Patric Bino, Prakash, Shomona Gracia, Jacob Radhameena
{"title":"Mining semantic representation from medical text: A Bayesian approach","authors":"Patric Bino, Prakash, Shomona Gracia, Jacob Radhameena","doi":"10.1109/ICRTIT.2014.6996197","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996197","url":null,"abstract":"Machine learning is a subfield of artificial intelligence that deals with the exploration and construction of systems that can learn from data. Machine learning trains the computers to manage the critical situations via examining, self-training, inference by observation and previous experience. This paper provides an overview of the development of an efficient classifier that represents the semantics in medical data (Medline) using a Machine Learning (ML) perspective. In recent days people are more concerned about their health and explore ways to identify health related information. But the process of identifying the semantic representation for the medical terms is a difficult task. The main goal of our work was to identify the semantic representation for the medical abstracts in the Medline repository using Machine Learning and Natural Language Processing (NLP).","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"273 21-24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120928796","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":"Data Fusion in Wireless Sensor Network using Simpson's 3/8 rule","authors":"G. Rajesh, B. Vinayagasundaram, G. Moorthy","doi":"10.1109/ICRTIT.2014.6996201","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996201","url":null,"abstract":"Wireless Sensor Network (WSN) is an anthology of distributed sensor nodes that constantly monitors physical and ecological conditions. Depending on the application, node count in WSN ranges from few hundreds to thousands. A node in Sensor Network constantly monitors and communally passes their data through the network to a Sink Node. Based on literatures, a trivial issue in densely deployed sensor network, the data collected from adjacent nodes has higher level of similarity and data redundancy. To overcome the redundancy issue, the proposed method called “Numerical Integration Technique” includes - Simpson's 3/8 rule to reduce data redundancy. On performance analysis, the proposed method achieves higher rate of data aggregation compared to Kalman Filter and minimizes energy utilization caused by not transmitting the redundant data.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126211773","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}
P. Pabitha, M. Mohana, S. Suganthi, B. Sivanandhini
{"title":"Automatic Question Generation system","authors":"P. Pabitha, M. Mohana, S. Suganthi, B. Sivanandhini","doi":"10.1109/ICRTIT.2014.6996216","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996216","url":null,"abstract":"The process of automating the question generation consists of many tasks. Selecting the target content (what to ask), question type (who, why, how) and actual question generation are the major issue of Automatic Question Generation. Certain definitions retrieved is available in Wikipedia either directly or is the outcome of executing set of sub queries for each key phrase categories The problem in the existing system is that some of the definition sentences which are taken out from Wikipedia were implicit. The proposed system overcomes the problems by using Supervised Learning Approach, Naïve Bayes method. It also extends its work to use Summarization, Noun Filtering and Question Generation in the aim of generating semantically correct questions.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127477718","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":"SCA - An energy efficient transmission in sensor cloud","authors":"S. Grace, M. Sumalatha","doi":"10.1109/ICRTIT.2014.6996172","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996172","url":null,"abstract":"Sensor cloud is an emerging technology which integrates wireless sensor network with cloud environment. The major issues to be addressed in the sensor cloud are storage and transmission. The existing compression algorithm inappropriate for small size files. The sensor data taken from different sensor are compressed based on their similarity but it is not appropriate when large numbers of sensors in the network. In this paper, we proposed an energy efficient middleware model for sensor cloud named as senud controller which is the combination of sensor gateway and cloud gateway. It can deal with the adverse situation in case of continuous and long duration monitoring of data. Senud Compression Algorithm (SCA) reduces the replication of data and suitable for the numerical data compression. It is basically designed for numerical valued sensor data that supports large voluminous data collection in an efficient manner.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125625959","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":"Detecting malicious tweets in trending topics using clustering and classification","authors":"Saini Jacob, Soman Research, Murugappan","doi":"10.1109/ICRTIT.2014.6996188","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996188","url":null,"abstract":"Detection of spam Twitter social networks is one of the significant research areas to discover unauthorized user accounts. A number of research works have been carried out to solve these issues but most of the existing techniques had not focused on various features and doesn't group similar user trending topics which become their major limitation. Trending topics collects the current Internet trends and topics of argument of each and every user. In order to overcome the problem of feature extraction,this work initially extracts many features such as user profile features, user activity features, location based features and text and content features. Then the extracted text features use Jenson-Shannon Divergence (JSD) measure to characterize each labeled tweet using natural language models. Different features are extracted from collected trending topics data in twitter. After features are extracted, clusters are formed to group similar trending topics of tweet user profile. Fuzzy K-means (FKM) algorithm primarily cluster the similar user profiles with same trending topics of tweet and centers are determined to similar user profiles with same trending topics of tweet from fuzzy membership function. Moreover, Extreme learning machine (ELM) algorithm is applied to analyze the growing characteristics of spam with similar topics in twitter from clustering result and acquire necessary knowledge in the detection of spam. The results are evaluated with F-measure, True Positive Rate (TPR), False Positive Rate (FPR) and Classification Accuracy with improved detection results.