International Conference

Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/151

Browse

Now showing 1 - 20 of 20

BIOMETRICS STANDARDS AND STANDARDIZATION
(PSGR Krishnammal College for Women, Coimbatore, 2014-01) Selvanayaki M; FemithaParveen M
Prevailing methods of human identification based on credentials (identification documents and PIN) are not able to meet the growing demands for stringent security in applications such as national ID cards, border crossings, government benefits, and access control. As a result, biometric recognition, or simply biometrics, which is based on physiological and behavioral characteristics of a person, is being increasingly adopted and mapped to rapidly growing person identification applications. Unlike credentials (documents and PIN), biometric traits (e.g., fingerprint, face, and iris) cannot be lost, stolen, or easily forged; they are also considered to be persistent and unique. These requirements are typically specified in terms of identification accuracy, throughput, user acceptance, system security, robustness, and return on investment.
PRIVACY RISK IN RECOMMENDED SYSTEM
(PSGR Krishnammal College for Women, 2014-01-09) K, Geethalakshmi; R, Divya
In many on-line applications, the range of content that is offered to users is so wide that a requirement for automatic recommender systems arises. Such systems will give a personalized selection of relevant things to users. In practice, this may facilitate people realize fun movies, boost sales through targeted advertisements, or facilitate social network users meet new friends. To produce correct personalized recommendations, recommender systems depend on detailed personal information on the preferences of users. Ratings, consumption histories and personal profiles are examples. Recommender systems are useful, but the privacy risks associated in aggregation and process personal information are typically underestimated or neglected. Many users are not sufficiently aware if and the way a lot of their information is collected, if such information is sold-out to third parties or how securely it is saved and for how long. This paper aims to provide insight into privacy in recommender systems. First, we shall discuss different varieties of existing recommender systems. Second, an overview of the data that is employed in recommender systems is given. Third, I analyze the associated risks to information privacy. Finally, relevant research areas for privacy-protection techniques and their relevancy to recommender systems are mentioned.
SURVEY ON MANET ROUTING PROTOCOLS FOR SECURED DATA TRANSMISSION
(Sri Ramakrishna College of Arts and Science, 2017) A, Kavitha; V S, Meenakshi
MANET is a Ad Hoc network in which a large number of nodes are connected wirelessly. It is used in different areas like military, disaster recovery etc. The nodes present in this network are openness and decentralized. MANET is frequently changing its topologies to transfer the data quickly, because nodes in this network are moving always (mobility) and data transfer has been done by finding the efficient routing path between source and destination. Due to the mobility there is a lot of chance to involve malicious node and the network will become more vulnerable to attacks like gray hole and black hole attack etc. These types of attacks affect the MANET routing path and it hence it is necessary to secure routing. To overcome the security problem, single or multilayer security algorithm is needed to link with protocol. In this paper, a survey is made of various kinds of existing protocols and algorithms involved are discussed.
STUDY ON MACHINE LEARNING TECHNIQUES USING SVM
(Pioneer College of Arts and Science, Coimbatore, 2017-01-06) Selvanayaki M; Anushya Devi T S
Machine Learning is the study of computer algorithms that improve automatically through experience. Applications range from data mining programs that discover general rules in large data sets, to information filtering systems that automatically learn user’s interests. An important task of machine learning is classification, also referred as pattern recognition; where one attempts to build algorithms capable of automatically constructing methods for distinguish between different exemplars. This paper deals about different machine learning techniques for the prediction process.
IMAGE PROCESSING TECHNIQUES
(Dr.N.G.P Arts and Science College, 2017-02-24) K, Geethalakshmi; A, Shivyaa
Digital Image Processing is always an interesting field as it gives improved pictorial information for human interpretation & processing of image data for storage, transmission and representation for machine perception. Image processing is a technique to enhance raw images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-ay life for various applications. This field of image processing significantly improved in recent times and extended to various fields of science & technology. The Image Processing mainly deals with image acquisition, Image Enhancement, Image Segmentation, Feature Extraction, and Image Classification. A number of Image Processing techniques, in addition to enhancement techniques can be applied to improve the data usefulness. Techniques include convolution edge detection, mathematics, filters, trend removal & image analysis. The various image enhancements and image processing techniques will be discussed in this paper.
