool for producing large-scale content in various forms,such as images,thanks to the significant role that AI plays in imitation and production.However,interpretability and controllability remain challenges.Existing AI methods often face challenges in producing images that are both flexible and controllable while considering causal relationships within the images.To address this issue,we have developed a novel method for causal controllable image generation(CCIG)that combines causal representation learning with bi-directional generative adversarial networks(GANs).This approach enables humans to control image attributes while considering the rationality and interpretability of the generated images and also allows for the generation of counterfactual images.The key of our approach,CCIG,lies in the use of a causal structure learning module to learn the causal relationships between image attributes and joint optimization with the encoder,generator,and joint discriminator in the image generation module.By doing so,we can learn causal representations in image’s latent space and use causal intervention operations to control image generation.We conduct extensive experiments on a real-world dataset,CelebA.The experimental results illustrate the effectiveness of CCIG.

A robust tensor watermarking algorithm for diffusion-tensor images

Watermarking algorithms that use convolution neural networks have exhibited good robustness in studies of deep learning networks.However,after embedding watermark signals by convolution,the feature fusion eficiency of convolution is relatively low;this can easily lead to distortion in the embedded image.When distortion occurs in medical images,especially in diffusion tensor images(DTIs),the clinical value of the DTI is lost.To address this issue,a robust watermarking algorithm for DTIs implemented by fusing convolution with a Transformer is proposed to ensure the robustness of the watermark and the consistency of sampling distance,which enhances the quality of the reconstructed image of the watermarked DTIs after embedding the watermark signals.In the watermark-embedding network,Ti-weighted(Tlw)images are used as prior knowledge.The correlation between T1w images and the original DTI is proposed to calculate the most significant features from the T1w images by using the Transformer mechanism.The maximum of the correlation is used as the most significant feature weight to improve the quality of the reconstructed DTI.In the watermark extraction network,the most significant watermark features from the watermarked DTI are adequately learned by the Transformer to robustly extract the watermark signals from the watermark features.Experimental results show that the average peak signal-to-noise ratio of the watermarked DTI reaches 50.47 dB,the diffusion characteristics such as mean diffusivity and fractional anisotropy remain unchanged,and the main axis deflection angleαAc is close to 1.Our proposed algorithm can effectively protect the copyright of the DTI and barely affects the clinical diagnosis.

Diffusionmodels for time-series applications: a survey

Diffusion models, a family of generative models based on deep learning, have become increasinglyprominent in cutting-edge machine learning research. With distinguished performance in generating samples thatresemble the observed data, diffusion models are widely used in image, video, and text synthesis nowadays. Inrecent years, the concept of diffusion has been extended to time-series applications, and many powerful models havebeen developed. Considering the deficiency of a methodical summary and discourse on these models, we providethis survey as an elementary resource for new researchers in this area and to provide inspiration to motivate futureresearch. For better understanding, we include an introduction about the basics of diffusion models. Except forthis, we primarily focus on diffusion-based methods for time-series forecasting, imputation, and generation, andpresent them, separately, in three individual sections. We also compare different methods for the same applicationand highlight their connections if applicable. Finally, we conclude with the common limitation of diffusion-basedmethods and highlight potential future research directions.

Design and verification of an FPGA programmable logic element based on Sense-Switch pFLASH

This paper proposes a kind of programmable logic element(PLE)based on Sense-Switch pFLASH technology.By programming Sense-Switch pFLASH,all three-bit look-up table(LUT3)functions,partial four-bit look-up table(LUT4)functions,latch functions,and d flip flop(DFF)with enable and reset functions can be realized.Because PLE uses a choice of operational logic(COOL)approach for the operation of logic functions,it allows any logic circuit to be implemented at any ratio of combinatorial logic to register.This intrinsic property makes it close to the basic application specific integrated circuit(ASIC)cell in terms of fine granularity,thus allowing ASIC-like cell-based mappers to apply all their optimization potential.By measuring Sense-Switch pFLASH and PLE circuits,the results show that the“on”state driving current of the Sense-Switch pFLASH is about 245.52μA,and that the“off”state leakage current is about 0.1 pA.The programmable function of PLE works normally.The delay of the typical combinatorial logic operation AND3 is 0.69 ns,and the delay of the sequential logic operation DFF is 0.65 ns,both of which meet the requirements of the design technical index.

