Feature selection methods for big data bioinformatics: A survey from the search perspective.

Literature survey is most important for understanding and gaining much more knowledge about specific area of a subject. In this paper a survey on content based image retrieval presented. Content Based Image Retrieval (CBIR) is a technique which uses visual features of image such as color, shape, texture, etc... to search user required image from large image database according to user's requests in the form of a query image. We consider Content Based Image Retrieval viz. labelled and unlabelled images for analyzing efficient image for different image retrieval process viz. D-EM, SVM, RF, etc. To determining the efficient imaging for Content Based Image Retrieval, We performance literature review by using principles of Content Based Image Retrieval based unlabelled images. And also give some recommendations for improve the CBIR system using unlabelled images.

A survey on content based image retrieval

In the domain of remote sensing, the classification of hyperspectral image (HSI) has become a popular topic. In general, the complicated features of hyperspectral data cause the precise classification difficult for standard machine learning approaches. Deep learning-based HSI classification has lately received a lot of interest in the field of remote sensing and has shown promising results. As opposed to conventional hand-crafted feature-based classification approaches, deep learning can automatically learn complicated features of HSIs with a greater number of hierarchical layers. Because HSI's data structure is complicated, applying deep learning to it is difficult. The primary objective of this research is to propose a deep feature extraction model for HSI classification. Deep networks can extricate features of spatial and spectral from HSI data simultaneously, which is advantageous for increasing the performances of the proposed system. The squeeze and excitation (SE) network is combined with convolutional neural networks (SE-CNN) in this work to increase its performance in extracting features and classifying HSI. The squeeze and excitation block is designed to improve the representation quality of a CNN. Three benchmark datasets are utilized in the experiment to evaluate the proposed model: Pavia Centre, Pavia University, and Salinas. The proposed model's performance is validated by a performance comparison with current deep transfer learning approaches such as VGG-16, Inception-v3, and ResNet-50. In terms of accuracy on each class of datasets and overall accuracy, the proposed SE-CNN model outperforms the compared models. The proposed model achieved an overall accuracy of 96.05% for Pavia University, 98.94% for Pavia Centre dataset, and 96.33% for Salinas dataset.

/pdf/hyperspectral-image-classification-model-using-squeeze-and-1ezweh41.pdf

Hyperspectral Image Classification Model Using Squeeze and Excitation Network with Deep Learning

The need for a novel automated mosquito perception and classification method is becoming increasingly essential in recent years, with steeply increasing number of mosquito-borne diseases and associated casualties. There exist remote sensing and GIS-based methods for mapping potential mosquito inhabitants and locations that are prone to mosquito-borne diseases, but these methods generally do not account for species-wise identification of mosquitoes in closed-perimeter regions. Traditional methods for mosquito classification involve highly manual processes requiring tedious sample collection and supervised laboratory analysis. In this research work, we present the design and experimental validation of an automated vision-based mosquito classification module that can deploy in closed-perimeter mosquito inhabitants. The module is capable of identifying mosquitoes from other bugs such as bees and flies by extracting the morphological features, followed by support vector machine-based classification. In addition, this paper presents the results of three variants of support vector machine classifier in the context of mosquito classification problem. This vision-based approach to the mosquito classification problem presents an efficient alternative to the conventional methods for mosquito surveillance, mapping and sample image collection. Experimental results involving classification between mosquitoes and a predefined set of other bugs using multiple classification strategies demonstrate the efficacy and validity of the proposed approach with a maximum recall of 98%.

https://www.mdpi.com/2076-3417/7/1/51/pdf

Vision-Based Perception and Classification of Mosquitoes Using Support Vector Machine

A combination of classifiers leads to a substantial reduction of classification errors in a wide range of applications. Among them, support vector machine (SVM) ensembles with bagging have shown better performance in classification than a single SVM. However, the training process of SVM ensembles is notably computationally intensive, especially when the number of replicated training datasets is large. This paper presents MRESVM, a MapReduce-based distributed SVM ensemble algorithm for scalable image annotation which re-samples the training dataset based on bootstrapping and trains an SVM on each dataset in parallel using a cluster of computers. A balanced sampling strategy for bootstrapping is introduced to increase the classification accuracy. MRESVM is evaluated in both experimental and simulation environments, and the results show that the MRESVM algorithm reduces the training time significantly while achieving a high level of accuracy in classifications.

