Showing papers by "Techno India published in 2021"

Prediction of Chronic Kidney Disease - A Machine Learning Perspective

Abstract: Chronic Kidney Disease is one of the most critical illness nowadays and proper diagnosis is required as soon as possible. Machine learning technique has become reliable for medical treatment. With the help of a machine learning classifier algorithms, the doctor can detect the disease on time. For this perspective, Chronic Kidney Disease prediction has been discussed in this article. Chronic Kidney Disease dataset has been taken from the UCI repository. Seven classifier algorithms have been applied in this research such as artificial neural network, C5.0, Chi-square Automatic interaction detector, logistic regression, linear support vector machine with penalty L1 & with penalty L2 and random tree. The important feature selection technique was also applied to the dataset. For each classifier, the results have been computed based on (i) full features, (ii) correlation-based feature selection, (iii) Wrapper method feature selection, (iv) Least absolute shrinkage and selection operator regression, (v) synthetic minority over-sampling technique with least absolute shrinkage and selection operator regression selected features, (vi) synthetic minority over-sampling technique with full features. From the results, it is marked that LSVM with penalty L2 is giving the highest accuracy of 98.86% in synthetic minority over-sampling technique with full features. Along with accuracy, precision, recall, F-measure, area under the curve and GINI coefficient have been computed and compared results of various algorithms have been shown in the graph. Least absolute shrinkage and selection operator regression selected features with synthetic minority over-sampling technique gave the best after synthetic minority over-sampling technique with full features. In the synthetic minority over-sampling technique with least absolute shrinkage and selection operator selected features, again linear support vector machine gave the highest accuracy of 98.46%. Along with machine learning models one deep neural network has been applied on the same dataset and it has been noted that deep neural network achieved the highest accuracy of 99.6%.

Dietary Flavonoids: Cardioprotective Potential with Antioxidant Effects and Their Pharmacokinetic, Toxicological and Therapeutic Concerns

Abstract: Flavonoids comprise a large group of structurally diverse polyphenolic compounds of plant origin and are abundantly found in human diet such as fruits, vegetables, grains, tea, dairy products, red wine, etc. Major classes of flavonoids include flavonols, flavones, flavanones, flavanols, anthocyanidins, isoflavones, and chalcones. Owing to their potential health benefits and medicinal significance, flavonoids are now considered as an indispensable component in a variety of medicinal, pharmaceutical, nutraceutical, and cosmetic preparations. Moreover, flavonoids play a significant role in preventing cardiovascular diseases (CVDs), which could be mainly due to their antioxidant, antiatherogenic, and antithrombotic effects. Epidemiological and in vitro/in vivo evidence of antioxidant effects supports the cardioprotective function of dietary flavonoids. Further, the inhibition of LDL oxidation and platelet aggregation following regular consumption of food containing flavonoids and moderate consumption of red wine might protect against atherosclerosis and thrombosis. One study suggests that daily intake of 100 mg of flavonoids through the diet may reduce the risk of developing morbidity and mortality due to coronary heart disease (CHD) by approximately 10%. This review summarizes dietary flavonoids with their sources and potential health implications in CVDs including various redox-active cardioprotective (molecular) mechanisms with antioxidant effects. Pharmacokinetic (oral bioavailability, drug metabolism), toxicological, and therapeutic aspects of dietary flavonoids are also addressed herein with future directions for the discovery and development of useful drug candidates/therapeutic molecules.

DEMNET: A Deep Learning Model for Early Diagnosis of Alzheimer Diseases and Dementia From MR Images

Abstract: Alzheimer’s Disease (AD) is the most common cause of dementia globally. It steadily worsens from mild to severe, impairing one’s ability to complete any work without assistance. It begins to outstrip due to the population ages and diagnosis timeline. For classifying cases, existing approaches incorporate medical history, neuropsychological testing, and Magnetic Resonance Imaging (MRI), but efficient procedures remain inconsistent due to lack of sensitivity and precision. The Convolutional Neural Network (CNN) is utilized to create a framework that can be used to detect specific Alzheimer’s disease characteristics from MRI images. By considering four stages of dementia and conducting a particular diagnosis, the proposed model generates high-resolution disease probability maps from the local brain structure to a multilayer perceptron and provides accurate, intuitive visualizations of individual Alzheimer’s disease risk. To avoid the problem of class imbalance, the samples should be evenly distributed among the classes. The obtained MRI image dataset from Kaggle has a major class imbalance problem. A DEMentia NETwork (DEMNET) is proposed to detect the dementia stages from MRI. The DEMNET achieves an accuracy of 95.23%, Area Under Curve (AUC) of 97% and Cohen’s Kappa value of 0.93 from the Kaggle dataset, which is superior to existing methods. We also used the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset to predict AD classes in order to assess the efficacy of the proposed model.

