Showing papers by "Chandigarh University published in 2021"

Deep learning based detection and analysis of COVID-19 on chest X-ray images

Abstract: Covid-19 is a rapidly spreading viral disease that infects not only humans, but animals are also infected because of this disease. The daily life of human beings, their health, and the economy of a country are affected due to this deadly viral disease. Covid-19 is a common spreading disease, and till now, not a single country can prepare a vaccine for COVID-19. A clinical study of COVID-19 infected patients has shown that these types of patients are mostly infected from a lung infection after coming in contact with this disease. Chest x-ray (i.e., radiography) and chest CT are a more effective imaging technique for diagnosing lunge related problems. Still, a substantial chest x-ray is a lower cost process in comparison to chest CT. Deep learning is the most successful technique of machine learning, which provides useful analysis to study a large amount of chest x-ray images that can critically impact on screening of Covid-19. In this work, we have taken the PA view of chest x-ray scans for covid-19 affected patients as well as healthy patients. After cleaning up the images and applying data augmentation, we have used deep learning-based CNN models and compared their performance. We have compared Inception V3, Xception, and ResNeXt models and examined their accuracy. To analyze the model performance, 6432 chest x-ray scans samples have been collected from the Kaggle repository, out of which 5467 were used for training and 965 for validation. In result analysis, the Xception model gives the highest accuracy (i.e., 97.97%) for detecting Chest X-rays images as compared to other models. This work only focuses on possible methods of classifying covid-19 infected patients and does not claim any medical accuracy.

Application of Blockchain and Internet of Things in Healthcare and Medical Sector: Applications, Challenges, and Future Perspectives

Abstract: Internet of Things (IoT) is one of the recent innovations in Information Technology, which intends to interconnect the physical and digital worlds. It introduces a vision of smartness by enabling communication between objects and humans through the Internet. IoT has diverse applications in almost all sectors like Smart Health, Smart Transportation, and Smart Cities, etc. In healthcare applications, IoT eases communication between doctors and patients as the latter can be diagnosed remotely in emergency scenarios through body sensor networks and wearable sensors. However, using IoT in healthcare systems can lead to violation of the privacy of patients. Thus, security should be taken into consideration. Blockchain is one of the trending research topics nowadays and can be applied to the majority of IoT scenarios. Few major reasons for using the Blockchain in healthcare systems are its prominent features, i.e., Decentralization, Immutability, Security and Privacy, and Transparency. This paper’s main objective was to enhance the functionality of healthcare systems using emerging and innovative computer technologies like IoT and Blockchain. So, initially, a brief introduction to the basic concepts of IoT and Blockchain is provided. After this, the applicability of IoT and Blockchain in the medical sector is explored in three major areas—drug traceability, remote patient-monitoring, and medical record management. At last, the challenges of deploying IoT and Blockchain in healthcare systems are discussed.

A Hybrid CNN-SVM Threshold Segmentation Approach for Tumor Detection and Classification of MRI Brain Images

Abstract: Objective In this research paper, the brain MRI images are going to classify by considering the excellence of CNN on a public dataset to classify Benign and Malignant tumors. Materials and Methods Deep learning (DL) methods due to good performance in the last few years have become more popular for Image classification. Convolution Neural Network (CNN), with several methods, can extract features without using handcrafted models, and eventually, show better accuracy of classification. The proposed hybrid model combined CNN and support vector machine (SVM) in terms of classification and with threshold-based segmentation in terms of detection. Result The findings of previous studies are based on different models with their accuracy as Rough Extreme Learning Machine (RELM)-94.233%, Deep CNN (DCNN)-95%, Deep Neural Network (DNN) and Discrete Wavelet Autoencoder (DWA)-96%, k-nearest neighbors (kNN)-96.6%, CNN-97.5%. The overall accuracy of the hybrid CNN-SVM is obtained as 98.4959%. Conclusion In today's world, brain cancer is one of the most dangerous diseases with the highest death rate, detection and classification of brain tumors due to abnormal growth of cells, shapes, orientation, and the location is a challengeable task in medical imaging. Magnetic resonance imaging (MRI) is a typical method of medical imaging for brain tumor analysis. Conventional machine learning (ML) techniques categorize brain cancer based on some handicraft property with the radiologist specialist choice. That can lead to failure in the execution and also decrease the effectiveness of an Algorithm. With a brief look came to know that the proposed hybrid model provides more effective and improvement techniques for classification.

