Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00015
C. Leung, Longjun Hao
Bernoulli bandits have found to mirror many practical situations in the context of reinforcement learning, and the aim is to maximize rewards through playing the machine over a set time frame. In an actual casino setting, it is often unrealistic to fix the time when playing stops, as the termination of play may be random and dependent on the outcomes of earlier lever pulls, which in turn affects the inclination of the gambler to continue playing. It is often assumed that exploration is repeated each time the game is played, and that the game tend to go on indefinitely. In practical situations, if the casino does not change their machines often, exploration need not be carried out repeatedly as this would be inefficient. Moreover, from the gamblers' point of view, they would likely to stop at some point or when certain conditions are fulfilled. Here, the bandit problem is studied in terms of stopping rules which are dependent on earlier random outcomes and on the behavior of the players. Rewards incorporating the cost of play and the size of payouts are then calculated on the conclusion of a playing episode. Here, the rewards for Bernoulli machines are placed within the context of martingales that are commonly used in gambling situations, and the fairness of the game is expressed through the parameters of the bandit machines which can be manifested as various forms of martingales. The average rewards and regrets as well as episode durations are obtained under different martingale stopping times. Exploration costs and regrets for different bandit machines are analyzed. Experimentation has also been undertaken which corroborate the theoretical results.
{"title":"Analysis of Rewards in Bernoulli Bandits Using Martingales","authors":"C. Leung, Longjun Hao","doi":"10.1109/AIKE48582.2020.00015","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00015","url":null,"abstract":"Bernoulli bandits have found to mirror many practical situations in the context of reinforcement learning, and the aim is to maximize rewards through playing the machine over a set time frame. In an actual casino setting, it is often unrealistic to fix the time when playing stops, as the termination of play may be random and dependent on the outcomes of earlier lever pulls, which in turn affects the inclination of the gambler to continue playing. It is often assumed that exploration is repeated each time the game is played, and that the game tend to go on indefinitely. In practical situations, if the casino does not change their machines often, exploration need not be carried out repeatedly as this would be inefficient. Moreover, from the gamblers' point of view, they would likely to stop at some point or when certain conditions are fulfilled. Here, the bandit problem is studied in terms of stopping rules which are dependent on earlier random outcomes and on the behavior of the players. Rewards incorporating the cost of play and the size of payouts are then calculated on the conclusion of a playing episode. Here, the rewards for Bernoulli machines are placed within the context of martingales that are commonly used in gambling situations, and the fairness of the game is expressed through the parameters of the bandit machines which can be manifested as various forms of martingales. The average rewards and regrets as well as episode durations are obtained under different martingale stopping times. Exploration costs and regrets for different bandit machines are analyzed. Experimentation has also been undertaken which corroborate the theoretical results.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134309187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Event logs contain abundant information, such as activity names, time stamps, activity executors, etc. However, much of existing trace clustering research has been focused on applying activity names to assist process scenarios discovery. In addition, many existing trace clustering algorithms commonly used in the literature, such as k-means clustering approach, require prior knowledge about the number of process scenarios existed in the log, which sometimes are not known aprior. This paper presents a two-phase approach that obtains timing information from event logs and uses the information to assist process scenario discoveries without requiring any prior knowledge about process scenarios. We use five real-life event logs to compare the performance of the proposed two-phase approach for process scenario discoveries with the commonly used k-means clustering approach in terms of model’s harmonic mean of the weighted average fitness and precision, i.e., the F1 score. The experiment data shows that (1) the process scenario models obtained with the additional timing information have both higher fitness and precision scores than the models obtained without the timing information; (2) the two-phase approach not only removes the need for prior information related to k, but also results in a comparable F1 score compared to the optimal k-means approach with the optimal k obtained through exhaustive search.
