Intent detection and slot filling are two important components of natural language understanding.Because their relevance,joint training is often performed to improve performance.Existing studies mostly use a joint mod...Intent detection and slot filling are two important components of natural language understanding.Because their relevance,joint training is often performed to improve performance.Existing studies mostly use a joint model of multi-intent detection and slot-filling with unidirectional interaction,which improves the overall performance of the model by fusing the intent information in the slot-filling part.On this basis,in order to further improve the overall performance of the model by exploiting the correlation between the two,this paper proposes a joint multi-intent detection and slot-filling model based on a bidirectional interaction structure,which fuses the intent encoding information in the encoding part of slot filling and fuses the slot decoding information in the decoding part of intent detection.Experimental results on two public multi-intent joint training datasets,MixATIS and MixSNIPS,show that the bidirectional interaction structure proposed in this paper can effectively improve the performance of the joint model.In addition,in order to verify the generalization of the bidirectional interaction structure between intent and slot,a joint model for single-intent scenarios is proposed on the basis of the model in this paper.This model also achieves excellent performance on two public single-intent joint training datasets,CAIS and SNIPS.展开更多
Aromatic nitro compounds present substantial health and environmental concerns due to their toxic nature and potential explosive properties.Consequently,the development of host–vip molecular recognition systems for...Aromatic nitro compounds present substantial health and environmental concerns due to their toxic nature and potential explosive properties.Consequently,the development of host–vip molecular recognition systems for these compounds serves a dual-purpose:enabling the fabrication of high-performance sensors for detection and guiding the design of efficient adsorbents for environmental remediation.This study investigated the host–vip recognition behavior of perethylated pillar[n]arenes toward two aromatic nitro molecules,1-chloro-2,4-dinitrobenzene and picric acid.Various techniques including^(1)H NMR,2D NOESY NMR,and UV-vis spectroscopy were employed to explore the binding behavior between pillararenes and aromatic nitro vips in solution.Moreover,valuable single crystal structures were obtained to elucidate the distinct solid-state assembly behaviors of these vips with different pillararenes.The assembled solid-state supramolecular structures observed encompassed a 1:1 host–vip inclusion complex,an external binding complex,and an exo-wall tessellation complex.Furthermore,based on the findings from these systems,a pillararene-based test paper was developed for efficient picric acid detection,and the removal of picric acid from solution was also achieved using pillararenes powder.This research provides novel insights into the development of diverse host–vip systems toward hazardous compounds,offering potential applications in environmental protection and explosive detection domains.展开更多
This paper presents an innovative approach to enhance the querying capability of ChatGPT,a conversational artificial intelligence model,by incorporating voice-based interaction and a convolutional neural network(CNN)-...This paper presents an innovative approach to enhance the querying capability of ChatGPT,a conversational artificial intelligence model,by incorporating voice-based interaction and a convolutional neural network(CNN)-based impaired vision detection model.The proposed system aims to improve user experience and accessibility by allowing users to interact with ChatGPT using voice commands.Additionally,a CNN-based model is employed to detect impairments in user vision,enabling the system to adapt its responses and provide appropriate assistance.This research tackles head-on the challenges of user experience and inclusivity in artificial intelligence(AI).It underscores our commitment to overcoming these obstacles,making ChatGPT more accessible and valuable for a broader audience.The integration of voice-based interaction and impaired vision detection represents a novel approach to conversational AI.Notably,this innovation transcends novelty;it carries the potential to profoundly impact the lives of users,particularly those with visual impairments.The modular approach to system design ensures adaptability and scalability,critical for the practical implementation of these advancements.Crucially,the solution places the user at its core.Customizing responses for those with visual impairments demonstrates AI’s potential to not only understand but also accommodate individual needs and preferences.展开更多
Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the d...Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the detection of HOIs is still an onerous challenge.Unlike most of the current works for HOIs detection which only rely on the pairwise information of a human and an object,we propose a graph-based HOIs detection method that models context and global structure information.Firstly,to better utilize the relations between humans and objects,the detected humans and objects are regarded as nodes to construct a fully connected undirected graph,and the graph is pruned to obtain an HOI graph that only preserving the edges connecting human and object nodes.Then,in order to obtain more robust features of human and object nodes,two different attention-based feature extraction networks are proposed,which model global and local contexts respectively.Finally,the graph attention network is introduced to pass messages between different nodes in the HOI graph iteratively,and detect the potential HOIs.Experiments on V-COCO and HICO-DET datasets verify the effectiveness of the proposed method,and show that it is superior to many existing methods.展开更多
This study addresses security and ethical challenges in LLM-based Multi-Agent Systems, as exemplified in a blockchain fraud detection case study. Leveraging blockchain’s secure architecture, the framework involves sp...This study addresses security and ethical challenges in LLM-based Multi-Agent Systems, as exemplified in a blockchain fraud detection case study. Leveraging blockchain’s secure architecture, the framework involves specialized LLM Agents—ContractMining, Investigative, Ethics, and PerformanceMonitor, coordinated by a ManagerAgent. Baseline LLM models achieved 30% accuracy with a threshold method and 94% accuracy with a random-forest method. The Claude 3.5-powered LLM system reached an accuracy of 92%. Ethical evaluations revealed biases, highlighting the need for fairness-focused refinements. Our approach aims to develop trustworthy and reliable networks of agents capable of functioning even in adversarial environments. To our knowledge, no existing systems employ ethical LLM agents specifically designed to detect fraud, making this a novel contribution. Future work will focus on refining ethical frameworks, scaling the system, and benchmarking it against traditional methods to establish a robust, adaptable, and ethically grounded solution for blockchain fraud detection.展开更多
