COVID-19 has been circulating around the world for over a year, causing a severe pandemic in every country, affecting billions of people. One of the most extensively utilized diagnostic... Show More

COVID-19 has been circulating around the world for over a year, causing a severe pandemic in every country, affecting billions of people. One of the most extensively utilized diagnostic methodologies for diagnosing and detecting the presence of the COVID-19 virus is reverse transcription-polymerase chain reaction (RT-PCR). Various ideas have been proposed for the detection of COVID-19 using medical imaging. CT or computed tomography is one of the beneficial technologies for diagnosing COVID-19 patients, the need for screening of positive patients is an essential task to prevent the spread of the disease. Segmentation of Lung CT is the initial step to segment the infection caused by the virus in the lungs and to analyze the lungs CT. This article introduces a novel Hidden Markov Random Field based on Gaussian Mix Model (GMM-HMRF) method ensembled with the modified ResNet18 deep architecture for binary classification. The proposed architecture performed well in terms of accuracy, sensitivity, and specificity and achieved 86.1%, 86.77%, and 85.45%, respectively.

The Ubiquitous behaviour of MOOCs for online learning has proven its importance specially in the Covid period. These platforms facilitate learners for peer support by communicating through the... Show More

The Ubiquitous behaviour of MOOCs for online learning has proven its importance specially in the Covid period. These platforms facilitate learners for peer support by communicating through the discussion forum. The communication held among learners is demonstrated through the social network (SN). The objective of this research is to analyse learner’s SN to find the seed of learners that maximizes the influence spread in the SN to handle its multi-objective research paradigm and avoid the influence maximization process of getting stuck in local optima. Henceforth, extensive experiments are performed using SN topological characteristics to build an effective objective function for the influence maximization problem, and BAT optimization algorithm is employed to achieve global optimum results to find out top influence spreader in course communication network. Efficient results have been obtained by the proposed approach which will help MOOC portals for substantial performance identification of influential learners as compared to ego-centric influential learner identification outcome.

In this paper, we propose a multiconnection-based Hopfield neural network (MC-HNN) based on the hamming distance and Lyapunov energy function to address the limited storage and inadequate recalling... Show More

In this paper, we propose a multiconnection-based Hopfield neural network (MC-HNN) based on the hamming distance and Lyapunov energy function to address the limited storage and inadequate recalling capability problems of Hopfield Neural Network (HNN). This study uses the Lyapunov energy function and Hamming Distance to recall correct stored patterns corresponding to noisy test patterns during the convergence phase. The proposed method also extends the traditional HNN storage capacity by storing the individual patterns in the form of etalon arrays through the unique connections among neurons. Hence, the storage capacity now depends on the number of connections and is independent of the total number of neurons in the network. The proposed method achieved the average recall success rate of 100% for bit map images with a noise level of 0, 2, 4, 6 bits, which is a better recall success rate than traditional and genetic algorithm-based HNN methods, respectively. The proposed method also shows quite encouraging results on hand-written images compared with some latest state of art methods.

With the ongoing covid-19 pandemic, people rely on online communication to remain connected as a precautionary measure to maintain social distancing. When we have no one on our side to listen and... Show More

With the ongoing covid-19 pandemic, people rely on online communication to remain connected as a precautionary measure to maintain social distancing. When we have no one on our side to listen and console us in state of fear and dilemma, we try to find comfort in anonymity of social media. Tracking real-time changes in sentiments are quite difficult as it could not correlate well with human understanding and emotions, which changes with time and many other factors. Collecting sentiments from users on search results, news articles, paintings, photographs are nowadays common. This is a more robust and effective method as traditional ways do not rely on a lot of retrospectives. In this paper, we will be analyzing the data collected from Twitter on Covid-19 and see topic modelling can be meant to detect sentiment analysis. The challenge is here we need to see results over time, and changes detect in topics and sentiments. We analyze our method over covid-19 data and farmer’s protest. Results from this experiment using the proposed methodology are promising and giving valuable insights.

To protect a network security, a good network IDS is essential. With the advancement of science and technology, present intrusion detection technology is unable to manage today's complex and... Show More

To protect a network security, a good network IDS is essential. With the advancement of science and technology, present intrusion detection technology is unable to manage today's complex and volatile network abnormal traffic without taking into account the detection technology's scalability, sustainability, and training time. A new deep learning method is presented to address these issues, which used an unsupervised non-symmetric convolutional autoencoder to learn the dataset features. Furthermore, a novel method based on a non-symmetric convolutional autoencoder and a multiclass SVM is proposed. The KDD99 dataset is used to create the simulation. In comparison to other approaches, the experimental outcomes suggest that the proposed approach achieves good results, which considerably lowers training time and enhances the IDS detection capability.

