Artificial sensory systems,designed to emulate human senses like sight,touch,and hearing,have garnered significant attention for their potential to enhance human capabilities,improve human-machine interactions,and ena...Artificial sensory systems,designed to emulate human senses like sight,touch,and hearing,have garnered significant attention for their potential to enhance human capabilities,improve human-machine interactions,and enable autonomous systems to better perceive their surroundings.Hydrogels,with their biocompatibility,flexibility,and water-rich polymer structure,are increasingly recognized as crucial materials in the development of these systems,especially in applications such as wearable sensors,artificial skin,and neural interfaces.This review explores various hydrogel fabrication techniques,including 3D bioprinting,electro spinning,and photopolymerization,which allow for the precise control of hydrogel properties like mechanical strength,flexibility,and conductivity.By tailoring these properties to mimic natural tissues,hydrogels offer transformative benefits in the creation of advanced,biocompatible,and durable sensory systems.We emphasize the importance of selecting appropriate fabrication methods to meet the specific functional requirements of artificial sensory applications,such as sensitivity to stimuli,durability,and ease of integration.This review further highlights the pivotal role of hydrogels in advancing future artificial sensory technologies and their broad potential in fields ranging from robotics to biomedical devices.展开更多
With the rapid development of artificial intelligence(AI)technology,the demand for high-performance and energyefficient computing is increasingly growing.The limitations of the traditional von Neumann computing archit...With the rapid development of artificial intelligence(AI)technology,the demand for high-performance and energyefficient computing is increasingly growing.The limitations of the traditional von Neumann computing architecture have prompted researchers to explore neuromorphic computing as a solution.Neuromorphic computing mimics the working principles of the human brain,characterized by high efficiency,low energy consumption,and strong fault tolerance,providing a hardware foundation for the development of new generation AI technology.Artificial neurons and synapses are the two core components of neuromorphic computing systems.Artificial perception is a crucial aspect of neuromorphic computing,where artificial sensory neurons play an irreplaceable role thus becoming a frontier and hot topic of research.This work reviews recent advances in artificial sensory neurons and their applications.First,biological sensory neurons are briefly described.Then,different types of artificial neurons,such as transistor neurons and memristive neurons,are discussed in detail,focusing on their device structures and working mechanisms.Next,the research progress of artificial sensory neurons and their applications in artificial perception systems is systematically elaborated,covering various sensory types,including vision,touch,hearing,taste,and smell.Finally,challenges faced by artificial sensory neurons at both device and system levels are summarized.展开更多
Based on the uncertainty theory, this paper is devoted to the redundancy allocation problem in repairable parallel-series systems with uncertain factors, where the failure rate, repair rate and other relative coeffici...Based on the uncertainty theory, this paper is devoted to the redundancy allocation problem in repairable parallel-series systems with uncertain factors, where the failure rate, repair rate and other relative coefficients involved are considered as uncertain variables. The availability of the system and the corresponding designing cost are considered as two optimization objectives. A crisp multiobjective optimization formulation is presented on the basis of uncertainty theory to solve this resultant problem. For solving this problem efficiently, a new multiobjective artificial bee colony algorithm is proposed to search the Pareto efficient set, which introduces rank value and crowding distance in the greedy selection strategy, applies fast non-dominated sort procedure in the exploitation search and inserts tournament selection in the onlooker bee phase. It shows that the proposed algorithm outperforms NSGA-II greatly and can solve multiobjective redundancy allocation problem efficiently. Finally, a numerical example is provided to illustrate this approach.展开更多
Adversarial attacks pose a significant threat to artificial intelligence systems by exposing them to vulnerabilities in deep learning models.Existing defense mechanisms often suffer drawbacks,such as the need for mode...Adversarial attacks pose a significant threat to artificial intelligence systems by exposing them to vulnerabilities in deep learning models.Existing defense mechanisms often suffer drawbacks,such as the need for model retraining,significant inference time overhead,and limited effectiveness against specific attack types.Achieving perfect defense against adversarial attacks remains elusive,emphasizing the importance of mitigation strategies.In this study,we propose a defense mechanism that applies random cropping and Gaussian filtering to input images to mitigate the impact of adversarial attacks.First,the image was randomly cropped to vary its dimensions and then placed at the center of a fixed 299299 space,with the remaining areas filled with zero padding.Subsequently,Gaussian×filtering with a 77 kernel and a standard deviation of two was applied using a convolution operation.Finally,the×smoothed image was fed into the classification model.The proposed defense method consistently appeared in the upperright region across all attack scenarios,demonstrating its ability to preserve classification performance on clean images while significantly mitigating adversarial attacks.This visualization confirms that the proposed method is effective and reliable for defending against adversarial perturbations.Moreover,the proposed method incurs minimal computational overhead,making it suitable for real-time applications.Furthermore,owing to its model-agnostic nature,the proposed method can be easily incorporated into various neural network architectures,serving as a fundamental module for adversarial defense strategies.展开更多
Rapid development of artificial intelligence requires the implementation of hardware systems with bioinspired parallel information processing and presentation and energy efficiency.Electrolyte-gated organic transistor...Rapid development of artificial intelligence requires the implementation of hardware systems with bioinspired parallel information processing and presentation and energy efficiency.Electrolyte-gated organic transistors(EGOTs)offer significant advantages as neuromorphic devices due to their ultra-low operation voltages,minimal hardwired connectivity,and similar operation environment as electrophysiology.Meanwhile,ionic–electronic coupling and the relatively low elastic moduli of organic channel materials make EGOTs suitable for interfacing with biology.This review presents an overview of the device architectures based on organic electrochemical transistors and organic field-effect transistors.Furthermore,we review the requirements of low energy consumption and tunable synaptic plasticity of EGOTs in emulating biological synapses and how they are affected by the organic materials,electrolyte,architecture,and operation mechanism.In addition,we summarize the basic operation principle of biological sensory systems and the recent progress of EGOTs as a building block in artificial systems.Finally,the current challenges and future development of the organic neuromorphic devices are discussed.展开更多
Processive catalysis represents a transformative approach to molecular transformations,wherein a catalyst remains bound to its substrate and undergoes multiple reaction cycles before dissociating.
