Advances in Computational Research

141-148

Authors: ASKALI M., NOUH S., AZOUAOUI A., BELKASMI M

The construction of optimal linear block error-correcting codes is not an easy problem, for this, many studies describe methods for generating good error correcting codes in terms of minimum distance. In a previous work, we have presented the multiple impulse method (MIM) to evaluate the minimum distance of linear codes. In this paper we will present an optimization of the MIM method by genetic algorithms, and we found many new optimal Double and Triple Circulant Codes (DCC & TCC) with the highest known parameters using the MIM method as an evaluator of the minimum distance. Two approaches are used in the exploration of the space of generators; the first is based on genetic algorithms, however the second is on the random search algorithm.

153-156

Authors: KAPADIA V.V., THAKKER V.K

Memory management on which researchers are mainly focusing are the different techniques related to memory management i.e. garbage collection techniques, scheduling, real time system, user oriented design and many more. The major problem found out in memory management is processor and operating system delays. Here a new design of processor is discussed in the paper that will improve to the over all system performance.

34-37

Authors: SHAIKH A.J., KURESHI ANIS, MANZA R.R.

In this paper we show some results on Epipolar Geometry applying on various images using MATLAB. The Fundamental matrix is give to the depth information on the images we get the critical view of images that can be transfer in to the Grayscale image in to binary image. Matlab is an ideal tool for simulating digital communication system, its gates easy scripting language and excellent data visualization capabilities. Images breaking them up in to their bit- planes images are collecting their pixel values the grey value of each image of an 8- bit image an 8- bit binary word. The binary image will have only given the two values 0 and 1 and hence the image shows best clarity results is fine. The Epipolar geometry is a key point in computer vision and the fundamental matrix estimation, computer vision and the fundamental matrix estimation is the unique way to compute it.

42-45

Authors: NIKITA KASHYAP, SINHA G.R.

A novel multi resolution watermarking method has been introduced for digital images. The proposed method is based on 2-level discrete wavelet transform (DWT) and alpha blending technique. In this technique the insertion and extraction of the watermark in the grayscale cover image is found to be simpler than other transform techniques. We have successfully implemented the digital watermarking technique on digital images based on 2-level discrete wavelet transform and compared the performance of proposed method with 1-level DWT by using statistical parameters peak signal to noise ratio (PSNR) and mean square error (MSE).

50-53

Authors: MANZA R.R., GAIKWAD B.P., MANZA G.R.

Mango fruit is one of the most popular, nutritionally rich fruit with unique flavor, fragrance, taste, and heath promoting qualities making it a common ingredient in new functional fruits often called “super fruits”. The Edge detection process detects outlines of mangos, mango quality evaluation and mango types, counting mangos, check Inflorescence quality. An edge is the boundary between mangos and the background. Simulink is a simulation modeling and design tool and GUI based diagram environment. The Simulink based customizable framework is designed for rapid simulation, implementation, and verification of video processing systems. In this work the comparative analysis of various mangos video edge detection methods is like Sobel, Prewitt, and Canny is presented.

57-60

Authors: BANSOD N.S., SEEMA KAWATHEKAR, DABHADE S.B.

Spoken language is the most natural way used by human to communicate information. Speech signal conveys linguistic information as well as speaker information (e.g. Emotional, regional and physiological characteristics). Such human ability has inspired many researches to understand production for developing the system that automatically process the richness of information in speech, this speech technology has many applications to find out “who is speaking” means speaker recognition system. This paper gives an overview of major techniques developed in each stage of speaker recognition. This paper has a list of techniques along with their results, merits and demerits. This also includes comparative study of different techniques, which are helping us to choose the technique for developing different language speaker recognition system like Marathi, Hindi and English. Time alignment of different utterances is a serious problem for distance measures and small shift would lead to incorrect identification. Dynamic time warping (DTW) is effective method. Vector quantization (VQ) is the classical quantization technique from signal processing. HMM is used for pattern matching. This paper shows the comparative result of PLC, PLPC and MFCC. MFCC have 73.62% is better result for Marathi language and 64.69% for Hindi language than PLC and PLPC techniques.

