Artificial intelligence in general and software agents in particular are recognized as computer science disciplines that aim to model or simulate so-called intelligent human behaviors such as perception, decision-maki...Artificial intelligence in general and software agents in particular are recognized as computer science disciplines that aim to model or simulate so-called intelligent human behaviors such as perception, decision-making, understanding, learning, etc. This work presents an approach to designing a generic Intelligent Agent that can be used in a multi-agent system to solve a complex problem. The generic agent that is proposed can be instantiated as a concrete agent, which is enabled with learning and autonomy capabilities by using Artificial Neural Networks. To highlight the generic aspect, the proposition is instantiated to be used in agriculture, health and education. The instantiated software agent applied in agriculture can process images in real time and detect defect on plants’ leaf. In the health field, the agent process image to diagnose breast cancer. When applied in Education, the agent can load an image of a student’s script and grade it. The performance of the designed agent system has the same accuracy as that of the respective neural networks used to instantiate them. In the educational field, the software agent has an accuracy of 98.9% and in the health field, it has an accuracy of 99.56% while in the agricultural field, it has an accuracy of 97.2%.展开更多
Early detection of pancreatic cancer has long eluded clinicians because of its insidious nature and onset.Often metastatic or locally invasive when symptomatic,most patients are deemed inoperable.In those who are symp...Early detection of pancreatic cancer has long eluded clinicians because of its insidious nature and onset.Often metastatic or locally invasive when symptomatic,most patients are deemed inoperable.In those who are symptomatic,multi-modal imaging modalities evaluate and confirm pancreatic ductal adenocarcinoma.In asymptomatic patients,detected pancreatic lesions can be either solid or cystic.The clinical implications of identifying small asymptomatic solid pancreatic lesions(SPLs)of<2 cm are tantamount to a better outcome.The accurate detection of SPLs undoubtedly promotes higher life expectancy when resected early,driving the development of existing imaging tools while promoting more comprehensive screening programs.An imaging tool that has matured in its reiterations and received many image-enhancing adjuncts is endoscopic ultrasound(EUS).It carries significant importance when risk stratifying cystic lesions and has substantial diagnostic value when combined with fine needle aspiration/biopsy(FNA/FNB).Adjuncts to EUS imaging include contrast-enhanced harmonic EUS and EUS-elastography,both having improved the specificity of FNA and FNB.This review intends to compile all existing enhancement modalities and explore ongoing research around the most promising of all adjuncts in the field of EUS imaging,artificial intelligence.展开更多
Clinical applications of Artificial Intelligence(AI)for mental health care have experienced a meteoric rise in the past few years.AIenabled chatbot software and applications have been administering significant medical...Clinical applications of Artificial Intelligence(AI)for mental health care have experienced a meteoric rise in the past few years.AIenabled chatbot software and applications have been administering significant medical treatments that were previously only available from experienced and competent healthcare professionals.Such initiatives,which range from“virtual psychiatrists”to“social robots”in mental health,strive to improve nursing performance and cost management,as well as meeting the mental health needs of vulnerable and underserved populations.Nevertheless,there is still a substantial gap between recent progress in AI mental health and the widespread use of these solutions by healthcare practitioners in clinical settings.Furthermore,treatments are frequently developed without clear ethical concerns.While AI-enabled solutions show promise in the realm of mental health,further research is needed to address the ethical and social aspects of these technologies,as well as to establish efficient research and medical practices in this innovative sector.Moreover,the current relevant literature still lacks a formal and objective review that specifically focuses on research questions from both developers and psychiatrists in AI-enabled chatbotpsychologists development.Taking into account all the problems outlined in this study,we conducted a systematic review of AI-enabled chatbots in mental healthcare that could cover some issues concerning psychotherapy and artificial intelligence.In this systematic review,we put five research questions related to technologies in chatbot development,psychological disorders that can be treated by using chatbots,types of therapies that are enabled in chatbots,machine learning models and techniques in chatbot psychologists,as well as ethical challenges.展开更多
Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual agents.However,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experi...Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual agents.However,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experiences that hinder convergence,resulting in ineffective training performance for multi‐agent systems.To tackle this issue,a novel reinforcement learning scheme,Mutual Information Oriented Deep Skill Chaining(MioDSC),is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration efficiency.These rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment state.In addition,MioDSC can generate cooperative policies using the options framework,allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi‐agent learning.MioDSC was evaluated in the multi‐agent particle environment and the StarCraft multi‐agent challenge at varying difficulty levels.The experimental results demonstrate that MioDSC outperforms state‐of‐the‐art methods and is robust across various multi‐agent system tasks with high stability.展开更多
文摘Artificial intelligence in general and software agents in particular are recognized as computer science disciplines that aim to model or simulate so-called intelligent human behaviors such as perception, decision-making, understanding, learning, etc. This work presents an approach to designing a generic Intelligent Agent that can be used in a multi-agent system to solve a complex problem. The generic agent that is proposed can be instantiated as a concrete agent, which is enabled with learning and autonomy capabilities by using Artificial Neural Networks. To highlight the generic aspect, the proposition is instantiated to be used in agriculture, health and education. The instantiated software agent applied in agriculture can process images in real time and detect defect on plants’ leaf. In the health field, the agent process image to diagnose breast cancer. When applied in Education, the agent can load an image of a student’s script and grade it. The performance of the designed agent system has the same accuracy as that of the respective neural networks used to instantiate them. In the educational field, the software agent has an accuracy of 98.9% and in the health field, it has an accuracy of 99.56% while in the agricultural field, it has an accuracy of 97.2%.