{"title":"Using Event Log Timing Information to Assist Process Scenario Discoveries","authors":"Zhenyu Zhang, Chunhui Guo, Wenyu Peng, Shangping Ren","doi":"10.1109/AIKE48582.2020.00017","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00017","url":null,"abstract":"Event logs contain abundant information, such as activity names, time stamps, activity executors, etc. However, much of existing trace clustering research has been focused on applying activity names to assist process scenarios discovery. In addition, many existing trace clustering algorithms commonly used in the literature, such as k-means clustering approach, require prior knowledge about the number of process scenarios existed in the log, which sometimes are not known aprior. This paper presents a two-phase approach that obtains timing information from event logs and uses the information to assist process scenario discoveries without requiring any prior knowledge about process scenarios. We use five real-life event logs to compare the performance of the proposed two-phase approach for process scenario discoveries with the commonly used k-means clustering approach in terms of model’s harmonic mean of the weighted average fitness and precision, i.e., the F1 score. The experiment data shows that (1) the process scenario models obtained with the additional timing information have both higher fitness and precision scores than the models obtained without the timing information; (2) the two-phase approach not only removes the need for prior information related to k, but also results in a comparable F1 score compared to the optimal k-means approach with the optimal k obtained through exhaustive search.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133415354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00042
Anas Al-Tirawi, R. Reynolds
In Computation intelligence algorithm performance is crucial especially when the complexity of the system increases and becomes chaotic (un-predictable). In Cultural Systems many algorithms are able to predict the system performance as the complexity is linear, or non-linear. However, when it is chaotic the prediction quality decreases dramatically. In this paper, we are show that Common Value Auctions are able to distribute sufficient information through the system in order to sustain the prediction rate even on the edge of chaos. This sustainability is expressed here in terms of increased resilience and robustness. Systems that rely on wisdom of the crowd based approaches are shown not to do as well when environmental change goes from linear to non-linear, and finally to chaotic.
{"title":"Using Cultural Algorithms with Common Value Auctions to Provide Sustainability in Complex Dynamic Environments","authors":"Anas Al-Tirawi, R. Reynolds","doi":"10.1109/AIKE48582.2020.00042","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00042","url":null,"abstract":"In Computation intelligence algorithm performance is crucial especially when the complexity of the system increases and becomes chaotic (un-predictable). In Cultural Systems many algorithms are able to predict the system performance as the complexity is linear, or non-linear. However, when it is chaotic the prediction quality decreases dramatically. In this paper, we are show that Common Value Auctions are able to distribute sufficient information through the system in order to sustain the prediction rate even on the edge of chaos. This sustainability is expressed here in terms of increased resilience and robustness. Systems that rely on wisdom of the crowd based approaches are shown not to do as well when environmental change goes from linear to non-linear, and finally to chaotic.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114774588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00041
Ying Fung Yiu, R. Mahapatra
Multiagent pathfinding (MAPF) problem is an important topic to various domains including video games, robotics, logistics, and crowd simulation. The goal of a pathfinding algorithm for MAPF is to find the shortest possible path for each agent without collisions with other agents. Search is among the most fundamental techniques for problem solving, and A* is the best known heuristic search algorithm. While A* guarantees to find the shortest path using a heuristic function, it cannot handle the large scale and many uncertainties in MAPF. The main challenge of MAPF is the scalability. The problem complexity grows exponentially as both the size of environments and the number of autonomous agents increase, which becomes more difficult for A* to compute results in real time under the constraints of memory and computing resources. To overcome the challenges in MAPF, distributed approaches are introduced to reduce the computational time and complexity. Contrast to centralized approaches, which use a single controller to determine every move of all agents, distributed approaches allow each agent to search for its own solution. Distributed MAPF algorithms need to refine solutions for all agents that are collision-free. The algorithm should lead agents to take another path, or standby on the same node at the moment, to avoid conflicts between any two paths. Under the circumstances, an optimal solution is no longer simply finding the shortest path for each agent. Instead, it should contain a collision-free path for every agent, with