A. H. Khabbaz, A. Pouyan, Mansoor Fateh, V. Abolghasemi
{"title":"An adaptive RL based fuzzy game for autistic children","authors":"A. H. Khabbaz, A. Pouyan, Mansoor Fateh, V. Abolghasemi","doi":"10.1109/AISP.2017.8324105","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324105","url":null,"abstract":"This paper, presents an adapted serious game for rating social ability in children with autism spectrum disorder (ASD). The required measurements are obtained by the challenges of the proposed serious game. The proposed serious game uses reinforcement learning concepts for being adaptive. It is based on fuzzy logic to evaluate the social ability level of the children with ASD. The game adapts itself to the level of the autistic patient by reducing or increasing the challenges in the game via an intelligent agent during the play time. This task is accomplished by making more elements and reshaping them to a variety of real world shapes and redesigning their motions and speed. If autistic patient's communication level grows during the playtime, the challenges of game may become harder to make a dynamic procedure for evaluation. At each step or state, using fuzzy logic, the level of the player is estimated based on some attributes such as average of the distances between the fixed points gazed by the player, or number of the correct answers selected by the player divided by the number of the questioned objects. The contribution of this paper is the usage of dynamic AI difficulty to enhance the conversation skills in autistic children.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124546868","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}
{"title":"Eigenvalue based features for semantic sentence similarity","authors":"Ali Vardasbi, Heshaam Faili, M. Asadpour","doi":"10.1109/AISP.2017.8324078","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324078","url":null,"abstract":"Due to its increasing importance, the semantic sentence similarity is getting more attention among natural language processing researchers during recent years. To the best of our knowledge, previous studies on the task have not exploited the eigenvalue analysis on their systems. In this paper we approach the sentence similarity task through eigenvalue analysis. We will propose a simple but efficient new aligner and introduce three new features for the task. Two of our proposed features are based on the eigenvalue analysis. Finally, we will show the significance of our proposed aligner and features through experiments. Specifically, we will show that our features outperform the STS2015 benchmarks for semantic sentence similarity.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"339 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122143048","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}
{"title":"Gene expression programming with a local search operator","authors":"A. A. Safavi, M. Kelarestaghi, F. Eshghi","doi":"10.1109/AISP.2017.8324106","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324106","url":null,"abstract":"Gene expression programming (GEP) is one of the newest evolutionary algorithms, the linear model of genetic programming that have been much attention to it, in recent years. In this article this algorithm and memetic algorithms are discussed. Here we are tried to improve its efficiency by combining gene expression programming with a local search method. The proposed algorithm called GEP-LS and it is applicable for all problems in the field of evolutionary computation. Random Mutation Hill-Climbing (RMHC) and Simulated Annealing (SA) methods are separately used to implement local search and their results are compared with each other. Finally, a comparison with the conventional gene expression programming algorithm is performed. These comparisons is performed on problems of symbolic regression, sequence induction with constants creation and robotic planning. The results show that performance of the proposed algorithm with RMHC method is relatively better than other algorithms and is able to solve all problems used here with higher accuracy and lower error.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126966528","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}
{"title":"Authentication based on face recognition under uncontrolled conditions","authors":"Niloofar Tvakolian, A. Nazemi, Z. Azimifar","doi":"10.1109/AISP.2017.8324120","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324120","url":null,"abstract":"This paper proposes a method to address issues regarding uncontrolled conditions in face recognition. This method extracts affecting factor from the test sample utilizing mask projection. Current methods remove occlusion from test sample and reconstruct it. Unlike these methods, proposed method tries to add extracted occlusion to all normal training samples and compares test sample with all synthetic affected training samples. The method has been applied for multi-factor authentication/verification based on face biometric. Obtained results indicate high accuracy, comparable to the best sparse method, in the lake of sufficient training samples for each class(single sample classes).","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133536915","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}
{"title":"Parkinson's disease detection using ensemble techniques and genetic algorithm","authors":"Najmeh Fayyazifar, N. Samadiani","doi":"10.1109/AISP.2017.8324074","DOIUrl":"https://doi.org/10.1109/AISP.2017.8324074","url":null,"abstract":"Parkinson's disease (PD) is a neurological disorder which progress by time. People suffering from PD experience shortage of Dopamine which is a chemical present in brain nerve cells. The symptoms of PD are tremor, rigidity, and slowness of movements and people with PD experience more severity by time progress. Therefore, the automation in early detection of PD is an important issue. In the literature, different classification methods have been proposed. Also, due to the high dimension of extracted features of voice, many feature selection algorithms have been developed. In this paper, we aim to propose a method for early detection of PD from voice recordings. The Genetic algorithm is used to select the optimal set of features which can reduce feature vector dimension from 22 to 6 features. We have achieved 96.55% and 98.28% detection rate by employing AdaBoost and Bagging algorithms for classification process, respectively.","PeriodicalId":386952,"journal":{"name":"2017 Artificial Intelligence and Signal Processing Conference (AISP)","volume":"1970 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129974213","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}