Objectives: To identify a new method for early detection and classification of Heart Diseases (HD); to improve the accuracy of the results by employing I-FCMML (Improved Fuzzy C-Means Machine Learning) and 2L-C (Two-Level Classifier) models along with the I-GA (Improved Genetic Algorithm) methods. Methods: The I-FCMML algorithm is utilized for feature selection and extraction. Machine learning techniques such as Ensembled Random Forest method (ERFM) and Robust Gradient Boost Method (RGBT) are employed to predict the likelihood of HD and 2L-C, I-GA is used to classify and detect the HD at a premature stage based on features like age, gender, blood pressure, etc. IFCMML with 2L-C & I-GA extracts all the features from the dataset (Cleveland HD dataset from the Cleveland Clinic Foundation, Ohio, USA) which includes 303 observations, 14 features and selects the suitable function to perform disease classification and detection with high accuracy. To evaluate the performance of the proposed method, MATLAB is used for implementation. The results are compared with existing algorithms such as 3P-ANN, ANN-FAHP, ADWFS, EDSS, and FE-PCA. Findings: Early HD detection and classification is achieved with 96.02% accuracy, 95.80% sensitivity, 94.76% specificity, 95% precision, 94% recall, 0.90 True Positive, 0.87 True Negative, and 94.13% F-Score to detect and classify the HD in a robust manner, which is comparatively high than the existing methods. Novelty: According to the findings of the comprehensive study, the proposed new method I-FCMML with 2L-C & I-GA has the potential to provide accurate and competent detection and classification of HD at an early stage, which could help for timely treatment and management of HD patients, and it also outperforms the existing methods such as 3P-ANN, ANNFAHP, ADWFS, EDSS, and FE-PCA. Keywords: Heart Disease Detection; Classification Algorithm; Genetic Algorithm; Fuzzy C-Means ML; Image Processing

The quality of the fabric item is considered as one of the most significant concentrations in the textile industry. Convolutional Neural Network has shown commendable execution of fabric defect identification with computer vision and image handling. In this paper, we have implemented a Reformed Convolution Neural Network architecture known as ‘EGNet’ for fabric defect detection. The model has trained on the Cotton Incorporated dataset with 70% data as training and 30% as validation dataset. The model consists of 22 layers of Convolutional layer and Pooling Layer one after the other. The recognition of fabric faults using EGNet is executed utilizing load image dataset, load EGNet, replace final layers, network training, classify validation images. The EGNet is optimized using stochastic gradient descent with momentum. Data augmentation and max-pooling techniques are used to reduce the network's overfitting issue. To infer the significance of EGNet, comparative analysis is done with AlexNet and the result shows that EGNet architecture exposes the fabric defects in 23 seconds of elapsed time and with 100 percent of accuracy.

In the digital world, data has turn out to be a most important asset for all kinds of organization. All industries are relying on the data for their day to day operations. We are living in the era of data driven decisions. Most of the industries are generating huge amount of data, Healthcare is one among the top. Health care industries generates large amount of data. The main challenge in healthcare professional is to analyze the data effectively for better treatment process. Modern approach in the health care is to prevent the disease with early diagnosis instead of treatment after diagnosis. It is possible to provide better healthcare services at lower costs and increase patient satisfaction with the current technologies. Big data analytics, data mining and machine learning are recent technologies used by healthcare professionals to analyze the data quickly and make better decisions on patient’s treatment process. These technologies are used to automate the prediction and diagnosis of disease. Heart diseases are the most prominent reason for death in the world. In the last few decades heart diseases have emerged as life threatening disease. It is preventable if the disease is predicted in the early stage. Early prediction and diagnosis of heart disease can save human life. In recent years many research works have been done using data mining and machine learning algorithms to prevent and predict non communicable diseases like cancer, heart disease, stress, diabetes etc. The objective of this study is to provide glimpse about heart disease, types of heart disease, heart disease prediction factors and various Machine learning algorithms for heart disease prediction. This research paper is also analyzing various existing research works in machine learning algorithms to predict heart diseases.