In wireless artificial intelligent computing systems,the construction of backbone network,which determines the optimum network for a set of given terminal nodes like users,switches,and concentrators,can be naturally f...In wireless artificial intelligent computing systems,the construction of backbone network,which determines the optimum network for a set of given terminal nodes like users,switches,and concentrators,can be naturally formed as the Steiner tree problem.The Steiner tree problem asks for a minimum edge-weighted tree spanning a given set of terminal vertices from a given graph.As a well-known graph problem,many algorithms have been developed for solving this computationally challenging problem in the past decades.However,existing algorithms typically encounter difficulties for solving large instances,i.e.,graphs with a high number of vertices and terminals.In this paper,we present a novel partition-and-merge algorithm for effectively handle large-scale graphs.The algorithm breaks the input network into small subgraphs and then merges the subgraphs in a bottom-up manner.In the merging procedure,partial Steiner trees in the subgraphs are also created and optimized by an efficient local optimization.When the merging procedure ends,the algorithm terminates and reports the final solution for the input graph.We evaluated the algorithm on a wide range of benchmark instances,showing that the algorithm outperforms the best-known algorithms on large instances and competes favorably with them on small or middle-sized instances.展开更多
Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variabil...Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variability,where characters frequently alter their appearance.To address this problem,we introduce the novel Kral Sakir dataset,a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions.This paper conducts a comprehensive benchmark study,evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks(CNNs),including DenseNet,ResNet,and VGG,against a custom baseline model trained from scratch.Our experiments,evaluated using metrics of F1-Score,accuracy,and Area Under the ROC Curve(AUC),demonstrate that fine-tuning pretrained models is a highly effective strategy.The best-performing model,DenseNet121,achieved an F1-Score of 0.9890 and an accuracy of 0.9898,significantly outperforming our baseline CNN(F1-Score of 0.9545).The findings validate the power of transfer learning for this domain and establish a strong performance benchmark.The introduced dataset provides a valuable resource for future research into developing robust and accurate character recognition systems.展开更多
Naturally complete mixing promotes the spontaneous redistribution of dissolved oxygen(DO),representing an ideal state for maintaining good water quality,and conducive to the biomineralization of organic matter.Water l...Naturally complete mixing promotes the spontaneous redistribution of dissolved oxygen(DO),representing an ideal state for maintaining good water quality,and conducive to the biomineralization of organic matter.Water lifting aerators(WLAs)can extend the periods of complete mixing and increase the initial mixing temperature.To evaluate the influence of artificial-induced continuously mixing on dissolved organic matter(DOM)removal performance,the variations of DOM concentrations,optical characteristic,environmental factors were studied after approaching the total mixing status via WLAs operation.During this process,the dissolved organic carbon reduced by 39.18%,whereas the permanganate index decreased by 20.47%.The optical properties indicate that the DOM became more endogenous and its molecular weight decreased.Based on the results of the Biolog Eco Plates,the microorganisms were maintained at a relatively high metabolic activity in the early stage of induced mixing when the mixing temperature was relatively high,whereas DOM declined at a high rate.With the continuous decrease in the water temperature,both the metabolic capacity and the diversity of aerobic microorganisms significantly decreased,and the rate of organic matter mineralization slowed down.The results of this study demonstrate that the artificial induced mixing largely enhanced the removal DOM performance by providing a long period of aerobic conditions and higher initial temperature.展开更多
An abstraction and an investigation to the worth of dendritic cells (DCs) ability to collect, process and present antigens are presented. Computationally, this ability is shown to provide a feature reduction mechanism...An abstraction and an investigation to the worth of dendritic cells (DCs) ability to collect, process and present antigens are presented. Computationally, this ability is shown to provide a feature reduction mechanism that could be used to reduce the complexity of a search space, a mechanism for development of highly specialized detector sets as well as a selective mechanism used in directing subsets of detectors to be activated when certain danger signals are present. It is shown that DCs, primed by different danger signals, provide a basis for different anomaly detection pathways. Different antigen-peptides are developed based on different danger signals present, and these peptides are presented to different adaptive layer detectors that correspond to the given danger signal. Experiments are then undertaken that compare current approaches, where a full antigen structure and the whole repertoire of detectors are used, with the proposed approach. Experiment results indicate that such an approach is feasible and can help reduce the complexity of the problem by significant levels. It also improves the efficiency of the system, given that only a subset of detectors are involved during the detection process. Having several different sets of detectors increases the robustness of the resulting system. Detectors developed based on peptides are also highly discriminative, which reduces the false positives rates, making the approach feasible for a real time environment.展开更多
Based on ACP(artificial systems,computational experiments,and parallel execution)methodology,parallel control and management has become a popularly systematic and complete solution for the control and management of co...Based on ACP(artificial systems,computational experiments,and parallel execution)methodology,parallel control and management has become a popularly systematic and complete solution for the control and management of complex systems.This paper focuses on summarizing comprehensive review of the research literature of parallel control and management achieved in the recent years including the theoretical framework,core technologies,and the application demonstration.The future research,application directions,and suggestions are also discussed.展开更多
