Search

Social networking sites in the most modernized world are flooded with large data volumes. Extracting the sentiment polarity of important aspects is necessary;as it helps to determine people’s opinions through what they write. The Coronavirus pandemic has invaded the world and been given a mention in the social media on a large scale. In a very short period of time, tweets indicate unpredicted increase of coronavirus. They reflect people’s opinions and thoughts with regard to coronavirus and its impact on society. The research community has been interested in discovering the hidden relationships from short texts such as Twitter and Weiboa;due to their shortness and sparsity. In this paper, a hierarchical twitter sentiment model (HTSM) is proposed to show people’s opinions in short texts. The proposed HTSM has two main features as follows: constructing a hierarchical tree of important aspects from short texts without a predefined hierarchy depth and width, as well as analyzing the extracted opinions to discover the sentiment polarity on those important aspects by applying a valence aware dictionary for sentiment reasoner (VADER) sentiment analysis. The tweets for each extracted important aspect can be categorized as follows: strongly positive, positive, neutral, strongly negative, or negative. The quality of the proposed model is validated by applying it to a popular product and a widespread topic. The results show that the proposed model outperforms the state-of-the-art methods used in analyzing people’s opinions in short text effectively.

Due to the increased disease occurrence rates in humans, the need for the Automated Disease Diagnosis (ADD) systems is also raised. Most of the ADD systems are proposed to support the doctor during the screening and decision making process. This research aims at developing a Computer Aided Disease Diagnosis (CADD) scheme to categorize the brain tumour of 2D MRI slices into Glioblastoma/Glioma class with better accuracy. The main contribution of this research work is to develop a CADD system with Convolutional-Neural-Network (CNN) supported segmentation and classification. The proposed CADD framework consist of the following phases; (i) Image collection and resizing, (ii) Automated tumour segmentation using VGG-UNet, (iv) Deep-feature extraction using VGG16 network, (v) Handcrafted feature extraction, (vi) Finest feature choice by firefly-algorithm, and (vii) Serial feature concatenation and binary classification. The merit of the executed CADD is confirmed using an investigation realized using the benchmark as well as clinically collected brain MRI slices. In this work, a binary classification with a 10-fold cross validation is implemented using well known classifiers and the results attained with the SVM-Cubic (accuracy >98%) is superior. This result confirms that the combination of CNN assisted segmentation and classification helps to achieve enhanced disease detection accuracy.

Haze reduces the perceived scene radiance and limits the visibility in outdoor images. The visibility is different for each scene point and is proportional to haze thickness, and distance from the camera. Transmission map represents percentage of scene radiance captured by the camera and is unknown for every pixel. This work generalizes the concept of haze-lines, and presents an algorithm to estimate transmission map and restore scene radiance accurately. The proposed technique depends on the perception that the colors of haze-free natural images can be well approximated by a set of distinct colors and their shades (natural color-palette) that can be learned beforehand. In presence of haze, the pixels forming a cluster in haze-free image, make a line (haze-line) in RGB color space. The two endpoints of this haze-line are the haze-free color and the airlight. We propose that these haze-lines can be generalized, with one end as learned color-palette of natural images and the other as airlight. Hence the scene radiance end can be made independent of underlying image. The algorithm recovers the transmission map, by determining membership of each pixel to a given haze-line and finding how far-off it is from its learned color-palette. The algorithm is linear to the size of image, and requires just a collection of haze-free natural images for training. The results obtained on a diverse range of images demonstrate the efficiency of proposed algorithm.

Atrial fibrillation (AF) is the type of arrhythmia that raises possibility of severe health problems such as heart failure and stroke and it is known that a major risk factor of AF includes overweight and obesity. Based on this association between such health-related indicators, we propose a smart scale that is capable of measuring weight and electrocardiography (ECG) simultaneously. The scale was developed using Arduino Uno, a Wheatstone bridge load cell, and ECG sensors. The ECG signals were processed to compute heart rate (in other words, RR interval). The smart scale was evaluated with four healthy volunteers in terms of reliability showing high agreement with a commercial device for ECG monitoring. In addition, it implements Atrial Fibrillation (AF) detection using machine-learning classifiers including a k-Nearest Neighbor (kNN) method, a Decision Tree (DT), and a Neural Network (NN) on relatively short recordings of ECG obtained while using the scale. The root mean square of the successive differences between heart beats (RMSSD) and the Shannon entropy of the RR interval (ECG features) were extracted from ECG signals for AF detection. Performance of AF detection was tested with patients who were treated at a Cardiology Center after balancing data by applying over- and under-sampling techniques such as Synthetic Minority Over-sampling Technique (SMOTE) and the Tomek Link (T-Link) algorithm. After addressing the data imbalance, the AF detection performance of each classifier (kNN, DT, and NNs) was 98.9%, 97.8%, and 98.9% respectively. This work has successfully demonstrated weight and cardio activity monitoring features while using a scale that may help keep the records of sensitive health related indexes on a daily basis.