Node localization process is a crucial prerequisite in the area of Wireless Sensor Networks (WSNs). The algorithms for node localization process can either range-based or range-free. Range-free... Show More

Node localization process is a crucial prerequisite in the area of Wireless Sensor Networks (WSNs). The algorithms for node localization process can either range-based or range-free. Range-free algorithms are preferred over range-based ones due to their cost-effectiveness. DV-Hop along with its variants is normally well-liked range-free algorithm because of its straightforwardness, scalability and distributed nature, but it has some disadvantages such as poor accuracy and high-power utilization. To deal with these limitations, this paper introduces an algorithm, called GWOGN-LA. GWOGN-LA improves accuracy by applying Grey-Wolf Optimization and Gauss-Newton method. The proposed algorithm restricts the forwarding of packets in order to limit energy consumption. Simulation results show that given proposal outperforms other state-of-art algorithms in terms of accuracy and power consumption.

Blockchain requires to validate the block with confirmed transactions from the unconfirmed pool of transactions through Miners. Miners pick up the transactions from the pool of unconfirmed... Show More

Blockchain requires to validate the block with confirmed transactions from the unconfirmed pool of transactions through Miners. Miners pick up the transactions from the pool of unconfirmed transactions approximately more than 2000 and solve the algorithmic puzzle i.e. also known as proof of work within the limited period of time. To maximize the throughput per second requires optimization of the time period to solve the algorithm puzzle for validating the block. Conventionally, for unconfirmed transactions, miners solve the proof of work using brute force algorithms which consume a lot of electrical energy due to the huge number of computations. To optimize the time for block chain mining, this paper proposes a Genetic algorithm based block mining (GAMB) approach to fetch the transactions from the unconfirmed pool of transactions in order to validate the block within a limited period of time. It is a population based algorithm which attempts to solve the proof of work for multiple transactions in parallel. The performance of GAMB is evaluated for transactions from 1000 to 5000.

Retinal images contain information about the retina's blood vessel structure to predict retinal diseases such as diabetics, obesity, glaucoma, etc. Segmentation of accurate retinal blood vessels is... Show More

Retinal images contain information about the retina's blood vessel structure to predict retinal diseases such as diabetics, obesity, glaucoma, etc. Segmentation of accurate retinal blood vessels is a challenging task in the low background of retinal images. Therefore, we proposed a Generalized Gamma Distribution probability distribution function (pdf) to extract the accurate vascular structure on the retinal images. The proposed approach is divided into processing steps, the Generalized Gamma distribution kernel, and the postprocessing step. In pre-processing, the conversion of a color retinal image into a grayscale image using PCA followed by the CLAHE method and the Toggle Contrast method enhances the grayscale images of the retina. The proposed matched filter of Generalized Gamma distribution generates the MFR images. The postprocessing step extracts the thick vessels and thin retinal blood vessels using the optimal thresholding technique. The results obtained on DIRVE database average accuracy 95.00% and the STARE database 93.85%, respectively.

background: Applications of deep learning for the societal issues are one of the debatable concerns where the community medicine and implication of artificial intelligence for the societal issues... Show More

background: Applications of deep learning for the societal issues are one of the debatable concerns where the community medicine and implication of artificial intelligence for the societal issues are a big concern. This article, it is shown the applications of neural networks in clinical practice for reproduction procedure enhancement. And this is a well-known issue where image analysis has the exact applications. In Embryology, fetal abnormality early-stage detection and diagnosis is one of the challenging tasks and thus, needs automation in the process of tomography and ultrasonic imaging. Also, Interpretation and accuracy in the medical imaging process are very important for accurate results.

Brain activity ensures the identification of emotions that are generally influenced by the personality of an individual. Similar to emotions, there exists a relationship between personality and... Show More

Brain activity ensures the identification of emotions that are generally influenced by the personality of an individual. Similar to emotions, there exists a relationship between personality and brain signals. These brain signals could be of a mentally healthy person or someone having psychological illness as well. In this paper, first, the survey related to work done on the personality prediction of healthy subjects is explored. Thereafter, the relationship between personality and psychologically ill subjects is also briefly presented based on the existing literature. Following this, an analysis of physiological signals (EEG) is also done for more understanding of personality prediction. ASCERTAIN – a multimodal database for implicit personality and recognition, is considered. It contains EEG recordings and self-annotated big five personality values of 58 students. Some time and frequency domain features are extracted and then put into various classifiers to predict the personality in five dimensions.