This paper puts forward a novel artificial immune response algorithm for optimal approximation of linear systems. A quaternion model of artificial immune response is proposed for engineering computing. The model abstr...This paper puts forward a novel artificial immune response algorithm for optimal approximation of linear systems. A quaternion model of artificial immune response is proposed for engineering computing. The model abstracts four elements, namely, antigen, antibody, reaction rules among antibodies, and driving algorithm describing how the rules are applied to antibodies, to simulate the process of immune response. Some reaction rules including clonal selection rules, immunological memory rules and immune regulation rules are introduced. Using the theorem of Markov chain, it is proofed that the new model is convergent. The experimental study on the optimal approximation of a stable linear system and an unstable one show that the approximate models searched by the new model have better performance indices than those obtained by some existing algorithms including the differential evolution algorithm and the multi-agent genetic algorithm.展开更多
AIM To establish a simplified, reproducible D-galactosamineinduced cynomolgus monkey model of acute liver failure having an appropriate treatment window. METHODS Sixteen cynomolgus monkeys were randomly dividedinto fo...AIM To establish a simplified, reproducible D-galactosamineinduced cynomolgus monkey model of acute liver failure having an appropriate treatment window. METHODS Sixteen cynomolgus monkeys were randomly dividedinto four groups(A, B, C and D) after intracranial pressure(ICP) sensor implantation. D-galactosamine at 0.3, 0.25, 0.20 + 0.05(24 h interval), and 0.20 g/kg body weight, respectively, was injected via the small saphenous vein. Vital signs, ICP, biochemical indices, and inflammatory factors were recorded at 0, 12, 24, 36, 48, 72, 96, and 120 h after D-galactosamine administration. Progression of clinical manifestations, survival times, and results of H&E staining, TUNEL, and Masson staining were recorded. RESULTS Cynomolgus monkeys developed different degrees of debilitation, loss of appetite, and jaundice after D-galactosamine administration. Survival times of groups A, B, and C were 56 ± 8.7 h, 95 ± 5.5 h, and 99 ± 2.2 h, respectively, and in group D all monkeys survived the 144-h observation period except for one, which died at 136 h. Blood levels of ALT, AST, CK, LDH, TBi L, Cr, BUN, and ammonia, prothrombin time, ICP, endotoxin, and inflammatory markers [(tumor necrosis factor(TNF)-α, interleukin(IL)-1β, and IL-6)] significantly increased compared with baseline values in different groups(P < 0.05). Pathological results showed obvious liver cell necrosis that was positively correlated with the dose of D-galactosamine.CONCLUSION We successfully established a simplified, reproducible D-galactosamine-induced cynomolgus monkey model of acute liver failure, and the single or divided dosage of 0.25 g/kg is optimal for creating this model.展开更多
Clinically,it is highly challenging to promote recovery in patients with acute liver failure(ALF)and acute-on-chronic liver failure(ACLF).Despite recent advances in understanding the underlying mechanisms of ALF and A...Clinically,it is highly challenging to promote recovery in patients with acute liver failure(ALF)and acute-on-chronic liver failure(ACLF).Despite recent advances in understanding the underlying mechanisms of ALF and ACLF,standard medical therapy remains the primary therapeutic approach.Liver transplantation(LT)is considered the last option,and in several cases,it is the only intervention that can be lifesaving.Unfortunately,this intervention is limited by organ donation shortage or exclusion criteria such that not all patients in need can receive a transplant.Another option is to restore impaired liver function with artificial extracorporeal blood purification systems.The first such systems were developed at the end of the 20th century,providing solutions as bridging therapy,either for liver recovery or LT.They enhance the elimination of metabolites and substances that accumulate due to compromised liver function.In addition,they aid in clearance of molecules released during acute liver decompensation,which can initiate an excessive inflammatory response in these patients causing hepatic encephalopathy,multiple-organ failure,and other complications of liver failure.As compared to renal replacement therapies,we have been unsuccessful in using artificial extracorporeal blood purification systems to completely replace liver function despite the outstanding technological evolution of these systems.Extracting middle to high-molecular-weight and hydrophobic/protein-bound molecules remains extremely challenging.The majority of the currently available systems include a combination of methods that cleanse different ranges and types of molecules and toxins.Furthermore,conventional methods such as plasma exchange are being re-evaluated,and novel adsorption filters are increasingly being used for liver indications.These strategies are very promising for the treatment of liver failure.Nevertheless,the best method,system,or device has not been developed yet,and its probability of getting developed in the near future is also low.Furthermore,little is known about the effects of liver support systems on the overall and transplant-free survival of these patients,and further investigation using randomized controlled trials and meta-analyses is needed.This review presents the most popular extracorporeal blood purification techniques for liver replacement therapy.It focuses on general principles of their function,and on evidence regarding their effectiveness in detoxification and in supporting patients with ALF and ACLF.In addition,we have outlined the basic advantages and disadvantages of each system.展开更多
Clonal selection feature selection algorithm （CSFS） based on clonal selection algorithm （CSA）, a new computational intelligence approach, has been proposed to perform the task of dimensionality reduction in high-d...Clonal selection feature selection algorithm （CSFS） based on clonal selection algorithm （CSA）, a new computational intelligence approach, has been proposed to perform the task of dimensionality reduction in high-dimensional images, and has better performance than traditional feature selection algorithms with more computational costs. In this paper, a fast clonal selection feature selection algorithm （FCSFS） for hyperspectral imagery is proposed to improve the convergence rate by using Cauchy mutation instead of non-uniform mutation as the primary immune operator. Two experiments are performed to evaluate the performance of the proposed algorithm in comparison with CSFS using hyperspectral remote sensing imagery acquired by the pushbroom hyperspectral imager （PHI） and the airborne visible/infrared imaging spectrometer （AVlRIS）, respectively. Experimental results demonstrate that the FCSFS converges faster than CSFS, hence providing an effective new option for dimensionality reduction of hyperspectral remote sensing imagery.展开更多
