Showing papers in "International Journal of Computer Applications in 2016"

Sentiment Analysis and Opinion Mining: A Survey

Abstract: In this age, in this nation, public sentiment is everything. With it, nothing can fail; against it, nothing can succeed. Whoever molds public sentiment goes deeper than he who enacts statutes, or pronounces judicial decisions (Abraham Lincoln, 1858 ) [1]. It is apparent from President Lincoln's well known quote that legislators understood the force of open assumption quite a while prior. In today world, the Internet is the main source of information. An enormous amount of information and opinion online is scattered and unstructured with no machine to arrange it. Because of demand the public to know opinions about exact product and services, political issues, or social scientists. That’s led us to study of field Opining Mining and Sentiment Analysis. Opining Mining and Sentiment Analysis have recently played a significant role for researchers because analysis of online text is beneficial for the market research political issue, business intelligence, online shopping, and scientific survey from psychological. Sentiment Analysis identifies the polarity of extracted public opinions. This paper presents a survey which covers Opining Mining, Sentiment Analysis, techniques, tools and classification.

Gesture Recognition: A Survey

Abstract: With increasing use of computers in our daily lives, lately there has been a rapid increase in the efforts to develop a better human computer interaction interface. The need of easy to use and advance types of human-computer interaction with natural interfaces is more than ever. In the present framework, the UI (User Interface) of a computer allows user to interact with electronic devices with graphical icons and visual indicators, which is still inconvenient and not suitable for working in virtual environments. An interface which allow user to communicate through gestures is the next step in the direction of advance human computer interface. In the present paper author explore different aspects of gesture recognition techniques.

Sentiment Analysis of Twitter Data: A Survey of Techniques

Abstract: With the advancement of web technology and its growth, there is a huge volume of data present in the web for internet users and a lot of data is generated too. Internet has become a platform for online learning, exchanging ideas and sharing opinions. Social networking sites like Twitter, Facebook, Google+ are rapidly gaining popularity as they allow people to share and express their views about topics, have discussion with different communities, or post messages across the world. There has been lot of work in the field of sentiment analysis of twitter data. This survey focuses mainly on sentiment analysis of twitter data which is helpful to analyze the information in the tweets where opinions are highly unstructured, heterogeneous and are either positive or negative, or neutral in some cases. In this paper, we provide a survey and a comparative analyses of existing techniques for opinion mining like machine learning and lexicon-based approaches, together with evaluation metrics. Using various machine learning algorithms like Naive Bayes, Max Entropy, and Support Vector Machine, we provide research on twitter data streams.We have also discussed general challenges and applications of Sentiment Analysis on Twitter.

Sequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks

Abstract: The aim of this paper is to present a deep neural network architecture and use it in time series weather prediction. It uses multi stacked LSTMs to map sequences of weather values of the same length. The final goal is to produce two types of models per city (for 9 cities in Morocco) to forecast 24 and 72 hours worth of weather data (for Temperature, Humidity and Wind Speed). Approximately 15 years (2000-2015) of hourly meteorological data was used to train the model. The results show that LSTM based neural networks are competitive with the traditional methods and can be considered a better alternative to forecast general weather conditions.

A Survey of Software Clone Detection Techniques

Abstract: If two fragments of source code are identical or similar to each other, they are called code clones. Code clones introduce difficulties in software maintenance and cause bug propagation. Software clones occur due to several reasons such as code reuse by copying pre-existing fragments, coding style, and repeated computation using duplicated functions with slight changes in variables or data structures used. If a code fragment is edited, it will have to be checked against all related code clones to see if they need to be modified as well. Removal, avoidance or refactoring of cloned code are other important issues in software maintenance. However, several research studies have demonstrated that removal or refactoring of cloned code is sometimes harmful. In this study, code clones, common types of clones, phases of clone detection, the state-ofthe-art in code clone detection techniques and tools, and challenges faced by clone detection techniques are discussed.