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133355533","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":"Probability based road network detection in satellite images","authors":"K. Maithili, K. Vani","doi":"10.1109/ICRTIT.2014.6996134","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996134","url":null,"abstract":"Road network detection is the process of detecting and extracting the road network from very high resolution satellite and aerial images. It is essential for many applications like map generation and updating. To do this road network detection, resolution of satellite and aerial images plays an important role. If experts try to label the road pixels manually, it will take more time and will lead to errors. Hence an automatic method is proposed here. Major operations of the proposed system are road network detection, estimation of road center pixel and road shape extraction. First, edge pixels are detected. Then, they are refined. Based on probability, road center pixels are estimated using edge pixels as observations. Next, road shape is extracted from the estimated center pixels using graph theory. The proposed method is tested on satellite (Quick bird and Ikonos) images. Obtained results indicate that the proposed method works well with 94% of accuracy when compared with the one existing in the literature. This work can be envisaged as a potential contribution to the science of automatic road network extraction from high resolution imagery.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133785938","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":"Biologically inspired QoS aware routing protocol to optimize lifetime in Sensor Networks","authors":"S. Archana, N. Saravanan","doi":"10.1109/ICRTIT.2014.6996123","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996123","url":null,"abstract":"A Wireless Sensor Network (WSN) is a self-governing network of sensor nodes organized in autonomous manner to monitor the region; connected using wireless links. Each node communicates with the other neighbor nodes, which lie in its transmission range and the entire region monitored by the combined effort of all the sensor nodes in the network, are termed as coverage area. The purpose of sensor nodes is to convey the event occurred to the base station or the sink node. Due to dynamic topology and limited network resources, sensor nodes experience a high failure rate. The ant based enhanced BiO4SeL QoS aware routing algorithm (EBiO4SeL) designed is based on the meta-heuristic approach of Ant Colony Optimization (ACO) framework, stimulated by natural ant behavior. Artificial ants are used to gather the QoS parameters such as delay, bandwidth, bit error rate, energy, signal strength etc., of the neighbor nodes. The path chosen for data transfer is computed with Path Preference Probability which satisfies all the Quality of Service (QoS) requirements. This algorithm is suitable for real time applications as it enhances node lifetime and downgrades packet loss and end to end delay. It is compared with existing BiO4SeL (Biologically-inspired Optimization for Sensor Lifetime) routing protocol.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134556097","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":"Enhancing security in Optimized Link State Routing protocol for MANET using threshold cryptography technique","authors":"K. Tamil Selvi, S. Kuppuswami","doi":"10.1109/ICRTIT.2014.6996122","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996122","url":null,"abstract":"The Optimized Link State Routing is a proactive link state routing protocol for Mobile Ad hoc Network. The Multipoint Relays nodes which are one-hop neighbors are used as a means for flooding of control and traffic messages into the network. The RFC 3626 does not consider the security issues. The secured OLSR framework consists of security module which provides the security with minimum overhead. The overhead is reduced by minimizing the number of Multipoint Relay nodes in the network and providing security for those selected nodes. The security is provided with the help of threshold cryptography technique. The use of threshold cryptography is to provide security measures by distributing the secret key shares and performing encryption with those shares of secrets. The share can be reconstructed using Lagrange interpolation. The destination could recover only if all or threshold numbers of the secret shares are not compromised. The share update mechanism is also aimed which provide security, when the threshold number of shares are compromised. The main aim is to provide the truthfulness of routing messages, especially Topology Control messages and hence prevent forwarding nodes from varying routing messages while forwarding them. The simulation of the above ideas also confirms the results and provides better security and performance improvement.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131861432","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":"Sphere decoding using threshold based Schnorr-Euchner enumeration in MIMO system","authors":"M. Karthikeyan, D. Saraswady","doi":"10.1109/ICRTIT.2014.6996088","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996088","url":null,"abstract":"A threshold based Schnorr-Euchner (TSE) sphere decoder (SD) is presented in this paper to reduce the high computational burden incur in multiple input multiple output (MIMO) decoding. The proposed method makes use of the probabilistic threshold for SE enumeration to remove the nodes which are most unlikely to be an ML solution. The threshold is chosen using the pruning probability based on noise statistics. By increasing the pruning probability, the higher level of complexity reduction can be achieved at the cost of slight performance loss. Simulations illustrate that the proposed TSE-SD achieves an improvement in performance through complexity reduction over conventional SE-SD.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129350362","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":"Integration of poses to enhance the shape of the object tracking from a single view video","authors":"J. Hemavathy, L. Sindhia, Dhananjay Kumar","doi":"10.1109/ICRTIT.2014.6996119","DOIUrl":"https://doi.org/10.1109/ICRTIT.2014.6996119","url":null,"abstract":"In computer vision, tracking human pose has received a growing attention in recent years. The existing methods used multi-view videos and camera calibrations to enhance the shape of the object in 3D view. In this paper, tracking and partial reconstruction of the shape of the object from a single view video is identified. The goal of the proposed integrated method is to detect the movement of a person more accurately in 2D view. The integrated method is a combination of Silhouette based pose estimation and Scene flow based pose estimation. The silhouette based pose estimation is used to enhance the shape of the object for 3D reconstruction and scene flow based pose estimation is used to capture the size as well as the stability of the object. By integrating these two poses, the accurate shape of the object has been calculated from a single view video.","PeriodicalId":422275,"journal":{"name":"2014 International Conference on Recent Trends in Information Technology","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132393065","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}