The brisk development of client information and geographic area information in the area built long range interpersonal communication applications, it is logically troublesome for clients to quick and absolutely discover the data they need. With the expedient development and generally abuse of cell phone, area based informal organization (LBSN) has turned out to be one critical stage for some novel applications. The area data will help to find companion relationship, companion suggestion, network identification, and manual for excursion, notice merchandise et cetera. We separated client social relationship, registration separation and registration compose are the three most huge key highlights. After the component extraction, we connected Adaboost troupe classifier with different base classifiers to order. In view of the trial results, Adaboost with Rehashed Incremental Pruning to Deliver Mistake Decrease (RIPPER) gives the best outcome contrasted with other base classifiers.

Long range interpersonal communication benefits gather data on clients' social contacts, make an expansive interrelated informal organization, and open to clients how they are connected to others in the system. The basic of an OSN contains of customized client profiles, which for the most part encase interests (e.g. bought in intrigue gatherings), perceiving data (e.g. name and photograph), and individual contacts (e.g. rundown of connected clients, alleged "companions"). The ability to accumulate and inspect such information conveys particular chances to perceive the central belief systems of interpersonal organizations, their creation, movement and attributes. These sorts of informal communities are classified to be specific scholarly, general and area based interpersonal organizations. In this paper, we concentrated on the area based interpersonal organizations. Here, we investigations the diverse kinds of information that utilizations in area based interpersonal organizations and furthermore examine the effect of online datasets on neighborhood based interpersonal organization.

Abstract A Secure and Dynamic Multi-keyword Ranked Search Scheme over Encrypted Cloud Data Due to the increasing popularity of cloud computing, more and more data owners are motivated to outsource their data to cloud servers for great convenience and reduced cost in data management. In this project, present a secure multi-keyword ranked search scheme over encrypted cloud data, which simultaneously supports dynamic update operations like deletion and insertion of documents. Specifically, the vector space model and the widely-used TFIDF model are combined in the index construction and query generation. The proposed hierarchical approach clusters the documents based on the minimum relevance threshold, and then partitions the resulting clusters into sub-clusters until the constraint on the maximum size of cluster is reached. In the search phase, this approach can reach a linear computational complexity against an exponential size increase of document collection. In order to verify the authenticity of search results, a structure called minimum hash sub-tree is designed in this paper. Due to the use of our special tree-based index structure, the proposed scheme can achieve sub-linear search time and deal with the deletion and insertion of documents flexibly. Extensive experiments are conducted to demonstrate the efficiency of the proposed scheme.

Abstract Most data sources in real-life are not static but change their information in time. This evolution of data in time can give valuable insights to business analysts. Temporal data refers to data, where changes over time or temporal aspects play a central role. Temporal data denotes the evaluation of object characteristics over time. One of the main unresolved problems that arise during the data mining process is treating data that contains temporal information. Temporal queries on time evolving data are at the heart of a broad range of business and network intelligence applications ranging from consumer behaviour analysis, trend analysis, temporal pattern mining, and sentiment analysis on social media, cyber security, and network monitoring. Social networks (SN) such as Facebook, twitter, LinkedIn contains huge amount of temporal information. Social media forms a dynamic and evolving environment. Similar to real-world friendships, social media interactions evolve over time. People join or leave groups; groups expand, shrink, dissolve, or split over time. Studying the temporal behaviour of communities is necessary for a deep understanding of communities in social media(SM). In this paper we focus on the use of temporal data and temporal data mining in social networks.

Identifying a person is a challenging job in our regular life. The conventional methods includes the password, ID cards, etc [1]. But these identities can easily be misused, lost or shared. To overcome the above limitations of the conventional methods, biometric system has been introduced. The biometric system plays an important role in providing high-security applications such as border control, immigration etc. This paper provides the detailed study of various modules, applications, methods and challenges of the multimodal biometric system.