Clustering Techniques and the Similarity Measures used in Clustering: A Survey

Abstract: Clustering is an unsupervised learning technique which aims at grouping a set of objects into clusters so that objects in the same clusters should be similar as possible, whereas objects in one cluster should be as dissimilar as possible from objects in other clusters. Cluster analysis aims to group a collection of patterns into clusters based on similarity. A typical clustering technique uses a similarity function for comparing various data items. This paper covers the survey of various clustering techniques, the current similarity measures based on distance based clustering, explains the limitations associated with the existing clustering techniques and propose that the combination of the advantages of the existing systems can help overcome the limitations of the existing systems. General Terms Data Mining, Machine Learning, Clustering, Pattern based Similarity, Negative Data, et. al.

Content based Image Retrieval using Color and Texture

Abstract: A Content Based Image Retrieval System is a computer system for browsing, searching and retrieving images from a large database of digital images .Most common methods of image retrieval utilize some method of adding meta data such as captioning, keywords or description to the images so that retrieval can be performed over the annotation words. Content Based Image Retrieval (CBIR) deals with retrieval of images based on visual features such as color, texture and shape. This paper presents retrieval of images based on color and texture using various proposed algorithms.

Donna Interactive Chat-bot acting as a Personal Assistant

Abstract: Chat-bots are computer programs coded to have a textual or verbal conversation which is logical or intelligent. Chat-bots are designed to make humans believe that they are talking to a human; but instead they are in fact talking to a machine. Taking advantage of this transparency property of chat-bot, an artificial character and personality can be given to a chat-bot which acts like a person of a specific profession. This paper describes an approach to the idea of implementing web-based artificially intelligent chat-bot as a personal assistant of the user, which stimulates setting and initiating meetings of user with his clients. The exchange of information happens through email conversations whereas its evaluation happens through natural language procession and natural language generation and AIML files. General Terms AIML, Artificial Intelligence, Pattern Matching.

A Review of some Pure-Pursuit based Path Tracking Techniques for Control of Autonomous Vehicle

Abstract: paper gives a brief review of few common path tracking techniques used in the design of autonomous vehicles. Technique such as pure-pursuit, vector pursuit as well as CF- pursuit which are all based on the pure-pursuit techniques were discussed and a detailed comparism was made between these geometric techniques. Also this review work discusses areas were little research has been done. Areas such as tracking of an implicit part of a mobile robot and proposes an area where feature research can be done such as tracking of both implicit and explicit path for a non-holonomic mobile robot.

Literature Review on Feature Selection Methods for High-Dimensional Data

Abstract: selection is a process of removing the redundant and the irrelevant features from a dataset to improve the performance of the machine learning algorithms. The feature selection is also known as variable selection or attribute selection. The features are also known as variables or attributes. The machine learning algorithms can be roughly classified into two categories one is supervised learning algorithm and another one is unsupervised learning algorithm. The supervised learning algorithms learn the labeled data and construct learning models that are known as classifiers. The classifiers are employed for classification or prediction to identify or predict the class-label of the unlabeled data. The unsupervised learning algorithms lean the unlabeled data and construct the learning models that known as clustering models. The clustering models are employed to cluster or categorize the given data for predicting or identifying their group or cluster. Mostly, the feature selections are employed for the supervised learning algorithms since they suffered by the high-dimensional space. Therefore, this paper presents a complete literature review on various feature selection methods for high-dimensional data.

A Survey on Sentiment Analysis Algorithms for Opinion Mining

Abstract: Opinion mining and sentiment analysis is rapidly growing area. There are numerous e-commerce sites available on internet which provides options to users to give feedback about specific product. These feedbacks are very much helpful to both the individuals, who are willing to buy that product and the organizations. An accurate method for predicting sentiments could enable us, to extract opinions from the internet and predict customer‟s preferences. There are various algorithms available for opinion mining. Before applying any algorithm for polarity detection, pre-processing on feedback is carried out. From these pre-processed reviews opinion words and object on which opinion is generated are extracted and any opinion mining technique is applied to find the polarity of the review. Opinion mining has three levels of granularities: Document level, Sentence level and Aspect level. In this paper various algorithms for sentiment analysis are studied and challenges and applications appear in this field are discussed.