66-68

Authors: PRAMOD ROKADE, MEHROTRA S.C. , BHARTI GAWALI , SHASHIBALA RAO, RAKESH DEORE

This paper focuses on number recognition from feature extracted using Electroencephalogram (EEG) readings. EEG signals were recorded at Department of Computer Science and IT, Dr. B. A. M. University, India, from 6 volunteer subjects. A random number generator Graphics User Interface was developed in VB7. It is used to display numbers from 0 to 9 which worked as Visually Evoked Potential (VEP) for the experiment. The database of 6 male right-handed subjects in the age group of (20-25) was created and used as training data set. By exposing the same set of subjects to the GUI again, new EEG recordings were collected. This new set of EEG readings was considered as testing data set. The testing data was searched and matched with trained data set for recognizing pattern of each number. The experiments were conducted by concentrating on Beta signal and Linear discriminate analysis (LDA) was implemented to classify the data. The recognition rate observed was different for different numbers. Overall recognition rate observed was 68.33%. It is also seen that there exist a unique pattern for each number.

74-77

Authors: PURNAIAH B., RAMA KRISHNA V., BALA VENKATA KISHORE G.

Software Reliability is defined as the probability of free-failure operation for a specified period of time in a specified environment. Software Reliability Growth models (SRGM) have been developed to estimate software reliability measures such as number of remaining faults, software failure rate and Software Reliability. Imperfect debugging models are considered in these models. However, most SRGM assume that faults will eventually be removed. Fault removal efficiency in the existing models is limited. This paper aims to incorporate the fault removal efficiency in software reliability growth modeling. In this paper imperfect debugging is considered in the sense that new faults can be introduced into the software during debugging and the detected faults may not be removed completely.

83-86

Authors: WANKHADE R.S., INGLE D.R., MESHRAM B.B

The main objective is to develop an automated system that would help in analytics the website performance efficiently. Web analytics will register the organizations or the websites & maintain their information. It will also provide the real time information about the number of visitors, visitors from a certain country etc. The software will provide the breakup of the user’s interest in the organization’s website. If the popularity is too low, then it would provide a template having the suggestions to improve the popularity. The main concept here is that a piece of code is placed on your webpage which enables us to analyze and monitor all the visitors to the website at run-time. The system takes as input the users login when he visits the website. Every website is provided with a piece of code and a log space. You put the piece of code on the webpage, and every time the visitor visits the webpage the code sends the valuable information about the visitor back to the log. Web tracker organizes this information into charts and lists to make your analysis easier. Web analytics is the practice of measuring, collecting, analyzing and reporting on Internet data for the purposes of understanding how a web site is used by its audience and how to optimize its usage. The study of visitor, navigation, and traffic patterns to determine the success of a given web site. Web Analytics does not purely focus on the amount of traffic which might only be helpful in evaluating your bandwidth usage and server’s capabilities. Instead it focuses on in-depth comparison of available visitor data, referral data, and site navigation patterns as well as being able to tell us the amount of traffic we receive over any specified period of time. Modern web analytics tools collect vast amounts of information about website visitors; these reporting systems make it difficult to identify trends in data due to the number of reports available. By developing a system that logically presents automated analysis based on trends and patterns, web analytics users will be able to implement improvements to their websites. In order to develop the web analytics dashboard and analysis system, data will be collected by a third party web analytics tool. Research will be undertaken into existing web analytics dashboards used to visualize data. The paper will consider the collection, use and display of data and how these elements can be automated. Major need for developing such a project is to create a general template which can be used by any website owner to check performance of his website. If website is very popular, website owner may decide to assign efficient servers which can handle more load. In some organizations, it may be necessary to view from which region more users are accessing the website. The solution to all these problems is obtained by web analytics.