Speciation of binary complexes of Co(II), Ni(II), and Cu(II) with L-Cysteine (Cys) in the presence of water-anionic surfactant mixtures in the concentration range of 0.0 -2.5% w/v SLS has been studied pH-metrically at a temperature of 303 K and at an ionic strength of 0.16 mol L-1. The selection of best fit chemical models is based on statistical parameters and residual analysis. The predominant species detected were ML2, ML2H and ML2H2 for Co(II), Ni(II), and Cu(II). The trend in the variation of stability constants with the mole fraction of SLS was explained on the basis of electrostatic and non-electrostatic forces. Distribution of the species with pH at different compositions of SLS-water media was also presented.

Objectives: This paper incorporates an outline of digital watermarking and further deals with the performance analysis of wavelet families. Methods: Discrete wavelet transform is an effective technique used in an extensive range of applications in signal manipulation such as de-noising, image compression, spectral clipping, dynamic filtering and so on etc., HAAR, DAUBECHIES, SYMLET and BIORTHOGONAL are some of the wavelet families discussed in this paper. Performance of these families are scrutinized based on the parameters namely MSE, PSNR, BPP and compression ratio. MATLAB R2012 is used to examine the performance using an image of size (126 x 226). Findings: Evaluating the results of the four wavelet families, biorthogonal gives a better result with the compression ratio of 1.65 and MSE with 26.83 which gives a better compressed image than other wavelets. Applications/Improvement: Comparison of the four wavelet families has been analyzed and the better one has to be chosen to compress a watermarked image, since compression is the first step in watermarking and also each wavelet family is best under different criteria. Keywords: BPP, Compression Ratio, DWT, MSE, PSNR, Wavelet Families

Objectives: This paper provides the performance analysis of three edge detection operators on the basis of intensity value and high gradient. Methods: Edge detection is considered to be the building blocks of image processing for object detection and it is an important technique in image segmentation. Sobel, Prewitt and Roberts are some of the edge detection operators discussed in this paper. MATLAB R2013a is used to analyze the performances of these operators using an input image. Findings: In order to classify the operators, the limitations are identified and the performance analysis is done on the basis of obtained results. Based on the intensity value, Prewitt produces better result than Sobel and Roberts. At the same time, Sobel locates the edges with high gradient. Likewise, Roberts produces quick result due to small filter. Application/Improvement: The performance of these operators has been analyzed and realized that each operator is recognized as the best under various conditions. Keywords: Edge Detection Operators, Image Segmentation, Prewitt, Roberts, Sobel

Steganalaysis is a technique for detecting the presence of hidden information. Artificial neural network (ANN) is a widespread method for steganalysis. Back propagation algorithm (BPA), radial basis function (RBF), and functional update back propagation algorithm (FUBPA) are some of the popular ANN algorithms for detecting hidden information. Training and testing performance is improved when two algorithms are combined instead of using them separately. This paper analyzes the performance of combined algorithms of BPARBF and FUBPARBF. Among the two combinations FUBPARBF provides promising results than BPARBF since FUBPA uses less number of iterations for the network to converge. But still organizing the retrieved information is a challenging task.

This paper presents energy efficient three phase 600Hz power system using amorphous metal core for industrial and commercial zones Which require high efficiency, less weight and space for the equipments. An experiment has been conducted on 40 Watt, 220V fluorescent tube light with 600Hz and 50Hz supply. The results show that the 600Hz system is efficient than 50Hz power system. A three phase parallel resonant inverter. circuit has been modeled and simulated using MATLAB/SIMULINK. XLPE Power cables are used for transmission which reduces the inductance drop. Further for compensating line voltage drop and unbalance voltage, Thyristored Switched Capacitors are adopted. An application example of high frequency drive systems used in synthetic yam textile industrial drives is explained.