A novel content-based image retrieval approach for classification using GLCM features and texture fused LBP variants

Abstract: This paper presents a content-based image retrieval technique that focuses on extraction and reduction in multiple features. To obtain multi-level decomposition of the image by extracting approximation and correct coefficients, discrete wavelet transformation is applied to the RGB channels initially. Therefore, both approximation and correct coefficients are applied to the dominant rotated local binary pattern termed as texture descriptor which is computationally effective and rotationally invariant. For a local neighbor patch, a rotation invariance function image is obtained by measuring the descriptor relative to the reference. The proposed approach contains the complete structural information extracted from the local binary patterns and also extracts the additional information using the information of magnitude, thereby achieving extra discriminative power. Then, GLCM description is used by obtaining the dominant rotated local binary pattern image to extract the statistical characteristics for texture image classification. The proposed technique is applied to CORAL dataset with the help of particle swarm optimization-based feature selector to minimize the number of features that can be used during the classification process. The three classifiers, i.e., support vector machine, K-nearest neighbor, and decision tree, are trained and tested. The comparison is based in terms of Accuracy, precision, recall, and F-measure performance metrics for classification. Experimental results show that the proposed approach achieves better accuracy, precision, recall, and F-measure values for most of the CORAL dataset classes.

A Novel Patient-Centric Architectural Framework for Blockchain-Enabled Healthcare Applications

Abstract: With the proliferation of information and communication technology in every walks of the society, including healthcare services, digitization, and increased sophistication have been gaining pace, digital healthcare alternatives such as electronic healthcare record (EHR) have gained prominence with increased patients’ data volume. However, traditional EHR-based systems are plagued by data loss risks, security and immutability consensus over health records, gapped communication among constituted hospitals, and inefficient clinical data retrieval systems, among others. Blockchain has been developed as a decentralized technology that holds the promise to address the aforesaid facilities in EHR-based systems. This article presents a patient-centric design of a decentralized healthcare management system with blockchain-based EHR using javascript-based smart contracts. A working prototype based on hyperledger fabric and composer technology has also been implemented which guarantees the security of the proposed model. Experiments with the hyperledger caliper benchmarking tool provide performance such as latency, throughput, resource utilization, and so on under varied scenarios and control parameters. The results affirm the efficacy of the proposed approach.

A Survey of Deep Convolutional Neural Networks Applied for Prediction of Plant Leaf Diseases.

Abstract: In the modern era, deep learning techniques have emerged as powerful tools in image recognition. Convolutional Neural Networks, one of the deep learning tools, have attained an impressive outcome in this area. Applications such as identifying objects, faces, bones, handwritten digits, and traffic signs signify the importance of Convolutional Neural Networks in the real world. The effectiveness of Convolutional Neural Networks in image recognition motivates the researchers to extend its applications in the field of agriculture for recognition of plant species, yield management, weed detection, soil, and water management, fruit counting, diseases, and pest detection, evaluating the nutrient status of plants, and much more. The availability of voluminous research works in applying deep learning models in agriculture leads to difficulty in selecting a suitable model according to the type of dataset and experimental environment. In this manuscript, the authors present a survey of the existing literature in applying deep Convolutional Neural Networks to predict plant diseases from leaf images. This manuscript presents an exemplary comparison of the pre-processing techniques, Convolutional Neural Network models, frameworks, and optimization techniques applied to detect and classify plant diseases using leaf images as a data set. This manuscript also presents a survey of the datasets and performance metrics used to evaluate the efficacy of models. The manuscript highlights the advantages and disadvantages of different techniques and models proposed in the existing literature. This survey will ease the task of researchers working in the field of applying deep learning techniques for the identification and classification of plant leaf diseases.

Spatial flood susceptibility prediction in Middle Ganga Plain: comparison of frequency ratio and Shannon’s entropy models

Abstract: This work focuses on comparing results of flood susceptibility modelling in the part of Middle Ganga Plain, Ganga foreland basin. Following inclusivity rule, 12 major flood explanatory factors incl...

Examining the Moderating Effect of Perceived Benefits of Maintaining Social Distance on E-learning Quality During COVID-19 Pandemic

Abstract: Technology has influenced every aspect of our living, and education is not an exception. During the current pandemic period of COVID-19, the latent motive of maintaining social distancing is leadin...