Effect of injection parameters and producer gas derived from redgram stalk on the performance and emission characteristics of a diesel engine

Abstract: The improvement in performance has been observed by changing the injector nozzle's geometry of the dual-fuel liquid–gas engine The combined effect of injector parameters and producer gas (PG) derived from the redgram stalk on the performance and emission characteristics of a dual-fuel diesel/Honge Oil Methyl Ester (HOME)-PG operated CI engine has been studied The injector nozzles with 4, 5, and 6 holes (diameter of 02, 025, and 03 mm) were analyzed Diesel-PG operation with 4 holes, 025 mm diameter nozzle and HOME-PG operation with 6 holes, 025 mm diameter nozzle resulted in better performance and lower emissions Diesel-PG operation has 45% higher BTE (brake thermal efficiency) with a 4 hole nozzle and 07% higher for a 025 mm diameter 6 holes nozzle than HOME-PG operation The HOME-PG operation results showed that the with an injection opening pressure of 240 bar, 6-hole nozzle, and a diameter of 025 mm have an improved BTE of 58% with emission levels 15–30% lower than those of other geometries

Dye-Sensitized Solar Cell for Indoor Applications:A Mini-Review

Abstract: Lightweight computing technologies such as the Internet of Things and flexible wearable systems have penetrated our everyday lives exponentially in recent years Without a question, the running of such electronic devices is a major energy problem Generally, these devices need power within the range of microwatts and operate mostly indoors Thus, it is appropriate to have a self-sustainable power source, such as the photovoltaic (PV) cell, which can harvest indoor light Among other PV cells, the dye-sensitized solar cell (DSSC) has immense capacity to satisfy the energy demands of most indoor electronics, making it a very attractive power candidates because of its many benefits such as readily available materials, relatively cheap manufacturing methods, roll-to-roll compatibility, easy processing capabilities on flexible substrates and exceptional diffuse/low-light performance This review discusses the recent developments in DSSC materials for its indoor applications Ultimately, the perspective on this topic is presented after summing up the current progress of the research

Taxonomy on EEG Artifacts Removal Methods, Issues, and Healthcare Applications

Abstract: Electroencephalogram (EEG) signals are progressively growing data widely known as biomedical big data, which is applied in biomedical and healthcare research. The measurement and processing of EEG ...

Investigation of Momordica charantia seed biodiesel with cerium oxide nanoparticle on CI engine

Abstract: The main fuel for transport is diesel. It adds to the success of overall economy, as it is widely used due to its high efficiency in combustion, versatility, unwavering quality and cost-effectivene...

Dynamic resource allocation with optimized task scheduling and improved power management in cloud computing

Abstract: Cloud computing is one among the emerging platforms in business, IT enterprise and mobile computing applications. Resources like Software, CPU, Memory and I/O devices etc. are utilized and charged as per the usage, instead of buying it. A Proper and efficient resource allocation in this dynamic cloud environment becomes the challenging task due to drastic increment in cloud usage. Various promising technologies have been developed to improve the efficiency of resource allocation process. But still there is some incompetency in terms of task scheduling and power consumption, when the system gets overloaded. So an energy efficient task scheduling algorithm is required to improve the efficiency of resource allocation process. In this paper an improved task scheduling and an optimal power minimization approach is proposed for efficient dynamic resource allocation process. Using prediction mechanism and dynamic resource table updating algorithm, efficiency of resource allocation in terms of task completion and response time is achieved. This framework brings an efficient result in terms of power reduction since it reduces the power consumption in data centers. The proposed approach gives accurate values for updating resource table. An efficient resource allocation is achieved by an improved task scheduling technique and reduced power consumption approach. The Simulation result gives 8% better results when comparing to other existing methods.