91-94

Authors: SHIRUDE S.B., KOLHE S.R.

We have proposed a recommender system UseLibrary, helping users of library to get proper journal articles, books and other library resources. Profile generation & maintenance and profile exploitation are two main tasks to develop the system. Currently in this system, dataset consists of 790 books and journal articles in PDF and TXT format. System learns the profiles of users and then provides recommendations. Information filtering is required for providing recommendations. Similarity between interest of user and available resources can be computed by different approaches. In this paper, we have compared two approaches, cosine similarity measure and ontology based measure. It is found that use of ontology based measure outperforms cosine similarity measure.

99-103

Authors: KAZI M.M., RODE Y.S., DABHADE S.B., AL-DAWLA N.N.H., MANE A.V., MANZA R.R., KALE K.V.

A multimodal biometric system combines the different biometric traits and provides better recognition performance as compared to the systems based on single biometric trait or modality. In multimodal biometric system the fusion of the information can be done at various levels, but due to the ease in combining and accessing the scores generated by different matchers, the most common approach is the integration at the matching score level. Before combining, the scores should alter into a common domain, since different matchers generate heterogeneous scores. In this paper, we have studied performance of a single fast normalized cross-correlation matcher and simple sum-rule fusion technique based on face and signature traits of a user. The experiments conducted on a database of 17 users indicate that simple sum of score fusion method results in better recognition performance than using single face or single signature based biometric system. However, experiments also reveal that the normalized cross-correlation based matcher gives better results, highlighting the need for a robust and efficient feature extraction technique.

108-112

Authors: PATIL M.P., KOLHE S.R.

The search of an image in image database using keywords is made powerful due to automatic image annotation. In this paper, an automatic image annotation using K- Nearest Neighbor (K-NN) is presented. The categorization based approach is presented for annotation. Images are first segmented using k-means clustering and then processed to form feature vector. Local features are extracted from the regions of the image. The feature vectors are experimented using K-NN. Our system is validated using ten categories from the COREL images. It is observed that in multiple instance learning using K-NN with color and texture features outperforms for all type of feature vectors.

117-121

Authors: IMRAN KHAN PATHAN, ABDULBARI AHMED ALI AND RAMTEKE R.J.

This paper presents an approach for recognition of offline handwritten isolated Urdu character based on Invariant Moments. Handwritten Urdu character recognition is lagging behind due to segmentation dilemma and complexity of Urdu letter writing. An attempt is made to apply Moment Invariant technique followed by Primary and secondary component separation. The Urdu letters were grouped into single component and multi-component characters. If letter is multi-component then Secondary component were separated from primary component. SVM is adopted for classification and position of secondary component (Above, Below and middle) is considered for recognition. For each of 46 characters 200 image samples were used for training and 600 for testing respectively. In this manner overall 36800 handwritten characters were used to apply the technique. Overall performance rate is found to be 93.59% for all offline handwritten isolated Urdu characters. It is possible to enhance the accuracy of system by combining more structural and statistical features.

125-129

Authors: PATHAK V.M., JOSHI M.R.

SMS based information retrieval is one of the challenging research driven application of information and communication technology. “A flexible natural language query in the form of an SMS could also be answered by applying information retrieval theory and practices”, is our research theme. In the initial phase, we have formulated a preparatory experimentation on SMS based Marathi query to retrieve Marathi literature documents. This paper presents the details about the ITRANS Marathi literature documents followed by the description of an appropriate Vector Space Model (VSM) to represent the documents and the queries. We designed a GUI and asked a group of hundred students to formulate an SMS query for 30 different questions in order to obtain user specific variations among typed in queries. A collection of sample Marathi documents in the ITRANS form and a set of acquired queries is processed using the system developed to retrieve relevant documents. The system uses the Cosine Similarity to rank the documents according to the relevance for each selected query. Experimental results of the system are presented in the paper. This is the first such type information retrieval model for the ITRANS Marathi documents.

