Browse Items (9795 total)
Sort by:
-
Enhanced Stock Market Prediction Using Hybrid LSTM Ensemble
Stock market value prediction is the activity of predicting future market values so as to increase gain and profit. It aids in forming important financial decisions which help make smart and informed investments. The challenges in stock market predictions come due to the high volatility of the market due to current and past performances. The slightest variation in current news, trend or performance will impact the market drastically. Existing models fall short in computation cost and time, thereby making them less reliable for large datasets on a real-time basis. Studies have shown that a hybrid model performs better than a stand-alone model. Ensemble models tend to give improved results in terms of accuracy and computational efficiency. This study is focused on creating a better yielding model in terms of stock market value prediction using technical analysis, and it is done by creating an ensemble of long short-term memory (LSTM) model. It analyzes the results of individual LSTM models in predicting stock prices and creates an ensemble model in an effort to improve the overall performance of the prediction. The proposed model is evaluated on real-world data of 4 companies from Yahoo Finance. The study has shown that the ensemble has performed better than the stacked LSTM model by the following percentages: 21.86% for the Tesla dataset, 22.87% for the Amazon dataset, 4.09% for Nifty Bank and 20.94% for the Tata dataset. The models implementation has been justified by the above results. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Effect of psychological pricing on consumer buying behaviour: A study on indian consumers
Consumer behaviour is a topic most sought after when it comes to creating successful marketing practices that affect consumers' psychology, acting as a stimulus and inducing them to make purchases. Evidence explains that the psychological pricing strategy communicates with the subconscious mind of consumers, creating a perceptual illusion. This makes the deal seem more appealing to them. This chapter entails a practical study examining the impact of psychological pricing strategies on consumers' buying behaviour. This study has used authentic primary data that has been collected directly from consumers in India based on their buying experiences when encountering psychological pricing. The findings of this research show how socio-demographic factors like age, income, education, gender and family size influence consumers' buying behaviour when encountered with psychological pricing and if psychological patterns such as the anchoring heuristics, recency bias, scarcity effect and halo effect can overpower the influence of psychological pricing strategies in consumer buying behaviour. 2024, IGI Global. -
Mathematical analysis of histogram equalization techniques for medical image enhancement: a tutorial from the perspective of data loss
This tutorial demonstrates a novel mathematical analysis of histogram equalization techniques and its application in medical image enhancement. In this paper, conventional Global Histogram Equalization (GHE), Contrast Limited Adaptive Histogram Equalization (CLAHE), Histogram Specification (HS) and Brightness Preserving Dynamic Histogram Equalization (BPDHE) are re-investigated by a novel mathematical analysis. All these HE methods are widely employed by researchers in image processing and medical image diagnosis domain, however, this has been observed that these HE methods have significant limitation of data loss. In this paper, a mathematical proof is given that any kind of Histogram Equalization method is inevitable of data loss, because any HE method is a non-linear method. All these Histogram Equalization methods are implemented on two different datasets, they are, brain tumor MRI image dataset and colorectal cancer H and E-stained histopathology image dataset. Pearson Correlation Coefficient (PCC) and Structural Similarity Index Matrix (SSIM) both are found in the range of 0.6-0.95 for overall all HE methods. Moreover, those results are compared with Reinhard method which is a linear contrast enhancement method. The experimental results suggest that Reinhard method outperformed any HE methods for medical image enhancement. Furthermore, a popular CNN model VGG-16 is implemented, on the MRI dataset in order to prove that there is a direct correlation between less accuracy and data loss. 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. -
Mobile Freeze-Net with Attention-based Loss Function for Covid-19 Detection from an Imbalanced CXR Dataset