Enhancing low-resource cross-lingual summarization from noisy data with fine-grained reinforcement learning

Cross-lingual summarization(CLS)is the task of generating a summary in a target language from a document in a source language.Recently,end-to-end CLS models have achieved impressive results using large-scale,high-quality datasets typically constructed by translating monolingual summary corpora into CLS corpora.However,due to the limited performance of low-resource language translation models,translation noise can seriously degrade the performance of these models.In this paper,we propose a fine-grained reinforcement learning approach to address low-resource CLS based on noisy data.We introduce the source language summary as a gold signal to alleviate the impact of the translated noisy target summary.Specifically,we design a reinforcement reward by calculating the word correlation and word missing degree between the source language summary and the generated target language summary,and combine it with cross-entropy loss to optimize the CLS model.To validate the performance of our proposed model,we construct Chinese-Vietnamese and Vietnamese-Chinese CLS datasets.Experimental results show that our proposed model outperforms the baselines in terms of both the ROUGE score and BERTScore.

Engineering applications and technical challenges of active array microsystems

In the post-Moore era,the development of active phased array antennas will inevitably trend towards active array microsystems.In this paper,the characteristics and composition of the active array antenna are briefly described.Owing to the high efficiency,low profile,and light weight of the active array microsystems,the application prospects and advantages in the engineering of multi-functional airborne radar,spaceborne radar,and communication systems are analyzed.Moreover,according to the characteristics of the post-Moore era of integrated circuits,scientific and technological problems in the active array microsystems are presented,including multi-scale,multi-signal,and multi-physics field coupling.The challenges are also discussed,such as new architectures and algorithms,miniaturization of passive components,novel materials and processes,ultra-wideband technology,and new interdisciplinary technological applications.This paper is expected to inspire in-depth research on active array microsystems.

Deep3DSketch-im:rapid high-fidelity AI 3D model generation by single freehand sketches

The rise of artificial intelligence generated content(AIGC)has been remarkable in the language and image fields,but artificial intelligence(AI)generated three-dimensional(3D)models are still under-explored due to their complex nature and lack of training data.The conventional approach of creating 3D content through computer-aided design(CAD)is labor-intensive and requires expertise,making it challenging for novice users.To address this issue,we propose a sketch-based 3D modeling approach,Deep3DSketch-im,which uses a single freehand sketch for modeling.This is a challenging task due to the sparsity and ambiguity.Deep3DSketch-im uses a novel data representation called the signed distance field(SDF)to improve the sketch-to-3D model process by incorporating an implicit continuous field instead of voxel or points,and a specially designed neural network that can capture point and local features.Extensive experiments are conducted to demonstrate the effectiveness of the approach,achieving state-of-the-art(SOTA)performance on both synthetic and real datasets.Additionally,users show more satisfaction with results generated by Deep3DSketch-im,as reported in a user study.We believe that Deep3DSketch-im has the potential to revolutionize the process of 3D modeling by providing an intuitive and easy-to-use solution for novice users.

Six-Writings multimodal processing with pictophonetic coding to enhance Chinese language models