An artificial immunity based multimodal evolution algorithm is developed to generate detectors with variable coverage for multidimensional intrusion detection. In this algorithm, a proper fitness function is used to d...An artificial immunity based multimodal evolution algorithm is developed to generate detectors with variable coverage for multidimensional intrusion detection. In this algorithm, a proper fitness function is used to drive the detectors to fill in those detection holes close to self set or among self spheres, and genetic algorithm is adopted to reduce the negative effects that different distribution of self imposes on the detector generating process. The validity of the algorithm is tested with spherical and rectangular detectors, respectively, and experiments performed on two real data sets （machine learning database and DAPRA99） indicate that the proposed algorithm can obtain good results on spherical detectors, and that its performances in detection rate, false alarm rate, stabih＇ty, time cost, and adaptability to incomplete training set on spherical detectors are all better than on rectangular ones.展开更多
The emulation of human multisensory functions to construct artificial perception systems is an intriguing challenge for developing humanoid robotics and cross-modal human–machine interfaces.Inspired by human multisen...The emulation of human multisensory functions to construct artificial perception systems is an intriguing challenge for developing humanoid robotics and cross-modal human–machine interfaces.Inspired by human multisensory signal generation and neuroplasticity-based signal processing,here,an artificial perceptual neuro array with visual-tactile sensing,processing,learning,and memory is demonstrated.The neuromorphic bimodal perception array compactly combines an artificial photoelectric synapse network and an integrated mechanoluminescent layer,endowing individual and synergistic plastic modulation of optical and mechanical information,including short-term memory,long-term memory,paired pulse facilitation,and“learning-experience”behavior.Sequential or superimposed visual and tactile stimuli inputs can efficiently simulate the associative learning process of“Pavlov's dog”.The fusion of visual and tactile modulation enables enhanced memory of the stimulation image during the learning process.A machine-learning algorithm is coupled with an artificial neural network for pattern recognition,achieving a recognition accuracy of 70%for bimodal training,which is higher than that obtained by unimodal training.In addition,the artificial perceptual neuron has a low energy consumption of~20 pJ.With its mechanical compliance and simple architecture,the neuromorphic bimodal perception array has promising applications in largescale cross-modal interactions and high-throughput intelligent perceptions.展开更多
Human consciousness is the most interesting and mysterious phenomenon inthe world. In this paper, the results of the computational study and simulationof the conscious behaviour, such as the learning of 1anguage and i...Human consciousness is the most interesting and mysterious phenomenon inthe world. In this paper, the results of the computational study and simulationof the conscious behaviour, such as the learning of 1anguage and image pat-terns, traditional conditioning, association, imagination and dream, have beenpresented. Based on these results, an experimental conscious system - CON-SCITRON, has been developed. Further discussion on development of artificialconscious systems is also provided.展开更多
The search for patterns or motifs in data represents a problem area of key interest to finance and economic researchers. In this paper, we introduce the motif tracking algorithm （MTA）, a novel immune inspired （IS）...The search for patterns or motifs in data represents a problem area of key interest to finance and economic researchers. In this paper, we introduce the motif tracking algorithm （MTA）, a novel immune inspired （IS） pattern identification tool that is able to identify unknown motifs of a non specified length which repeat within time series data. The power of the algorithm comes from the fact that it uses a small number of parameters with minimal assumptions regarding the data being examined or the underlying motifs. Our interest lies in applying the algorithm to financial time series data to identify unknown patterns that exist. The algorithm is tested using three separate data sets. Particular suitability to financial data is shown by applying it to oil price data. In all cases, the algorithm identifies the presence of a motif population in a fast and efficient manner due to the utilization of an intuitive symbolic representation. The resulting population of motifs is shown to have considerable potential value for other applications such as forecasting and algorithm seeding.展开更多
Oppositional Defiant Disorder(ODD)and Attention Deficit/Hyperactivity Disorder(ADHD)are mental health conditions that have traditionally been managed through behavioral therapies and medication.However,the integration...Oppositional Defiant Disorder(ODD)and Attention Deficit/Hyperactivity Disorder(ADHD)are mental health conditions that have traditionally been managed through behavioral therapies and medication.However,the integration of Artificial Intelligence(AI)has brought about a revolutionary shift in treatment approaches.This article explores the role of AI-driven noninvasive treatments for ODD and ADHD.AI offers personalized treatment plans,predictive analytics,virtual therapeutic platforms,and continuous monitoring,enhancing the effectiveness and accessibility of interventions.Ethical considerations and the need for a balanced approach are discussed.As technology evolves,collaborative efforts between mental health professionals and technologists will shape the future of mental health care for individuals with ODD and ADHD.展开更多
基金supported by the National Research Foundation of Korea(NRF)Grants funded by the Korea government(MSIT)(Nos.RS-2023-00213047 and RS-2024-00405818)。
文摘Artificial sensory systems,designed to emulate human senses like sight,touch,and hearing,have garnered significant attention for their potential to enhance human capabilities,improve human-machine interactions,and enable autonomous systems to better perceive their surroundings.Hydrogels,with their biocompatibility,flexibility,and water-rich polymer structure,are increasingly recognized as crucial materials in the development of these systems,especially in applications such as wearable sensors,artificial skin,and neural interfaces.This review explores various hydrogel fabrication techniques,including 3D bioprinting,electro spinning,and photopolymerization,which allow for the precise control of hydrogel properties like mechanical strength,flexibility,and conductivity.By tailoring these properties to mimic natural tissues,hydrogels offer transformative benefits in the creation of advanced,biocompatible,and durable sensory systems.We emphasize the importance of selecting appropriate fabrication methods to meet the specific functional requirements of artificial sensory applications,such as sensitivity to stimuli,durability,and ease of integration.This review further highlights the pivotal role of hydrogels in advancing future artificial sensory technologies and their broad potential in fields ranging from robotics to biomedical devices.