Modelling of supply chain disruption analytics using an integrated approach: An emerging economy example

Abstract: The purpose of this paper is to develop a framework to identify, analyze, and to assess supply chain disruption factors and drivers Based on an empirical analysis, four disruption factor categories including natural, human-made, system accidents, and financials with a total of sixteen disruption drivers are identified and examined in a real-world industrial setting This research utilizes an integrated approach comprising both the Delphi method and the fuzzy analytic hierarchy process (FAHP) To test this integrated method, one of the well-known examples in industrial contexts of developing countries, the ready-made garment industry in Bangladesh is considered To evaluate this industrial example, a sensitivity analysis is conducted to ensure the robustness and viability of the framework in practical settings This study not only expands the literature scope of supply chain disruption risk assessment but through its application in any context or industry will reduce the impact of such disruptions and enhance the overall supply chain resilience Consequently, these enhanced capabilities arm managers the ability to formulate relevant mitigation strategies that are robust and computationally efficient These strategies will allow managers to take calculated decisions proactively Finally, the results reveal that political and regulatory instability, cyclones, labor strikes, flooding, heavy rain, and factory fires are the top six disruption drivers causing disruptions to the ready-made garment industry in Bangladesh

Crop prediction based on soil and environmental characteristics using feature selection techniques

Abstract: Earlier, crop cultivation was undertaken on the basis of farmers’ hands-on expertise. However, climate change has begun to affect crop yields badly. Consequently, farmers are unable to choose the r...

Classification of Indian Classical Music With Time-Series Matching Deep Learning Approach

Abstract: Music is a heavenly way of expressing feelings about the world. The language of music has vast diversity. For centuries, people have indulged in debates to stratisfy between Western and Indian Classical Music. But through this paper, an understanding can be fabricated while differentiating the types of Indian Classical Music. Classical music is one of the essential characteristics of Indian Cultural Heritage. Indian Classical Music is divided into two major parts, i.e. Hindustani and Carnatic. Models have been sculptured and trained to classify between Hindustani and Carnatic Music. In this paper, two approaches are used to implement classification models. MFCCs are used as features and implemented models like DNN (1 Layer, 2 Layers, 3 Layers), CNN (1 Layer, 2 Layers, 3 Layers), RNN-LSTM, SVM (Sigmoid, Polynomial & Gaussian Kernel) as one approach. A 3 channels input is created by merging features like MFCC, Spectrogram and Scalogram and implemented models like VGG-16, CNN (1 Layer, 2 Layers, 3 Layers), ResNet-50 as another approach. 3 Layered CNN and RNN-LSTM model performed best among all the approaches.

A simple fractional-order chaotic system based on memristor and memcapacitor and its synchronization application

Abstract: Memelements play an important part in the design of high density memory systems and low power memory. In this paper, we created a novel fractional-order chaotic circuit with a memristor and a memcapacitor with a linear inductor. The various dynamical properties of the fractional-order system are investigated by using some dynamic analysis methods like Lyapunov exponents and bifurcation after the numerical solution for the fractional-order system. In addition, to show the applicative advantages of the proposed chaotic system, we have realized about the synchronization of fractional-order chaotic systems and used it in secure communication systems first time in the literature according to our knowledge. The results of the theoretical analysis and simulation show that the simple fractional-order chaotic system has very rich dynamic properties and can be used in different engineering applications.

Elasto-thermodiffusive response in a spherical shell subjected to memory-dependent heat transfer

Abstract: Enlightened by the Caputo fractional derivative, the present study deals with a novel mathematical model of elasto-thermodiffusion to investigate the transient phenomena for a spherical she...

Characterization and Properties of Silicon Carbide Reinforced Ni-10Co-5Cr (Superalloy) Matrix Composite Produced Via Powder Metallurgy Route

Abstract: In this investigation, Ni-Co-Cr-SiC composites with various weight percentages were manufactured via powder metallurgy (PM) route. The compositions of the composites are Ni-10%Co-5%Cr, Ni-10% Co-5%Cr-4%SiC, Ni-10%Co-5%Cr-8%SiC and Ni-10%Co-5%Cr-12%SiC. The powders were mixed using planetary ball mill for a period of 10 h. The ball milled powders were subjected to X-ray diffraction (XRD) and Scanning Electron Microscope (SEM) analysis. By utilizing 150 kN hydraulic press with appropriate punch and die the ball milled powders were compacted as a cylindrical billets. The green compacts were sintered in a tubular furnace at two different temperatures 1000 °C and 1200 °C for3 h. The characterization examination namely XRD, SEM and Energy Dispersive Analysis (EDAX) was made on the sintered samples. Unreinforced Ni-Co-Cr exhibits higher sinterability at both sintering temperature. The sintering temperature and reinforcement weight percentage effect on the mechanical properties and corrosion behavior of the composites were examined. From these investigations, the mechanical properties and corrosion resistance of the composites were enhanced while increasing the sintering temperature and SiC weight percentage in the Ni-Co-Cr super alloy matrix.