An Efficient Spam Detection Technique for IoT Devices Using Machine Learning

Abstract: The Internet of Things (IoT) is a group of millions of devices having sensors and actuators linked over wired or wireless channel for data transmission. IoT has grown rapidly over the past decade with more than 25 billion devices expected to be connected by 2020. The volume of data released from these devices will increase many-fold in the years to come. In addition to an increased volume, the IoT devices produces a large amount of data with a number of different modalities having varying data quality defined by its speed in terms of time and position dependency. In such an environment, machine learning (ML) algorithms can play an important role in ensuring security and authorization based on biotechnology, anomalous detection to improve the usability, and security of IoT systems. On the other hand, attackers often view learning algorithms to exploit the vulnerabilities in smart IoT-based systems. Motivated from these, in this article, we propose the security of the IoT devices by detecting spam using ML. To achieve this objective, Spam Detection in IoT using Machine Learning framework is proposed. In this framework, five ML models are evaluated using various metrics with a large collection of inputs features sets. Each model computes a spam score by considering the refined input features. This score depicts the trustworthiness of IoT device under various parameters. REFIT Smart Home data set is used for the validation of proposed technique. The results obtained proves the effectiveness of the proposed scheme in comparison to the other existing schemes.

Investigation on mechanical, tribological and microstructural properties of Al–Mg–Si–T6/SiC/muscovite-hybrid metal-matrix composites for high strength applications

Abstract: The wide range of aluminium variants (alloys and composites) has made it an important material for aviation, automotive components, auto-transmission locomotive section units, SCUBA tanks, ship, vessels, submarines fabrication and design etc regardless of the fact that the aluminium alloys were being utilized in myriads of sectors owing to its exceptional superior and versatile functional characteristics, the property such as wear-resistant ought to be enhanced in order to further prolong diverse spectrum of applications An aluminium alloy having lower hardness and tensile strength has been incorporated with silicon carbide that drastically strengthens the properties This study involves fabrication of aluminium silicon carbide with muscovite/hydrated aluminium potassium silicate/aluminosilicate in stir casting method to obtain a hybrid metal matrix composite Maintaining a constant amount of aluminium and silicon carbide, muscovite or hydrated aluminium potassium silicate is varied to obtain three distinctive compositions of (Al/SiC/muscovite) composites The mechanical characteristics like tensile-strength, flexural-strength, toughness, hardness, scratch adhesion, percent-porosity and density were studied The dispersion of muscovite and silicon carbide particles were observed by viewing the microstructure photographs obtained using optical microscopy and Scanning Electron Microscope (SEM) EDAX analysis affirms the presence of reinforcing constituents in Al–Mg–Si–T6 alloy matrix A drum type wear apparatus was utilized to evaluate the percentage of wear-loss in different compositions using different loads and it was found that the wear-loss decreases linearly as the muscovite percentage was increased

A Statistical Analysis of Impact of COVID19 on the Global Economy and Stock Index Returns

Abstract: The outbreak of pandemic COVID-19 across the world has completely disrupted the political, social, economic, religious, and financial structures of the world. According to the data of April 22nd, 2020, more than 4.6 million people have been screened, in which the infection has made more than 2.7 million people positive, in which 182,740 people have died due to infection. More than 80 countries have closed their borders from transitioning countries, ordered businesses to close, instructed their populations to self-quarantine, and closed schools to an estimated 1.5 billion children. The world’s top ten economies such as the United States, China, Japan, Germany, United Kingdom, France, India, Italy, Brazil, and Canada stand on the verge of complete collapse. In addition, stock markets around the world have been pounded, and tax revenue sources have fallen off a cliff. The epidemic due to infection is having a noticeable impact on global economic development. It is estimated that by now the virus could exceed global economic growth by more than 2.0% per month if the current situation persists. Global trade may also fall from 13 to 32% depending on the depth and extent of the global economic slowdown. The full impact will not be known until the effects of the epidemic occurred. This research analyses the impact of COVID-19 on the economic growth and stock market as well. The aim of this research is to present how well COVID-19 correlated with economic growth through gross domestic products (GDP). In addition, the research considers the top five other tax revenue sources like S&P500 (GPSC), Crude oil (CL = F), Gold (GC = F), Silver (SI = F), Natural Gas (NG = F), iShares 20 + Year Treasury Bond (TLT), and correlate with the COVID-19. To fulfill the statistical analysis purpose this research uses publically available data from yahoo finance, IMF, and John Hopkins COVID-19 map with regression models that revealed a moderated positive correlation between them. The model was used to track the impact of COVID 19 on economic variation and the stock market to see how well and how far in advance the prediction holds true, if at all. The hope is that the model will be able to correctly make predictions a couple of quarters in advance, and describe why the changes are occurring. This research can support how policymakers, business strategy makers, and investors can understand the situation and use the model for prediction.

Emerging role of non-coding RNA in health and disease.

