{"title":"Creating language and acoustic models using Kaldi to build an automatic speech recognition system for Kannada language","authors":"Thimmaraja G. Yadava","doi":"10.1109/RTEICT.2017.8256578","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256578","url":null,"abstract":"In this paper, creation of the Language Models (LMs) and Acoustic Models (AMs) using Kaldi speech recognition toolkit to build a robust Automatic Speech Recognition (ASR) system for Kannada language is demonstrated. The speech data is collected from the farmers of Karnataka under uncontrolled environment is used for the development of ASR models. The collected speech data needs to be translated to machine level language and hence the Indic Language Transliteration Tool (IT3 to UTF-8) is used for transcription. The dictionary for the collected speech data is created by using Indian Language Speech sound Label (ILSL12) set. The AMs are created by using Gaussian Mixture Model (GMM) and Subspace GMM (SGMM). The 80% and 20% of validated speech data is used for training and testing respectively. The accuracy and Word Error Rate (WER) of ASR models are highlighted and discussed in this work. The developed ASR models can be used in spoken query system which enables the farmers to access the on time agricultural commodity prices and weather information in Kannada language.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130530275","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}
Aurobind V. Iyer, Viral Pasad, Smita Sankhe, Karan D. Prajapati
{"title":"Emotion based mood enhancing music recommendation","authors":"Aurobind V. Iyer, Viral Pasad, Smita Sankhe, Karan D. Prajapati","doi":"10.1109/RTEICT.2017.8256863","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256863","url":null,"abstract":"Music is one of the most effective media as it can instill deep feelings and swamp listeners with subliminal messages. It deftly plays with our emotions which in turn affect our mood. Books, movies and television dramas are a few other media but, in contrast to these, music delivers its message in mere moments. It can aid us when we are feeling low and empower us. When we listen to sad songs, we tend to feel a decline in mood. When we listen to happy songs, we feel happier. Manual classification of songs based on mood, for making of a playlist, is time consuming and labour intensive. Our paper proposes a system ‘EmoPlayer’, an Android application, which help to minimize these efforts by suggesting the user a list of songs based on his current emotion. The system captures user's image using camera and detects his face. It then detects the emotion and makes a list of songs which will enhance his mood as the songs keep playing. EmoPlayer uses Viola Jones algorithm for face detection and Fisherfaces classifier for emotion classification.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129077455","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}
Akshay A Nayak, N. K. Sridhar, G. Poornima, Shivashankar
{"title":"Security issues in cloud computing and its counter measure","authors":"Akshay A Nayak, N. K. Sridhar, G. Poornima, Shivashankar","doi":"10.1109/RTEICT.2017.8256554","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256554","url":null,"abstract":"The Cloud computing is one of the most important on Internet of Services and computer infrastructure. More and more industries have begun to explore cloud computing. Cloud computing is a developing technique in a distributed computing system that increases the scalability and flexibility in processing due to the ability to decrease the time for calculation. However, the high flexibility and portability of cloud have caused a number of security concerns, the security issue is a big threat in cloud computing. Data security can be defined as a confidentiality and integrity of data maintained by an organization. It is, therefore, necessary to solve this security issue to enable extensive use of cloud computing. This paper mainly deals with cloud computing and analyzes security issues in cloud computing and the countermeasure which can be taken to resolve the issues of security in cloud computing.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129096940","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 novel approach for graph isomorphism: Handling large graphs","authors":"Rachna K. Somkunwar, Vinod Vaze","doi":"10.1109/RTEICT.2017.8256797","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256797","url":null,"abstract":"Graph Isomorphism has been proved as most crucial and very difficult process in Pattern Matching. The Graph Isomorphism problem is to check if two graphs are similar or not based on different properties like degree, vertex, edges etc. Two graphs are Isomorphic if they satisfy above properties. A Novel Approach is proposed for Graph Isomorphism Detection Problem (GIDP) based on two different methods. First method is to match an Input Graph with a Model Graph and second method is to match an input graph to the set of Model Graphs (Database of Model Graphs). This Novel Approach is used to solve Isomorphic Problems in an efficient way. Numbers of experiments are performed on large graphs and compared its performance with well-established algorithms like Ullman and VF2.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114377201","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 novel 8T SRAM with minimized power and delay","authors":"S. Naik, S. Kuwelkar","doi":"10.1109/RTEICT.2017.8256847","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256847","url":null,"abstract":"In this paper, a novel 8T SRAM cell is proposed which aims at decreasing the delay and lowering the total power consumption of the cell. The threshold voltage variations in the transistor affect the read and write stability of the cell. Also, power dissipation increases with the number of transistors which in turn affects the read and write stability. The proposed 8T SRAM bitcell is designed using 180 nm CMOS, n-well technology with a supply voltage of 1.8 V. The results show that the average delay has been improved by 80 % compared to the conventional 6T cell. The total power is improved by 14.5 % as compared to conventional 6T SRAM cell.