While large language models(LLMs)have made significant strides in natural language processing(NLP),they continue to face challenges in adequately addressing the intricacies of the Chinese language in certain scenarios.We propose a framework called Six-Writings multimodal processing(SWMP)to enable direct integration of Chinese NLP(CNLP)with morphological and semantic elements.The first part of SWMP,known as Six-Writings pictophonetic coding(SWPC),is introduced with a suitable level of granularity for radicals and components,enabling effective representation of Chinese characters and words.We conduct several experimental scenarios,including the following:(1)We establish an experimental database consisting of images and SWPC for Chinese characters,enabling dual-mode processing and matrix generation for CNLP.(2)We characterize various generative modes of Chinese words,such as thousands of Chinese idioms,used as question-and-answer(Q&A)prompt functions,facilitating analogies by SWPC.The experiments achieve 100%accuracy in answering all questions in the Chinese morphological data set(CA8-Mor-10177).(3)A fine-tuning mechanism is proposed to refine word embedding results using SWPC,resulting in an average relative error of≤25%for 39.37%of the questions in the Chinese wOrd Similarity data set(COS960).The results demonstrate that SWMP/SWPC methods effectively capture the distinctive features of Chinese and offer a promising mechanism to enhance CNLP with better efficiency.

Asynchronous gain-scheduled control of deepwater drilling riser system with hybrid event-triggered sampling and unreliable communication

This paper investigates the recoil control of the deepwater drilling riser system with nonlinear tension force and energy-bounded friction force under the circumstances of limited network resources and unreliable communication.Different from the existing linearization modeling method,a triangle-based polytope modeling method is applied to the nonlinear riser system.Based on the polytope model,to improve resource utilization and accommodate random data loss and communication delay,an asynchronous gain-scheduled control strategy under a hybrid event-triggered scheme is proposed.An asynchronous linear parameter-varying system that blends input delay and impulsive update equation is presented to model the nonlinear networked recoil control system,where the asynchronous deviation bounds of scheduling parameters are calculated.Resorting to the Lyapunov-Krasovskii functional method,some solvable conditions of disturbance attenuation analysis and recoil control design are derived such that the resulting networked system is exponentially mean-square stable with prescribed H∞performance.The obtained numerical results verified that the proposed nonlinear networked control method can achieve a better recoil response of the riser system with less transmission data compared with the linear control method.

Towards resilient average consensus in multi-agent systems:a detection and compensation approach

Consensus is one of the fundamental distributed control technologies for collaboration in multi-agent systems such as collaborative handling in intelligent manufacturing.In this paper,we study the problem of resilient average consensus for multi-agent systems with misbehaving nodes.To protect consensus value from being influenced by misbehaving nodes,we address this problem by detecting misbehaviors,mitigating the corresponding adverse impact,and achieving the resilient average consensus.General types of misbehaviors are considered,including attacks,accidental faults,and link failures.We characterize the adverse impact of misbehaving nodes in a distributed manner via two-hop communication information and develop a deterministic detection compensation based consensus(D-DCC)algorithm with a decaying fault-tolerant error bound.Considering scenarios wherein information sets are intermittently available due to link failures,a stochastic extension named stochastic detection compensation based consensus(S-DCC)algorithm is proposed.We prove that D-DCC and S-DCC allow nodes to asymptotically achieve resilient accurate average consensus and unbiased resilient average consensus in a statistical sense,respectively.Then,the Wasserstein distance is introduced to analyze the accuracy of S-DCC.Finally,extensive simulations are conducted to verify the effectiveness of the proposed algorithms.

Towards sustainable adversarial training with successive perturbation generation

Adversarial training with online-generated adversarial examples has achieved promising performance in defending adversarial attacks and improving robustness of convolutional neural network models.However,most existing adversarial training methods are dedicated to finding strong adversarial examples for forcing the model to learn the adversarial data distribution,which inevitably imposes a large computational overhead and results in a decrease in the generalization performance on clean data.In this paper,we show that progressively enhancing the adversarial strength of adversarial examples across training epochs can effectively improve the model robustness,and appropriate model shifting can preserve the generalization performance of models in conjunction with negligible computational cost.To this end,we propose a successive perturbation generation scheme for adversarial training(SPGAT),which progressively strengthens the adversarial examples by adding the perturbations on adversarial examples transferred from the previous epoch and shifts models across the epochs to improve the efficiency of adversarial training.The proposed SPGAT is both efficient and effective;e.g.,the computation time of our method is 900 min as against the 4100 min duration observed in the case of standard adversarial training,and the performance boost is more than 7%and 3%in terms of adversarial accuracy and clean accuracy,respectively.We extensively evaluate the SPGAT on various datasets,including small-scale MNIST,middle-scale CIFAR-10,and large-scale CIFAR-100.The experimental results show that our method is more efficient while performing favorably against state-of-the-art methods.

