{"title":"Integrating data science and R programming at an early stage","authors":"Soma Datta, Veneela Nagabandi","doi":"10.1109/ISCMI.2017.8279587","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279587","url":null,"abstract":"The use of data has become an integral part of everyday life. Hence, introducing data science with games would generate an interest and prepare students for the rapidly changing world of technology. This study is especially intended to teach data science (DS) and R programming using games for cognitive learning. Tangible learning with real-life examples were used to teach Data Science. A correlation between the typical toys that are played are tied to concepts of DS. The three variables of social cognitive learning are integrated in this study. The data collected from the workshops are different from other studies because of broadly two reasons. First, the games used to teach data science were measured with the elements of cognitive learning. The other, was that the learning data collected from the students that participated in the study had a modified environment. The data that was collected during the experimental study for thirty hours for about 100 students. Students at the end of each session were able to identify the data science terms with respect to the games. They were able to write a small R program that they self-taught themselves due to the environmental factor of cognitive learning.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132458145","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":"Eye-motion detection system for mnd patients","authors":"Chu-Lian Xu, Chyi-Yeu Lin","doi":"10.1109/ISCMI.2017.8279606","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279606","url":null,"abstract":"This paper aims to develop an eye-motion based communication system for motor neuron disease (MND) patients to contact with care providers any time they want when they lie on the bed. This eye-motion detection system involves technical modules of eye-blink detection, gaze estimation and head pose estimation on MND patients. The system comprises a rotating arm with a camera, an infrared light source and a speaker. The arm with the camera will autonomously rotate to track the face of the patient with arbitrary body directions so that necessary eye detections can be properly conducted when it is called. When the patient needs to call out, only designated blinking and eye motions will trigger the call out action for the need of finding the care provider.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114250980","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":"Accuracy based weighted aging ensemble (AB-WAE) — Algorithm for data stream classification","authors":"Michal Wozniak","doi":"10.1109/ISCMI.2017.8279591","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279591","url":null,"abstract":"Nowadays, most of the data comes continuously and its distribution may change over the time. Unfortunately, most of classifiers assume that statistical characteristics of used predicting model are not being changed. This work presents modification of the previously proposed Weighted Aging Classifier Ensemble (WAE), called Accuracy Based WAE (AB-WAE), which can easily adapt to the probability characteristic changes caused by so-called concept drift. The proposed model does not exploit a drift detection mechanism, but AB-WAE tries to change the line-up of the classifier ensemble and weights assigned to base classifiers. Thus, one individual classifier is trained on the basis of the each incoming data chunk, then AB-WAE chooses the most valuable ensemble taking into consideration: fixed ensemble size, the previously trained models and new trained classifier. The discussed WAE modification uses the ensemble of homogeneous classifiers only, what allows to employ more sophisticated combination rule based on support functions, what should boost the classification accuracy, what was confirmed by the computer experiments.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126064082","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":"Dynamic confidence values selection — Experimental studies","authors":"R. Burduk","doi":"10.1109/ISCMI.2017.8279620","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279620","url":null,"abstract":"The machine learning methods are often used in the development of the effective medical decision support systems. One of the latest trends in data mining is the ensemble selection. In this paper, we present the algorithm of the dynamic confidence values selection, which is dedicated to the binary classification task. In the experiment we use Support Vector Machine, k-Nearest-Neighbors, Neutral Network and Decision Trees models as base classifiers. Experiments on several publicly available medical diagnosis data sets verify the effectiveness of the proposed algorithm. The results demonstrate that the dynamic confidence values selection outperforms the ensemble classifier built with all base learning models.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130535848","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":"Five-elements cycle optimization algorithm for solving continuous optimization problems","authors":"Mandan Liu","doi":"10.1109/ISCMI.2017.8279601","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279601","url":null,"abstract":"The Five-elements Cycle Optimization Algorithm (FECO) is proposed in this paper inspired by the theory of Five-elements in Chinese traditional culture. It is built for finding the optimal solution of continuous functions based on the Five-elements Cycle Model which characterizes the mechanism of generation and restriction among five elements. The comparison with 11 optimization algorithms based on various mechanisms for 23 benchmark functions is given, which indicates the suitability and universality of FECO.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129940441","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}