Here, we use multi-type feature fusion and selection to predict COVID-19 infections on chest computed tomography (CT) scans The scheme operates in four steps Initially, we prepared a database containing COVID-19 pneumonia and normal CT scans These images were retrieved from the Radiopaedia COVID-19 website The images were divided into training and test sets in a ratio of 70:30 Then, multiple features were extracted from the training data We used canonical correlation analysis to fuse the features into single vectors;this enhanced the predictive capacity We next implemented a genetic algorithm (GA) in which an Extreme Learning Machine (ELM) served to assess GA fitness Based on the ELM losses, the most discriminatory features were selected and saved as an ELM Model Test images were sent to the model, and the best-selected features compared to those of the trained model to allow final predictions Validation employed the collected chest CT scans The best predictive accuracy of the ELM classifier was 93 9%;the scheme was effective

Stock market forecasting is an important research area, especially for better business decision making Efficient stock predictions continue to be significant for business intelligence Traditional short-term stock market forecasting is usually based on historical market data analysis such as stock prices, moving averages, or daily returns However, major events’ news also contains significant information regarding market drivers An effective stock market forecasting system helps investors and analysts to use supportive information regarding the future direction of the stock market This research proposes an efficient model for stock market prediction The current proposed study explores the positive and negative effects of coronavirus events on major stock sectors like the airline, pharmaceutical, e-commerce, technology, and hospitality We use the Twitter dataset for calculating the coronavirus sentiment with a Long Short-Term Memory (LSTM) model to improve stock prediction The LSTM has the advantage of analyzing relationship between time-series data through memory functions The performance of the system is evaluated by Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) The results show that performance improves by using coronavirus event sentiments along with the LSTM prediction model © 2021 Tech Science Press All rights reserved

From the perspective of visual interaction, this paper examines the ethnic characteristics of visual features clothing and the extraction area of the totem ethnic clothing. We employed a feature extraction approach based on extensive data colour and used a classifier to identify the various totems of the ethnic clothing image. We further used PS to extract colour intensities and the DBSCAN algorithm to extract the characteristics of various ethnic colours and examine the phenomenon of judging culture research methods with colour characteristics. With the help of PS, the colour value of multiple images is proposed to provide a scientific and rigorous research method for ethnic minority colour research, improving the efficiency of the DBSCAN clustering algorithm for colour extraction. The obtained results can assist designers to reproduce colour images in their design work. We employed the support vector machine (SVM) to build a classification model to classify and recognize the extracted feature algorithm’s fusion features. The study found that the fusion feature classification and recognition model have higher recognition accuracy. This research lays a good foundation for the information processing of ethnic costumes and contributes to the inheritance and protection of ethnic costume culture.

In March 2020, the World Health Organization declared the coronavirus disease (COVID-19) outbreak as a pandemic due to its uncontrolled global spread. Reverse transcription polymerase chain reaction is a laboratory test that is widely used for the diagnosis of this deadly disease. However, the limited availability of testing kits and qualified staff and the drastically increasing number of cases have hampered massive testing. To handle COVID19 testing problems, we apply the Internet of Things and artificial intelligence to achieve self-adaptive, secure, and fast resource allocation, real-time tracking, remote screening, and patient monitoring. In addition, we implement a cloud platform for efficient spectrum utilization. Thus, we propose a cloud based intelligent system for remote COVID-19 screening using cognitive radio-based Internet of Things and deep learning. Specifically, a deep learning technique recognizes radiographic patterns in chest computed tomography (CT) scans. To this end, contrast-limited adaptive histogram equalization is applied to an input CT scan followed by bilateral filtering to enhance the spatial quality. The image quality assessment of the CT scan is performed using the blind/referenceless image spatial quality evaluator. Then, a deep transfer learning model, VGG-16, is trained to diagnose a suspected CT scan as either COVID-19 positive or negative. Experimental results demonstrate that the proposed VGG-16 model outperforms existing COVID-19 screening models regarding accuracy, sensitivity, and specificity. The results obtained from the proposed system can be verified by doctors and sent to remote places through the Internet.

