Search

Clustering has proved to be a successful classification method when it comes to dealing with multiview data. Each method and technique tries to achieve efficiency and accuracy in classifying the multiview data. Multi-source data contains noise and divergence. Another problem is that each view contains many features, so usually the multiview dataset is multi-dimensional. This raises basic problems like the need for a dimensionality reduction technique for optimal selection of features, fusing the data of different views, and maintaining the inter- and intra-consensus of the multiview dataset. The fusion technique should merge the complementary information efficiently. The goal of this study is to use a promising technique for dimension reduction that reduces the noise but maintains the inter-view and cross-view consensus. A self-organizing map is one of the well-known unsupervised neural network algorithms used for preserving typologies during mapping from the input space (high-dimensional) to the display (low-dimensional).An algorithm called Local Adaptive Receptive Field Dimension Selective Self-Organizing Map 2 is a modified form of a self-organizing Map to cater different data types in the dataset. It calculates the dimension relevance with various data instances. These further place the relevant dimension samples in one group. The method does not need to know the number of clusters before hand, as it dynamically determines it during the process. Finally, this study proposed a novel multi-view learning framework that analyzes multi-source data and generates fine clusters efficiently.

Image denoising and super-resolution play vital roles in imaging systems, greatly reducing the preprocessing cost of many AI techniques for object detection, segmentation, and tracking. Various advancements have been accomplished in this field, but progress is still needed. In this paper, we have proposed a novel technique named the Enhanced Learning Enriched Features (ELEF) mechanism using a deep convolutional neural network, which makes significant improvements to existing techniques. ELEF consists of two major processes: (1) Denoising, which removes the noise from images; and (2) Super-resolution, which improves the clarity and details of images. Features are learned through deep CNN and not through traditional algorithms so that we can better refine and enhance images. To effectively capture features, the network architecture adopted Dual Attention Units (DUs), which align with the Multi-Scale Residual Block (MSRB) for robust feature extraction, working sidewise with the feature-matching Selective Kernel Extraction (SKF). In addition, resolution mismatching cases are processed in detail to produce high-quality images. The effectiveness of the ELEF model is highlighted by the performance metrics, achieving a Peak Signal-to-Noise Ratio (PSNR) of 42.99 and a Structural Similarity Index (SSIM) of 0.9889, which indicates the ability to carry out the desired high-quality image restoration and enhancement.

In this paper, a convolved feature vector based adaptive fuzzy filter is proposed for impulse noise removal. The proposed filter follows traditional approach, i.e., detection of noisy pixels based on certain criteria followed by filtering process. In the first step, proposed noise detection mechanism initially selects a small layer of input image pixels, convolves it with a set of weighted kernels to form a convolved feature vector layer. This layer of features is then passed to fuzzy inference system, where fuzzy membership degrees and reduced set of fuzzy rules play an important part to classify the pixel as noise-free, edge or noisy. Noise-free pixels in the filtering phase remain unaffected causing maximum detail preservation whereas noisy pixels are restored using fuzzy filter. This process is carried out traditionally starting from top left corner of the noisy image to the bottom right corner with a stride rate of one for small input layer and a stride rate of two during convolution. Convolved feature vector is very helpful in finding the edge information and hidden patterns in the input image that are affected by noise. The performance of the proposed study is tested on large data set using standard performance measures and the proposed technique outperforms many existing state of the art techniques with excellent detail preservation and effective noise removal capabilities.

Today, data center networks (DCNs) are built using multi-tier architecture. These large-scale networks face many challenges, such as security, delay, low throughput, loops, link oversubscription, TCP Incast and Outcast, etc. In this paper, a TCAM (Ternary Content Addressable Memory) based routing technique is proposed, augmenting the routing capabilities of multi-tier architectures in large scale networks. The routing complexities in these architectures are rectified and improved by implementing an additional TCAM based routing table in Leaf/ToR switches for a specific number of compute nodes in particular Pods, and it is scalable to whole datacenter nodes. To test the model, we implemented two prototype models: one depicting our proposed TCAM based switch and the other is a typical Top-of-the-Rack (ToR) switch and compared the performance of the proposed model and if any overhead introduced in it. The preliminary results show that our TCAM based routing table technique is fast and it forwards the network packets at line-rate, does not introduce considerable latency, on-chip resources power consumptions is less than 3%, and helps to solve or mitigate the above critical problems that are present in the current large DC's three-tier architecture, especially in Top of the Rack and aggregation layers switches.