基金supported by the National Natural Science Foundation of China(Nos.U20A20209 and 62304228)the China National Postdoctoral Program for Innovative Talents(No.BX2021326)+3 种基金the China Postdoctoral Science Foundation(No.2021M703310)the Zhejiang Provincial Natural Science Foundation of China(No.LQ22F040003)the Ningbo Natural Science Foundation of China(No.2023J356)the State Key Laboratory for Environment-Friendly Energy Materials(No.20kfhg09).
文摘With the rapid development of artificial intelligence(AI)technology,the demand for high-performance and energyefficient computing is increasingly growing.The limitations of the traditional von Neumann computing architecture have prompted researchers to explore neuromorphic computing as a solution.Neuromorphic computing mimics the working principles of the human brain,characterized by high efficiency,low energy consumption,and strong fault tolerance,providing a hardware foundation for the development of new generation AI technology.Artificial neurons and synapses are the two core components of neuromorphic computing systems.Artificial perception is a crucial aspect of neuromorphic computing,where artificial sensory neurons play an irreplaceable role thus becoming a frontier and hot topic of research.This work reviews recent advances in artificial sensory neurons and their applications.First,biological sensory neurons are briefly described.Then,different types of artificial neurons,such as transistor neurons and memristive neurons,are discussed in detail,focusing on their device structures and working mechanisms.Next,the research progress of artificial sensory neurons and their applications in artificial perception systems is systematically elaborated,covering various sensory types,including vision,touch,hearing,taste,and smell.Finally,challenges faced by artificial sensory neurons at both device and system levels are summarized.
基金supported by National Natural Science Foundation of China (No. 71171199)Natural Science Foundation of Shaanxi Province of China (No. 2013JM1003)
文摘Based on the uncertainty theory, this paper is devoted to the redundancy allocation problem in repairable parallel-series systems with uncertain factors, where the failure rate, repair rate and other relative coefficients involved are considered as uncertain variables. The availability of the system and the corresponding designing cost are considered as two optimization objectives. A crisp multiobjective optimization formulation is presented on the basis of uncertainty theory to solve this resultant problem. For solving this problem efficiently, a new multiobjective artificial bee colony algorithm is proposed to search the Pareto efficient set, which introduces rank value and crowding distance in the greedy selection strategy, applies fast non-dominated sort procedure in the exploitation search and inserts tournament selection in the onlooker bee phase. It shows that the proposed algorithm outperforms NSGA-II greatly and can solve multiobjective redundancy allocation problem efficiently. Finally, a numerical example is provided to illustrate this approach.
基金supported by the Glocal University 30 Project Fund of Gyeongsang National University in 2025.
文摘Adversarial attacks pose a significant threat to artificial intelligence systems by exposing them to vulnerabilities in deep learning models.Existing defense mechanisms often suffer drawbacks,such as the need for model retraining,significant inference time overhead,and limited effectiveness against specific attack types.Achieving perfect defense against adversarial attacks remains elusive,emphasizing the importance of mitigation strategies.In this study,we propose a defense mechanism that applies random cropping and Gaussian filtering to input images to mitigate the impact of adversarial attacks.First,the image was randomly cropped to vary its dimensions and then placed at the center of a fixed 299299 space,with the remaining areas filled with zero padding.Subsequently,Gaussian×filtering with a 77 kernel and a standard deviation of two was applied using a convolution operation.Finally,the×smoothed image was fed into the classification model.The proposed defense method consistently appeared in the upperright region across all attack scenarios,demonstrating its ability to preserve classification performance on clean images while significantly mitigating adversarial attacks.This visualization confirms that the proposed method is effective and reliable for defending against adversarial perturbations.Moreover,the proposed method incurs minimal computational overhead,making it suitable for real-time applications.Furthermore,owing to its model-agnostic nature,the proposed method can be easily incorporated into various neural network architectures,serving as a fundamental module for adversarial defense strategies.
基金financial support by the self-supporting project of Pazhou Lab(No.PZL2023ZZ0011)by National Key R&D Program of China(No.2019YFA0904801).
文摘Rapid development of artificial intelligence requires the implementation of hardware systems with bioinspired parallel information processing and presentation and energy efficiency.Electrolyte-gated organic transistors(EGOTs)offer significant advantages as neuromorphic devices due to their ultra-low operation voltages,minimal hardwired connectivity,and similar operation environment as electrophysiology.Meanwhile,ionic–electronic coupling and the relatively low elastic moduli of organic channel materials make EGOTs suitable for interfacing with biology.This review presents an overview of the device architectures based on organic electrochemical transistors and organic field-effect transistors.Furthermore,we review the requirements of low energy consumption and tunable synaptic plasticity of EGOTs in emulating biological synapses and how they are affected by the organic materials,electrolyte,architecture,and operation mechanism.In addition,we summarize the basic operation principle of biological sensory systems and the recent progress of EGOTs as a building block in artificial systems.Finally,the current challenges and future development of the organic neuromorphic devices are discussed.