Abstract: Human diseases have always been a significant turf of concern since the origin of mankind. It is cardinal to know the cause, treatment, and cure for every disease condition. With the advent and advancement in technology, the molecular arena at the microscopic level to study the mechanism, progression, and therapy is more rational and authentic pave than a macroscopic approach. Non-coding RNAs (ncRNAs) have now emerged as indispensable players in the diagnosis, development, and therapeutics of every abnormality concerning physiology, pathology, genetics, epigenetics, oncology, and developmental diseases. This is a comprehensive attempt to collate all the existing and proven strategies, techniques, mechanisms of genetic disorders including Silver Russell Syndrome, Fascio- scapula humeral muscular dystrophy, cardiovascular diseases (atherosclerosis, cardiac fibrosis, hypertension, etc.), neurodegenerative diseases (Spino-cerebral ataxia type 7, Spino-cerebral ataxia type 8, Spinal muscular atrophy, Opitz-Kaveggia syndrome, etc.) cancers (cervix, breast, lung cancer, etc.), and infectious diseases (viral) studied so far. This article encompasses discovery, biogenesis, classification, and evolutionary prospects of the existence of this junk RNA along with the integrated networks involving chromatin remodelling, dosage compensation, genome imprinting, splicing regulation, post-translational regulation and proteomics. In conclusion, all the major human diseases are discussed with a facilitated technology transfer, advancements, loopholes, and tentative future research prospects have also been proposed.

MBCP: Performance Analysis of Large Scale Mainstream Blockchain Consensus Protocols

Abstract: As Blockchain innovation picks up popularity in many areas, it is frequently hailed as a sound innovation. Because of the decentralization and encryption, many imagine that data put away in a Blockchain is and will consistently be protected. Among various abstraction layers of Blockchain architecture, the consensus layer is the core component behind the performance and security measures of the Blockchain network. Consensus mechanisms are a critical component of a Blockchain system’s long-term stability. Consensus forms the core of blockchain technology. Therefore, a range of consensus protocols has been introduced to maximize Blockchain systems’ efficiency and meet application domains’ individual needs. This research paper describes the layered architecture of Blockchain. A comprehensive review of mainstream consensus protocols mainly Proof of Work (PoW), Proof of Stake (PoS), Delegated Proof of Stake (DPoS), Proof of Activity (PoA) is presented in the paper. These mainstream consensus protocols have been explained and detailed performance analysis of these consensus protocols has been done. We have proposed a performance matrix of these consensus protocols based on different parameters like Degree of decentralization, Latency, Fault Tolerance Rate, Scalability, etc. Consensus protocols being the core of a strong fault-tolerant secured blockchain system, the proposed work intends to help inappropriate protocol selection and further research on strengthening trust and ownership in the technology. Depending upon different parameters like decentralization which is low in POA compared to other protocols, whereas POW is non-scalable, so depending on the priority of a particular performance parameter, the paper will help in the selection of a specific protocol.

Deep-Learning-Based Blockchain Framework for Secure Software-Defined Industrial Networks

Abstract: Software-defined industrial network has emer-ged as an autonomous ecosystem where the network control relies on a centralized controller to provide seamless data transfer. However, the reliance on a centralized controller can lead to several challenges, such as single point of failure. An adversary can initiate a denial of service attack and limit the availability of the controller by projecting malicious or uncontrolled traffic flows. To overcome this, in this article, a deep-learning-based blockchain framework is designed for providing secure software-defined industrial network. In this framework, a blockchain mechanism is designed wherein all the switch are registered, verified (using zero-knowledge proof), and, thereafter, validated in the blockchain using a voting-based consensus mechanism. A deep Boltzmann machine based flow analyzer is deployed at the control plane to identify the anomalous switch requests. The evaluation is performed using a mininet emulator wherein the results obtained depict the superiority of the proposed framework.

Functional importance of bioactive compounds of foods with Potential Health Benefits: A review on recent trends

Abstract: Researchers are nowadays focused on the importance of bioactive compounds (BACs) of natural origin, which are secondary metabolites derived from seeds, food and fermentation-based metabolic products. Several factors such as food matrix, molecule's size, environmental factors and association with gastrointestinal (GI) material, can impede the bioavailability and absorption of these BACs in host cell systems and target sites. Natural BACs like flavonoids, carotenoids, phenolic acids, etc. are particularly important for the production of functional foods and medicinal products, which may have industrial relevance also. Thus the isolation of such natural BACs can be promising multifunctional extracts that can be used in food applications to aid health-promoting effects in host cell systems. Sufficient evidences are however required to make a health claim and to promote functional foods in international markets. This review focuses primarily on recent developments and modulatory roles of potential health-promoting food BACs. Analyses on the techno-chemical and physiological features of functional food components are addressed besides discussing their analytical methods, bioavailability and bioaccessibility. The current study also considers the health potential of BACs and their rising demand in form of functional foods in the world.

