{"title":"A Two-Step Method for Sentiment Analysis of Tweets","authors":"Nimit Bindal, N. Chatterjee","doi":"10.1109/ICIT.2016.052","DOIUrl":"https://doi.org/10.1109/ICIT.2016.052","url":null,"abstract":"Sentiment Mining refers to extraction of public sentiment, typically from a set of texts or documents. The present work aims at gaining insights into sentiment mining on tweets using Machine Learning and Natural Language Processing techniques. We propose a lexicon-based sentiment scoring method, and use it in combination with Support Vector Machine (SVM) classifier as a two-step method for sentiment classification. The proposed scheme creates a sentiment lexicon from Sentiment140 corpus using Point-wise Mutual Information (PMI) measure. The lexicon is used to score tweets with positive or negative polarity. Tweets with low polarity strength are passed to a Support Vector Machine (SVM) classifier. This system is compared with several supervised statistical learning algorithms. The classification performance of the proposed scheme has been found to be better than commonly used one-step methods. We also discuss efficacy of several linguistic features, such as Part-of-Speech (POS) tags and higher order n-grams in sentiment mining.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122310644","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 Comparative Analysis of Different Modulation Techniques Based on Subcarrier Intensity Modulation in Free Space Optics Using Log-Normal Turbulence Model","authors":"R. Giri, B. Patnaik","doi":"10.1109/ICIT.2016.016","DOIUrl":"https://doi.org/10.1109/ICIT.2016.016","url":null,"abstract":"In this paper, the error rate performance of free space optics (FSO) is analyzed by employing different subcarrier-intensity modulation (SIM) based techniques like binary phase shift keying(BPSK-SIM), quadrature amplitude modulation(QAM-SIM), differential phase shift keying (DPSK-SIM). So a comparative study is presented based on bit error rate (BER) plots with respect to signal-to-noise ratio (SNR), average irradiance, scintillation index etc. The analysis has been performed by considering log-normal channel model. The simulation results are verified in Matlab with the mathematical analysis. In our work we have used Gauss-Hermite integration approximation for the BER analysis. The simulation results show that BPSK-SIM is superior to other techniques but QAM-SIM and DPSK-SIM have other advantages. So from this comparative analysis, the appropriate technique can be chosen according to the desired applications.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133663602","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":"An Efficient Load Balancing Mechanism with Cost Estimation on GridSim","authors":"D. Patel, C. Tripathy","doi":"10.1109/ICIT.2016.027","DOIUrl":"https://doi.org/10.1109/ICIT.2016.027","url":null,"abstract":"Due to the rapid technological advancements, the Grid computing has emerged as a new field, distinguished from conventional distributed computing. The load balancing is considered to be very important in Grid systems. In this paper, we propose a new dynamic and distributed load balancing method called \"Enhanced GridSim with Load Balancing based on Cost Estimation\" (EGCE) for computational Grid with heterogeneous resources. The proposed algorithm EGCE is an improved version of the existing EGDC in which we perform load balancing by estimating the expected finish time of a job on resources on each job arrival and then balance the load by migrating jobs to resources by taking into account the resource heterogeneity and network heterogeneity. We simulate the proposed algorithm on the GridSim platform. From the results, our algorithm is shown to be quite efficient in minimizing the average response time.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"416 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117304859","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 Quantum Cryptography Protocol","authors":"Subhashree Basu, Supriyo Sengupta","doi":"10.1109/ICIT.2016.024","DOIUrl":"https://doi.org/10.1109/ICIT.2016.024","url":null,"abstract":"Quantum key distribution is a sub topic under quantumcryptography where two parties distribute a shared random bit stringknown only to them and which can be used as a key to encrypt anddecrypt messages. This paper proposes a novel method of QKD todistribute the secret key. The basic concept of QKD remains the samebut the process by which the key is exchanged between the twoparties is different and is much more secure than the existing QKDprotocols. The proposed method exploits the concept of hamming weight.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123760619","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":"Hybrid Technique for Underground Cable to Locate the Fault","authors":"P. Ray, D. Mishra, G. K. Budumuru","doi":"10.1109/ICIT.2016.055","DOIUrl":"https://doi.org/10.1109/ICIT.2016.055","url":null,"abstract":"Hybrid technique is implemented in this paper to identify the fault location in a 20 KV, 5 km underground cable line with 7.5 MW inductive loads at the delivery end. The projected fault location technique implements properly sampled values of singlecycle post faulty voltage and current signal as of the relayingtermination of the underground cable. Thereafter signaldecomposition has been carried out using wavelet transform toextract a set of statistical features. Further feature extraction is usedto diminish the element of the huge data set. To enhance thecorrectness and reduce the computational burden, feature selection technique (forward feature selection) is implemented where the prime features are collected and the redundant features are removed as ofthe whole feature set. Then the selected features are given to neural network (extreme learning machine) intended for fault position. The performance of the suggested fault location technique is applied a model of transmission and distribution system. It was observed that wavelet transform with extreme learning machine based hybrid technique gives least fault locality error (less than 0.21%) as related with other technique applied by other investigators.