基金supported by National Natural Science Foundation of China(No.23CAA01015)China Petroleum&Chemical Corporation Seed Plan(No.2550042076).
文摘Processive catalysis represents a transformative approach to molecular transformations,wherein a catalyst remains bound to its substrate and undergoes multiple reaction cycles before dissociating.
基金funded by the Sichuan Province Science and Technology Program(No.2024NSFTD0033)the National Natural Science Foundation of China(Nos.62372093 and 62376055)+1 种基金the Natural Science Foundation of Sichuan Province of China(No.2023NSFSC1415)the Shenzhen Agency of Innovation(No.KJZD20240903095712016).
文摘In wireless artificial intelligent computing systems,the construction of backbone network,which determines the optimum network for a set of given terminal nodes like users,switches,and concentrators,can be naturally formed as the Steiner tree problem.The Steiner tree problem asks for a minimum edge-weighted tree spanning a given set of terminal vertices from a given graph.As a well-known graph problem,many algorithms have been developed for solving this computationally challenging problem in the past decades.However,existing algorithms typically encounter difficulties for solving large instances,i.e.,graphs with a high number of vertices and terminals.In this paper,we present a novel partition-and-merge algorithm for effectively handle large-scale graphs.The algorithm breaks the input network into small subgraphs and then merges the subgraphs in a bottom-up manner.In the merging procedure,partial Steiner trees in the subgraphs are also created and optimized by an efficient local optimization.When the merging procedure ends,the algorithm terminates and reports the final solution for the input graph.We evaluated the algorithm on a wide range of benchmark instances,showing that the algorithm outperforms the best-known algorithms on large instances and competes favorably with them on small or middle-sized instances.
文摘Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variability,where characters frequently alter their appearance.To address this problem,we introduce the novel Kral Sakir dataset,a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions.This paper conducts a comprehensive benchmark study,evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks(CNNs),including DenseNet,ResNet,and VGG,against a custom baseline model trained from scratch.Our experiments,evaluated using metrics of F1-Score,accuracy,and Area Under the ROC Curve(AUC),demonstrate that fine-tuning pretrained models is a highly effective strategy.The best-performing model,DenseNet121,achieved an F1-Score of 0.9890 and an accuracy of 0.9898,significantly outperforming our baseline CNN(F1-Score of 0.9545).The findings validate the power of transfer learning for this domain and establish a strong performance benchmark.The introduced dataset provides a valuable resource for future research into developing robust and accurate character recognition systems.
基金supported by the National Natural Science Foundation of China(No.51979217)the National Key Research and Development Program of China(No.2019YFD1100101)the Shaanxi Provincial Key Research and Development Project(Nos.2019ZDLSF06-01 and 2019ZDLSF06-02)。
文摘Naturally complete mixing promotes the spontaneous redistribution of dissolved oxygen(DO),representing an ideal state for maintaining good water quality,and conducive to the biomineralization of organic matter.Water lifting aerators(WLAs)can extend the periods of complete mixing and increase the initial mixing temperature.To evaluate the influence of artificial-induced continuously mixing on dissolved organic matter(DOM)removal performance,the variations of DOM concentrations,optical characteristic,environmental factors were studied after approaching the total mixing status via WLAs operation.During this process,the dissolved organic carbon reduced by 39.18%,whereas the permanganate index decreased by 20.47%.The optical properties indicate that the DOM became more endogenous and its molecular weight decreased.Based on the results of the Biolog Eco Plates,the microorganisms were maintained at a relatively high metabolic activity in the early stage of induced mixing when the mixing temperature was relatively high,whereas DOM declined at a high rate.With the continuous decrease in the water temperature,both the metabolic capacity and the diversity of aerobic microorganisms significantly decreased,and the rate of organic matter mineralization slowed down.The results of this study demonstrate that the artificial induced mixing largely enhanced the removal DOM performance by providing a long period of aerobic conditions and higher initial temperature.
基金Project(50275150) supported by the National Natural Science Foundation of ChinaProjects(20040533035, 20070533131) supported by the National Research Foundation for the Doctoral Program of Higher Education of China
文摘An abstraction and an investigation to the worth of dendritic cells (DCs) ability to collect, process and present antigens are presented. Computationally, this ability is shown to provide a feature reduction mechanism that could be used to reduce the complexity of a search space, a mechanism for development of highly specialized detector sets as well as a selective mechanism used in directing subsets of detectors to be activated when certain danger signals are present. It is shown that DCs, primed by different danger signals, provide a basis for different anomaly detection pathways. Different antigen-peptides are developed based on different danger signals present, and these peptides are presented to different adaptive layer detectors that correspond to the given danger signal. Experiments are then undertaken that compare current approaches, where a full antigen structure and the whole repertoire of detectors are used, with the proposed approach. Experiment results indicate that such an approach is feasible and can help reduce the complexity of the problem by significant levels. It also improves the efficiency of the system, given that only a subset of detectors are involved during the detection process. Having several different sets of detectors increases the robustness of the resulting system. Detectors developed based on peptides are also highly discriminative, which reduces the false positives rates, making the approach feasible for a real time environment.