CPIDM: A Clustering-Based Profound Iterating Deep Learning Model for HSI Segmentation

Abstract: The existing work on unsupervised segmentation frequently does not present any statistical extent to estimating and equating procedures, gratifying a qualitative calculation. Furthermore, regardless of the datum that enormous research is dedicated to the advancement of a novel segmentation approach and upgrading the deep learning techniques, there is an absence of research comprehending the assessment of eminent conventional segmentation methodologies for HSI. In this paper, to moderately fill this gap, we propose a direct method that diminishes the issues to some extent with the deep learning methods in the arena of a HSI space and evaluate the proposed segmentation techniques based on the method of the clustering-based profound iterating deep learning model for HSI segmentation termed as CPIDM. The proposed model is an unsupervised HSI clustering technique centered on the density of pixels in the spectral interplanetary space and the distance concerning the pixels. Furthermore, CPIDM is a fully convolutional neural network. In general, fully convolutional nets remain spatially invariant preventing them from modeling position-reliant outlines. The proposed network maneuvers this by encompassing an innovative position inclined convolutional stratum. The anticipated unique edifice of deep unsupervised segmentation deciphers the delinquency of oversegmentation and nonlinearity of data due to noise and outliers. The spectrum efficacy is erudite and incidental from united feedback via deep hierarchy with pooling and convolutional strata; as a consequence, it formulates an affiliation among class dissemination and spectra along with three-dimensional features. Moreover, the anticipated deep learning model has revealed that it is conceivable to expressively accelerate the segmentation process without substantive quality loss due to the existence of noise and outliers. The proposed CPIDM approach outperforms many state-of-the-art segmentation approaches that include watershed transform and neuro-fuzzy approach as validated by the experimental consequences.

Energy efficient optimal parent selection based routing protocol for Internet of Things using firefly optimization algorithm

Abstract: Energy conservation is a major challenge in the Internet of Things (IoT) as the number of resource‐constrained devices is connected to the network. Routing plays a vital role in IoT to ext...

Influence of processing conditions on the properties of thermal sprayed coating: a review

Abstract: Thermal spray coatings are a group of coating processes that enhance the performance of parts by adding functionality to surfaces. In the past few decades, thermal spray coatings technology was use...

Exceptional antibacterial and cytotoxic potency of monodisperse greener AgNPs prepared under optimized pH and temperature.

Abstract: In the present work, silver nanoparticles were prepared by using the extract of Camellia Sinensis. The extract contains phytochemicals which are mainly polyphenols acting as the natural reducing and stabilizing agents leading to the formation of uniformly dispersed and stabilized silver nanoparticles. The synthesis of silver nanoparticles was significantly influenced by the impact of the pH, as well as temperature conditions. It was found that at pH 5 and 25 °C, nanoparticles of different morphologies (spherical, polygonal, capsule) and sizes were formed. However, with the increase in temperature from 25 °C to 65 °C but at the same pH, these particles started attaining the spherical shape of different sizes owing to an increase in the reduction rate. Furthermore, for the reaction of the mixture at 65 °C, an increase in pH from 5 to 11 led to an increase in the monodispersity of spherically shaped nanoparticles, attributed to the hydroxide ions facilitated reduction. The prepared nanoparticles were investigated for their antibacterial activity using Nathan’s Agar Well-Diffusion method. It was found that AgNPs prepared at pH 9 and 65 °C demonstrated strong antibacterial activity against gram-negative Escherichia coli in contrast to gram-positive Staphylococcus aureus. In reference to the cytotoxic potency, the prepared AgNPs showed clear cytotoxicity for HeLa cells and showcased a close relationship between activity and concentration as evidenced by the decrease in the percentage (100 to 30%) of metabolically active cells up to 25 µM–75 µM concentration of silver nanoparticles.

A Deep Learning-Based Blockchain Mechanism for Secure Internet of Drones Environment

Abstract: Drones are equipped with high-vision cameras, advanced sensors, and GPS receivers to deliver diverse services from high altitude thereby creating an airborne network. In this environment, physical things (drones, sensors, etc.,) are controlled using computational algorithms to form a cyber-physical system for the Internet of drones. Although the drones provide manifold benefits still there are many issues (security, privacy, and data integrity) which must be resolved before the usage of drones in smart cyber-physical systems. So, in this paper, a blockchain-based security mechanism for cyber-physical systems is proposed to ensure secure transfer of information among drones. In this mechanism, the miner node is selected using a deep learning-based approach, i.e., a deep Boltzmann machine, using features like computational resources, the available battery power, and flight time of the drone. The proposed mechanism is evaluated based on different performance metrics and the results obtained show the potential benefits of the proposed scheme.