IMAGE MINING AND TECHNOLOGY CAPABILITIES
(PSG College of Arts and Science, 2017-02-24) Geethalakshmi K; Sri priyanka
In the area of data mining, Image mining technology has been considered on advanced field for discovering information related to the images. Image mining is the processing and discovering valuable information and knowledge in large volume of data. Image mining draws basic principles from concepts in databases, machine learning, statistics, pattern recognition and soft computing. All techniques and process used for automated analysis of image content on the internet for marketing and advertising purpose. There are many techniques developed in the earlier researches and eventually these techniques can reveal useful information according to the human requirements but image mining still requires more development especially in the area of web images. Image mining is focused on extracting patterns, implicit knowledge, image data relationship or patterns which are not explicitly found in the image from databases or collections of images some of the methods used to gather knowledge are: image retrieval, data mining, image processing and artificial intelligence. This paper presents study on various image mining technology. It also provides an improvement for future research.
STUDY ON IMAGE PROCESSING AND SEGMENTATION TECHNIQUES
(St.Aloysius College, 2017-11-16) K, Geethalakshmi
Digital Image Processing is always an interesting field as it gives improved pictorial information for human interpretation & processing of image data for storage, transmission and representation for machine perception. Image processing is a technique to enhance raw images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-ay life for various applications. This field of image processing significantly improved in recent times and extended to various fields of science & technology. The Image Processing mainly deals with image acquisition, Image Enhancement, Image Segmentation, Feature Extraction, and Image Classification. A number of Image Processing techniques, in addition to enhancement techniques can be applied to improve the data usefulness. Techniques include convolution edge detection, mathematics, filters, trend removal & image analysis. The various image enhancements and image processing techniques will be discussed in this paper.
BIG DATA
(Sri Sankara Arts and Science College, 2018) T, Saranya; D, Nivetha
Big data is a term applied to data sets whose size or type is beyond the ability of traditional relational databases to capture, manage, and process the data with low-latency. And it has one or more of the following characteristics – high volume, high velocity, or high variety. Big data comes from sensors, devices, video/audio, networks, log files, transactional applications, web, and social media - much of it generated in real time and in a very large scale.
AN ANALYSIS OF DEEP LEARNING APPROACH IN WIRELESS NETWORK
(KSG College of Arts and Science, 2018) A, Kavitha; L, Sheeba
Intrusion detection has attracted a considerable interest from researchers and industries. The community, after many years of research, still faces the problem of building reliable and efficient IDS that are capable of handling large quantities of data, with changing patterns in real time situations. The work presented in this manuscript classifies intrusion detection systems (IDS). Moreover, a taxonomy and survey of shallow and deep networks intrusion detection systems is presented based on previous and current works. This taxonomy and survey reviews machine learning techniques and their performance in detecting anomalies. Feature selection which influences the effectiveness of machine learning (ML) IDS is discussed to explain the role of feature selection in the classification and training phase of ML IDS.. Deep learning, as one of the most currently remarkable machine learning techniques, has achieved great success in many applications such as image analysis, speech recognition and text understanding. It uses supervised and unsupervised strategies to learn multi-level representations and features in hierarchical architectures for the tasks of classification and pattern recognition. In this paper, we review the emerging researches of deep learning models for NIDS feature learning. Furthermore, we point out the remaining challenges of Intrusion detection system deep learning and discuss the future topics.
ANALYSIS ON ARTIFICIAL NEURAL NETWORK AND ITS APPLICATIONS
(PKR Arts College for Women, 2018-08) Selvanayaki M; MohanaPriya S
Network is an approach of gathering simple elements to produce complex system. There are a large number of different types of networks, but they all are characterized by the following components: a set of nodes, and connections between nodes. The nodes can be seen as computational units. They receive inputs, and process them to obtain an output. This processing might be very simple (such as summing the inputs), or quite complex (a node might contain another network). The connections determine the information flow between nodes. They can be unidirectional, when the information flows only in one sense, and bidirectional, when the information flows in either sense. The interactions of nodes though the connections lead to a global behavior of the network, which cannot be observed in the elements of the network. This means that the abilities of the network supercede the ones of its elements, making networks a very powerful tool.
ANALYSIS ON ARTIFICIAL NEURAL NETWORK AND ITS APPLICATIONS
(PKR Arts College for Women, 2018-08) Selvanayaki M; Mohanapriya S
Network is an approach of gathering simple elements to produce complex system. There are a large number of different types of networks, but they all are characterized by the following components: a set of nodes, and connections between nodes. The nodes can be seen as computational units. They receive inputs, and process them to obtain an output. This processing might be very simple (such as summing the inputs), or quite complex (a node might contain another network). The connections determine the information flow between nodes. They can be unidirectional, when the information flows only in one sense, and bidirectional, when the information flows in either sense. The interactions of nodes though the connections lead to a global behavior of the network, which cannot be observed in the elements of the network. This means that the abilities of the network supercede the ones of its elements, making networks a very powerful tool.