the lowest makespan, which is the number of time steps required for all agents to reach their target. However, minimizing the makespan and the sum of cost for all agents is a NP-hard problem. Given MAPF problems often require to be solved in real time with limited resources, minimizing only the makespan is a more practical approach.To achieve accurate search and high scalability, a MAPF algorithm must fulfill the following requirements: 1) it is capable to compute collision-free paths for all agents; 2) it can provides an accurate priority decision mechanism to ensure solution optimality; and 3) it should maintain the successful rate to obtain a solution as the number of agents increases. In this paper, we proposed a novel hierarchical pathfinding technique named Multi-Agent Hierarchical Evolutionary Heuristics A* (MA-HEHA*). Our contributions in this paper are: 1) we propose MA-HEHA* that can identify bottleneck areas to reduce collisions in abstract search; 2) our algorithm evolves heuristic functions by itself to avoid potential conflicts during local search; 3) we prove that MA-HEHA* maintain high successful rate when the scalability is high; 4) we evaluate MA-HEHA* on different types of MAPF problems to show its effectiveness. Our experiment results show that ourMA-HEHA* can efficiently solve large scale MAPF problems compared to traditional MAPF approaches.
{"title":"Multi-Agent Pathfinding with Hierarchical Evolutionary Hueristic A*","authors":"Ying Fung Yiu, R. Mahapatra","doi":"10.1109/AIKE48582.2020.00041","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00041","url":null,"abstract":"Multiagent pathfinding (MAPF) problem is an important topic to various domains including video games, robotics, logistics, and crowd simulation. The goal of a pathfinding algorithm for MAPF is to find the shortest possible path for each agent without collisions with other agents. Search is among the most fundamental techniques for problem solving, and A* is the best known heuristic search algorithm. While A* guarantees to find the shortest path using a heuristic function, it cannot handle the large scale and many uncertainties in MAPF. The main challenge of MAPF is the scalability. The problem complexity grows exponentially as both the size of environments and the number of autonomous agents increase, which becomes more difficult for A* to compute results in real time under the constraints of memory and computing resources. To overcome the challenges in MAPF, distributed approaches are introduced to reduce the computational time and complexity. Contrast to centralized approaches, which use a single controller to determine every move of all agents, distributed approaches allow each agent to search for its own solution. Distributed MAPF algorithms need to refine solutions for all agents that are collision-free. The algorithm should lead agents to take another path, or standby on the same node at the moment, to avoid conflicts between any two paths. Under the circumstances, an optimal solution is no longer simply finding the shortest path for each agent. Instead, it should contain a collision-free path for every agent, with the lowest makespan, which is the number of time steps required for all agents to reach their target. However, minimizing the makespan and the sum of cost for all agents is a NP-hard problem. Given MAPF problems often require to be solved in real time with limited resources, minimizing only the makespan is a more practical approach.To achieve accurate search and high scalability, a MAPF algorithm must fulfill the following requirements: 1) it is capable to compute collision-free paths for all agents; 2) it can provides an accurate priority decision mechanism to ensure solution optimality; and 3) it should maintain the successful rate to obtain a solution as the number of agents increases. In this paper, we proposed a novel hierarchical pathfinding technique named Multi-Agent Hierarchical Evolutionary Heuristics A* (MA-HEHA*). Our contributions in this paper are: 1) we propose MA-HEHA* that can identify bottleneck areas to reduce collisions in abstract search; 2) our algorithm evolves heuristic functions by itself to avoid potential conflicts during local search; 3) we prove that MA-HEHA* maintain high successful rate when the scalability is high; 4) we evaluate MA-HEHA* on different types of MAPF problems to show its effectiveness. Our experiment results show that ourMA-HEHA* can efficiently solve large scale MAPF problems compared to traditional MAPF approaches.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125454527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00045
H. Nieto-Chaupis
In this paper the action to deliver nanoparticles in prospective Nanomedicine is computationally simulated. For this end, the usage of quantum mechanics has as end to describe the different paths that nanoparticles travel from a generator to a concrete target. The presence of ions might be against the purpose of the technique of Drug Delivery Targeted by which assumes that not any noise might coexist together to the nanoparticles. This paper presents simulations by which the Brownian dynamics would alter the nanoparticles paths. From the results one finds that depending on the energy interactions it would be a cause for errors and deviation of nanoparticles along their path to the desired target.