For inter and intra cluster communication, member nodes jointly build a mutual session key called cluster key to allow secure communication. Most existing schemes for cluster key management use messages exchange among the member nodes within a cluster for the new cluster key establishment when a node leaves or joins a cluster. This causes significant communication and computation costs. Furthermore, the secure distribution of cluster keys among member nodes in frequently changing environments is a difficult task without encryption and decryption operations. For secure cluster key management, we utilized polynomial (P) to accomplish effective intra-cluster key management and produced polynomial for making an inter-cluster key distribution. The main contribution is to generate polynomials and broadcast to nodes whenever a change occurs in a network or demanding nodes for secure key management. The presented scheme supports scalability for an increasing number of nodes using polynomials. The proposed scheme increases the lifetime of the network by decreasing the key pool size.

Selecting a cluster head (CH) in wireless mobile sensor network is a crucial task. Numerous algorithms have been presented for this purpose in recent literature. In these algorithms, all nodes are permitted to contend in CH selection process regardless of their less resource. This meaningless participation of ineligible nodes in the CH selection process causes unnecessary communication cost. Similarly the use of real data for CH selection increases communication cost. Additionally, no one algorithm has focus in security aspect of CH selection process. In this article Pattern Based secure CH Selection algorithm has been presented. This algorithm filters the ineligible nodes, puts them to sleep mode thereby restricting them from not participating in the CH selection process. Additionally the uses of pattern instead of real data in CH selection decrease communication cost and increase security of CH selection process. The simulation results show the improvement in lifetime and enhancement in security of CH selection.

A 2-D Adaptive Trimmed Mean Autoregressive (ATMAR) model has been proposed for denoising of medical images corrupted with poisson noise. Unfiltered images are divided into smaller chunks and ATMAR model is applied on each chunk separately. In this paper, two 5x5 windows with 40% overlapping are used to predict the center pixel value of the central row. The AR coefficients are updated by sliding both windows forward with 60% shift. The same process is repeated to scan the entire image for prediction of a new denoised image. The Adaptive Trimmed Mean Filter (ATMF) eradicates the lowest and highest variations in pixel values of the ATMAR model denoised image and also average out the remaining neighborhood pixel values. Finally, power-law transformation is applied on the resultant image of the ATMAR model for contrast stretching. Image quality is judged in terms of correlation, Mean Squared Error (MSE), Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) of the image with latest denoising techniques. The proposed technique showed an efficient way to scale down poisson noise in scintigraphic images on a pixel-by-pixel basis.

The main benefit of selecting a suitable node as cluster head (CH) in clustering for wireless mobile sensor networks (MWSNs) is to prolong the network lifetime. But the safe selection of CH is a challenging task by taking security into account. Mostly CH selection algorithms in MWSN do not consider security when selecting CH. We have proposed secure CH selection algorithm by calculating weight of each node to deal with secure selection using minimum energy consumption. The weight of node is a combination of different metrics including trust metric (behaviors of sensor node) which promotes a secure decision of a CH selection; in terms of this, the node will never be a malicious one. The trust metric is definitive and permits the proposed clustering algorithm to keep away from any malignant node in the area to select a CH, even if the rest of the parameters are in its favor. Other metrics of node include waiting time, connectivity degree, and distance among nodes. The selection of CHs is completed utilizing weights of member nodes. The preparatory outcomes acquired through simulation exhibit the adequacy of our proposed scheme as far as average rate of avoiding malicious node as a CH, energy efficiency, and some other performance parameters are concerned.

Background/Aim: Amiodarone, a class III antiarrhythmic drug, has been found to be effective in the management of patients with life-threatening ventricular arrhythmias. The aim of this study was to test whether the co administration of vitamin-E with amiodarone can reduce amiodarone-induced liver damage. Materials and Methods: Twelve male albino rats were divided into three groups (ml vegetable oil/day by oral gavages daily for 2 weeks and were used as control group. The rats of the second group received 5.4 mg amiodarone/100 gm rat dissolved in vegetable oil daily by oral gavages for 2 weeks. In the third group, the rats received 5.4 mg amiodarone and 5 mg vitamin-E/100 gram rat dissolved in 2 ml vegetable oil by oral gavages daily for 2 weeks. Two weeks after treatment, the rats were sacrificed and liver specimens were immediately taken and processed for transmission electron microscopic examinations. Results : Sections from the rat liver receiving amiodarone examined by electron microscopy showed disrupted hepatocytes with increased vacuolations. Degenerated organelles and disrupted nuclei were observed. The microvilli of bile canaliculi were disrupted and the hepatocytes showed increased lipid contents. Both endothelial cells and Kupffer cells were damaged. Phospholipids inside the mitochondria showed a loss of cristae. Sections from the liver of rats received amiodarone and vitamin-E showed lesser effects, especially in depositions of phospholipids in the mitochondria and the whole organelles and the nucleus showed minor damage in comparison to the previous group. Conclusion: Milder hepatotoxic effects are seen in rats administered amiodarone and vitamin E simultaneously suggesting that vitamin-E may play a role in amelioration of the effects of amiodarone.