134-137

Authors: CHIKHALE S.N., HATE S.

The Indian economy mostly depends on agriculture. But the farmers in leading state like Maharashtra are committing suicides because of environmental parameters which strongly affect the crops. This forced us to think in the direction of farming and we mood to the topic mentioned below inspired by Eden project in UK and BIOS-3 project in Russia. Greenhouse provided up to present era is not completely automatic and there are many errors and limitations in its working and are unaffordable, large, difficult to maintain and less accepted by the technologically unskilled workers. So we are trying to provide completely automised CES (Closed Ecological System) using runtime TCP-IP protocol to monitor and control the parameters which governs the plant growth. The architecture of a green house monitoring system comprises of a set of sensor nodes and a control unit that communicate with each sensor node and collects local information to make necessary decisions about the physical environment. The user is updated with the run time information of his field.

31-36

Authors: SAROJ KUMAR LENKA, AMBARISH G. MOHAPATRA

Driving under the influence (DUI) is a synonymous term that represents the criminal offense of operating a motor vehicle while being under the influence of alcohol. Semiconductor oxides such as SnO2, TiO2, and ZnO have been more successfully employed as sensing materials compare to organic semiconductors for the detection of ethanol gas concentration. This work investigates the fabrication and characterization of the thick-film gas sensor based on Zinc-oxide on an Alumina substrate. The sensor exhibits excellent ethanol sensing characteristics at temperatures between 175°C to 300°C and the characteristics of the sensor for different concentration of the ethanol gas has been successfully studied using Linear Discriminant Analysis (LDA). This system can be used to detect alcoholic driving for automotive safety applications. The system is designed to detect the exact concentration of ethanol gas using virtual instrumentation software and data acquisition hardware. This work presents the data analysis results of 230 samples of each concentration levels of ethanol gas using Linear Discriminant Analysis (LDA) technique. The overall system can be tested with the engine ignition system for automotive safety and warning applications in the prevention of a crash during drunken driving.

42-49

Authors: AMBARISH G. MOHAPATRA, SAROJ KUMAR LENKA

In this work, a simple and efficient artifact cancellation in ambulatory ECG using adaptive filter is designed for the detection of different cardiac diseases like bradycardia, tachycardia, left ventricular hypertrophy and right ventricular hypertrophy. Our work is focused on extraction of noise free ECG signal and the real-time implementation of artifacts removal techniques. As ECG signal is very sensitive in nature, and even if small noise mixed with original signal the various characteristics of the signal changes, data corrupted with noise must either filtered or discarded, filtering is important issue for design consideration of real-time ECG measurement systems. Here we have implemented different adaptive filtering algorithms (LMS-Least Mean Square, RLS-Recursive Least Squares) using virtual instrumentation technique to minimize the noisy components and to analyze different cardiac diseases like bradycardia, tachycardia, left ventricular hypertrophy and right ventricular hypertrophy. Finally the overall performance of LMS and RLS algorithm is also compared according to the error signal generated by the techniques.

6-14

Authors: Potnis Anjali, Somkuwar Ajay , Sapre S.D.

Denoising of natural images is the fundamental and challenging research problem of Image processing. This problem appears to be very simple however that is not so when considered under practical situations, where the type of noise, amount of noise and the type of images all are variable parameters, and the single algorithm or approach can never be sufficient to achieve satisfactory results. Fourier transform method is localized in frequency domain where the Wavelet transform method is localized in both frequency and spatial domain but both the above methods are not data adaptive .Independent Component Analysis (ICA) is a higher order statistical tool for the analysis of multidimensional data with inherent data adaptiveness property. The noise is considered as Gaussian random variable and the image data is considered as non-Gaussian random variable. Specifically the Natural images are considered for research as they provide the basic knowledge for understanding and modeling of human vision system and development of computer vision systems. This paper reviews significant existing denoising methods based on Independent Component Analysis and concludes with the tabular Summary of denoising methods and their salient features / applications.