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127109819","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":"Multi-bit Data Hiding in Randomly Chosen LSB Layers of an Audio","authors":"B. Datta, P. Pal, S. Bandyopadhyay","doi":"10.1109/ICIT.2016.063","DOIUrl":"https://doi.org/10.1109/ICIT.2016.063","url":null,"abstract":"LSB techniques generally embed data in the same LSB position of consecutive samples which helps intruders to extract secret information easily. This paper solve this problem by introducing a robust audio steganography technique where data is embedded in multiple layers of LSB chosen randomly and in non-consecutive samples. The choice of random LSB layers and non-consecutive pixels for embedding increases robustness as well as the strength of proposed steganography algorithm. It is seriously a problem that the data hiding at non-contiguous sample locations loses the capacity of stego audio. This problem is solved here by embedding three bits within a target samples. The capacity is also increased by using 6 bits ASCII representation of secret message instead of 7. The proposed technique is tested by embedding text of different payloads within the cover audio and also compared with existing techniques based on quality and capacity.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126765546","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}
Kshira Sagar Sahoo, B. Sahoo, Ratnakar Dash, Mayank Tiwary
{"title":"Solving Multi-controller Placement Problem in Software Defined Network","authors":"Kshira Sagar Sahoo, B. Sahoo, Ratnakar Dash, Mayank Tiwary","doi":"10.1109/ICIT.2016.047","DOIUrl":"https://doi.org/10.1109/ICIT.2016.047","url":null,"abstract":"The Software Defined Network (SDN), is the next generation Internet technology, which not only solve the ossification of the Internet, but also creates new innovations and simplify the network management. The key idea behind SDN is separation of control plane from data plane, as a result devices in the data plane becomes the forwarding device and transfer all the decision making activities in a centralized system called a controller. In SDN architecture, it is a great challenge to find a solution to the controller placement problem (CPP). The CPP decides where to place the K number of controllers with a limited amount of resources within the SDN network. Among many proposed solutions to this problem, we apply clustering algorithms such as K-median, K-center on the topology which are obtained from a topology-zoo. A spectral clustering technique has been proposed for partitioning the network and place the controller within the sub-domain. Latency is one of the performance matrices that we have considered in the simulation. The simulation results show that the graph partition method reduces the inter-controller latency within the network.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115385964","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":"Efficient Attribute Revocation Scheme for Multi-authority Attribute Cloud Storage System","authors":"K. Dhal, P. Pattnaik, S. C. Rai","doi":"10.1109/ICIT.2016.049","DOIUrl":"https://doi.org/10.1109/ICIT.2016.049","url":null,"abstract":"Cloud computing is an emerging computing tool in which resources accessed as a service over Internet on pay for use basis. Most of the organization are changing their storage server to cloud server without any botheration. It is a great challenge for the cloud service provider to attract the customers to store their sensitive data/file in the cloud storage. Service provisioning with respect to privacy preservation and data security is an area of concern. In general the cloud servers are being deployed on different trusted domain. Fine grained access control is major area of concern in data outsourcing and sharing in untrusted cloud server. There will be need to encrypt sensitive data and store them in cloud server and disclose decryption key to authorized users. But drawback of this method is that owner of file has to know receivers prior to encryption which is not possible in most of the case. Cipher text Policy Attribute Based Encryption (CPABE) is one of the technique that is used for fine grained access control in untrusted server. This techniques used to keep shared data confidential even if data is stored on remote server. It uses trusted authority to issue attribute and distribute key to users in the system. There can be multiple authority in a CPABE system and each authority issue attributes and keys independent of each other. Efficient decryption and attribute revocation is major area of research in multi authority cloud storage system. Attribute revocation in multi authority cloud storage system should achieve both forward and backward security.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129479661","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":"Enhanced Multicast Routing Protocol in MANET","authors":"Sambhu Dahal, N. Ray","doi":"10.1109/ICIT.2016.015","DOIUrl":"https://doi.org/10.1109/ICIT.2016.015","url":null,"abstract":"In this paper we have proposed an Enhanced MulticastRouting Protocol (EMRP) for MANET. It is based on MAODV. The proposed EMRP is operated in two phase: (i) Route Discovery and Multicast Tree Formation (ii) Multicast Tree Maintenance. EMRP selects the path based on node lifetime and hop count to the destination node. A mechanism is used to reduce the route discovery during link break. A node uses two hop neighbor information to repair the link. The proposed protocol is compared with an existing one. From the simulation results it is observed that the proposed EMRP has higher throughput.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122465166","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":"Clustering of microRNAs Using Rough Hypercuboid Based Fuzzy C-Means","authors":"Partha Garai, P. Maji","doi":"10.1109/ICIT.2016.067","DOIUrl":"https://doi.org/10.1109/ICIT.2016.067","url":null,"abstract":"MicroRNAs form a family of single strand RNA molecules having length of approximately 22 nucleotides that are present in all animals and plants. Various studies have revealed that microRNA tend to cluster on chromosomes. In this regard, a novel clustering algorithm is presented in this paper, integrating rough hypercuboid approach with fuzzy c-means. Using the concept of rough hypercuboid equivalence partition matrix, the lower approximation and boundary region are implicitly computed for the clusters without the need of any user specified threshold. The effectiveness of proposed technique, along with a comparison with existing clustering methods, is presented using some microRNA data sets with the help of several well known cluster validity indices.","PeriodicalId":220153,"journal":{"name":"2016 International Conference on Information Technology (ICIT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124013922","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}