2D Ruddlesden-Popper(RP)polar perovskite,displaying the intrinsic optical anisotropy and structural polarity,has a fantastic application perspective in self-powered polarized light detection.However,the weak van der W...2D Ruddlesden-Popper(RP)polar perovskite,displaying the intrinsic optical anisotropy and structural polarity,has a fantastic application perspective in self-powered polarized light detection.However,the weak van der Waals interaction between the organic spacing bilayers is insufficient to preserve the stability of RP-type materials.Hence,it is of great significance to explore new stable 2D RP-phase candidates.In this work,we have successfully constructed a highly-stable polar 2D perovskite,(t-ACH)_(2)PbI_(4)(1,where t-ACH^(+)is HOOC_(8)H_(12)NH_(3)^(+)),by adopting a hydrophobic carboxylate trans-isomer of tranexamic acid as the spacing component.Strikingly,strong O-H…O hydrogen bonds between t-ACH^(+)organic bilayers compose the dimer,thus decreasing van der Waals gap and enhancing structural stability.Besides,such orientational hydrogen bonds contribute to the formation of structural polarity and generate an obvious bulk photovoltaic effect in 1,which facilitates its self-powered photodetection.As predicted,the combination of inherent anisotropy and polarity leads to self-powered polarized-light detection with a high ratio of around∼5.3,superior to those of inorganic 2D counterparts.This work paves a potential way to design highly-stable 2D perovskites for high-performance optoelectronic devices.展开更多
In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible t...In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible to unsafe events(such as falls)that can have disastrous consequences.However,automatically detecting falls fromvideo data is challenging,and automatic fall detection methods usually require large volumes of training data,which can be difficult to acquire.To address this problem,video kinematic data can be used as training data,thereby avoiding the requirement of creating a large fall data set.This study integrated an improved particle swarm optimization method into a double interactively recurrent fuzzy cerebellar model articulation controller model to develop a costeffective and accurate fall detection system.First,it obtained an optical flow(OF)trajectory diagram from image sequences by using the OF method,and it solved problems related to focal length and object offset by employing the discrete Fourier transform(DFT)algorithm.Second,this study developed the D-IRFCMAC model,which combines spatial and temporal(recurrent)information.Third,it designed an IPSO(Improved Particle Swarm Optimization)algorithm that effectively strengthens the exploratory capabilities of the proposed D-IRFCMAC(Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller)model in the global search space.The proposed approach outperforms existing state-of-the-art methods in terms of action recognition accuracy on the UR-Fall,UP-Fall,and PRECIS HAR data sets.The UCF11 dataset had an average accuracy of 93.13%,whereas the UCF101 dataset had an average accuracy of 92.19%.The UR-Fall dataset had an accuracy of 100%,the UP-Fall dataset had an accuracy of 99.25%,and the PRECIS HAR dataset had an accuracy of 99.07%.展开更多
Many studies revealed unconscious effects on conscious processing. However, in this study, we tried to investigate whether unconscious processes could interact with each other by using simultaneously presented face pi...Many studies revealed unconscious effects on conscious processing. However, in this study, we tried to investigate whether unconscious processes could interact with each other by using simultaneously presented face pictures with the same or a different unconscious valence (SUV versus DUV). In the first event-related potential (ERP) study, DUV elicited a smaller N2 as compared with SUV. In the second functional magnetic resonance imaging (fMRI) experiment, the left middle frontal gyrus (MFG) was activated under DUV condition in comparison to SUV condition. These results support the idea of interactions between unconscious processes (unconscious mismatch detection). The theoretical implications are discussed in the light of the global neuronal workspace theory.展开更多
As computer graphics technology continues to advance,Collision Detection(CD)has emerged as a critical element in fields such as virtual reality,computer graphics,and interactive simulations.CD is indispensable for ens...As computer graphics technology continues to advance,Collision Detection(CD)has emerged as a critical element in fields such as virtual reality,computer graphics,and interactive simulations.CD is indispensable for ensuring the fidelity of physical interactions and the realism of virtual environments,particularly within complex scenarios like virtual assembly,where both high precision and real-time responsiveness are imperative.Despite ongoing developments,current CD techniques often fall short in meeting these stringent requirements,resulting in inefficiencies and inaccuracies that impede the overall performance of virtual assembly systems.To address these limitations,this study introduces a novel algorithm that leverages the capabilities of a Backpropagation Neural Network(BPNN)to optimize the structural composition of the Hybrid Bounding Volume Tree(HBVT).Through this optimization,the research proposes a refined Hybrid Hierarchical Bounding Box(HHBB)framework,which is specifically designed to enhance the computational efficiency and precision of CD processes.The HHBB framework strategically reduces the complexity of collision detection computations,thereby enabling more rapid and accurate responses to collision events.Extensive experimental validation within virtual assembly environments reveals that the proposed algorithm markedly improves the performance of CD,particularly in handling complex models.The optimized HBVT architecture not only accelerates the speed of collision detection but also significantly diminishes error rates,presenting a robust and scalable solution for real-time applications in intricate virtual systems.These findings suggest that the proposed approach offers a substantial advancement in CD technology,with broad implications for its application in virtual reality,computer graphics,and related fields.展开更多
This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion b...This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting process.Since that human actions and interacted objects provide strong context information,i.e.some actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of them.Through the proposed method,both global and local temporal features from skeleton sequences are extracted to model human actions.In the meantime,kernel features are utilized to describe interacted objects.Finally,all possible solutions from actions and objects are optimized by modeling the context between them.The results of experiments demonstrate the effectiveness of our method.展开更多
Many existing efforts have taken advantage of large-scale spatial-temporal data to partition cities via constructed human interaction networks.However,few studies focus on communities emerging between adjacent cities ...Many existing efforts have taken advantage of large-scale spatial-temporal data to partition cities via constructed human interaction networks.However,few studies focus on communities emerging between adjacent cities in big urban agglomerations,which we call“cross-city”communities.In this study,we introduce a novel framework to detect cross-city communities in urban agglomerations under different scales leveraging a large number of fine-grained mobile signaling data aiming to break the original administrative boundaries.Taking the Pearl River Delta(PRD)urban agglomeration in China as study area,we investigate the existence of potential communities at three scales,i.e.city-group level,city level and sub-city level.The partition results are expected to benefit transportation planning,urban zoning and administrative boundary re-delineation.The results from our study highlight the necessity of considering cross-city communities and their scale effects when examining urban spatial interactions.展开更多