An intelligent internet of things-based secure healthcare framework using blockchain technology with an optimal deep learning model

Abstract: Today, the internet of things (IoT) is becoming more common and finds applications in several domains, especially in the healthcare sector. Due to the rising demands of IoT, a massive quantity of sensing data gets generated from diverse sensing devices. Artificial intelligence (AI) techniques are vital for providing a scalable and precise analysis of data in real time. But the design and development of a useful big data analysis technique face a few challenges, like centralized architecture, security, and privacy, resource constraints, and the lack of adequate training data. On the other hand, the rising blockchain technology offers a decentralized architecture. It enables secure sharing of data and resources to the different nodes of the IoT network and is promoted for removing centralized control and resolving the problems of AI. This study develops an optimal deep-learning-based secure blockchain (ODLSB) enabled intelligent IoT and healthcare diagnosis model. The proposed model involves three major processes: secure transaction, hash value encryption, and medical diagnosis. The ODLSB technique comprises the orthogonal particle swarm optimization (OPSO) algorithm for the secret sharing of medical images. In addition, the hash value encryption process takes place using neighborhood indexing sequence (NIS) algorithm. At last, the optimal deep neural network (ODNN) is applied as a classification model to diagnose the diseases. The utilization of OPSO algorithm for secret sharing and optimal parameter tuning process shows the novelty of the work. We carried out detailed experiments to validate the outcome of the proposed method, and several aspects of the results are considered. At the time of the diagnosis process, the OPSO-DNN model has yielded superior results, with the highest sensitivity (92.75%), specificity (91.42%), and accuracy (93.68%).

Comprehensive review on various parameters that influence the performance of parabolic trough collector

Abstract: Among the different kinds of renewable energy sources, solar energy plays a major role because it is safe and inexpensive at all times. Several techniques are developed for steam and electricity generation by solar energy, in which the parabolic trough collector is an advantageous method for generating steam and electricity. Different types of collectors for various temperatures, in which PTCs are used to produce medium temperature ranges using the readily available solar energy, were developed, produced, and tests. Many theoretical and experimental studies have been carried out to improvise parabolic trough collectors’ optical and thermal characteristics. The modifications are reviewed in this paper to enhance the design modification, optical and thermal properties utilized in the collector. This analysis paper also elucidates the use of PTC desalination, various integrated parabolic trough collector methods for power generation, and the economic aspects of parabolic trough collector.

Optimization of Parameters to Improve the Properties of AA7178/Si3N4 Composites Employing Taguchi Approach

Abstract: In the recent days, the employ of aluminum alloy has enriched dramatically especially in engineering applications extensively employed in ship building, aerospace, structural, non-structural and automotive applications like driveshaft, wheels, crankshaft, connecting rod, chassis, brake rotors, cylinder blocks and piston etc. The foremost objective of this evaluation is to optimize the impacts of stir casting parameters of Aluminium Alloy AA7178/Si3N4 with response of tensile strength by utilizing Taguchi approach. MINITAB software was employed for conducting the Taguchi analysis. The stir casting parameters of this examination are stirring speed, stirring time and reinforcement percentage. The tensile behaviour of AA7178/Si3N4 composites for varying filler mass proportionate, stirring speed and stirring time were assessed employing a “universal testing machine”, and using a L9 (3)3 Taguchi orthogonal array. The nine samples of trials are employed to estimate the tensile behaviour of the composite material. The Analysis of Variance (ANOVA) is extensively assistance to intimate which parameter is highly impact for this evaluation. Amid those factors, filler content as highly influenced factor to response value followed as stirring time and stirring rpm.

Mechanical and Microstructural Characterization of Friction Stir Welded SiC and B4C Reinforced Aluminium Alloy AA6061 Metal Matrix Composites

Abstract: This study focuses on the properties and process parameters dictating behavioural aspects of friction stir welded Aluminium Alloy AA6061 metal matrix composites reinforced with varying percentages of SiC and B4C. The joint properties in terms of mechanical strength, microstructural integrity and quality were examined. The weld reveals grain refinement and uniform distribution of reinforced particles in the joint region leading to improved strength compared to other joints of varying base material compositions. The tensile properties of the friction stir welded Al-MMCs improved after reinforcement with SiC and B4C. The maximum ultimate tensile stress was around 172.8 ± 1.9 MPa for composite with 10% SiC and 3% B4C reinforcement. The percentage elongation decreased as the percentage of SiC decreases and B4C increases. The hardness of the Al-MMCs improved considerably by adding reinforcement and subsequent thermal action during the FSW process, indicating an optimal increase as it eliminates brittleness. It was seen that higher SiC content contributes to higher strength, improved wear properties and hardness. The wear rate was as high as 12 ± 0.9 g/s for 10% SiC reinforcement and 30 N load. The wear rate reduced for lower values of load and increased with B4C reinforcement. The microstructural examination at the joints reveals the flow of plasticized metal from advancing to the retreating side. The formation of onion rings in the weld zone was due to the cylindrical FSW rotating tool material impression during the stirring action. Alterations in chemical properties are negligible, thereby retaining the original characteristics of the materials post welding. No major cracks or pores were observed during the non-destructive testing process that established good quality of the weld. The results are indicated improvement in mechanical and microstructural properties of the weld.