{"title":"Computational Simulation of Artificial Nanoparticles Paths","authors":"H. Nieto-Chaupis","doi":"10.1109/AIKE48582.2020.00045","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00045","url":null,"abstract":"In this paper the action to deliver nanoparticles in prospective Nanomedicine is computationally simulated. For this end, the usage of quantum mechanics has as end to describe the different paths that nanoparticles travel from a generator to a concrete target. The presence of ions might be against the purpose of the technique of Drug Delivery Targeted by which assumes that not any noise might coexist together to the nanoparticles. This paper presents simulations by which the Brownian dynamics would alter the nanoparticles paths. From the results one finds that depending on the energy interactions it would be a cause for errors and deviation of nanoparticles along their path to the desired target.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130614944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00044
H. Nieto-Chaupis
In this paper a nonlinear mathematical model based at convolution theory and translated in terms of Machine Learning philosophy is presented. In essence, peaks functions are assumed as the pattern of rate of infections at large cities. In this manner, once the free parameters of theses patterns are identified then one proceeds to engage to the well-known Mitchell’s criteria in order to construct the algorithm that would yield the best estimates as to carry out social intervention as well as to predict dates about the main characteristics of infection’s distributions. The distributions are modeled by the Dirac-Delta function whose spike property is used to make the numerical convolutions. In this manner the parameters of Dirac-Delta function’s argument are interpreted as the model parameters that determine the dates of social regulation such as quarantine as well as the possible date of end of first wave and potential periods of the beginning of a second one. The theoretical and computational approach is illustrated with a case of outbreak depending on free parameters simulating the implementation of new rules to detain the infections.
{"title":"Convolution-based Machine Learning To Attenuate Covid-19’s Infections in Large Cities","authors":"H. Nieto-Chaupis","doi":"10.1109/AIKE48582.2020.00044","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00044","url":null,"abstract":"In this paper a nonlinear mathematical model based at convolution theory and translated in terms of Machine Learning philosophy is presented. In essence, peaks functions are assumed as the pattern of rate of infections at large cities. In this manner, once the free parameters of theses patterns are identified then one proceeds to engage to the well-known Mitchell’s criteria in order to construct the algorithm that would yield the best estimates as to carry out social intervention as well as to predict dates about the main characteristics of infection’s distributions. The distributions are modeled by the Dirac-Delta function whose spike property is used to make the numerical convolutions. In this manner the parameters of Dirac-Delta function’s argument are interpreted as the model parameters that determine the dates of social regulation such as quarantine as well as the possible date of end of first wave and potential periods of the beginning of a second one. The theoretical and computational approach is illustrated with a case of outbreak depending on free parameters simulating the implementation of new rules to detain the infections.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116911836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00043
Ying Fung Yiu, R. Mahapatra
A* is an informed pathfinding algorithm that depends on an accurate heuristic function to search for the shortest path. A complex pathfinding problem requires a well-informed heuristic function to efficiently process all data and compute the next move. Hence, designing good heuristic functions for specific domains becomes the primary research focus on pathfinding algorithms optimization. However, designing new heuristic functions is time consuming and difficult. Evolutionary Heuristic A* (EHA*) search proposed to have a self-evolving heuristic function to reduce the engineering efforts on heuristic functions design. The Genetic Algorithm is one of the most popular and efficient optimization techniques that is based on the Darwinian principle of survival of the fittest. It has been successfully applied on many complex real world applications including VLSI circuit partitioning, Travelling Salesman Problem (TSP), and robotic designs. Although the Genetic Algorithm is proved to be efficient on solving complex problems, the amount of computations and iterations required for this method is enormous. Therefore, we propose a hardware accelerator architecture for EHA* that is implemented on a Field Programmable Gate Array(FPGA) by employing a combination of pipelining and parallelization to achieve better performance. Moreover, the proposed Genetic Algorithm accelerator can be customized in terms of the population size, number of generations, crossover rates, and mutation rates for flexibility. The FPGA accelerator proposed in this paper achieves more than 8x speed up compared to the software implementation.