Human object interaction(HOI)recognition plays an important role in the designing of surveillance and monitoring systems for healthcare,sports,education,and public areas.It involves localizing the human and object tar...Human object interaction(HOI)recognition plays an important role in the designing of surveillance and monitoring systems for healthcare,sports,education,and public areas.It involves localizing the human and object targets and then identifying the interactions between them.However,it is a challenging task that highly depends on the extraction of robust and distinctive features from the targets and the use of fast and efficient classifiers.Hence,the proposed system offers an automated body-parts-based solution for HOI recognition.This system uses RGB(red,green,blue)images as input and segments the desired parts of the images through a segmentation technique based on the watershed algorithm.Furthermore,a convex hullbased approach for extracting key body parts has also been introduced.After identifying the key body parts,two types of features are extracted.Moreover,the entire feature vector is reduced using a dimensionality reduction technique called t-SNE(t-distributed stochastic neighbor embedding).Finally,a multinomial logistic regression classifier is utilized for identifying class labels.A large publicly available dataset,MPII(Max Planck Institute Informatics)Human Pose,has been used for system evaluation.The results prove the validity of the proposed system as it achieved 87.5%class recognition accuracy.展开更多
The continuous mutation and rapid spread of the severe acute respiratory syndrome coronavirus 2(SARSCoV-2)have led to the ineffectiveness of many antiviral drugs targeting the original strain.To keep pace with the vi...The continuous mutation and rapid spread of the severe acute respiratory syndrome coronavirus 2(SARSCoV-2)have led to the ineffectiveness of many antiviral drugs targeting the original strain.To keep pace with the virus’evolutionary speed,there is a crucial need for the development of rapid,cost-effective,and efficient inhibitor screening methods.In this study,we created a novel approach based on fluorescence resonance energy transfer(FRET)technology for in vitro detection of inhibitors targeting the interaction between the SARS-CoV-2 spike protein RBD(s-RBD)and the virus receptor angiotensin-converting enzyme 2(ACE2).Utilizing crystallographic insights into the s-RBD/ACE2 interaction,we modified ACE2 by fusing SNAP tag to its N-terminus(resulting in SA740)and Halo tag to s-RBD’s C-terminus(producing R525H and R541H),thereby ensuring the proximity(<10 nm)of labeled FRET dyes.We found that relative to the R541H fusion protein,R525H exhibited higher FRET efficiency,which attributed to the shortened distance between FRET dyes due to the truncation of s-RBD.Utilizing the sensitive FRET effect between SA740 and R525H,we evaluated its efficacy in detecting inhibitors of SARS-CoV-2 entry in solution and live cells.Ultimately,this FRET-based detection method was demonstrated high sensitivity,rapidity,and simplicity in solution and held promise for high-throughput screening of SARS-CoV-2 inhibitors.展开更多
In the new era of technology,daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds.To understand the scenes and activities from human life logs,human-object interac...In the new era of technology,daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds.To understand the scenes and activities from human life logs,human-object interaction(HOI)is important in terms of visual relationship detection and human pose estimation.Activities understanding and interaction recognition between human and object along with the pose estimation and interaction modeling have been explained.Some existing algorithms and feature extraction procedures are complicated including accurate detection of rare human postures,occluded regions,and unsatisfactory detection of objects,especially small-sized objects.The existing HOI detection techniques are instancecentric(object-based)where interaction is predicted between all the pairs.Such estimation depends on appearance features and spatial information.Therefore,we propose a novel approach to demonstrate that the appearance features alone are not sufficient to predict the HOI.Furthermore,we detect the human body parts by using the Gaussian Matric Model(GMM)followed by object detection using YOLO.We predict the interaction points which directly classify the interaction and pair them with densely predicted HOI vectors by using the interaction algorithm.The interactions are linked with the human and object to predict the actions.The experiments have been performed on two benchmark HOI datasets demonstrating the proposed approach.展开更多
Disentangling the influence of multiple signal components on receivers and elucidating general processes influencing complex signal evolution are difficult tasks. In this study we test mate preferences of female squir...Disentangling the influence of multiple signal components on receivers and elucidating general processes influencing complex signal evolution are difficult tasks. In this study we test mate preferences of female squirrel treefrogs Hyla squirella and female tungara frogs Physalaemus pustulosus for similar combinations of acoustic and visual components of their multimodal courtship signals. In a two-choice playback experiment with squirrel treefrogs, the visual stimulus of a male model significantly increased the attractivness of a relatively unattractive slow call rate. A previous study demonstrated that faster call rates are more attractive to female squirrel treefrogs, and all else being equal, models of male frogs with large body stripes are more attractive. In a similar experiment with female tungara frogs, the visual stimulus of a robotic frog failed to increase the attractiveness of a relatively unattractive call. Females also showed no preference for the distinct stripe on the robot that males commonly bear on their throat. Thus, features of conspicuous signal components such as body stripes are not universally important and signal function is likely to differ even among species with similar ecologies and communication systems. Finally, we discuss the putative information content of anuran signals and suggest that the categorization of redundant versus multiple messages may not be sufficient as a general explanation for the evolution of multimodal signaling. Instead of relying on untested assumptions concerning the information content of signals, we discuss the value of initially collecting comparative empirical data sets related to receiver responses.展开更多