Fog computing is a modern computing model which offers geographically dispersed end-users with the latency-aware and highly scalable services. It is comparatively safer than cloud computing, due to information being rapidly stored and evaluated closer to data sources on local fog nodes. The advent of Blockchain (BC) technology has become a remarkable, most revolutionary, and growing development in recent years. BT’s open platform stresses data protection and anonymity. It also guarantees data is protected and valid through the consensus process. BC is mainly used in money-related exchanges; now it will be used in many domains, including healthcare; This paper proposes efficient Blockchain-based secure healthcare services for disease prediction in fog computing. Diabetes and cardio diseases are considered for prediction. Initially, the patient health information is collected from Fog Nodes and stored on a Blockchain. The novel rule-based clustering algorithm is initially applied to cluster the patient health records. Finally, diabetic and cardio diseases are predicted using feature selection based adaptive neuro-fuzzy inference system (FS-ANFIS). To evaluate the performance of the proposed work, an extensive experiment and analysis were conducted on data from the real world healthcare. Purity and NMI metrics are used to analyze the performance of the rule based clustering and the accuracy is used for prediction performance. The experimental results show that the proposed work efficiently predicts the disease. The proposed work reaches more than 81% of prediction accuracy compared to the other neural network algorithms.

Coronavirus 19 (COVID-19) can cause severe pneumonia that may be fatal. Correct diagnosis is essential. Computed tomography (CT) usefully detects symptoms of COVID-19 infection. In this retrospective study, we present an improved framework for detection of COVID-19 infection on CT images;the steps include pre-processing, segmentation, feature extraction/ fusion/selection, and classification. In the pre-processing phase, a Gabor wavelet filter is applied to enhance image intensities. A marker-based, watershed controlled approach with thresholding is used to isolate the lung region. In the segmentation phase,COVID-19 lesions are segmented using an encoder- /decoder-based deep learning model in which deepLabv3 serves as the bottleneck and mobilenetv2 as the classification head. DeepLabv3 is an effective decoder that helps to refine segmentation of lesion boundaries. The model was trained using fine-tuned hyperparameters selected after extensive experimentation. Subsequently, the Gray Level Co-occurrence Matrix (GLCM) features and statistical features including circularity, area, and perimeters were computed for each segmented image. The computed features were serially fused and the best features (those that were optimally discriminatory) selected using a Genetic Algorithm (GA) for classification. The performance of the method was evaluated using two benchmark datasets: The COVID-19 Segmentation and the POF Hospital datasets. The results were better than those of existing methods. © 2021 Tech Science Press. All rights reserved.

The recent COVID-19 pandemic caused by the novel coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has had a significant impact on human life and the economy around the world. A reverse transcription polymerase chain reaction (RT-PCR) test is used to screen for this disease, but its low sensitivity means that it is not sufficient for early detection and treatment. As RT-PCR is a time-consuming procedure, there is interest in the introduction of automated techniques for diagnosis. Deep learning has a key role to play in the field of medical imaging. The most important issue in this area is the choice of key features. Here, we propose a set of deep learning features based on a system for automated classification of computed tomography (CT) images to identify COVID-19. Initially, this method was used to prepare a database of three classes: Pneumonia, COVID-19, and Healthy. The dataset consisted of 6000 CT images refined by a hybrid contrast stretching approach. In the next step, two advanced deep learning models (ResNet50 and DarkNet53) were fine-tuned and trained through transfer learning. The features were extracted from the second last feature layer of both models and further optimized using a hybrid optimization approach. For each deep model, the Rao-1 algorithm and the PSO algorithm were combined in the hybrid approach. Later, the selected features were merged using the new minimum parallel distance non-redundant (PMDNR) approach. The final fused vector was finally classified using the extreme machine classifier. The experimental process was carried out on a set of prepared data with an overall accuracy of 95.6%. Comparing the different classification algorithms at the different levels of the features demonstrated the reliability of the proposed framework.