In this paper, we present a novel framework, that is, Mobile Freeze-Net along with Attention-based Loss Function, for Covid-19 detection from a Chest X-Ray (CXR) dataset. First, we have observed that by freezing 50% of a Mobile Net-V2 model (means fine-tuning 50% layers from ImageNet dataset) has automatically removed the class imbalance problem from the CXR dataset considerably. We call this 50% frozen Mobile Net-V2 model as Mobile Freeze-Net. Secondly, we have proposed an Attention-based Loss function, which provides more attention to the class, having higher inter-class similarity. We have computed attention weights for each class from the statistical inference of the dataset itself, by employing a Monte-Carlo method and thereafter, we have incorporated those weights into WCCE loss function of Mobile Freeze-Net model. By utilizing Mobile freeze-Net, we have achieved testing accuracy, F1 score, precision and recall of 93%, 94%, 93% and 94% respectively. This is approximately 3-4% improvement compared to 100% fine tuning of Mobile-Net V2. Furthermore, we have achieved approximate 1-2% improvement of Mobile Freeze-Net, after incorporating Attention-based Loss function. For the validity of the proposed framework, we have conducted experiments with 10-fold cross validation. All these experimental results suggest that our proposed framework has outperformed other existing models considerably. 2023 Owner/Author(s). -
Log-Base2 of Gaussian Kernel for Nuclei Segmentation from Colorectal Cancer H and E-Stained Histopathology Images
Nuclei Segmentation is a very essential and intermediate step for automatic cancer detection from H and E stained histopathology images. In the recent advent, the rise of Convolutional Neural Network (CNN), has enabled researchers to detect nuclei automatically from histopathology images with higher accuracy. However, the performance of automatic nuclei segmentation by CNN is fraught with overfitting, due to very less number of annotated segmented images available. Indeed, we find that the problem of nuclei segmentation is an unsupervised problem, because still now there is no automatic tool available which can make annotated images (nuclei segmented images) accurately, to the best of our knowledge. In this research article, we present a Logarithmic-Base2 of Gaussian (Log-Base2-G) Kernel which has the ability to track only the nuclei portions automatically from Colorectal Cancer H and E stained histopathology images. First, Log-Base2-G Kernel is applied to the input images. Thereafter, we apply an adaptive Canny Edge detector, in order to segment only the nuclei edges from H and E stained histopathology images. Experimental results revealed that our proposed method achieved higher accuracy and F1 score, without the help of any annotated data which is a significant improvement. We have used two different datasets (Con-SeP dataset, and Glass-contest dataset, both contains Colorectal Cancer histopathology images) to check the effectiveness and validity of our proposed method. These results have shown that our proposed method outperformed other image processing or unsupervised methods both qualitatively and quantitatively. 2023 SPIE. -
The presence of others increases prosociality: examining the role of dating Partners accompany on donation
Research in the field of prosocial behavior has shown that the presence of others has a significant effect on individuals prosociality. However, no research has explored such an effect of romantic partners presence. Studies in evolutionary psychology have shown benevolence/prosociality as an important factor when choosing a romantic partner. Therefore, in the present study, we hypothesized that people will donate more in the presence of dating partners to maintain a positive impression on them. The research followed a mixed-method approach. The first study, a vignette-based experiment showed that people believed the presence of a dating partner significantly enhances the chances of donation. The second study was a between-subject experiment that confirmed the findings of study 1 from both donors and receivers perspectives. The third study was a qualitative investigation, where a semi-structured interview method was used to find out how and why the presence of a dating partner may influence donation. The interviews showed that the presence of dating partners increases prosociality mainly because donors want to make a good impression and project the right image of them in their partners eyes. The research overall suggests that the human need for self-presentation that projects them more socially likable shapes their willingness to extend a helping hand to others in the presence of their romantic partners. 2024 Taylor & Francis Group, LLC. -
Performance Improvement in E-Gun Deposited SiOx- Based RRAM Device by Switching Material Thickness Reduction