Brazil is the world leader in sugarcane production and the largest sugar exporter. Developing new varieties is one of the main factors that contribute to yield increase. In order to select the best genotypes, during t...Brazil is the world leader in sugarcane production and the largest sugar exporter. Developing new varieties is one of the main factors that contribute to yield increase. In order to select the best genotypes, during the final selection stage, varieties are tested in different environments (locations and years), and breeders need to estimate the phenotypic performance for main traits such as tons of cane yield per hectare (TCH) considering the genotype × environment interaction (GEI) effect. Geneticists and biometricians have used different methods and there is no clear consensus of the best method. In this study, we present a comparison of three methods, viz. Eberhart-Russel (ER), additive main effects and multiplicative interaction (AMMI) and mixed model (REML/BLUP), in a simulation study performed in the R computing environment to verify the effectiveness of each method in detecting GEI, and assess the particularities of each method from a statistical standpoint. In total, 63 cases representing different conditions were simulated, generating more than 34 million data points for analysis by each of the three methods. The results show that each method detects GEI differently in a different way, and each has some limitations. All three methods detected GEI effectively, but the mixed model showed higher sensitivity. When applying the GEI analysis, firstly it is important to verify the assumptions inherent in each method and these limitations should be taken into account when choosing the method to be used.展开更多
Human interaction becomes an important issue in the field of mobile robotics. To achieve humanfriendly naviga tion, the robot needs to recognize human on cluttered backgrounds, and this can be fulfilled by the detecti...Human interaction becomes an important issue in the field of mobile robotics. To achieve humanfriendly naviga tion, the robot needs to recognize human on cluttered backgrounds, and this can be fulfilled by the detection of human legs. The detection of human legs is advantageous because it enables detecting environmental obstacles at such heights. In this pa per, we compared the performance of an algorithm using a single laser range finder（LRF） proposed in Ref. L 1 ] with that of wellknown feature extraction approaches bounding box and circle fitting proposed in Ref. [ 2 ] by using the same laser scanned image.展开更多
Based on the traditional Human-Computer Interaction method which is mainly touch input system, the way of capturing the movement of people by using cameras is proposed. This is a convenient technique which can provide...Based on the traditional Human-Computer Interaction method which is mainly touch input system, the way of capturing the movement of people by using cameras is proposed. This is a convenient technique which can provide users more experience. In the article, a new way of detecting moving things is given on the basis of development of the image processing technique. The system architecture decides that the communication should be used between two different applications. After considered, named pipe is selected from many ways of communication to make sure that video is keeping in step with the movement from the analysis of the people moving. According to a large amount of data and principal knowledge, thinking of the need of actual project, a detailed system design and realization is finished. The system consists of three important modules: detecting of the people's movement, information transition between applications and video showing in step with people's movement. The article introduces the idea of each module and technique.展开更多
The statistical model for community detection is a promising research area in network analysis.Most existing statistical models of community detection are designed for networks with a known type of community structure...The statistical model for community detection is a promising research area in network analysis.Most existing statistical models of community detection are designed for networks with a known type of community structure,but in many practical situations,the types of community structures are unknown.To cope with unknown community structures,diverse types should be considered in one model.We propose a model that incorporates the latent interaction pattern,which is regarded as the basis of constructions of diverse community structures by us.The interaction pattern can parameterize various types of community structures in one model.A collapsed Gibbs sampling inference is proposed to estimate the community assignments and other hyper-parameters.With the Pitman-Yor process as a prior,our model can automatically detect the numbers and sizes of communities without a known type of community structure beforehand.Via Bayesian inference,our model can detect some hidden interaction patterns that offer extra information for network analysis.Experiments on networks with diverse community structures demonstrate that our model outperforms four state-of-the-art models.展开更多
Most of the intelligent surveillances in the industry only care about the safety of the workers.It is meaningful if the camera can know what,where and how the worker has performed the action in real time.In this paper...Most of the intelligent surveillances in the industry only care about the safety of the workers.It is meaningful if the camera can know what,where and how the worker has performed the action in real time.In this paper,we propose a light-weight and robust algorithm to meet these requirements.By only two hands'trajectories,our algorithm requires no Graphic Processing Unit(GPU)acceleration,which can be used in low-cost devices.In the training stage,in order to find potential topological structures of the training trajectories,spectral clustering with eigengap heuristic is applied to cluster trajectory points.A gradient descent based algorithm is proposed to find the topological structures,which reflects main representations for each cluster.In the fine-tuning stage,a topological optimization algorithm is proposed to fine-tune the parameters of topological structures in all training data.Finally,our method not only performs more robustly compared to some popular offline action detection methods,but also obtains better detection accuracy in an extended action sequence.展开更多
基金Supported by the National Nature Science Foundation of China(62462037,62462036)Project for Academic and Technical Leader in Major Disciplines in Jiangxi Province(20232BCJ22013)+1 种基金Jiangxi Provincial Natural Science Foundation(20242BAB26017,20232BAB202010)Jiangxi Province Graduate Innovation Fund Project(YC2023-S320)。
文摘Intent detection and slot filling are two important components of natural language understanding.Because their relevance,joint training is often performed to improve performance.Existing studies mostly use a joint model of multi-intent detection and slot-filling with unidirectional interaction,which improves the overall performance of the model by fusing the intent information in the slot-filling part.On this basis,in order to further improve the overall performance of the model by exploiting the correlation between the two,this paper proposes a joint multi-intent detection and slot-filling model based on a bidirectional interaction structure,which fuses the intent encoding information in the encoding part of slot filling and fuses the slot decoding information in the decoding part of intent detection.Experimental results on two public multi-intent joint training datasets,MixATIS and MixSNIPS,show that the bidirectional interaction structure proposed in this paper can effectively improve the performance of the joint model.In addition,in order to verify the generalization of the bidirectional interaction structure between intent and slot,a joint model for single-intent scenarios is proposed on the basis of the model in this paper.This model also achieves excellent performance on two public single-intent joint training datasets,CAIS and SNIPS.