基金supported in part by the National Key Research and Development Program of China(2018YFB1702701)the National Natural Science Foundation of China(61773381,61773382)+1 种基金Dongguan’s Innovation Talents Project(Gang Xiong)Chinese Guangdong’s Science and Technology Project(2017B090912001)
文摘Based on ACP(artificial systems,computational experiments,and parallel execution)methodology,parallel control and management has become a popularly systematic and complete solution for the control and management of complex systems.This paper focuses on summarizing comprehensive review of the research literature of parallel control and management achieved in the recent years including the theoretical framework,core technologies,and the application demonstration.The future research,application directions,and suggestions are also discussed.
基金supported by the National Natural Science Foundation of China(Grant Nos,60133010 and 60372045)the Graduate Innovation Fund of Xidian University(Grant No.05004),
文摘This paper puts forward a novel artificial immune response algorithm for optimal approximation of linear systems. A quaternion model of artificial immune response is proposed for engineering computing. The model abstracts four elements, namely, antigen, antibody, reaction rules among antibodies, and driving algorithm describing how the rules are applied to antibodies, to simulate the process of immune response. Some reaction rules including clonal selection rules, immunological memory rules and immune regulation rules are introduced. Using the theorem of Markov chain, it is proofed that the new model is convergent. The experimental study on the optimal approximation of a stable linear system and an unstable one show that the approximate models searched by the new model have better performance indices than those obtained by some existing algorithms including the differential evolution algorithm and the multi-agent genetic algorithm.
基金Supported by The National Natural Science Foundation of China,No.81470875The Natural Science Foundation of Guangdong Province,China,No.2014A030312013+1 种基金The Science and Technology Planning Project of Guangdong Province,China,No.2014B020227002,No.2015B090903069,and No.2015B020229002The Science and Technology Program of Guangzhou,China,No.201604020002
文摘AIM To establish a simplified, reproducible D-galactosamineinduced cynomolgus monkey model of acute liver failure having an appropriate treatment window. METHODS Sixteen cynomolgus monkeys were randomly dividedinto four groups(A, B, C and D) after intracranial pressure(ICP) sensor implantation. D-galactosamine at 0.3, 0.25, 0.20 + 0.05(24 h interval), and 0.20 g/kg body weight, respectively, was injected via the small saphenous vein. Vital signs, ICP, biochemical indices, and inflammatory factors were recorded at 0, 12, 24, 36, 48, 72, 96, and 120 h after D-galactosamine administration. Progression of clinical manifestations, survival times, and results of H&E staining, TUNEL, and Masson staining were recorded. RESULTS Cynomolgus monkeys developed different degrees of debilitation, loss of appetite, and jaundice after D-galactosamine administration. Survival times of groups A, B, and C were 56 ± 8.7 h, 95 ± 5.5 h, and 99 ± 2.2 h, respectively, and in group D all monkeys survived the 144-h observation period except for one, which died at 136 h. Blood levels of ALT, AST, CK, LDH, TBi L, Cr, BUN, and ammonia, prothrombin time, ICP, endotoxin, and inflammatory markers [(tumor necrosis factor(TNF)-α, interleukin(IL)-1β, and IL-6)] significantly increased compared with baseline values in different groups(P < 0.05). Pathological results showed obvious liver cell necrosis that was positively correlated with the dose of D-galactosamine.CONCLUSION We successfully established a simplified, reproducible D-galactosamine-induced cynomolgus monkey model of acute liver failure, and the single or divided dosage of 0.25 g/kg is optimal for creating this model.
文摘Clinically,it is highly challenging to promote recovery in patients with acute liver failure(ALF)and acute-on-chronic liver failure(ACLF).Despite recent advances in understanding the underlying mechanisms of ALF and ACLF,standard medical therapy remains the primary therapeutic approach.Liver transplantation(LT)is considered the last option,and in several cases,it is the only intervention that can be lifesaving.Unfortunately,this intervention is limited by organ donation shortage or exclusion criteria such that not all patients in need can receive a transplant.Another option is to restore impaired liver function with artificial extracorporeal blood purification systems.The first such systems were developed at the end of the 20th century,providing solutions as bridging therapy,either for liver recovery or LT.They enhance the elimination of metabolites and substances that accumulate due to compromised liver function.In addition,they aid in clearance of molecules released during acute liver decompensation,which can initiate an excessive inflammatory response in these patients causing hepatic encephalopathy,multiple-organ failure,and other complications of liver failure.As compared to renal replacement therapies,we have been unsuccessful in using artificial extracorporeal blood purification systems to completely replace liver function despite the outstanding technological evolution of these systems.Extracting middle to high-molecular-weight and hydrophobic/protein-bound molecules remains extremely challenging.The majority of the currently available systems include a combination of methods that cleanse different ranges and types of molecules and toxins.Furthermore,conventional methods such as plasma exchange are being re-evaluated,and novel adsorption filters are increasingly being used for liver indications.These strategies are very promising for the treatment of liver failure.Nevertheless,the best method,system,or device has not been developed yet,and its probability of getting developed in the near future is also low.Furthermore,little is known about the effects of liver support systems on the overall and transplant-free survival of these patients,and further investigation using randomized controlled trials and meta-analyses is needed.This review presents the most popular extracorporeal blood purification techniques for liver replacement therapy.It focuses on general principles of their function,and on evidence regarding their effectiveness in detoxification and in supporting patients with ALF and ACLF.In addition,we have outlined the basic advantages and disadvantages of each system.