A performance improvement by reduction in switching material thickness in a e-gun deposited SiOx based resistive switching memory device was investigated. Reduction in thickness cause thinner filamentary path formation during ON-state by controlling the vacancydefects. Thinner filament cause lowering of operation current from 500 ?A to 100 ?A and also improves the reset current (from >400 ?A to <100 ?A). Switching material thickness reductionalso cause the forming free ability in the device. All these electrical parametric improvements enhance the device reliability performances. The device show >200 dc endurance, >3-hour dataretention and >1000 P/E endurance with 100 ns pulses. 2022 Institute of Physics Publishing. All rights reserved. -
Leveraging Deep Autoencoders for Security in Big Data Framework: An Unsupervised Cloud Computing Approach
Abnormalities recognition in bank transaction big data is the number one issue for stability of financial security system. Due to the rate digital transactions are increasing it is vital to have effective ways. Encryption with deep autoencoder model should be explored as it involves trained neural networks that learn such patterns from the complex transaction data. The following paper demonstrates application of anomaly detection using deep autoencoders in the banking big data transactions. It focuses on the theoretical bases, network design, preparedness and the testing measures for deep autoencoders. On the other hand, it solves problems such as high dimensionality and imbalanced dataset. This research paper shows deep autoencoders effectiveness in deep learning and how the network identifies different fraudulent big data transactions, money laundry and unauthorized access. It also encompasses recent developments of cloud environments and future methods using deep autoencoders including the fact that constant search for new possible solutions is a must. The insights delivered contribute to the discourse in financial security community, which incorporates researchers, practitioners, and policymakers involved in anomaly detection in cloud. 2024 IEEE. -
The development and primary validation of employee green behavior scale
Purpose: The increasing adverse impact of human behavior toward the environment has brought in changes in research focus on environmental behavior toward the workplace. Because the employee spends one-third of his day in his workplace, the initiatives taken by the employee also have an impact on the companys environmental stance. Therefore, the researchers gradually focus on employee green behavior (EGB) and its measurement. The study aims to devise a tool for measuring EGB. Design/methodology/approach: Two studies were carried out using the survey method using the purposive sampling technique. The data were collected (Studies 1 and 2) from managers and supervisors working in manufacturing companies located in Kolkata, India. Findings: The first study was done to extract the principal factors using an initial 30 items (N = 220). The result of the principal component analysis shows the emergence of three factors spread over 20 items with loadings above 0.40. The 20-item scale was again administered on managers and supervisors (N = 243). The second study was carried out to examine the convergent and discriminant validity as well as stability of the tool through confirmatory factor analysis (CFA) (N = 243). The result of CFA showed the presence of 16 items spread through three factors: practice and policy, digital use and recycle and reuse. Multiple fit indices support a three-factor model of the 16-item EGB scale. Research limitations/implications: The scale would be a good measure of EGB and can be used for further research. The EGB scale is a composite scale containing three major dimensions that can be used as a complete measure of EGB. Originality/value: The present research aims to fill the current gap by building a comprehensive tool for measuring EGB. The present scale has also addressed the shortcoming of the previous scale and tried to include varied proenvironmental behaviors exhibited in the workplace. 2024, Emerald Publishing Limited. -
SVD-CLAHE boosting and balanced loss function for Covid-19 detection from an imbalanced Chest X-Ray dataset
Covid-19 disease has had a disastrous effect on the health of the global population, for the last two years. Automatic early detection of Covid-19 disease from Chest X-Ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data-augmentation technique, called SVD-CLAHE Boosting and a novel loss function Balanced Weighted Categorical Cross Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-Ray image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, a novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes, so that the number of images per class will be more balanced. Thereafter, Balanced Weighted Categorical Cross Entropy (BWCCE) loss function is proposed in order to further reduce small class imbalance after SVD-CLAHE Boosting. Experimental results reveal that ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 95% recall, 96% precision and 96% AUC, which is far better than the results by other conventional Convolutional Neural Network (CNN) models like InceptionV3, DenseNet-121, Xception etc. as well as other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on VGG-19 model in order to check the validity of our proposed framework. Both ResNet-50 and VGG-19 model are pre-trained on the ImageNet dataset. We publicly shared our proposed augmented dataset on Kaggle website (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset), so that any research community can widely utilize this dataset. Our code is available on GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE). 2022 Elsevier Ltd -
