{"title":"Greek sign language alphabet recognition using the leap motion device","authors":"Merkourios Simos, N. Nikolaidis","doi":"10.1145/2903220.2903249","DOIUrl":"https://doi.org/10.1145/2903220.2903249","url":null,"abstract":"The goal of this paper is to present a method for sign language recognition using the Leap Motion Controller and apply it to the recognition of the Greek sign language alphabet. The method utilizes 3D positional data provided by the device along with SVM classification and achieves over 99% classification accuracy in an experiment involving 6 subjects and leave-one-person-out cross validation.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264638","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":"Evolving Multi-Layer Neural Networks for Othello","authors":"Vassilis Makris, Dimitris Kalles","doi":"10.1145/2903220.2903231","DOIUrl":"https://doi.org/10.1145/2903220.2903231","url":null,"abstract":"Othello has long been a favorite AI subject due to its very simple rules, its very low branching factor, its well defined strategic concepts and its dramatic changes in board topology as a game unfolds. In this paper, we investigate several neural network architectures using co-evolutionary learning techniques, with the objective to learn to play Othello strongly. Our resulting neural networks were able to learn to play the game at an expert-master level and to discover advanced strategies, within a few thousand generations, without any prior knowledge, beyond the game rules.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123442918","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}
Ines Berrazega, R. Faiz, A. Bouhafs, Ghassan Mourad
{"title":"A Semantic Annotation Model for Arabic Legal Texts","authors":"Ines Berrazega, R. Faiz, A. Bouhafs, Ghassan Mourad","doi":"10.1145/2903220.2903244","DOIUrl":"https://doi.org/10.1145/2903220.2903244","url":null,"abstract":"This paper addresses an issue in the field of Artificial Intelligence and Law. It's concerned with the problem of automatically identifying and semantically annotating normative provisions' categories in Arabic legal texts. This goal has been achieved through the construction of a semantic annotation model, which combines three linguistic resources namely a taxonomy of Arabic normative provisions' categories, an Arabic normative terminological base and a semantic annotation rule base. The performance of the model has been evaluated over a test dataset of Arabic normative texts collected from the Official Gazette of the Republic of Tunisia. Precision, Recall and F-score measures have been used for evaluation. Obtained results are very promising: 96,4% for Precision, 96,06% for Recall and 96,23% for F-score.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122702915","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}
Konstantinos Tziortziotis, Nikolaos Tziortziotis, K. Vlachos, K. Blekas
{"title":"Autonomous navigation of an over-actuated marine platform using reinforcement learning","authors":"Konstantinos Tziortziotis, Nikolaos Tziortziotis, K. Vlachos, K. Blekas","doi":"10.1145/2903220.2903254","DOIUrl":"https://doi.org/10.1145/2903220.2903254","url":null,"abstract":"This paper investigates the use of reinforcement learning for the navigation of an over-actuated marine platform in unknown environments. The proposed approach uses an online least-squared policy iteration scheme for value function approximation in order to estimate optimal policy. We evaluate our approach in a simulation platform and report some initial results concerning its performance on estimating optimal navigation policies to unknown environments under different environmental disturbances. The results are promising.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132020599","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":"A constrained molecular graph generation with imposed and forbidden fragments","authors":"Mohamed Amine Omrani, Wady Naanaa","doi":"10.1145/2903220.2903234","DOIUrl":"https://doi.org/10.1145/2903220.2903234","url":null,"abstract":"In analytical chemistry, the molecular structure generation problem consists in finding all molecular structure that are consistent with a dataset derived from different kind of spectra. The automation of this task is an important research area which has been investigated in many systems known under the name of structure elucidation systems. In this paper, we encoded this real-world problem as a constraint satisfaction problem (CSP) in order to take advantage of the flurry of efficient solution algorithms available within the constraint programming (CP) framework. The CSP encoding allowed to take into account structural constraints like inter-atom distances, imposed and forbidden fragments.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134296816","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":"A planning problem validator based on reachability analysis","authors":"Moses Symeonidis, Dimitris Giouroukis, D. Vrakas","doi":"10.1145/2903220.2903237","DOIUrl":"https://doi.org/10.1145/2903220.2903237","url":null,"abstract":"AI planning is the field that focuses on creating abstract representations of various processes. As such, it is obvious that it is a broad field and demands specialized tools to be used in order to ease the process of designing domains and problems. The literature shows that most of these tools do not offer an option to re-examine and validate the result of the aforementioned designing process. This work presents a novel approach to validating a description of a problem as well as presenting information related to this validation process in an efficient way. It introduces a proxy web service that implements the process of finding invalid descriptions as well as the extension of the relevant tool VLEPpO, that suited the needs of the visualization process.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115529071","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":"Classifier-assisted optimization","authors":"Y. Tenne","doi":"10.1145/2903220.2903251","DOIUrl":"https://doi.org/10.1145/2903220.2903251","url":null,"abstract":"Engineering design optimization often uses computer simulations to evaluate candidate designs. Such numerical simulations may consistently fail for some designs, but the failure reason being unknown. If such failures are frequent than the effectiveness of the optimization process can severely degrade. To address this issue this study describes the integration of classifiers, borrowed from the domain of machine learning, into the optimization search. The classifiers attempt to predict if a candidate design will cause a simulation crash, and this prediction is then used to bias the search. The effectiveness of the approach is demonstrated through several numerical experiments.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122971178","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":"Efficiently Reasoning about Qualitative Constraints through Variable Elimination","authors":"Michael Sioutis, Zhiguo Long, Sanjiang Li","doi":"10.1145/2903220.2903226","DOIUrl":"https://doi.org/10.1145/2903220.2903226","url":null,"abstract":"We introduce, study, and evaluate a novel algorithm in the context of qualitative constraint-based spatial and temporal reasoning, that is based on the idea of variable elimination, a simple and general exact inference approach in probabilistic graphical models. Given a qualitative constraint network N, our algorithm enforces a particular directional local consistency on N, which we denote by ←-consistency. Our discussion is restricted to distributive subclasses of relations, i.e., sets of relations closed under converse, intersection, and weak composition and for which weak composition distributes over non-empty intersections for all of their relations. We demonstrate that enforcing ←-consistency on a given qualitative constraint network defined over a distributive subclass of relations allows us to decide its satisfiability. The experimentation that we have conducted with random and real-world qualitative constraint networks defined over a distributive subclass of relations of the Region Connection Calculus, shows that our approach exhibits unparalleled performance against competing state-of-the-art approaches for checking the satisfiability of such constraint networks.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124974987","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":"Distance Measurement of Objects using Stereo Vision","authors":"Mozammel Chowdhury, Junbin Gao, R. Islam","doi":"10.1145/2903220.2903247","DOIUrl":"https://doi.org/10.1145/2903220.2903247","url":null,"abstract":"Vision based distance measurement of objects is continues to be a popular research topic in computer and robot vision nowadays. Measuring distance of targets are important for robot navigation, obstacle detection, navigation of autonomous vehicles, surveillance monitoring, person localization and tracking, and many more. In this paper, we propose an efficient approach for distance measurement of objects using stereo vision. The distance is measured from the estimated depth information of the object from its two image sequences (called left and right image pair) captured by a stereo camera. In order to estimate the depth information we employ a fast stereo algorithm. Experimental evaluation proves the efficiency of our proposed approach comparable to other related methods.","PeriodicalId":122018,"journal":{"name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116612222","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}