基金supported by the fundamental research funds of Zhejiang Sci-Tech University(No.22212286-Y)the Natural Science Foundation of Zhejiang Province(No.LQ24B040003)。
文摘Aromatic nitro compounds present substantial health and environmental concerns due to their toxic nature and potential explosive properties.Consequently,the development of host–vip molecular recognition systems for these compounds serves a dual-purpose:enabling the fabrication of high-performance sensors for detection and guiding the design of efficient adsorbents for environmental remediation.This study investigated the host–vip recognition behavior of perethylated pillar[n]arenes toward two aromatic nitro molecules,1-chloro-2,4-dinitrobenzene and picric acid.Various techniques including^(1)H NMR,2D NOESY NMR,and UV-vis spectroscopy were employed to explore the binding behavior between pillararenes and aromatic nitro vips in solution.Moreover,valuable single crystal structures were obtained to elucidate the distinct solid-state assembly behaviors of these vips with different pillararenes.The assembled solid-state supramolecular structures observed encompassed a 1:1 host–vip inclusion complex,an external binding complex,and an exo-wall tessellation complex.Furthermore,based on the findings from these systems,a pillararene-based test paper was developed for efficient picric acid detection,and the removal of picric acid from solution was also achieved using pillararenes powder.This research provides novel insights into the development of diverse host–vip systems toward hazardous compounds,offering potential applications in environmental protection and explosive detection domains.
基金This work was supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(Grant Number:IMSIU-RP23008).
文摘This paper presents an innovative approach to enhance the querying capability of ChatGPT,a conversational artificial intelligence model,by incorporating voice-based interaction and a convolutional neural network(CNN)-based impaired vision detection model.The proposed system aims to improve user experience and accessibility by allowing users to interact with ChatGPT using voice commands.Additionally,a CNN-based model is employed to detect impairments in user vision,enabling the system to adapt its responses and provide appropriate assistance.This research tackles head-on the challenges of user experience and inclusivity in artificial intelligence(AI).It underscores our commitment to overcoming these obstacles,making ChatGPT more accessible and valuable for a broader audience.The integration of voice-based interaction and impaired vision detection represents a novel approach to conversational AI.Notably,this innovation transcends novelty;it carries the potential to profoundly impact the lives of users,particularly those with visual impairments.The modular approach to system design ensures adaptability and scalability,critical for the practical implementation of these advancements.Crucially,the solution places the user at its core.Customizing responses for those with visual impairments demonstrates AI’s potential to not only understand but also accommodate individual needs and preferences.
基金Project(51678075)supported by the National Natural Science Foundation of ChinaProject(2017GK2271)supported by the Hunan Provincial Science and Technology Department,China。
文摘Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the detection of HOIs is still an onerous challenge.Unlike most of the current works for HOIs detection which only rely on the pairwise information of a human and an object,we propose a graph-based HOIs detection method that models context and global structure information.Firstly,to better utilize the relations between humans and objects,the detected humans and objects are regarded as nodes to construct a fully connected undirected graph,and the graph is pruned to obtain an HOI graph that only preserving the edges connecting human and object nodes.Then,in order to obtain more robust features of human and object nodes,two different attention-based feature extraction networks are proposed,which model global and local contexts respectively.Finally,the graph attention network is introduced to pass messages between different nodes in the HOI graph iteratively,and detect the potential HOIs.Experiments on V-COCO and HICO-DET datasets verify the effectiveness of the proposed method,and show that it is superior to many existing methods.
文摘This study addresses security and ethical challenges in LLM-based Multi-Agent Systems, as exemplified in a blockchain fraud detection case study. Leveraging blockchain’s secure architecture, the framework involves specialized LLM Agents—ContractMining, Investigative, Ethics, and PerformanceMonitor, coordinated by a ManagerAgent. Baseline LLM models achieved 30% accuracy with a threshold method and 94% accuracy with a random-forest method. The Claude 3.5-powered LLM system reached an accuracy of 92%. Ethical evaluations revealed biases, highlighting the need for fairness-focused refinements. Our approach aims to develop trustworthy and reliable networks of agents capable of functioning even in adversarial environments. To our knowledge, no existing systems employ ethical LLM agents specifically designed to detect fraud, making this a novel contribution. Future work will focus on refining ethical frameworks, scaling the system, and benchmarking it against traditional methods to establish a robust, adaptable, and ethically grounded solution for blockchain fraud detection.