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121735693","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 using kernalized correlation filters (KCF) and Kalman predictive estimates","authors":"A. Rani, V. Maik, B. Chithravathi","doi":"10.1109/RTEICT.2017.8256664","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256664","url":null,"abstract":"Visual object tracking and detection is an advanced interdisciplinary research area which is crucial for many surveillance security applications. In this paper, we aim to track moving objects more accurately and significantly faster when compared to other approaches. This can be achieved through Kernalized Correlation Filters (KCF). The proposed work adopts a novel approach where the KCF filter is enhanced by integrating it with Kalman filter. The integrated Kalman based KCF (KKCF) tracker outperforms the traditional KCF by performing well for outlier or failure cases which is corrected through Kalman filter. Experimental results show the performance compared to KCF and other existing methods.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114824352","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":"Algorithmic motion planning in robotics along with time based performance analysis","authors":"Shubham Sharma, Sanket Lakhtariya, S. Mehta","doi":"10.1109/RTEICT.2017.8256662","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256662","url":null,"abstract":"A∗ algorithm is well known for finding the shortest path from a starting point to a goal on a given map. This paper presents a method which makes use of it for robotic traversal when there are multiple starts (up to 2) and goals (up to 2), which is based on python. It shows how a customized heuristic matrix for every goal be obtained, which helps cutting down the runtime, for shortest path finding and is the supporting pillar of A∗. For the demonstration of the algorithm, a MATLAB based GUI is used to create a 2D map using which the python based script returns the shortest path. This path is then shown on the GUI.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127881928","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":"Real time threat detection system in cloud using big data analytics","authors":"Rohit More, Anand Unakal, V. Kulkarni, R. Goudar","doi":"10.1109/RTEICT.2017.8256801","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256801","url":null,"abstract":"The network data is the information generated over the network and this data is always under the cyber attack. The cyber criminals try to steal the useful information of someone's personal data or the organizations confidential data. In cloud applications, huge amount of data is processed in cluster of computers and stores the data at Common storage which is always under the threat of the cyber attacks. The data generation over cloud is increasing rapidly and it is huge in amount such data is called as big data. This big data is more vulnerable to cyber attacks. Due to big data's properties such as volume, variety, velocity it is very difficult to detect the attacks using traditional detection system. In this paper we proposed the threat detection system which uses big data technologies to analyze huge data and detects the cyber attacks over cloud networks in less time.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126303074","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":"Modelling of dual input DC/DC converter for hybrid energy system","authors":"Sushmita N. Shetty, Md. Abdul Raheman","doi":"10.1109/RTEICT.2017.8256779","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256779","url":null,"abstract":"Alternative energy sources like photovoltaic, fuel cell, wind, ultra capacitor, etc., are widely used in many applications such as in hybrid vehicles, micro grids etc. Combining two or more sources effectively, provides reliable power for the required application. Hence, the concept of hybrid energy system arises. In hybridization of energy systems, conventional sources and non-conventional sources are interfaced efficiently to drive the load. Two or more sources can be interfaced using different power electronic converters. Multiple Input DC/DC Converters (MIC) are one of the interfacing circuits used for hybridization of renewable and storage energy sources. In this paper, Dual input DC/DC converter is proposed which is useful in supplying the load from renewable and storage energy sources individually or simultaneously by connecting the two input sources in series. The two input sources to the converter used are photo-voltaic (PV) cell and a lead acid battery. Operation can be based on Buck, Boost or Buck-Boost modes. Using MATLAB/Simulink software, proposed converter is simulated.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126199791","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":"Outer race bearing fault identification of induction motor based on stator current signature by wavelet transform","authors":"S. Yeolekar, G. Mulay, J. Helonde","doi":"10.1109/RTEICT.2017.8256951","DOIUrl":"https://doi.org/10.1109/RTEICT.2017.8256951","url":null,"abstract":"This paper presents the results of laboratory work carried out for identifying the outer race bearing fault occurred in an induction motor. The knowledge about fault behavior of an induction motor is extremely important for overall operational life of the machine. The paper refers to spectral analysis of the motor stator current, which includes routine stator current, noise and specific fault current signature. Using separate healthy and faulty bearing on the machine, testing is carried out for obtaining set of healthy and faulty currents for different load conditions. The specific fault signature can be separated using feature extraction in time domain Wavelet and after getting spectral information using classification technique ANN fault is identified.","PeriodicalId":342831,"journal":{"name":"2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128102733","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}