Effect of banana, pineapple and coir fly ash filled with hybrid fiber epoxy based composites for mechanical and morphological study

Abstract: This research is mainly focused on the impact of bio waste filler in mechanical applications. The bio wastes from banana, pineapple and coconut plants were used for preparing Banana Fly Ash (BFA), Pineapple Fly Ash (PFA) and Coir Fly Ash (CFA) fillers. These fillers (1–4 wt. %) were incorporated with 30 wt. % of Sisal (S)/Pineapple (P) hybrid fiber composites using epoxy matrix. The X-Ray Diffraction (XRD) results proved the presence of quartz as the main element in the fly ash powders. Tensile strength of 23.78–33.79 MPa was observed by the substitution of BFA, PFA and CFA filler powders, compared to hybrid natural fiber composites with 20.45 MPa properties. Filler mixing add to the adhesion between fiber/matrix and increases the mechanical properties. Similarly, flexural and impact properties enhanced up to 22.11%, 21.77%, with filler incorporation. The SEM results explains good bonding nature by the application of filler powders. The EDX results proved the presence of silica and other inorganic content in the polymer composites adding to the properties.

Optimisation of Mechanical Properties in Saw-Dust/Woven-Jute Fibre/Polyester Structural Composites under Liquid Nitrogen Environment Using Response Surface Methodology.

Abstract: Natural fibre-based composites are replacing traditional materials in a wide range of structural applications that are used in different environments. Natural fibres suffer from thermal shocks, which affects the use of these composites in cold environment. Considering these, a goal was set in the present research to investigate the impact of cryogenic conditions on natural fibre composites. Composites were developed using polyester as matrix and jute-fibre and waste Teak saw-dust as reinforcement and filler, respectively. The effects of six parameters, viz., density of saw-dust, weight ratio of saw-dust, grade of woven-jute, number of jute layers, duration of cryogenic treatment of composite and duration of alkaline treatment of fibres on the mechanical properties of the composite was evaluated with an objective to maximise hardness, tensile, impact and flexural strengths. Taguchi method was used to design the experiments and response-surface methodology was used to model, predict and plot interactive surface plots. Results indicated that the duration of cryogenic treatment had a significant effect on mechanical properties, which was better only up to 60 min. The models were found to be statistically significant. The study concluded that saw-dust of density 300 kg/m3 used as a filler with a weight ratio of 13 wt.% and a reinforcement of a single layer of woven-jute-fibre mat of grade 250 gsm subjected to alkaline treatment for 4 h in a composite that has undergone 45 min of cryogenic treatment presented an improvement of 64% in impact strength, ca. 21% in flexural strength, ca. 158% in tensile strength and ca. 28% in hardness.

Fusion of mel and gammatone frequency cepstral coefficients for speech emotion recognition using deep C-RNN

Abstract: Emotions play a significant role in human life. Recognition of human emotions has numerous tasks in recognizing the emotional features of speech signals. In this regard, Speech Emotion Recognition (SER) has multiple applications in various fields of education, health, forensics, defense, robotics, and scientific purposes. However, SER has the limitations of data labeling, misinterpretation of speech, annotation of audio, and time complexity. This work presents the evaluation of SER based on the features extracted from Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC) to study the emotions from different versions of audio signals. The sound signals are segmented by extracting and parametrizing each frequency calls using MFCC, GFCC, and combined features (M-GFCC) in the feature extraction stage. With the recent advances in Deep Learning techniques, this paper proposes a Deep Convolutional-Recurrent Neural Network (Deep C-RNN) approach to classify the effectiveness of learning emotion variations in the classification stage. We use a fusion of Mel–Gammatone filter in convolutional layers to first extract high-level spectral features then recurrent layers is adopted to learn the long-term temporal context from high-level features. Also, the proposed work differentiates the emotions from neutral speech with suitable binary tree diagrammatic illustrations. The methodology of the proposed work is applied on a large dataset covering Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset. Finally, the proposed results which obtained accuracy more than 80% and have less loss are compared with the state of the art approaches, and an experimental result provides evidence that fusion results outperform in recognizing emotions from speech signals.