{"title":"Sentiment Analysis of Yelp Reviews by Machine Learning","authors":"H. S., Ramathmika Ramathmika","doi":"10.1109/ICCS45141.2019.9065812","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065812","url":null,"abstract":"Sentiment analysis is a process of analyzing a piece of text written by a writer to identify and classify the opinions buried in that text and to determine whether the views of the writer about the topic is positive, negative, or neutral. Yelp is a review forum which provides reviews on local businesses. Users from anywhere in the world can post reviews and rate any business in this social networking site. In this paper, the textual yelp reviews of businesses are analyzed to assign a probability for the review as having positive or negative sentiment. The data considered for the sentiment analysis are the reviews on restaurants about food, service, price and ambience. Machine learning algorithms in the nltk library of python can prove to be very useful in any such research on Natural Language Processing and the library has been used extensively in this work. Each algorithm used has been analyzed and has been compared on the basis of their efficiency (confidence).","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"509 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115471283","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}
B. Shabarinath, K. Challagulla, Majety Ramsankar Visodhan
{"title":"A Comparative Study of Epileptic Seizure Detection Framework using SVM and ELM","authors":"B. Shabarinath, K. Challagulla, Majety Ramsankar Visodhan","doi":"10.1109/ICCS45141.2019.9065458","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065458","url":null,"abstract":"Poverty and lack of health awareness are major reasons for illnesses, particularly neurology-related problems in India. Epilepsy is one such problem that affects the brain by causing seizures termed as epileptic seizures. People in rural areas believe epileptic attacks to be results of influence of black magic and resorted to unscientific practices for treatment. Repeated occurrence of seizures could lead to death. The early detection and treatment would cure 70 percent of the cases. The study of the epileptic activity can be done using EEG recordings of the brain. Although many software packages offers complete tool set for complex EEG analysis which is not as candid compared to brain-imaging techniques user need to choose appropriate framework suitable for their application scenario. In this paper we propose four different combination of feature extraction and classification techniques for detecting epileptic seizures and this study aims to compare the results in context of accuracy. The combination of discrete wavelet transform for feature extraction and early learning machine algorithm for classifications generates 90.1% accuracy in classifying epileptic seizures. Also this framework reduces computation time by selection of proper EEG channel data by preprocessing which helps to develop an expert system which emulates the decision making of a human expert.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117115180","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":"Internet Traffic Detection using Naïve Bayes and K-Nearest Neighbors (KNN) algorithm","authors":"M. Dixit, R. Sharma, Saniya Shaikh, Krutika Muley","doi":"10.1109/ICCS45141.2019.9065655","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065655","url":null,"abstract":"Growth of internet has led to rise in number of users and its usage. Despite its advantages, exponential rise in internet usage has resulted in excess data flow over the system flooding the internet. To maintain quality of service and speed of internet along with ensuring data security as well as preventing data misuse, analysis of the internet data becomes essential. Analysis of the dataflow involves characterizing it into different types. This can be done by inspecting the packets either on basis of port numbers, payload information or statistical features. This paper aims to discuss the analysis of internet traffic using statistical features such as interpacket arrival time, time to live and number of packets helping us prevent invasion of packet information. This helps us protect user’s privacy. To automate the process of categorizing internet traffic, machine learning based supervised classification techniques namely Naive Bayes and K Nearest Neighbors are implemented. Experiments to obtain highest accuracy in classifying internet traffic on basis of transaction protocol were performed. The dataset used is UNSW-NB. The results show that classification using K-Nearest Neighbors algorithm gives accuracy of 85% whereas maximum accuracy achieved using Naïve Bayes algorithm is 54%.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"48 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120887195","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}
Anshuman Panda, Animesh Das, S. S. Pati, Saroj Kumar Mishra
{"title":"A PSO Based PIDF Controller for Multiarea Multisource System Incorporating Dish Stirling Solar System","authors":"Anshuman Panda, Animesh Das, S. S. Pati, Saroj Kumar Mishra","doi":"10.1109/ICCS45141.2019.9065804","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065804","url":null,"abstract":"The comprehensive evaluation of Automatic Generation Control (AGC) scheme is performed for a multi-area multisource model with implementation of a proportional integral derivative controller with derivative Filter (PIDF). Optimal parameters of the controller are extracted by applying stochastic population motivated Particle Swarm Optimization (PSO) technique. The study of Dish Stirling Solar Thermal System (DSTS) is utilized in the proposed three area system which highlights the significance of renewable energy in the AGC scheme. Appropriate generation rate constraints are considered for thermal and hydro plants. Better tie line power on load perturbation and dynamic response of frequency is achieved with PIDF by regulating the real power output of the generators. Various conventional controllers like proportional integral (PI) and proportional integral derivative (PID) are employed in the multi-area system and the performances are compared to the output of the designed PIDF controller.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121093983","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":"Energy Efficient Routing HART Protocol in Soil Nutrition Analysis for Agriculture","authors":"Ayushi Singh, Abhishek Mishra, M. Ahmed","doi":"10.1109/ICCS45141.2019.9065827","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065827","url":null,"abstract":"Wireless communications energy consumption model reveals that the energy consumed by the sensor nodes is directly dependent on the communication distance. The basic requirement is to reduce the energy consumption of the various sensor nodes in the networks. The concept of highway addressable remote transducer (HART) protocol is introduced by hierarchical a routing protocol that helps to simplify the network in the case of large scale sensor networks. Many types of sensor network to use the soil nutrition analysis for agriculture field. In this paper the introduced to HART protocol used to soil nutrition analysis and calculated different parameter. Using the protocol concept in wireless Sensor networks enhances scalability and reliability of the sensor networks and provides an efficient method for prolonging the network lifetime of sensor nodes. The HART protocol is improvement of some parameter i.e. packet delivery ratio, throughput and delay for wireless sensor network.