{"title":"Heuristic Function Evolution For Pathfinding Algorithm in FPGA Accelerator","authors":"Ying Fung Yiu, R. Mahapatra","doi":"10.1109/AIKE48582.2020.00043","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00043","url":null,"abstract":"A* is an informed pathfinding algorithm that depends on an accurate heuristic function to search for the shortest path. A complex pathfinding problem requires a well-informed heuristic function to efficiently process all data and compute the next move. Hence, designing good heuristic functions for specific domains becomes the primary research focus on pathfinding algorithms optimization. However, designing new heuristic functions is time consuming and difficult. Evolutionary Heuristic A* (EHA*) search proposed to have a self-evolving heuristic function to reduce the engineering efforts on heuristic functions design. The Genetic Algorithm is one of the most popular and efficient optimization techniques that is based on the Darwinian principle of survival of the fittest. It has been successfully applied on many complex real world applications including VLSI circuit partitioning, Travelling Salesman Problem (TSP), and robotic designs. Although the Genetic Algorithm is proved to be efficient on solving complex problems, the amount of computations and iterations required for this method is enormous. Therefore, we propose a hardware accelerator architecture for EHA* that is implemented on a Field Programmable Gate Array(FPGA) by employing a combination of pipelining and parallelization to achieve better performance. Moreover, the proposed Genetic Algorithm accelerator can be customized in terms of the population size, number of generations, crossover rates, and mutation rates for flexibility. The FPGA accelerator proposed in this paper achieves more than 8x speed up compared to the software implementation.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126210985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00013
Wasif Bokhari, A. Bansal
In binary classification applications, such as medical disease diagnosis, the cost of one type of error could greatly outweigh the other enabling the need of asymmetric error control. Due to this unique nature of the problem, where one error greatly outweighs the other, traditional machine learning techniques, even with much improved accuracy, may not be ideal as they do not provide a way to control the false negatives below a certain threshold. To address this need, a classification algorithm that can control the false negatives to a certain threshold is proposed. The theoretical foundation for this algorithm is based on Neyman-Pearson (NP) Lemma, which is used to construct a novel tree-based classifier that enables asymmetric error control. This classifier is evaluated on the data obtained from the Framingham heart study and it predicts the risk of a ten-year cardiac disease, not only with improved accuracy and F1 score but also with full control over the number of false negatives. With an improved accuracy in predicting cardiac disease, this tree-based classifier with asymmetric error control can reduce the burden of cardiac disease in populations and potentially save a lot of human lives. The methodology used to construct this classifier can be expanded to many more use cases in medical disease diagnosis.