An anti-collision algorithm for robotic search-and-rescue tasks in unknown dynamic environments

This paper deals with the search-and-rescue tasks of a mobile robot with multiple interesting targets in an unknown dynamic environment.The problem is challenging because the mobile robot needs to search for multiple targets while avoiding obstacles simultaneously.To ensure that the mobile robot avoids obstacles properly,we propose a mixed-strategy Nash equilibrium based Dyna-Q(MNDQ)algorithm.First,a multi-objective layered structure is introduced to simplify the representation of multiple objectives and reduce computational complexity.This structure divides the overall task into subtasks,including searching for targets and avoiding obstacles.Second,a risk-monitoring mechanism is proposed based on the relative positions of dynamic risks.This mechanism helps the robot avoid potential collisions and unnecessary detours.Then,to improve sampling efficiency,MNDQ is presented,which combines Dyna-Q and mixed-strategy Nash equilibrium.By using mixed-strategy Nash equilibrium,the agent makes decisions in the form of probabilities,maximizing the expected rewards and improving the overall performance of the Dyna-Q algorithm.Furthermore,a series of simulations are conducted to verify the effectiveness of the proposed method.The results show that MNDQ performs well and exhibits robustness,providing a competitive solution for future autonomous robot navigation tasks.

Availability evaluation of controller area networks under the influence of intermittent connection faults

Controller area networks(CANs),as one of the widely used fieldbuses in the industry,have been extended to the automation field with strict standards for safety and reliability.In practice,factors such as fatigue and insulation wear of the cables can cause intermittent connection(IC)faults to occur frequently in the CAN,which will affect the dynamic behavior and the safety of the system.Hence,quantitatively evaluating the performance of the CAN under the influence of IC faults is crucial to real-time health monitoring of the system.In this paper,a novel methodology is proposed for real-time quantitative evaluation of CAN availability when considering IC faults,with the system availability parameter being calculated based on the network state transition model.First,the causal relationship between IC fault and network error response is constructed,based on which the IC fault arrival rate is estimated.Second,the states of the network considering IC faults are analyzed,and the deterministic and stochastic Petri net(DSPN)model is applied to describe the transition relationship of the states.Then,the parameters of the DSPN model are determined and the availability of the system is calculated based on the probability distribution and physical meaning of markings in the DSPN model.A testbed is constructed and case studies are conducted to verify the proposed methodology under various experimental setups.Experimental results show that the estimation results obtained using the proposed method agree well with the actual values.

FaSRnet:a feature and semantics refinement network for human pose estimation

Due to factors such as motion blur,video out-of-focus,and occlusion,multi-frame human pose estimation is a challenging task.Exploiting temporal consistency between consecutive frames is an efficient approach for addressing this issue.Currently,most methods explore temporal consistency through refinements of the final heatmaps.The heatmaps contain the semantics information of key points,and can improve the detection quality to a certain extent.However,they are generated by features,and feature-level refinements are rarely considered.In this paper,we propose a human pose estimation framework with refinements at the feature and semantics levels.We align auxiliary features with the features of the current frame to reduce the loss caused by different feature distributions.An attention mechanism is then used to fuse auxiliary features with current features.In terms of semantics,we use the difference information between adjacent heatmaps as auxiliary features to refine the current heatmaps.The method is validated on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018,and the results demonstrate the effectiveness of our method.