基金Supported by the Major State Basic Research Development Program (973 Program) of China (No. 2009CB723905)the National High Technology Research and Development Program (863 Program) of China (Nos.2009AA12Z114, 2007AA12Z148, 2007AA12Z181)+2 种基金the National Natural Sci-ence Foundation of China(Nos. 40771139,40523005, 40721001)the Research Fund for the Doctoral Program of Higher Education of China(No.200804861058)the Foundation of National Laboratory of Pattern Recognition
文摘Clonal selection feature selection algorithm （CSFS） based on clonal selection algorithm （CSA）, a new computational intelligence approach, has been proposed to perform the task of dimensionality reduction in high-dimensional images, and has better performance than traditional feature selection algorithms with more computational costs. In this paper, a fast clonal selection feature selection algorithm （FCSFS） for hyperspectral imagery is proposed to improve the convergence rate by using Cauchy mutation instead of non-uniform mutation as the primary immune operator. Two experiments are performed to evaluate the performance of the proposed algorithm in comparison with CSFS using hyperspectral remote sensing imagery acquired by the pushbroom hyperspectral imager （PHI） and the airborne visible/infrared imaging spectrometer （AVlRIS）, respectively. Experimental results demonstrate that the FCSFS converges faster than CSFS, hence providing an effective new option for dimensionality reduction of hyperspectral remote sensing imagery.
文摘An artificial immunity based multimodal evolution algorithm is developed to generate detectors with variable coverage for multidimensional intrusion detection. In this algorithm, a proper fitness function is used to drive the detectors to fill in those detection holes close to self set or among self spheres, and genetic algorithm is adopted to reduce the negative effects that different distribution of self imposes on the detector generating process. The validity of the algorithm is tested with spherical and rectangular detectors, respectively, and experiments performed on two real data sets （machine learning database and DAPRA99） indicate that the proposed algorithm can obtain good results on spherical detectors, and that its performances in detection rate, false alarm rate, stabih＇ty, time cost, and adaptability to incomplete training set on spherical detectors are all better than on rectangular ones.
基金National Natural Science Foundation of China,Grant/Award Numbers:52002246,52192614,U22A2077,U20A20166,52125205,52372154Natural Science Foundation of Beijing Municipality,Grant/Award Numbers:2222088,Z180011+4 种基金Shenzhen Fundamental Research Project,Grant/Award Number:JCYJ20190808170601664Shenzhen Science and Technology Program,Grant/Award Number:KQTD20170810105439418Science and Technology Innovation Project of Shenzhen Excellent Talents,Grant/Award Number:RCBS20200714114919006National Key R&D Program of China,Grant/Award Numbers:2021YFB3200304,2021YFB3200302Fundamental Research Funds for the Central Universities。
文摘The emulation of human multisensory functions to construct artificial perception systems is an intriguing challenge for developing humanoid robotics and cross-modal human–machine interfaces.Inspired by human multisensory signal generation and neuroplasticity-based signal processing,here,an artificial perceptual neuro array with visual-tactile sensing,processing,learning,and memory is demonstrated.The neuromorphic bimodal perception array compactly combines an artificial photoelectric synapse network and an integrated mechanoluminescent layer,endowing individual and synergistic plastic modulation of optical and mechanical information,including short-term memory,long-term memory,paired pulse facilitation,and“learning-experience”behavior.Sequential or superimposed visual and tactile stimuli inputs can efficiently simulate the associative learning process of“Pavlov's dog”.The fusion of visual and tactile modulation enables enhanced memory of the stimulation image during the learning process.A machine-learning algorithm is coupled with an artificial neural network for pattern recognition,achieving a recognition accuracy of 70%for bimodal training,which is higher than that obtained by unimodal training.In addition,the artificial perceptual neuron has a low energy consumption of~20 pJ.With its mechanical compliance and simple architecture,the neuromorphic bimodal perception array has promising applications in largescale cross-modal interactions and high-throughput intelligent perceptions.
文摘Human consciousness is the most interesting and mysterious phenomenon inthe world. In this paper, the results of the computational study and simulationof the conscious behaviour, such as the learning of 1anguage and image pat-terns, traditional conditioning, association, imagination and dream, have beenpresented. Based on these results, an experimental conscious system - CON-SCITRON, has been developed. Further discussion on development of artificialconscious systems is also provided.
文摘The search for patterns or motifs in data represents a problem area of key interest to finance and economic researchers. In this paper, we introduce the motif tracking algorithm （MTA）, a novel immune inspired （IS） pattern identification tool that is able to identify unknown motifs of a non specified length which repeat within time series data. The power of the algorithm comes from the fact that it uses a small number of parameters with minimal assumptions regarding the data being examined or the underlying motifs. Our interest lies in applying the algorithm to financial time series data to identify unknown patterns that exist. The algorithm is tested using three separate data sets. Particular suitability to financial data is shown by applying it to oil price data. In all cases, the algorithm identifies the presence of a motif population in a fast and efficient manner due to the utilization of an intuitive symbolic representation. The resulting population of motifs is shown to have considerable potential value for other applications such as forecasting and algorithm seeding.
文摘Oppositional Defiant Disorder(ODD)and Attention Deficit/Hyperactivity Disorder(ADHD)are mental health conditions that have traditionally been managed through behavioral therapies and medication.However,the integration of Artificial Intelligence(AI)has brought about a revolutionary shift in treatment approaches.This article explores the role of AI-driven noninvasive treatments for ODD and ADHD.AI offers personalized treatment plans,predictive analytics,virtual therapeutic platforms,and continuous monitoring,enhancing the effectiveness and accessibility of interventions.Ethical considerations and the need for a balanced approach are discussed.As technology evolves,collaborative efforts between mental health professionals and technologists will shape the future of mental health care for individuals with ODD and ADHD.