基金supported by the National Natural Science Foundation of China(NSFC,Nos.22125110,U23A2094,22205233,22193042,21921001,22305248 and U21A2069)the Natural Science Foundation of Fujian Province(No.2023J02028)+3 种基金the Key Research Program of Frontier Sciences of Chinese Academy of Sciences(No.ZDBS-LY-SLH024)Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China(No.2021ZR126)the National Key Research and Development Program of China(No.2019YFA0210402)the China Postdoctoral Science Foundation(Nos.2022TQ0337 and 2023M733497).
文摘2D Ruddlesden-Popper(RP)polar perovskite,displaying the intrinsic optical anisotropy and structural polarity,has a fantastic application perspective in self-powered polarized light detection.However,the weak van der Waals interaction between the organic spacing bilayers is insufficient to preserve the stability of RP-type materials.Hence,it is of great significance to explore new stable 2D RP-phase candidates.In this work,we have successfully constructed a highly-stable polar 2D perovskite,(t-ACH)_(2)PbI_(4)(1,where t-ACH^(+)is HOOC_(8)H_(12)NH_(3)^(+)),by adopting a hydrophobic carboxylate trans-isomer of tranexamic acid as the spacing component.Strikingly,strong O-H…O hydrogen bonds between t-ACH^(+)organic bilayers compose the dimer,thus decreasing van der Waals gap and enhancing structural stability.Besides,such orientational hydrogen bonds contribute to the formation of structural polarity and generate an obvious bulk photovoltaic effect in 1,which facilitates its self-powered photodetection.As predicted,the combination of inherent anisotropy and polarity leads to self-powered polarized-light detection with a high ratio of around∼5.3,superior to those of inorganic 2D counterparts.This work paves a potential way to design highly-stable 2D perovskites for high-performance optoelectronic devices.
基金supported by the National Science and Technology Council under grants NSTC 112-2221-E-320-002the Buddhist Tzu Chi Medical Foundation in Taiwan under Grant TCMMP 112-02-02.
文摘In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible to unsafe events(such as falls)that can have disastrous consequences.However,automatically detecting falls fromvideo data is challenging,and automatic fall detection methods usually require large volumes of training data,which can be difficult to acquire.To address this problem,video kinematic data can be used as training data,thereby avoiding the requirement of creating a large fall data set.This study integrated an improved particle swarm optimization method into a double interactively recurrent fuzzy cerebellar model articulation controller model to develop a costeffective and accurate fall detection system.First,it obtained an optical flow(OF)trajectory diagram from image sequences by using the OF method,and it solved problems related to focal length and object offset by employing the discrete Fourier transform(DFT)algorithm.Second,this study developed the D-IRFCMAC model,which combines spatial and temporal(recurrent)information.Third,it designed an IPSO(Improved Particle Swarm Optimization)algorithm that effectively strengthens the exploratory capabilities of the proposed D-IRFCMAC(Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller)model in the global search space.The proposed approach outperforms existing state-of-the-art methods in terms of action recognition accuracy on the UR-Fall,UP-Fall,and PRECIS HAR data sets.The UCF11 dataset had an average accuracy of 93.13%,whereas the UCF101 dataset had an average accuracy of 92.19%.The UR-Fall dataset had an accuracy of 100%,the UP-Fall dataset had an accuracy of 99.25%,and the PRECIS HAR dataset had an accuracy of 99.07%.
文摘Many studies revealed unconscious effects on conscious processing. However, in this study, we tried to investigate whether unconscious processes could interact with each other by using simultaneously presented face pictures with the same or a different unconscious valence (SUV versus DUV). In the first event-related potential (ERP) study, DUV elicited a smaller N2 as compared with SUV. In the second functional magnetic resonance imaging (fMRI) experiment, the left middle frontal gyrus (MFG) was activated under DUV condition in comparison to SUV condition. These results support the idea of interactions between unconscious processes (unconscious mismatch detection). The theoretical implications are discussed in the light of the global neuronal workspace theory.
文摘As computer graphics technology continues to advance,Collision Detection(CD)has emerged as a critical element in fields such as virtual reality,computer graphics,and interactive simulations.CD is indispensable for ensuring the fidelity of physical interactions and the realism of virtual environments,particularly within complex scenarios like virtual assembly,where both high precision and real-time responsiveness are imperative.Despite ongoing developments,current CD techniques often fall short in meeting these stringent requirements,resulting in inefficiencies and inaccuracies that impede the overall performance of virtual assembly systems.To address these limitations,this study introduces a novel algorithm that leverages the capabilities of a Backpropagation Neural Network(BPNN)to optimize the structural composition of the Hybrid Bounding Volume Tree(HBVT).Through this optimization,the research proposes a refined Hybrid Hierarchical Bounding Box(HHBB)framework,which is specifically designed to enhance the computational efficiency and precision of CD processes.The HHBB framework strategically reduces the complexity of collision detection computations,thereby enabling more rapid and accurate responses to collision events.Extensive experimental validation within virtual assembly environments reveals that the proposed algorithm markedly improves the performance of CD,particularly in handling complex models.The optimized HBVT architecture not only accelerates the speed of collision detection but also significantly diminishes error rates,presenting a robust and scalable solution for real-time applications in intricate virtual systems.These findings suggest that the proposed approach offers a substantial advancement in CD technology,with broad implications for its application in virtual reality,computer graphics,and related fields.
文摘This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted objects.Human-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting process.Since that human actions and interacted objects provide strong context information,i.e.some actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of them.Through the proposed method,both global and local temporal features from skeleton sequences are extracted to model human actions.In the meantime,kernel features are utilized to describe interacted objects.Finally,all possible solutions from actions and objects are optimized by modeling the context between them.The results of experiments demonstrate the effectiveness of our method.