A visual analysis approach for data imputation via multi-party tabular data correlation strategies

Data imputation is an essential pre-processing task for data governance,aimed at filling in incomplete data.However,conventional data imputation methods can only partly alleviate data incompleteness using isolated tabular data,and they fail to achieve the best balance between accuracy and eficiency.In this paper,we present a novel visual analysis approach for data imputation.We develop a multi-party tabular data association strategy that uses intelligent algorithms to identify similar columns and establish column correlations across multiple tables.Then,we perform the initial imputation of incomplete data using correlated data entries from other tables.Additionally,we develop a visual analysis system to refine data imputation candidates.Our interactive system combines the multi-party data imputation approach with expert knowledge,allowing for a better understanding of the relational structure of the data.This significantly enhances the accuracy and eficiency of data imputation,thereby enhancing the quality of data governance and the intrinsic value of data assets.Experimental validation and user surveys demonstrate that this method supports users in verifying and judging the associated columns and similar rows using theirdomain knowledge.

Event-triggered finite-time command-filtered tracking control for nonlinear time-delay cyber physical systems against cyber attacks

This article addresses the secure finite-time tracking problem via event-triggered command-filtered control for nonlinear time-delay cyber physical systems(CPSs)subject to cyber attacks.Under the attack circumstance,the output and state information of CPSs is unavailable for the feedback design,and the classical coordinate conversion of the iterative process is incompetent in relation to the tracking task.To solve this,a new coordinate conversion is proposed by considering the attack gains and the reference signal simultaneously.By employing the transformed variables,a modified fractional-order command-filtered signal is incorporated to overcome the complexity explosion issue,and the Nussbaum function is used to tackle the varying attack gains.By systematically constructing the Lyapunov-Krasovskii functional,an adaptive event-triggered mechanism is presented in detail,with which the communication resources are greatly saved,and the finite-time tracking of CPSs under cyber attacks is guaranteed.Finally,an example demonstrates the effectiveness.

Outlier-resistant distributed fusion filtering for nonlinear discrete-time singular systems under a dynamic event-triggered scheme

This paper investigates the problem of outlier-resistant distributed fusion filtering(DFF)for a class of multi-sensor nonlinear singular systems(MSNSSs)under a dynamic event-triggered scheme(DETS).To relieve the effect of measurement outliers in data transmission,a self-adaptive saturation function is used.Moreover,to further reduce the energy consumption of each sensor node and improve the efficiency of resource utilization,a DETS is adopted to regulate the frequency of data transmission.For the addressed MSNSSs,our purpose is to construct the local outlier-resistant filter under the effects of the measurement outliers and the DETS;the local upper bound(UB)on the filtering error covariance(FEC)is derived by solving the difference equations and minimized by designing proper filter gains.Furthermore,according to the local filters and their UBs,a DFF algorithm is presented in terms of the inverse covariance intersection fusion rule.As such,the proposed DFF algorithm has the advantages of reducing the frequency of data transmission and the impact of measurement outliers,thereby improving the estimation performance.Moreover,the uniform boundedness of the filtering error is discussed and a corresponding sufficient condition is presented.Finally,the validity of the developed algorithm is checked using a simulation example.

Federated learning on non-IID and long-tailed data viadual-decoupling

Federated learning(FL),a cutting-edge distributed machine learning training paradigm,aims to generate a global model by collaborating on the training of client models without revealing local private data.The co-occurrence of non-independent and identically distributed(non-IID)and long-tailed distribution in FL is one challenge that substantially degrades aggregate performance.In this paper,we present a corresponding solution called federated dual-decoupling via model and logit calibration(FedDDC)for non-IID and long-tailed distributions.The model is characterized by three aspects.First,we decouple the global model into the feature extractor and the classifier to fine-tune the components affected by the joint problem.For the biased feature extractor,we propose a client confidence re-weighting scheme to assist calibration,which assigns optimal weights to each client.For the biased classifier,we apply the classifier re-balancing method for fine-tuning.Then,we calibrate and integrate the client confidence re-weighted logits with the re-balanced logits to obtain the unbiased logits.Finally,we use decoupled knowledge distillation for the first time in the joint problem to enhance the accuracy of the global model by extracting the knowledge of the unbiased model.Numerous experiments demonstrate that on non-IID and long-tailed data in FL,our approach outperforms state-of-the-art methods.