A MapReduce-based distributed SVM ensemble for scalable image classification and annotation

Images captured using smartphones and video cameras are recorded and can be used anywhere and at any time. While taking a quick shot or while capturing the moving objects, it may lead to the motion blurred images. In order to recover the sharp images from motion blurred images, blind motion deblurring can be used. Motion deblurring can be done by knowing both edge and non-edge of motion blurred images. Edge and non-edge are the two methods used in total variation and alternate direction method for deblurring of digital images. Step edges can be predicted and detected by using edge-specific method. In non-edge method, it explores various image statistics, such as the prior distributions and it is sensitive to statistical variation over different images. Both methods are used in large dataset images, but it fails extremely in simple images. To overcome this problem, total variation (TV) based regularization method is used which is followed by an iteratively reweighted algorithm based on alternating direction method. To get higher results, LSED prediction—based technique is employed, which first of all restores sharp edges and then uses them to estimate initial kernel that traps the optimization of local minimum corresponding to sharp images.

Total Variation and Alternate Direction Method for Deblurring of Digital Images

With many potential practical applications, content-based image retrieval (CBIR) has attracted substantial attention during the past few years. A variety of relevance feedback (RF) schemes have been developed as a powerful tool to bridge the semantic gap between low-level visual features and high-level semantic concepts, and thus to improve the performance of CBIR systems. First, it treats the positive and negative feedbacks equally, which is not appropriate since the two groups of training feedbacks have distinct properties. Second, most of the SVM-based RF techniques do not take into account the unlabeled samples, although they are very helpful in constructing a good classifier. To explore solutions to overcome these two drawbacks, in this paper, we propose a biased maximum margin analysis and a semi-supervised BMMA for integrating the distinct properties of feedbacks and utilizing the information of unlabeled samples for SVM-based RF schemes. During the past few years, content-based image retrieval (CBIR) has gained much attention for its potential applications in multimedia management. It is motivated the explosive growth of image records and the online accessibility of remotely stored images. An effective search scheme is urgently required to manage the huge image database. Different from the traditional search engine, in CBIR, an image query is described by using one or more example images, and low-level visual features (e.g., color , texture, shape, etc.) are automatically extracted to represent the images in the database. However, the low-level features captured from the images may not accurately characterize the high-level semantic concepts. To narrow down the so-called semantic gap, relevance feedback (RF) was introduced as a powerful tool to enhance the performance of CBIR, the query movement and the re-weighting techniques. A selforganizing map was used to construct the RF algorithms. In [16], one-class support vector machine (SVM) estimated the density of positive feedback samples. Derived from one-class SVM, a biased SVM inherited the merits of one-class SVM but incorporated the negative feedback samples. Considering the geometry structure of image low-level visual features, and proposed manifoldlearning-based approaches to find the intrinsic structure of images and improve the retrieval performance. With the observation that "all positive examples are alike; each negative example is negative in its own way," RF was formulated as a biased subspace learning problem, in which there is an unknown number of classes, but the user is only concerned about the positive class. However, all of these methods have some limitations. Heuristically based, the density estimation method in ignores any information contained in the negative feedback samples, and the discriminant subspace learning techniques in often suffer from the so- called -small sample size" problem. Regarding the positive and negative feedbacks as two different groups, classification-based RFs have become a popular technique in the CBIR community. However, RF is very different from the traditional classification problem because the feedbacks provided by the user are often limited in real-world image retrieval systems. Therefore, small sample learning methods are most promising for RF. Random sampling techniques were applied to alleviate unstable, biased, and over fitting problems in SVM RF proposed a multi training SVM method by adapting a constraining technique and a random sampling method. Nevertheless, most of the SVM RF approaches ignore the basic difference between the two distinct groups of feedbacks, i.e., all positive feedbacks share a similar concept while each negative feedback usually varies with different concepts. For instance, a typical set of feedback samples in RF iteration is shown in Fig. 1. All the samples labeled as positive feedbacks share a common concept (i.e., elephant), while each sample labeled as negative feed back varies with diverse concepts (i.e., flower, horse, banquet, hill, etc.). Traditional to explore solutions to these two aforementioned problems in the current exiiscdogy, we propose a biased maximum margin analysis (BMMA) and a SVMRF techniques treat positive and negative feedbacks equally. Directly using SVM as an RF scheme is potentially damaging to the performance of CBIR systems. One problem stems from the fact that different semantic concepts live in different subspaces and each image can live in many different subspaces, and it is the goal of RF schemes to figure out "which one". However, it will be a burden for traditional SVM-based RF schemes to tune the internal parameters to adapt to the changes of the subspace. Such difficulties have severely degraded the effectiveness of traditional SVM RF approaches for CBIR. Additionally, it is problematic to incorporate the information of unlabeled samples into traditional SVM