基金supported in part by the Guangxi science and technology program(GuiKe 2021AB30019)Sichuan Science and Technology Program(2022YFN0031,2023YFN0022,and 2023YFS0381)+2 种基金Hubei key R&D plan(2022BAA048)Zhuhai industry university research cooperation project of China(ZH22017001210098PWC)Shanxi Science and Technology Program(202201150401020).
文摘Many existing efforts have taken advantage of large-scale spatial-temporal data to partition cities via constructed human interaction networks.However,few studies focus on communities emerging between adjacent cities in big urban agglomerations,which we call“cross-city”communities.In this study,we introduce a novel framework to detect cross-city communities in urban agglomerations under different scales leveraging a large number of fine-grained mobile signaling data aiming to break the original administrative boundaries.Taking the Pearl River Delta(PRD)urban agglomeration in China as study area,we investigate the existence of potential communities at three scales,i.e.city-group level,city level and sub-city level.The partition results are expected to benefit transportation planning,urban zoning and administrative boundary re-delineation.The results from our study highlight the necessity of considering cross-city communities and their scale effects when examining urban spatial interactions.
基金This research was supported by a grant(2021R1F1A1063634)of the Basic Science Research Program through the National Research Foundation(NRF)funded by the Ministry of Education,Republic of Korea.
文摘Human object interaction(HOI)recognition plays an important role in the designing of surveillance and monitoring systems for healthcare,sports,education,and public areas.It involves localizing the human and object targets and then identifying the interactions between them.However,it is a challenging task that highly depends on the extraction of robust and distinctive features from the targets and the use of fast and efficient classifiers.Hence,the proposed system offers an automated body-parts-based solution for HOI recognition.This system uses RGB(red,green,blue)images as input and segments the desired parts of the images through a segmentation technique based on the watershed algorithm.Furthermore,a convex hullbased approach for extracting key body parts has also been introduced.After identifying the key body parts,two types of features are extracted.Moreover,the entire feature vector is reduced using a dimensionality reduction technique called t-SNE(t-distributed stochastic neighbor embedding).Finally,a multinomial logistic regression classifier is utilized for identifying class labels.A large publicly available dataset,MPII(Max Planck Institute Informatics)Human Pose,has been used for system evaluation.The results prove the validity of the proposed system as it achieved 87.5%class recognition accuracy.
基金supported by the National Natural Science Foundation of China(Nos.22225806,22378385,22078314,22278394)Dalian Institute of Chemical Physics(Nos.DICPI202142,DICPI202436,DMU-1&DICP UN202301).
文摘The continuous mutation and rapid spread of the severe acute respiratory syndrome coronavirus 2(SARSCoV-2)have led to the ineffectiveness of many antiviral drugs targeting the original strain.To keep pace with the virus’evolutionary speed,there is a crucial need for the development of rapid,cost-effective,and efficient inhibitor screening methods.In this study,we created a novel approach based on fluorescence resonance energy transfer(FRET)technology for in vitro detection of inhibitors targeting the interaction between the SARS-CoV-2 spike protein RBD(s-RBD)and the virus receptor angiotensin-converting enzyme 2(ACE2).Utilizing crystallographic insights into the s-RBD/ACE2 interaction,we modified ACE2 by fusing SNAP tag to its N-terminus(resulting in SA740)and Halo tag to s-RBD’s C-terminus(producing R525H and R541H),thereby ensuring the proximity(<10 nm)of labeled FRET dyes.We found that relative to the R541H fusion protein,R525H exhibited higher FRET efficiency,which attributed to the shortened distance between FRET dyes due to the truncation of s-RBD.Utilizing the sensitive FRET effect between SA740 and R525H,we evaluated its efficacy in detecting inhibitors of SARS-CoV-2 entry in solution and live cells.Ultimately,this FRET-based detection method was demonstrated high sensitivity,rapidity,and simplicity in solution and held promise for high-throughput screening of SARS-CoV-2 inhibitors.
基金supported by Priority Research Centers Program through NRF funded by MEST(2018R1A6A1A03024003)the Grand Information Technology Research Center support program IITP-2020-2020-0-01612 supervised by the IITP by MSIT,Korea.
文摘In the new era of technology,daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds.To understand the scenes and activities from human life logs,human-object interaction(HOI)is important in terms of visual relationship detection and human pose estimation.Activities understanding and interaction recognition between human and object along with the pose estimation and interaction modeling have been explained.Some existing algorithms and feature extraction procedures are complicated including accurate detection of rare human postures,occluded regions,and unsatisfactory detection of objects,especially small-sized objects.The existing HOI detection techniques are instancecentric(object-based)where interaction is predicted between all the pairs.Such estimation depends on appearance features and spatial information.Therefore,we propose a novel approach to demonstrate that the appearance features alone are not sufficient to predict the HOI.Furthermore,we detect the human body parts by using the Gaussian Matric Model(GMM)followed by object detection using YOLO.We predict the interaction points which directly classify the interaction and pair them with densely predicted HOI vectors by using the interaction algorithm.The interactions are linked with the human and object to predict the actions.The experiments have been performed on two benchmark HOI datasets demonstrating the proposed approach.