A REVIEW ON CONTENT BASED IMAGE RETRIEVAL SYSTEM TECHNIQUES
(PKR Arts College for Women, 2018-08-16) K, Geethalakshmi
A database is a collection of information that is structured for easy storage, retrieval and update. This information is represented in many forms like text, table, image, chart and graph etc. Content Based Image Retrieval (CBIR) technique explores various methodologies in extracting implicit knowledge, patterns and relationships found in the images from the collection of images. As the network and development of multimedia technologies are becoming more popular, users are not satisfied with the traditional information retrieval techniques. Nowadays the content based image retrieval (CBIR) are becoming a source of exact and fast retrieval. This paper focuses on the overview of CBIR and various techniques that were proposed in earlier literature.
A STUDY ON DATA MINING TOOLS AND TECHNIQUES
(PKR Arts College for Women, 2018-08-16) T S, Anushya Devi
Information Technology has a positive impact on other disciplines. Using today's technology, Agriculture and Information Technology are integrated with each other. Use of IT in agriculture will lead to improvements in productivity. For this purpose, the raw data is transformed into useful information through data mining. The analysis of these agricultural data base with different data mining methods may have some advantages in agriculture. Data mining software application includes various methodologies that have been developed by both commercial and research center. These techniques have been used for industrial, commercial and, scientific purpose. For example data mining has been used to analyze large datasets and established useful classification and patterns in the data sets. Agriculture and Biological research studies have been used for various techniques of data analysis including, natural trees, statistical machine learning in other analysis methods. Data Mining Techniques have led over various methods to gain knowledge from vast amount of data. There are the various research tools available for the large amount of data. Data mining has more technique to analyze the large amount of data like various classification algorithms. There are various data mining research tools available for analysing the large amount of data. Data Mining tools like WEKA and various data mining classification algorithms like Bayesian classification Algorithm, Rule based classification and classification by Decision tree.
A SURVEY ON DEEP LEARNING APPROACHES IN RETINAL VESSEL SEGMENTATION FOR DISEASE IDENTIFICATION
(Sankara College of Science and Commerce, 2018-10-10) K, Geethalakshmi
Human retinal image plays a vital role in detection and diagnosis of various eye diseases for ophthalmologist. Automated blood vessel segmentation diagnoses many eye diseases like diabetic retinopathy, hypertension retinopathy, retinopathy of prematurity or glaucoma based on the feature extraction. Automated image analysis tool based on machine learning algorithms are the key point to improve the quality of image analysis. Deep learning (DL) is a subset of machine learning which is completely based on artificial neural network. It helps a machine to analyze the data efficiently. Deep learning is one extensively applied techniques that provides state of the art accuracy. Different types of neural network and platform used for DL also discussed. This paper reviews the different DL approaches for blood vessels segmentation. It concludes that the deep learning methods produces high level of accuracy in disease identification
ESTABLISHING THE EFFICIENCY OF ALGORITHMS IN DATA MINING FOR USERS
(NPR Arts and Science College, 2018-12-28) S, Kavitha; K, Sarojini
Data mining has successfully yielded a large number of tools, different methods, various algorithms and a range of approaches for handling large amounts of data for various problem solving. Data mining has become the essential part of many areas such as business intelligence, decision support systems, data warehousing, bio-informatics, predictive analytics etc,. The main of objective is to effectively handle large scale data, extract patterns, and gain intuitive knowledge. Knowledge discovery in databases includes Data Mining as main part. This paper presents comparisons of various algorithms necessary for handling large data sets. A vast range of structures and methods applied to manipulate big data are defined. This review discusses about the process of the algorithm, its advantages and disadvantages. This paper evaluates the efficiency of certain algorithms that the data mining users can select and apply on which algorithm that they will be searching for problem solving. The main aim of this paper is to provide the users with a review about the algorithms for data mining.