Semi-supervised biased maximum margin analysis for interactive image retrieval

The imaging modalities are used to view other organs and analyze different tissues in the body. In such imaging modalities, a new and developing imaging technique is hyperspectral imaging. This multicolour representation of tissues helps us to better understand the issues compared to the previous image models. This research aims to analyze the tumor localization in the brain by performing different operations on hyperspectral images. The tumor is located using the combination of k-based clustering processes like k-nearest neighbour and k-means clustering. The value of k in both methods is determined using the optimization process called the firefly algorithm. The optimization processes reduce the manual calculation for finding K's optimal value to segment the brain regions. The labelling of the areas of the brain is done using the multilayer feedforward neural network. The proposed technique produced better results than the existing methods like hybrid k-means clustering and parallel k-means clustering by having a higher peak signal-to-noise ratio and a lesser mean absolute error value. The proposed model achieved 96.47% accuracy, 96.32% sensitivity, and 98.24% specificity, which are improved compared to other techniques.

/pdf/investigations-on-brain-tumor-classification-using-hybrid-31jcilhi.pdf

Investigations on Brain Tumor Classification Using Hybrid Machine Learning Algorithms

Due to the lack of security and safety measures, the crime rate on child abuse has been increased at an unprecedented rate in India. Our propose model will enhance the security and safety especially for girl children in India. In this connection smart band which comprises multiple sensors and programmable hardware. Smart band which communicates with smart phone through wireless communication. The application of a smart band has been developed and installed to smart phone with required quantities & smart band generates signal is send out to smart phone. Track the exact location with help of GPS and the automatic S MS service is done by GSM and screaming alarm which are already preprogrammed, whenever we receive emergency signal, smart phone which will automatically send “help me & save me, I am in danger situation” message along with location send to nearest police station/patrol/control room and also send the message to prime contacts which you saved and also send alert sms to who are all using this application in nearest circumstance. And the smart band will generate electric shocks up to 12 V, and then get started screaming alarm asking help.

Internet of Things (IOT) based smart band to ensure the security for women

Cloud computing is the recent technology used to share and store the computer resources rather than having resources in local server to maintain the application. Though cloud is used for a large amount of storage, there is no security in cloud. In general, all the groups have data owners and data members each should have user name, key, and group key. If a user shifts from one group to another, they can easily access the information from another group. It leads to a security problem. In order to increase security and confidentiality, author generates the new group key via Email using Diffie-Hellman algorithm. In case of a new user is added or an existing user leaves themselves from the group. The data members have to get permission from the data owners in case of any data updation. If the user misbehaves, i.e., (DDOS) attack, data owner or cloud terminates the user from the group. The updated key is sent to the users through Email. This mechanism significantly improves security in cloud computing.

S. Rinesh

Papers

Total Variation and Alternate Direction Method for Deblurring of Digital Images

Semi-supervised biased maximum margin analysis for interactive image retrieval

Investigations on Brain Tumor Classification Using Hybrid Machine Learning Algorithms

Internet of Things (IOT) based smart band to ensure the security for women

Generation of Multiple Key Based on Monitoring the User Behavior