An Intelligent Fire Detection and Mitigation System Safe from Fire (SFF)

Abstract: Safe From Fire (SFF) is an intelligent self controlled smart fire extinguisher system assembled with multiple sensors, actuators and operated by micro-controller unit (MCU). It takes input signals from various sensors placed in different position of the monitored area, and combines integrated fuzzy logic to identify fire breakout locations and severity. Data fusion algorithm facilitates the system to discard deceptive fire situations such as: cigarette smoke, welding etc. During the fire hazard SFF notifies the fire service and others by text messages and telephone calls. Along with ringing fire alarm it announces the fire affected locations and severity. To prevent fire from spreading it breaks electric circuits of the affected area, releases the extinguishing gas pointing to the exact fire locations. This paper presents how this system is built, components, and connection diagram and implementation logic. Overall performance is evaluated through experimental tests by creating real time fire hazard prototype scenarios to investigate reliability. It is observed that SFF system demonstrated its efficiency most of the cases perfectly.

Analysis of Various Sentiment Classification Techniques

Abstract: Sentiment analysis is an ongoing research area in the field of text mining. People post their review in form of unstructured data so opinion extraction provides overall opinion of reviews so it does best job for customer, people, organization etc. The main aim of this paper is to find out approaches that generate output with good accuracy. This paper presents recent updates on papers related to classification of sentiment analysis of implemented various approaches and algorithms. The main contribution of this paper is to give idea about that careful feature selection and existing classification approaches can give better accuracy.

Stop-Word Removal Algorithm and its Implementation for Sanskrit Language

Abstract: In the Information era, optimization of processes for Information Retrieval, Text Summarization, Text and Data Analytic systems becomes utmost important. Therefore in order to achieve accuracy, extraction of redundant words with low or no semantic meaning must be filtered out. Such words are known as stopwords. Stopwords list has been developed for languages like English, Chinese, Arabic, Hindi, etc. Stopword list is also available for Sanskrit language. Stop-word removal is an important preprocessing techniques used in Natural Language processing applications so as to improve the performance of the Information Retrieval System, Text Analytics & Processing System, Text Summarization, Question-Answering system, stemming etc. In this paper, a simple approach is used to design stop-word removal algorithm and its implementation for Sanskrit language. The algorithm and its implementation uses dictionary based approach. In dictionary based approach predefined list of stopwords is compared to the target text on which removal is required.

Heart Disease Prediction System using Data Mining Techniques and Intelligent Fuzzy Approach: A Review

Abstract: The Healthcare trade usually clinical diagnosis is ended typically by doctor’s knowledge and practice. Computer Aided Decision Support System plays a major task in medical field. Data mining provides the methodology and technology to alter these mounds of data into useful information for decision making. By using data mining techniques it takes less time for the prediction of the disease with more accuracy. Among the increasing research on heart disease predicting system, it has happened to significant to categories the research outcomes and gives readers with an outline of the existing heart disease prediction techniques in each category. Data mining tools can answer trade questions that conventionally in use much time overriding to decide. In this paper we study different papers in which one or more algorithms of data mining used for the prediction of heart disease. As of the study it is observed that Fuzzy Intelligent Techniques increase the accuracy of the heart disease prediction system. The generally used techniques for Heart Disease Prediction and their complexities are summarized in this paper.