文摘Early detection of pancreatic cancer has long eluded clinicians because of its insidious nature and onset.Often metastatic or locally invasive when symptomatic,most patients are deemed inoperable.In those who are symptomatic,multi-modal imaging modalities evaluate and confirm pancreatic ductal adenocarcinoma.In asymptomatic patients,detected pancreatic lesions can be either solid or cystic.The clinical implications of identifying small asymptomatic solid pancreatic lesions(SPLs)of<2 cm are tantamount to a better outcome.The accurate detection of SPLs undoubtedly promotes higher life expectancy when resected early,driving the development of existing imaging tools while promoting more comprehensive screening programs.An imaging tool that has matured in its reiterations and received many image-enhancing adjuncts is endoscopic ultrasound(EUS).It carries significant importance when risk stratifying cystic lesions and has substantial diagnostic value when combined with fine needle aspiration/biopsy(FNA/FNB).Adjuncts to EUS imaging include contrast-enhanced harmonic EUS and EUS-elastography,both having improved the specificity of FNA and FNB.This review intends to compile all existing enhancement modalities and explore ongoing research around the most promising of all adjuncts in the field of EUS imaging,artificial intelligence.
基金This work was supported by the grant“Development of an intellectual system prototype for online-psychological support that can diagnose and improve youth’s psychoemotional state”funded by the Ministry of Education of the Republic of Kazakhstan.Grant No.IRN AP09259140.
文摘Clinical applications of Artificial Intelligence(AI)for mental health care have experienced a meteoric rise in the past few years.AIenabled chatbot software and applications have been administering significant medical treatments that were previously only available from experienced and competent healthcare professionals.Such initiatives,which range from“virtual psychiatrists”to“social robots”in mental health,strive to improve nursing performance and cost management,as well as meeting the mental health needs of vulnerable and underserved populations.Nevertheless,there is still a substantial gap between recent progress in AI mental health and the widespread use of these solutions by healthcare practitioners in clinical settings.Furthermore,treatments are frequently developed without clear ethical concerns.While AI-enabled solutions show promise in the realm of mental health,further research is needed to address the ethical and social aspects of these technologies,as well as to establish efficient research and medical practices in this innovative sector.Moreover,the current relevant literature still lacks a formal and objective review that specifically focuses on research questions from both developers and psychiatrists in AI-enabled chatbotpsychologists development.Taking into account all the problems outlined in this study,we conducted a systematic review of AI-enabled chatbots in mental healthcare that could cover some issues concerning psychotherapy and artificial intelligence.In this systematic review,we put five research questions related to technologies in chatbot development,psychological disorders that can be treated by using chatbots,types of therapies that are enabled in chatbots,machine learning models and techniques in chatbot psychologists,as well as ethical challenges.
基金National Natural Science Foundation of China,Grant/Award Number:61872171The Belt and Road Special Foundation of the State Key Laboratory of Hydrology‐Water Resources and Hydraulic Engineering,Grant/Award Number:2021490811。
文摘Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual agents.However,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experiences that hinder convergence,resulting in ineffective training performance for multi‐agent systems.To tackle this issue,a novel reinforcement learning scheme,Mutual Information Oriented Deep Skill Chaining(MioDSC),is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration efficiency.These rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment state.In addition,MioDSC can generate cooperative policies using the options framework,allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi‐agent learning.MioDSC was evaluated in the multi‐agent particle environment and the StarCraft multi‐agent challenge at varying difficulty levels.The experimental results demonstrate that MioDSC outperforms state‐of‐the‐art methods and is robust across various multi‐agent system tasks with high stability.