We isolated a bioactive streptomycete from marine sediment samples collected at Bay of Bengal, India, during our systematic study of marine actinobacteria. The taxonomic studies indicated that the isolate is related to Strepomyces corchorusii. However, it differed in certain aspects, and, hence, was designated as S. corchorusii AUBN(1)/7. A solvent extraction followed by a chromatographic purification helped obtain from the isolate two cytotoxic compounds, which were identified as resistomycin, a quinone-related antibiotic, and tetracenomycin D, an anthraquinone antibiotic, on the basis of spectral data of pure compounds. They demonstrated in vitro a potent cytotoxic activity against cell lines HMO2 (gastric adenocarcinoma) and HepG2 (hepatic carcinoma) and also exhibited weak antibacterial activities against Gram-positive and Gram-negative bacteria. The English version of the paper: Russian Journal of Bioorganic Chemistry, 2006, vol. 32, no. 3; see also http://www.maik.ru.

We isolated a bioactive streptomycete from marine sediment samples collected at Bay of Bengal, India, during our systematic study of marine actinobacteria. The taxonomic studies indicated that the isolate is related to Strepomyces corchorusii . However, it differed in certain aspects, and, hence, was designated as S. corchorusii AUBN 1 /7. A solvent extraction followed by a chromatographic purification helped obtain from the isolate two cytotoxic compounds, which were identified as resistomycin, a quinone-related antibiotic, and tetracenomycin D, an anthraquinone antibiotic, on the basis of spectral data of pure compounds. They demonstrated in vitro a potent cytotoxic activity against cell lines HMO2 (gastric adenocarcinoma) and HePG2 (hepatic carcinoma) and also exhibited weak antibacterial activities against Gram-positive and Gram-negative bacteria.

Lipase production by the mutant strain Rhizopus sp. BTNT-2 was optimized in submerged fermentation. Different chemical and physical parameters such as carbon sources, nitrogen sources, oils, inoculum level, pH, incubation time, incubation temperature and aeration have been extensively studied to increase lipase productivity. Potato starch (1.25% w/v) as a carbon source, corn steep liquor (1.5% w/v) as a nitrogen source and olive oil (0.5% v/v) as lipid source Were found to be optimal for lipase production. The optimal levels of other parameters are 4 ml of inoculum (2.6 x 10(8) spores/ml), initial pH of 5.5, incubation time of 48 hours, incubation temperature of 28 degrees C and aeration rate of 120 rpm. With the optimized parameters, the highest production of lipase was 59.2 U/ml while an yield of only 28.7 U/ml was obtained before optimization resulting in 206% increase in the productivity.

A new actinomycete strain designated as BT-408 producing polyketide antibiotic SBR-22 and showing antibacterial activity against methicillin resistant Staphylococcus aureus has been characterized and found to be a novel strain of Streptomyces psammoticus. Nutritional and cultural conditions for the production of antibiotic by this organism under shake-flask conditions have been optimized. Glucose and ammonium nitrate were found to be best carbon and nitrogen sources respectively for growth and antibiotic production. Similarly initial medium pH of 7.2, incubation temperature of 30°C and incubation time of 96h were found to be optimal. Optimization of medium and cultural conditions resulted in 1.82-fold increase in antibiotic yield.

The purpose of the present investigation is to enhance production of biomedically important enzyme lipase by subjecting the indigenous lipase producing strain Rhizopus sp. BTS-24 to improvement by natural selection and random mutagenesis (UV and N-methyl-N'-nitro-N-nitroso guanidine, NTG). The isolation of mutants and the lipolytic activity of selected mutants were described. The best natural selectant BTNS 12 showed 110% higher lipase activity than the wild strain (BTS-24). The lipase yield of the best UV mutant BTUV3 was 164% higher than the parent strain (BTNS 12 ) and 180% times higher than the wild strain (BTS-24). Also, the lipase yield of the best NTG mutant BTNT 2 was 133 % higher than the parent strain (BTUV 3 ) and 232% higher than the wild strain (BTS-24). The results indicated that UV and NTG were effective mutagenic agents for strain improvement of Rhizopus sp . BTS-24 for enhanced lipase productivity. Key Words: Lipase, Rhizopus, UV, NTG. African Journal of Biotechnology Vol.3(11) 2004: 618-621