21-24

Authors: Hiremath P.S. , Kodge B.G.

This study presents a new visualization tool for classification of satellite imagery. Visualization of feature space allows exploration of patterns in the image data and insight into the classification process and related uncertainty. Visual Data Mining provides added value to image classifications as the user can be involved in the classification process providing increased confidence in and understanding of the results. In this study, we present a prototype visualization tool for visual data mining (VDM) of satellite imagery. The visualization tool is showcased in a classification study of highresolution imageries of Latur district in Maharashtra state of India.

10-13

Authors: Desai C.G., Patil M.B., Mahale V.D., Umrikar B.

Due to the rapid course of urbanization, the haphazard growth of major cities is one of the challenging situations in front of any country. As unorganized urbanization is becoming the major problem, it requires the immediate solution for sustainable development of urban land. In the emerging scenario it is essential to have updated information on urban growth patterns and its impact on the living environment. The growth and development of cities are likely to continue and therefore there will be a need for proper planning and managing or improving the existing infrastructure facilities. In this juncture, the state of the art technologies Remote Sensing (RS) and Geographic Information System (GIS) can play an imperative role. Pune metropolis is one such rapidly developing city in Maharashtra. This paper explores the study of Urbanization growth of Pune city using RS data and GIS.

18-29

Authors: Mahajan P.M., Kolhe S.R., Patil P.M.

Quality inspection is an important aspect of modern industrial manufacturing. In textile industry production, automate fabric inspection is important for maintain the fabric quality. For a long time the fabric defects inspection process is still carried out with human visual inspection, and thus, insufficient and costly. Therefore, automatic fabric defect inspection is required to reduce the cost and time waste caused by defects. The development of fully automated web inspection system requires robust and efficient fabric defect detection algorithms. The detection of local fabric defects is one of the most intriguing problems in computer vision. Texture analysis plays an important role in the automated visual inspection of texture images to detect their defects. Various approaches for fabric defect detection have been proposed in past and the purpose of this paper is to categorize and describe these algorithms. This paper attempts to present the survey on fabric defect detection techniques, with a comprehensive list of references to some recent works. The aim is to review the state-of-the-art techniques for the purposes of visual inspection and decision making schemes that are able to discriminate the features extracted from normal and defective regions. Therefore, on the basis of nature of features from the fabric surfaces, the proposed approaches have been characterized into three categories; statistical, spectral and model-based.

34-38

Authors: Tayade A.Y., Prabhu-Ajgaonkar S.G.

This paper is a contribution to stylostatistics which has, as a discipline, established itself in the recent years. We have considered probability distribution to the data of sentence-length collected from the book of late Pandit Jawaharlal Nehru.

43-46

Authors: Sunanda Gupta, Garg M.L.

During the last two decades solving combinatorial optimization problems, using genetic algorithms (GA), has attracted the attention of many researchers. The genetic algorithm on which this work is based on uses a special repair operator to prevent the generation of infeasible solutions and to transform each feasible solution into a locally optimal solution. In longer runs it is likely that this algorithm produces candidate solutions that have already been generated and evaluated before. This effect can significantly reduce the algorithm's overall performance. To prevent the reconsideration of already evaluated solutions, a solution based on a Trie is studied. This paper presents the algorithms and data structures for compressing the Binary Trie and incorporates this in the GA implementation of the Multi Dimensional Knapsack Problem.

52-55

Authors: Sangame S.K., Ramteke R.J., Rajkumar Benne

This paper presents unconstrained handwritten Kannada vowels recognition based upon invariant moments. The proposed system extracts Invariant moments feature from zoned images. A Euclidian distance criterion and K-NN classifier is used to classify the handwritten Kannada vowels. A total 1625 image are considered for experimentation and overall accuracy found to be 85.53%. The novelty of the proposed method is independent of size, slant, orientation, and translation in handwritten characters.