文摘Disentangling the influence of multiple signal components on receivers and elucidating general processes influencing complex signal evolution are difficult tasks. In this study we test mate preferences of female squirrel treefrogs Hyla squirella and female tungara frogs Physalaemus pustulosus for similar combinations of acoustic and visual components of their multimodal courtship signals. In a two-choice playback experiment with squirrel treefrogs, the visual stimulus of a male model significantly increased the attractivness of a relatively unattractive slow call rate. A previous study demonstrated that faster call rates are more attractive to female squirrel treefrogs, and all else being equal, models of male frogs with large body stripes are more attractive. In a similar experiment with female tungara frogs, the visual stimulus of a robotic frog failed to increase the attractiveness of a relatively unattractive call. Females also showed no preference for the distinct stripe on the robot that males commonly bear on their throat. Thus, features of conspicuous signal components such as body stripes are not universally important and signal function is likely to differ even among species with similar ecologies and communication systems. Finally, we discuss the putative information content of anuran signals and suggest that the categorization of redundant versus multiple messages may not be sufficient as a general explanation for the evolution of multimodal signaling. Instead of relying on untested assumptions concerning the information content of signals, we discuss the value of initially collecting comparative empirical data sets related to receiver responses.
文摘Brazil is the world leader in sugarcane production and the largest sugar exporter. Developing new varieties is one of the main factors that contribute to yield increase. In order to select the best genotypes, during the final selection stage, varieties are tested in different environments (locations and years), and breeders need to estimate the phenotypic performance for main traits such as tons of cane yield per hectare (TCH) considering the genotype × environment interaction (GEI) effect. Geneticists and biometricians have used different methods and there is no clear consensus of the best method. In this study, we present a comparison of three methods, viz. Eberhart-Russel (ER), additive main effects and multiplicative interaction (AMMI) and mixed model (REML/BLUP), in a simulation study performed in the R computing environment to verify the effectiveness of each method in detecting GEI, and assess the particularities of each method from a statistical standpoint. In total, 63 cases representing different conditions were simulated, generating more than 34 million data points for analysis by each of the three methods. The results show that each method detects GEI differently in a different way, and each has some limitations. All three methods detected GEI effectively, but the mixed model showed higher sensitivity. When applying the GEI analysis, firstly it is important to verify the assumptions inherent in each method and these limitations should be taken into account when choosing the method to be used.
基金The MKE(The Ministry of Knowledge Economy),Korea,under the ITRC(Infor mation Technology Research Center)support programsupervised by the NIPA(National ITIndustry Promotion Agency)(NIPA-2012-C1090-1221-0010)The MKE,Korea,under the Human Resources Development Program for Convergence Robot Specialists support programsu-pervised by the NIPA(NIPA-2012-H1502-12-1002)Basic Science Research Program through the NRF funded by the MEST(2011-0025980)and MEST(2012-0005487)
文摘Human interaction becomes an important issue in the field of mobile robotics. To achieve humanfriendly naviga tion, the robot needs to recognize human on cluttered backgrounds, and this can be fulfilled by the detection of human legs. The detection of human legs is advantageous because it enables detecting environmental obstacles at such heights. In this pa per, we compared the performance of an algorithm using a single laser range finder（LRF） proposed in Ref. L 1 ] with that of wellknown feature extraction approaches bounding box and circle fitting proposed in Ref. [ 2 ] by using the same laser scanned image.
文摘Based on the traditional Human-Computer Interaction method which is mainly touch input system, the way of capturing the movement of people by using cameras is proposed. This is a convenient technique which can provide users more experience. In the article, a new way of detecting moving things is given on the basis of development of the image processing technique. The system architecture decides that the communication should be used between two different applications. After considered, named pipe is selected from many ways of communication to make sure that video is keeping in step with the movement from the analysis of the people moving. According to a large amount of data and principal knowledge, thinking of the need of actual project, a detailed system design and realization is finished. The system consists of three important modules: detecting of the people's movement, information transition between applications and video showing in step with people's movement. The article introduces the idea of each module and technique.
基金Project supported by Beijing Natural Science Foundation,China(Grant Nos.L181010 and 4172054)the National Key R&D Program of China(Grant No.2016YFB0801100)the National Basic Research Program of China(Grant No.2013CB329605)。
文摘The statistical model for community detection is a promising research area in network analysis.Most existing statistical models of community detection are designed for networks with a known type of community structure,but in many practical situations,the types of community structures are unknown.To cope with unknown community structures,diverse types should be considered in one model.We propose a model that incorporates the latent interaction pattern,which is regarded as the basis of constructions of diverse community structures by us.The interaction pattern can parameterize various types of community structures in one model.A collapsed Gibbs sampling inference is proposed to estimate the community assignments and other hyper-parameters.With the Pitman-Yor process as a prior,our model can automatically detect the numbers and sizes of communities without a known type of community structure beforehand.Via Bayesian inference,our model can detect some hidden interaction patterns that offer extra information for network analysis.Experiments on networks with diverse community structures demonstrate that our model outperforms four state-of-the-art models.
基金Our research has been supported in part by National Natural Science Foundation of China under Grants 61673261 and 61703273.We gratefully acknowledge the support from some companies.
文摘Most of the intelligent surveillances in the industry only care about the safety of the workers.It is meaningful if the camera can know what,where and how the worker has performed the action in real time.In this paper,we propose a light-weight and robust algorithm to meet these requirements.By only two hands'trajectories,our algorithm requires no Graphic Processing Unit(GPU)acceleration,which can be used in low-cost devices.In the training stage,in order to find potential topological structures of the training trajectories,spectral clustering with eigengap heuristic is applied to cluster trajectory points.A gradient descent based algorithm is proposed to find the topological structures,which reflects main representations for each cluster.In the fine-tuning stage,a topological optimization algorithm is proposed to fine-tune the parameters of topological structures in all training data.Finally,our method not only performs more robustly compared to some popular offline action detection methods,but also obtains better detection accuracy in an extended action sequence.