Detection and Recognition of Diseases from Paddy Plant Leaf Images

Abstract: In agricultural field, paddy cultivation plays a vital role. But their growths are affected by various diseases. There will be decrease in the production, if the diseases are not identified at an early stage. The main goal of this work is to develop an image processing system that can identify and classify the various paddy plant diseases affecting the cultivation of paddy namely brown spot disease, leaf blast disease and bacterial blight disease. This work can be divided into two parts namely, paddy plant disease detection and recognition of paddy plant diseases. In disease detection, the disease affected portion of the paddy plant is first identified using Haar-like features and AdaBoost classifier. The detection accuracy rate is found to be 83.33%. In disease recognition, the paddy plant disease type is recognized using Scale Invariant Feature Transform (SIFT) feature and classifiers namely k-Nearest Neighbour (k-NN) and Support Vector Machine (SVM). By this approach one can detect the disease at an early stage and thus can take necessary steps in time to minimize the loss of production. The disease recognition accuracy rate is 91.10% using SVM and 93.33% using k-NN.

Sentiment Analysis using Support Vector Machine based on Feature Selection and Semantic Analysis

Abstract: Social media is a popular network through which user can share their reviews about various topics, news, products etc. People use internet to access or update reviews so it is necessary to express opinion. Sentiment analysis is to classify these reviews based on its opinion as either positive or negative category. First we have preprocessed the dataset to convert unstructured reviews into structured form. Then we have used lexicon based approach to convert structured review into numerical score value. In lexicon based approach we have preprocessed dataset using feature selection and semantic analysis. Stop word removal, stemming, POS tagging and calculating sentiment score with help of SentiWordNet dictionary have been done in preprocessing part. Then we have applied classification algorithm to classify opinion as either positive or negative. Support vector machine algorithm is used to classify reviews where RBF kernel SVM is modified by its hyper parameters which are soft margin constant C , Gamma γ. So optimized SVM gives good result than SVM and naïve bayes. At last we have compared performance of all classifier with respect to accuracy.

An Overview of Various Template Matching Methodologies in Image Processing

Abstract: The recognition and classification of objects in images is a emerging trend within the discipline of computer vision community. A general image processing problem is to decide the vicinity of an object by means of a template once the scale and rotation of the true target are unknown. Template is primarily a sub-part of an object that‟s to be matched amongst entirely different objects. The techniques of template matching are flexible and generally easy to make use of, that makes it one amongst the most famous strategies of object localization. Template matching is carried out in versatile fields like image processing,signal processing, video compression and pattern recognition.This paper gives brief description of applications and methods where template matching methods were used. General Terms Template matching,computer vision,image processing,object recognition.

Gain and Bandwidth Enhancement Techniques in Microstrip Patch Antennas - A Review

Abstract: Today antenna designers are paying more focus on microstrip patch antennas, because of its numerous advantages in field of communication, such as high reliability, light weight, ease of fabrication etc. But despite of its bountiful advantages, patch antennas also experience some drawbacks viz low gain and narrow bandwidth. These drawbacks can be overcome by taking care of some parameters in the design of antennas. There are numerous designing factors affecting the radiating characteristics of antenna such as patch height, feeding techniques, substrate used in manufacturing of antenna etc. The paper is focused on various bandwidth enhancement techniques. The paper comprises of a brief study in feeding techniques, parasitic patch elements, introduction of slots, dual feed, shorting pin, air gap and recently introduced concept of defective ground structure that enhances the gain and bandwidth of antenna without increasing its height.

MoodyPlayer: A Mood based Music Player

Abstract: Increasing and maintaining human productivity of different tasks in stressful environment is a challenge. Music is a vital mood controller and helps in improving the mood and state of the person which in turn will act as a catalyst to increase productivity. Continuous music play requires creating and managing personalized song playlist which is a time consuming task. It would be very helpful if the music player itself selects a song according to the current mood of the user. The mood of the user can be detected by a facial expression of the person. A facial expression detection system should address three major problems: detection of face from an image, facial feature extraction and facial expression classification[1].The first stage is of face detection from an image for which various techniques used are model based face tracking which includes real-time face detection using edge orientation matching [2], Robust face detection using Hausdorff distance [3], weak classifier cascade which includes Viola and Jones algorithm [4], and Histograms of Oriented Gradients (HOG) descriptors. The next stage is to extract features from detected face. Two major approaches for feature extraction which use Gabor filters [Dennis Gabor] and Principle Component Analysis [Jolliffe]. The final stage is of image classification for mood detection, where various classifiers like BrownBoost [Freund, 2001], AdaBoost [Freund and Schapire, 1995] and Support Vector Machines (SVM) are available. The proposed system will use classic Histograms of Oriented Gradients (HOG) along with facial landmark detection technique; these detected features then passed through SVM classifier to predict the mood of the user. This predicted mood will stimulate the creation of playlist. General Terms Pattern Recognition, Image Classification, Pattern Matching, Emotion Recognition,

