{"title":"Prediction of User's Purchase Intention Based on Machine Learning","authors":"Liu Bing, Shi Yuliang","doi":"10.1109/ISCMI.2016.21","DOIUrl":"https://doi.org/10.1109/ISCMI.2016.21","url":null,"abstract":"In recent years, the use of machine learning methods to deal with the problem of user interest prediction has become a hot research direction in the field of electronic commerce. In the present stage, a naive Bayesian algorithm has the advantages of simple implementation and high classification efficiency. However, this method is too dependent on the distribution of samples in the sample space, and has the potential of instability. To this end, the decision tree method is introduced to deal with the problem of interest classification, and the innovative use of Localstorage technology in HTML5 to obtain the required the experimental data. Classification method uses the information entropy of the training data set to build the classification model, through the simple search of the classification model to complete the classification of unknown data items. Both theoretical analysis and experimental results show that the decision tree is used to deal with the problem of prediction of users' interests has obvious advantages in the efficiency and stability.","PeriodicalId":417057,"journal":{"name":"2016 3rd International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129953121","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 Single Layer Hermite Neural Network Based Direct Adaptive Control of DC-DC Buck Converter","authors":"Tousif Khan Nizami, C. Mahanta","doi":"10.1109/ISCMI.2016.19","DOIUrl":"https://doi.org/10.1109/ISCMI.2016.19","url":null,"abstract":"This paper presents a novel control scheme for the output voltage tracking problem of dc-dc buck converter. The proposed control structure integrates a direct adaptive backstepping control approach with a single functional layer Hermite neural network (HNN). Buck converter is a variable structure model with a highly uncertain loading pattern. Hence an estimator based on HNN is employed to estimate the load perturbations influencing the converter. The accurate and timely information about the unanticipated load resistance strengthens the control law in order to attain the desired objective. The online adaptive laws are derived based on Lyapunov stability criterion ensuring the overall stability of the buck converter equipped with the proposed control. The performance of the proposed method is evaluated by subjecting the buck converter to a wide range variations in load resistance, input voltage and reference output voltage. Further, the merits of proposed control are highlighted by comparing the performance with the standard adaptive backstepping control technique under identical conditions of simulation study. Performance indices such as peak overshoot, peak undershoot and settling time have been evaluated, which clearly indicate the outperformance of proposed control.","PeriodicalId":417057,"journal":{"name":"2016 3rd International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"581 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123459683","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":"Name-Centric Gender Inference Using Data Analytics","authors":"S. Pudaruth, Upasana Singh, Hoshiladevi Ramnial","doi":"10.1109/ISCMI.2016.44","DOIUrl":"https://doi.org/10.1109/ISCMI.2016.44","url":null,"abstract":"In this era of globalisation and technology, determining the gender of a person from forenames has numerous applications especially in the machine translation and natural language processing fields. In this paper, we used a supervised machine learning approach to classify 10000 first names into either a male or female name. The names were manually extracted from an online telephone directory and then manually classified into an appropriate category. We obtained the highest accuracy of 88.0% when using support vector machines while the Naïve Bayes produced the lowest accuracy of 84.7%. A total of 15 features were used in this study. Traditionally, such systems have relied on a name dictionary to output the gender of forenames. However, our proposed system can predict the gender of unseen or unknown names. Furthermore, our dataset consists of names from different origins such as European, African, Arabic, Indian and Chinese, unlike previous studies which use names from one origin only.","PeriodicalId":417057,"journal":{"name":"2016 3rd International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124513651","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":"Robust Object Tracking Method Dealing with Occlusion","authors":"Qinjun Zhao, Wei Tian, Qin Zhang, Junxu Wei","doi":"10.1109/ISCMI.2016.41","DOIUrl":"https://doi.org/10.1109/ISCMI.2016.41","url":null,"abstract":"This paper proposes a robust object tracking algorithm dealing with the occlusion problem and illumination change. In particular, we judge whether each frame image is occluded by the confidence map, and two object spatial-temporal context models are established, one is updated every frame in the process of tracking, and the other is set up before the frame that the object is occluded. This method can correct the tracking drift caused by the model update during the occlusion process. Besides, the target image's pixel value is normalized to remove the effect of illumination change, and the phase of the object image's Fast Fourier Transform is used as the texture of the image. Experimental results show that the proposed method is robust to complex situation such as heavy occlusion, dramatic illumination change and surface variation.","PeriodicalId":417057,"journal":{"name":"2016 3rd International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125543685","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":"Visuo-Somatosensory Interaction for Space Telescience of Fluid Experiments","authors":"Ge Yu, Yan Wang, Taotao Fu, Ji Liang, Lili Guo","doi":"10.1109/ISCMI.2016.17","DOIUrl":"https://doi.org/10.1109/ISCMI.2016.17","url":null,"abstract":"In this paper, we propose a novel visuo-somatosensory interaction strategy for space telescience experiments to provide a realistic 'virtual presence' at the space experiment workplace in a sequential multi-step process. We provide background on the current available tools for telescience experiment and discuss the requirements when performing the liquid bridge experiment. We model the fluid as physical-based data-driven dynamic particles and develop to display in 3D stereoscopic scenario using the Oculus Rift. We design the task-command hierarchical interaction solution for less mental workload and the recognition algorithm of a series of understandable hand(s) gestures for intuitive control using Leap Motion. We introduce tactile-based augmentation interaction to provide a helpful guide. Finally, the results show the proposed method can provide a more efficient, natural and intuitive user experience compared with traditional interaction. For space experiment of liquid bridge, two-hand gestures show the higher accuracy and less mental workload than the single-hand gesture and the variant gesture. Also, a pilot study of gesture-based control with tactile feedback is validated to be a potentially powerful solution to enhance the user's interaction experience.","PeriodicalId":417057,"journal":{"name":"2016 3rd International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116891290","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":"Topic Identification System to Filter Twitter Feeds","authors":"S. Altammami, O. Rana","doi":"10.1109/ISCMI.2016.14","DOIUrl":"https://doi.org/10.1109/ISCMI.2016.14","url":null,"abstract":"Twitter is a micro-blogging service where users publish messages of 140 characters. This simple feature makes Twitter the source for concise, instant and interesting information ranging from friends’ updates to breaking news. However, a problem emerge when a user follows many accounts while interested in a subset of its content, which leads to overwhelming tweets he is not interested in receiving. We propose a solution to this problem by filtering incoming tweets based on the user’s interests, which is accomplished through a classifier. The proposed classifier system categorizes tweets into generic classes like Entertainment, Health, Sport, News, Food, Technology and Health. This paper describes the creation and evaluation of the classifier until 89% accuracy obtained.","PeriodicalId":417057,"journal":{"name":"2016 3rd International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132269133","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}