Malware is a rapidly increasing menace to modern computing. Malware authors continually incorporate various sophisticated features like code obfuscations to create malware variants and elude detection by existing malware detection systems. The classification of unseen malware variants with similar characteristics into their respective families is a significant challenge, even if the classifier is trained with known variants belonging to the same family. The identification and extraction of distinct features for each malware is another issue for generalizing the malware detection system. Features that contribute to the generalization capability of the classifier are difficult to be engineered with modifications in each malware. Conventional malware detection systems employ static signature-based methods and dynamic behavior-based methods, which are inefficient in analyzing and detecting advanced and zero-day malware. To address these issues, this work employs a visualization approach where malware is represented as 2D images and proposes a robust machine learning-based anti-malware solution. The proposed system is based on a layered ensemble approach that mimics the key characteristics of deep learning techniques but performs better than the latter. The proposed system does not require hyperparameter tuning or backpropagation and works with reduced model complexity. The proposed model outperformed other state-of-the-art techniques with a detection rate of 98.65%, 97.2%, and 97.43% for Malimg, BIG 2015, and MaleVis malware datasets, respectively. The results demonstrate that the proposed solution is effective in identifying new and advanced malware due to its diverse features.

Malware is `malicious software' programs that carry out many of the cyberattacks on the Internet, including cybercrime, fraud, scams and nation-state cyberwar. These malicious software programs come in a wide range of different classifications such as viruses, Trojans, worms, spyware, botnet malware, ransomware, Rootkit, etc. Ransomware is class of malware that holds the victim's data hostage by encrypting the data on a user's computer to make it unavailable to the user and only decrypt it after the user pays a ransom in the form of a sum of money. To avoid detection, different variants of ransomware utilise one or more techniques in their attack flow including Machine Learning (ML) algorithms. There is, therefore, a need to understand the techniques used ransomware development and their deployment strategy in order to understand their attack flow better to develop appropriate countermeasures. In this paper, we propose DNAact-Ran, A Digital DNA Sequencing Engine for Ransomware Detection Using Machine Learning. DNAact-Ran utilises Digital DNA sequencing design constraints and k-mer frequency vector. To measure the efficacy of the proposed approach, we evaluated DNAact-Run on 582 ransomware and 942 goodware instances to measure the performance of precision, recall, f-measure and accuracy. Compared to other methods, the evaluation results show that DNAact-Run can predict and detect ransomware accurately and effectively.

Underwater wireless sensor networks (UWSNs) is emerging as an advance terminology for monitoring and controlling the underwater aquatic life. This technology determines the undiscovered resources present in the water through computational intelligence (CI) techniques. CI here pertains to the capability of a system to acquire a specific task from data or experimental surveillance below the water. In today's time data is considered as the identity for everything that exists in nature, whether that data is related to human beings, machines or any type of device like internet of underwater things (IoUT). The collected data should be correct, complete and fulfill the requirements of a particular task to be done. Underwater data collection is very tough because of sensors mobility due to water drift 3 meters/sec, crest and trough. A lot of packet drop also exists due to underwater conditions that hurdles the data collection process. Various techniques already exists for efficient collection of data below the water but these are not properly classified. This manuscript has summarized the concept of data collection in UWSN along with its classification based on routing. Also, a short discussion about existence of CORONA below the water along with water purification is carried out. Furthermore, some data routing approaches are also analyzed on the basis of quality of service parameters and the current challenges to be tackled during data collection are also discussed.

The resource-constrained nature and large-scale adoption of Internet of Things (IoT) have a significant challenge for securing IoT applications. This necessitates a robust and lightweight security architecture and schemes as the existing traditional Internet security architecture and protocols require huge resources and lack of end-to-end security mechanism. In this research, a resource efficient end-to-end security scheme has been proposed by offloading computations and storage of security parameters to fog nodes in the vicinity. In addition, a symmetric-key payload encryption has been used to minimize the overhead of message communication in the resource-contested IoT environment. The analysis shows that the proposed scheme outperforms Transport Layer Security (TLS) in resource usage while it maintains equivalent authenticated end-to-end communication between communicating IoT nodes. The proposed end-to-end security scheme saves more communication bandwidth and incurs less overhead as compared to existing TLS-based security schemes. In particular, the proposed system uses less number of handshakes and achieves a decrease in the number of transmitted messages (approximately 184 bytes as compared to compared TSL message size of 332 bytes) for every handshake. Further, it has been demonstrated through experiments that the proposed security method incurs less overheads as compared to the TLS bandwidth consumption considering a single connection session during message subscription.