Survey of Named Entity Recognition Systems with respect to Indian and Foreign Languages

Abstract: Named Entity Recognition (NER) is sub task of Information Extraction that includes identification of named entities and classification of them into named entity classes such as person, location and organization etc. NER can be used to preprocess textual information and convert it into structured form that can be useful for Information Retrieval, Machine Translation, Question Answering System and Text Summarization. This paper presents a survey regarding NER research done for various Indian and non Indian languages. The study and observations related to approaches, techniques and features required to implement NER for various languages especially for Indian languages is reported. General Terms NER (Named Entity Recognition), HMM (Hidden Markov Model), CRF (Conditional Random Fields), SVM (Support Vector Machine)

Enabling Cloud Storage Auditing with Key Exposure Resistance

Abstract: Cloud storage auditing is viewed as an imperative service to corroborate the veracity of the data in public cloud. Existing auditing protocols are all based on the supposition that theClient’s secret key for auditing is completely protected. Such assumption may not always be held, due to the probably weak sense of security and/or low security settings at the client. In most of the current auditing protocols would inevitably become unable to work when a secret key for auditing is exposed. It is investigated on how to reduce the damage of the client’s key revelation in cloud storage auditing, and provide the first handy elucidation for this new problem setting. Formalized the definition and the security model of auditing protocol with key-exposure resilience and propose such a protocol. Utilized and developed a novel authenticator construction to support the forward security and the property of block less verifiability using the current design. The security proof and the performance analysis show that the projected protocol is protected and well-organized.

Smart Parking System Based on Embedded System and Sensor Network

Abstract: Locating a parking space in central city areas, especially during the peak hours, is cumbersome for drivers. The issue arises from not having the knowledge of where the available spaces may be at the time, even if known, many vehicles may seek very limited parking spaces to cause severe traffic congestion. In this paper the design and implementation with a prototype of Reservation-based Smart Parking System (RSPS) that permits drivers to effectively locate and withhold the vacant parking spaces in mentioned. This system use cluster based algorithm which helps in periodically learning the parking status from the sensor networks deployed in parking spaces, the reservation service is influenced by the change of parking status. The drivers are allowed to access this said cyber-physical system with their personal communication devices. The system implemented is cost efficient smart parking system for multi-level parking facility using WSN (IR Sensor) and develop an android based application, by cluster based allocation method and performs automatic billing process. The system monitors the availability of idle parking slots and guides the vehicle to the nearest free slot. Cost is minimized by keeping the number of sensors low without sacrificing the reliability. Energy consumption of each mote is kept in check by allowing the systems to sleep periodically and by reducing their communication range. This system‟s reservation-based parking policy has the potential to smoothen the operations of parking systems, as well as mitigate traffic congestion caused by searching for parking.

Brain Tumor Segmentation

Abstract: Tumor is an uncontrolled growth of tissues in any part of the body. Tumors are of different types and they have different characteristics and different treatment. As it is known, brain tumor is inherently serious and life threatening. Brain tumor analysis is done by doctors but its grading gives different conclusion which may vary from one doctor to another. However this method of detection resists the accurate determination of size of tumor. To avoid that, uses computer aided method for segmentation of brain tumor based on the combination of three algorithms. This algorithm allows the segmentation of tumor tissue with accuracy comparable to manual segmentation. It also reduces time analysis. At the end of the process the tumor is extracted for MR image and its exact position and its shape is also determined.