Larissa Müller, Arne Bernin, A. Kamenz, Sobin Ghose, Kai von Luck, C. Grecos, Qi Wang, Florian Vogt
{"title":"Emotional journey for an emotion provoking cycling exergame","authors":"Larissa Müller, Arne Bernin, A. Kamenz, Sobin Ghose, Kai von Luck, C. Grecos, Qi Wang, Florian Vogt","doi":"10.1109/ISCMI.2017.8279607","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279607","url":null,"abstract":"In this work we present a novel concept for affective entertainment, which we call Emotional Journey. It provides a dynamic and adaptive story path based on a player's emotional responses and yields improved accurate recognition of the player's emotions. We conducted a case study with 25 players to evaluate our concept using our cycling exercise machine. We evaluated three different journey types and two of the three types were recognized reliably by the participants. We introduce a real time multimodal analysis method for facial expressions and electrodermal activity (EDA) measurements. This method results in significantly more robust emotion recognition rates. Therefore our exergaming system is able to provoke emotions and adapt the game play to individual emotional reactions.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134579969","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":"Interactive concepts for shaping generative models of spatial behavior","authors":"Ronny Hug, W. Hübner, Michael Arens","doi":"10.1109/ISCMI.2017.8279594","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279594","url":null,"abstract":"A technique widely used in video based situation assessment, and especially in anomaly detection, is the analysis of spatial behavior in terms of motion profiles recorded along trajectories. An intuitive assessment metric is the deviation from normal behavior, where generative models are a natural choice for capturing the underlying statistics. Applying such outlier methods in open world scenarios has the drawback that long observation times are required, in order to fully determine the model, while underdetermined models are very prone to generate non-intuitive or wrong results. In order to address this problem, the usage of interactive concepts for supporting the learning process and refining learned models is proposed. Thereby, the method keeps track of automatically integrated observations and stochastic priors generated by examples provided by the user. Examples can be given in terms of individual labeled samples, or in terms of complex pdfs. The feasibility of the proposed approach is illustrated on the BIWI Walking Pedestrians dataset, using partitioned Gaussian mixture models as the generative model.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116116522","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":"Cuckoo search: State-of-the-art and opportunities","authors":"Xin-She Yang, S. Deb","doi":"10.1109/ISCMI.2017.8279597","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279597","url":null,"abstract":"Since the development of cuckoo search (CS) by Yang and Deb in 2009, CS has been applied in a diverse range of applications. This paper first outlines the key features of the algorithm and its variants, and then briefly summarizes the state-of-the-art developments in many applications. The opportunities for further research are also identified.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133806096","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":"Inertia weight control strategies: Particle roaming behavior","authors":"A. Engelbrecht","doi":"10.1109/ISCMI.2017.8279625","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279625","url":null,"abstract":"The performance of particle swarm optimization (PSO) algorithms have shown to be very sensitive to the main control parameters. Due to this sensitivity, various approaches have been developed to dynamically adjust the value of these control parameters in an attempt to remove the necessity of prior control parameter tuning. A large number of these adaptive approaches are different ways in which the inertia weight value can be adjusted during the search process. Recent studies have shown that these adaptive approaches are not very efficient. This paper supplements previous studies of the different inertia weight control strategies, focusing on the roaming behavior of particles under the different control strategies. It is shown that a number of these inertia weight control strategies exhibit excessive roaming behavior, resulting in wasted search effort.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132391079","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}
Zhenlong Xiao, Jiazuan Ni, Qiong Liu, Liang Jiang, Xin Wang
{"title":"Study on automatic tracking algorithm of neurons in most atlas of mouse brain based on open curve snake","authors":"Zhenlong Xiao, Jiazuan Ni, Qiong Liu, Liang Jiang, Xin Wang","doi":"10.1109/ISCMI.2017.8279614","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279614","url":null,"abstract":"In spite of the rapid development of science and technology, the nervous system of human is still the most sophisticated functional system, which is based on billions of neurons, the basic structure of brains. In this paper, section atlas of mouse brain were scanned by micro-optic Sectioning Tomography (MOST). In the current literature reports, the existing algorithms cannot track neurons of complex image data effectively. In order to achieve a more effective tracking method for MOST data, our paper proposed an improved scheme based on the OpenSnake tracking algorithm, and used the C++ language to implement algorithm. Our methods provide important theoretical basis for the study of AD.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115406492","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}