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125036562","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":"Comprehensive study of Multi heuristic image segmentation techniques","authors":"Gurbakash Phonsa, R. Ruchi","doi":"10.1109/ICCS45141.2019.9065826","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065826","url":null,"abstract":"Image segmentation is the process in which image is partitioned into multiple regions which results into number of fragments of objects. The main purpose of image segmentation is to make modifications and simplifications in an image to make it more clear and meaningful. The main feature of segmentation is to find boundaries and objects in an image .Resultant of image segmentation composed of multiple regions that entitrely cover the whole image. Pixels in a common area are alike to each other on the basis of some computed property such as color, texture.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125940011","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":"Design and Verification of DDR SDRAM Memory Controller Using SystemVerilog For Higher Coverage","authors":"P. M P, S. Panda","doi":"10.1109/ICCS45141.2019.9065407","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065407","url":null,"abstract":"In present electronic systems, DDR SDRAM (Double Data Rate Synchronous Dynamic Random-AccessMemory) is an next level advanced version of regular SDRAM, and it was developed with advanced key features such as effective use of memory bandwidth and its capability to transact data on both edges of clock cycles. DDR SDRAM is widely used in computer applications like laptops, DSP processing systems and networking. Cost and speed are the two important factors in designing memories like DDR SDRAM which will meet the standards in the field of DSP applications. Because of its high speed, burst access and pipeline feature DDR SDRAM becomes more popular. The main basic operations of DDR SDRAM memory controller are very much common to that of SDR (Single Data Rate) SDRAM memory controller and they differ only in their circuit design. DDR simply use sophisticated circuit techniques to achieve high speed in order to perform a greater number of operations per clock cycles. DDR SDRAM uses double data rate architecture wherein DDR SDRAM (also known DDR1) means transaction of data on both the rising and falling edge of the clock cycles. The DDR SDRAM controller makes many lowlevel tasks invisible to the user like refresh, initialization and timings. DDR SDRAM also designed with objective of using proper commands like Read/Write accesses, proper active and pre-charge command etc. In this work a DDR SDRAM controller is designed using Verilog HDL and Verification is carried out using SystemVerilog by Questasim Tool. Functional coverage of 100% is achieved by applying randomized test cases.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126799830","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}
Chitra Prasad, V. K. Balakandan, Pranav Moorthy V, Sreeja Kochuvila
{"title":"Classification of sEMG Signals for Controlling of a Prosthetic foot using SVM and KNN","authors":"Chitra Prasad, V. K. Balakandan, Pranav Moorthy V, Sreeja Kochuvila","doi":"10.1109/ICCS45141.2019.9065394","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065394","url":null,"abstract":"Prosthesis plays an important role in rehabilitation. Majority of the powered prosthetic foot available for Trans-tibial amputees (TTA) today take the signal for the control action of the prosthetic foot from the residual stump. Bio-signals from the Biceps Femoris muscle of the thigh is found to be more stable as compared to signals from other thigh muscles and is found to have a reduced metabolic rate during the gait cycle.This study is done on the surface EMG signal measurements of 20 healthy subjects obtained using muscle sensor and conclusions as to which feature extraction technique of the EMG signal is accurate to classify 1-Degree of Freedom (DoF) — dorsiflexion and plantar flexion are derived using weighted KNN and Linear SVM classifier. The comparison of the accuracy of the two classifiers showed that weighted KNN has better efficiency","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116565504","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}
B. Pathak, Deepti R. Patil, Shweta More, Nikita R. Mhetre
{"title":"Comparison between five classification techniques for classifying emotions in human speech","authors":"B. Pathak, Deepti R. Patil, Shweta More, Nikita R. Mhetre","doi":"10.1109/ICCS45141.2019.9065620","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065620","url":null,"abstract":"This paper presents an algorithm for recognition of emotions in speech by extracting features such as formants, Perceptual Linear Prediction coefficients, Mel-Frequency Cepstral Coefficients, Bark Frequency Cepstral Coefficients, energy, pitch and standard deviation. The classifiers implemented are K-Nearest Neighbors (KNN), Linear Support Vector Machine (SVM), Quadratic SVM, Bagged Tree Ensemble and Quadratic discriminant. The paper presents a comparative study on the different classification techniques that can be used to distinguish between various emotions present in human speech. A comparison in terms of testing accuracy obtained using these classifiers has been performed in this paper on a database created for 4 emotions viz. anger, joy, sorrow and neutral in Marathi language.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122688577","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}
Saket Kumar Ojha, Kasiviswanath Challa, Madhu Kiran Vemuri, Naga Sri Vardhan Yarlagadda, B. P. Phaneendra Kumar
{"title":"Land Use Prediction on Satillite images using Deep Neural Nets","authors":"Saket Kumar Ojha, Kasiviswanath Challa, Madhu Kiran Vemuri, Naga Sri Vardhan Yarlagadda, B. P. Phaneendra Kumar","doi":"10.1109/ICCS45141.2019.9065698","DOIUrl":"https://doi.org/10.1109/ICCS45141.2019.9065698","url":null,"abstract":"Land is an important natural resource for any species as life and developmental activities depend upon it. Land use and land cover are important aspect of information for land resource management. Using land use and land cover information helps in better management of land resource and it also makes us to understand the relationships and interactions between the human and natural phenomena. So, using satellite images of earth surface and apply concepts of deep learning to identify land use, which class the land belongs to.","PeriodicalId":433980,"journal":{"name":"2019 International Conference on Intelligent Computing and Control Systems (ICCS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114412512","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}