Smart Precision based Agriculture using Sensors

Abstract: Smart precision based agriculture makes use of wireless sensor networks to monitor the agricultural environment. Zigbee and raspberry pi-based agriculture monitoring system serves as a reliable and efficient method for monitoring agricultural parameters. Wireless monitoring of field not only allows user to reduce the human power, but it also allows user to see accurate changes in it. It focuses on developing devices and tools to manage, display and alert the users using the advantages of a wireless sensor network system. A smart system based on precision agriculture would pave the way to a new revolution in agriculture. The user can monitor the agriculture environment from a remote location, thus providing a greenhouse condition for the plants. India being an agro based economy; precision agriculture can bring about an improvement in the primitive methods, thus developing the country stature hugely. General Terms Sensor networks, smart agriculture.

Various Image Compression Techniques: Lossy and Lossless

Abstract: Image compression is an implementation of the data compression which encodes actual image with some bits. Thepurpose of the image compression is to decrease the redundancy and irrelevance of image data to be capable to record or send data in an effective form. Hence the image compression decreases the time of transmit in the network and raises the transmission speed. In Lossless technique of image compression, no data get lost while doing the compression. To solve these types of issues various techniques for the image compression are used. Now questions like how to do mage compression and second one is which types of technology is used, may be arises. For this reason commonly two types’ of approaches are explained called as lossless and the lossy image compression approaches. These techniques are easy in their applications and consume very little memory. An algorithm has also been introduced and applied to compress images and to decompress them back, by using the Huffman encoding techniques.

Vehicle Number Plate Recognition System: A Literature Review and Implementation using Template Matching

Abstract: growing affluence of urban India has made the ownership of vehicles a necessity. This has resulted in an unexpected civic problem - that of traffic control and vehicle identification. Parking areas have become overstressed due to the growing numbers of vehicles on the roads today. The Automatic Number Plate Recognition System (ANPR) plays an important role in addressing these issues as its application ranges from parking admission to monitoring urban traffic and to tracking automobile thefts. There are numerous ANPR systems available today which are based on different methodologies. In this paper, we attempt to review the various techniques and their usage. The ANPR system has been implemented using template Matching and its accuracy was found to be 80.8% for Indian number plates.

A Hybrid Flower Pollination Algorithm for Engineering Optimization Problems

Abstract: pollination algorithm (FP) is a new nature-inspired algorithm, based on the characteristics of flowering plants. Combining with the features of flower pollination algorithm, an improved simulated annealing algorithm is proposed in this paper (FPSA). It can improve the speed of annealing. The initial state of simulated annealing and new solutions are generated by flower pollination. Therefore, it has the advantage of high quality and efficiency. The method combines the standard flower pollination algorithm (FP) with simulated annealing to enhance the search performance and speeds up the global convergence rate. Structural engineering optimization problems are presented to demonstrate the effectiveness and robustness of the proposed algorithm. The experimental results showed that the accuracy of finding the best solution and convergence speed performance of the proposed algorithm is competitive to those achieved by the

Weighted Naive Bayes Classifier: A Predictive Model for Breast Cancer Detection

Abstract: this paper investigation of the performance criterion of a machine learning tool, Naive Bayes Classifier with a new weighted approach in classifying breast cancer is done . Naive Bayes is one of the most effective classification algorithms. In many decision making system, ranking performance is an interesting and desirable concept than just classification. So to extend traditional Naive Bayes, and to improve its performance, weighted concept is incorporated. Exploration of Domain knowledge based weight assignment on UCI machine learning repository dataset of breast cancer is performed. As Breast cancer is considered to be second leading cause of death in women today. The experiments show that a weighted naive bayes approach outperforms naive bayes. KeywordsMining, Breast cancer, Naive bayes classifier, Domain based weight, Weights, Posterior probability, UCI machine learning repository, Prediction.