DEFENDING AGAINST COLLABORATIVE ATTACKS BY MALICIOUS NODES IN MANETS: A COOPERATIVE BAIT DETECTION APPROACH
(KSG college of Arts and Science, 2019) A, Kavitha
A Mobile Adhoc NETwork (MANET) is a type of ad hoc network that can change locations and configure itself on the fly. Because MANETS are mobile, they use wireless connections to connect to various networks. However the flexibility of these characteristic creates the security threats. Security is an important issue for mobile ad hoc networks, due to the vulnerable nature of MANETs. This flexibility comes at a price and introduces new security threats. Furthermore, many conventional security solutions used for wired networks are ineffective and inefficient for the highly dynamic and resource-constrained environments where MANET use might be expected. To develop suitable security solutions for such new environments, must first understand how MANETs can be attacked. The nodes in the network can be easily affected by collaborative attacks such as blackhole attack, grayhole attack and jellyfish attacks. A cooperative bait detection approach is proposed against the collaborative attacks. The comparison was made between the different techniques that have been listed. The performance evaluation conducted was proved that the each and every method has unique advantage and disadvantages among each other.
KNOWLEDGE DISCOVERY AND DATA MANAGEMENT USING GENERIC ALGORITHMS
(Sri Ramakrishna College of Arts and Science for Women, 2019-01) T, Saranya; D, Nivetha
The term Knowledge Discovery in Databases, or KDD for short, refers to the broad process of finding knowledge in data, and emphasizes the "high-level" application of particular data mining methods. It is of interest to researchers in machine learning pattern recognition, databases, statistics,artificial intelligence, knowledge acquisition for expert systems, and data visualization. The unifying goal of the KDD process is to extract knowledge from data in the context of large databases. It does this by using data mining methods (algorithms) to extract (identify) what is deemed knowledge, according to the specifications of measures and thresholds, using a database along with any required pre-processing, sub sampling, and transformations of that database.
A REVIEW ON DIFFERENT CLUSTERING ALGORITHM FOR CANCER DATA ANALYSIS
(K.S.G College of Arts and Science, 2019-09-20) S, Kavitha; G, Sangeetha
In recent years DM has attracted great attention in the healthcare industry and society as a whole. The objective of this research work is focused on the cluster creation of two cacancer dataset and analyzed the performance of partition based algorithms. The three tytypes of partition based algorithms namely Global kMeans, Kmeans Plus and Affinithy Prpropagation are implemented. Comparative analysis of clustering algorithms is also cacarried out using two different dataset Colon and Leukemia. The performance of a algorithms depends on the Correctly classified clusters and the Average accuracy of data. The Affinity Propagation algorithm is efficient for clustering the cancer dataset. The final outcome of this work is suitable to analyses the behavior of cancer in the department of oncology in cancer centers. Ultimate goal of this research work is to find out which type of dadataset and algorithm will be most suitable for analysis of cancer data.
SMART HOSPITAL MANAGEMENT USING IOT
(Sri Ramakrishna College of Arts and Science for Women, 2020-02-29) Kavitha S
A worldwide network of Internet of Things (IOT) is going to be the future network, which connects objects of different application fields, functionality and technology. These objects are uniquely addressable and use standard communication protocol and communicate in a heterogeneous networking environment. This study discusses with the implemented real-world scenario of smart autonomous hospital management with the IOT and aims at explaining in detail the technology drivers behind the IOT and health care with the information on data modelling of medical devices, data validation of critical incident data, data mapping of existing IOT data into different other associated system data, workflow or the process flow behind the technical operations of the remote device coordination, the architecture of network, middleware, databases, application services. The challenges and the associated solution in this field are discussed
DIABETIC RETINOPATHY LESIONS IDENTIFICATION IN THE COLOR FUNDUS IMAGES USING MULTI-LAYER PERCEPTRON
(IEEE, 2022-03-25) Geethalakshmi K; Meenakshi V.S
The prognosis of Diabetic Retinopathy (DR) is characterized by Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR). The early stage of DR is known as NPDR. Detecting NPDR in the early stage becomes crucial to avoid blindness. The purpose of this study is to perceive NPDR lesions using image processing techniques and classification methods. The detection of lesions is carried out by pre-processing, feature extraction, feature vector construction, and classification. The vessel network is extracted for feature extraction in the pre-processing stage. Apart from the regular statistical image features, the color layer features are extracted from the smoothened input image. A clustering-based feature extraction method is introduced to capture features from each color layer. The filtered features, which produce the desired output, are combined and fed into Multi-Layer Perceptron (MLP) classifier. The proposed algorithm achieves 100% accuracy in detecting DR. Hence, this study shows that the proposed method can able to find the DR lesions in the early stage itself.