{"title":"Asymmetric Error Control for Binary Classification in Medical Disease Diagnosis","authors":"Wasif Bokhari, A. Bansal","doi":"10.1109/AIKE48582.2020.00013","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00013","url":null,"abstract":"In binary classification applications, such as medical disease diagnosis, the cost of one type of error could greatly outweigh the other enabling the need of asymmetric error control. Due to this unique nature of the problem, where one error greatly outweighs the other, traditional machine learning techniques, even with much improved accuracy, may not be ideal as they do not provide a way to control the false negatives below a certain threshold. To address this need, a classification algorithm that can control the false negatives to a certain threshold is proposed. The theoretical foundation for this algorithm is based on Neyman-Pearson (NP) Lemma, which is used to construct a novel tree-based classifier that enables asymmetric error control. This classifier is evaluated on the data obtained from the Framingham heart study and it predicts the risk of a ten-year cardiac disease, not only with improved accuracy and F1 score but also with full control over the number of false negatives. With an improved accuracy in predicting cardiac disease, this tree-based classifier with asymmetric error control can reduce the burden of cardiac disease in populations and potentially save a lot of human lives. The methodology used to construct this classifier can be expanded to many more use cases in medical disease diagnosis.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131922268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00038
Nahed Abdelgaber, C. Nikolopoulos
This paper will review the basic building blocks of quantum computing and discuss the main applications in artificial intelligence that can be addressed more efficiently using the quantum computers of today. Artificial intelligence and quantum computing have many features in common. Quantum computing can provide artificial intelligence and machine learning algorithms with speed of training and computational power in less price. Artificial intelligence on the other hand can provide quantum computers with the necessary error correction algorithms. Some of the algorithms in AI that have been successfully implemented on a quantum computer, that we will present in this paper, are both unsupervised learning algorithms (clustering and Principal component analysis) and also supervised learning classification, such as support vector machines.
{"title":"Overview on Quantum Computing and its Applications in Artificial Intelligence","authors":"Nahed Abdelgaber, C. Nikolopoulos","doi":"10.1109/AIKE48582.2020.00038","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00038","url":null,"abstract":"This paper will review the basic building blocks of quantum computing and discuss the main applications in artificial intelligence that can be addressed more efficiently using the quantum computers of today. Artificial intelligence and quantum computing have many features in common. Quantum computing can provide artificial intelligence and machine learning algorithms with speed of training and computational power in less price. Artificial intelligence on the other hand can provide quantum computers with the necessary error correction algorithms. Some of the algorithms in AI that have been successfully implemented on a quantum computer, that we will present in this paper, are both unsupervised learning algorithms (clustering and Principal component analysis) and also supervised learning classification, such as support vector machines.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124414417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/AIKE48582.2020.00020
Mirjam Minor, Miriam Herold
Analogical knowledge considers functional properties of objects in contrast to literal similarity which compares the degree of featural overlap. A classical example from Gentner’s structure mapping theory is "An electric battery is like a reservoir" [1]. Acquiring analogical knowledge in a computational approach is a challenging task. In this paper, we present a solution that combines learning with knowledge engineering. The proposed knowledge discovery approach uses word embeddings to learn analogy on workflow tasks. The resulting knowledge is integrated with an ontology for the purpose of workflow transfer across application domains. A case study is conducted on the two example domains ’passenger and baggage handling at the airport’ and ’SAP warehouse management’. The experimental results on comparing the computational analogy with a golden standard from a knowledge engineering expert are quite promising and provide a proof-of-concept for the feasibility of the approach.
{"title":"Discovery of Analogical Knowledge for the Transfer of Workflow Tasks","authors":"Mirjam Minor, Miriam Herold","doi":"10.1109/AIKE48582.2020.00020","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00020","url":null,"abstract":"Analogical knowledge considers functional properties of objects in contrast to literal similarity which compares the degree of featural overlap. A classical example from Gentner’s structure mapping theory is \"An electric battery is like a reservoir\" [1]. Acquiring analogical knowledge in a computational approach is a challenging task. In this paper, we present a solution that combines learning with knowledge engineering. The proposed knowledge discovery approach uses word embeddings to learn analogy on workflow tasks. The resulting knowledge is integrated with an ontology for the purpose of workflow transfer across application domains. A case study is conducted on the two example domains ’passenger and baggage handling at the airport’ and ’SAP warehouse management’. The experimental results on comparing the computational analogy with a golden standard from a knowledge engineering expert are quite promising and provide a proof-of-concept for the feasibility of the approach.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123291989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：