Lightweight Spectral-Spatial Squeeze-and- Excitation Residual Bag-of-Features Learning for Hyperspectral Classification
Of late, convolutional neural networks (CNNs) find great attention in hyperspectral image (HSI) classification since deep CNNs exhibit commendable performance for computer vision-related areas. CNNs have already proved to be very effective feature extractors, especially for the classification of large data sets composed of 2-D images. However, due to the existence of noisy or correlated spectral bands in the spectral domain and nonuniform pixels in the spatial neighborhood, HSI classification results are often degraded and unacceptable. However, the elementary CNN models often find intrinsic representation of pattern directly when employed to explore the HSI in the spectral-spatial domain. In this article, we design an end-to-end spectral-spatial squeeze-and-excitation (SE) residual bag-of-feature (S3EResBoF) learning framework for HSI classification that takes as input raw 3-D image cubes without engineering and builds a codebook representation of transform feature by motivating the feature maps facilitating classification by suppressing useless feature maps based on patterns present in the feature maps. To boost the classification performance and learn the joint spatial-spectral features, every residual block is connected to every other 3-D convolutional layer through an identity mapping followed by an SE block, thereby facilitating the rich gradients through backpropagation. Additionally, we introduce batch normalization on every convolutional layer (ConvBN) to regularize the convergence of the network and scale invariant BoF quantization for the measure of classification. The experiments conducted using three well-known HSI data sets and compared with the state-of-the-art classification methods reveal that S3EResBoF provides competitive performance in terms of both classification and computation time. 1980-2012 IEEE. -
Attitude of public towards higher education: Conceptual analysis /
Scholedge International Journal Of Multidisciplinary And Allied Studies, Vol.2, Issue 12, pp.19-28, ISSN No: 2394-336X. -
Analgesic and Anti-Inflammatory Potential of Indole Derivatives
Some indole analogues show a good analgesic activity but on the other hand, it has some serious side effects like gastric ulcer. Therefore, there is still a need to develop derivatives of non-steroidal anti-inflammatory drugs (NSAIDs) with fewer side effects. For this purpose, some indole derivatives were prepared with objectives to develop new derivatives with maximum efficacy and minimum side effects. 1-(1H-indol-1-yl)-2-(sstituephenoxy)-ethan-1-one derivatives (M1M4) were analyzed further by thin-layer chromatorgarphy (TLC), melting point, IR, and 1H-NMR. The synthesized compounds then underwent oral toxicity studies that include hematological, biochemical, and histopathological findings. The compound was then evaluated for invivo anti-inflammatory and analgesic activities on carrageenan-induced rat paw edema and acetic acid-induced writhing methods. As a result of the biological activities, promising results were obtained in the compound M2 (2-(2-aminophenoxy)-1-(1H-indol-1-yl)ethanone) and it was subjected to further studies. It was found that compound M2 was practically nontoxic, and no clinical abnormalities were found in hematology and biochemistry, correlated with histopathological observation. It also showed significant anti-inflammatory and analgesic activities at its oral high dose (400 mg/kg). The study suggested that compound M2 was found to have significant anti-inflammatory and analgesic activities. The possible mechanism of M2 might suggest being act as a central anti-nociceptive agent and peripheral inhibitor of painful inflammation. The possible mechanism of action of the compounds whose biological activity was evaluated was explained by molecular docking study against COX-1 and COX-2, and the most active compound M2 formed ?9.3 and ?8.3 binding energies against COX-1 and COX-2. In addition, molecular dynamics (MD) simulation of both M2s complexes with COX-1 and COX-2 was performed to examine the stability and behavior of the molecular docking pose, and the MM-PBSA binding free energies were measured as ?153.820 11.782 and ?172.604 9.591, respectively. Based on computational ADME studies, compounds comply with the limiting guidelines. 2022 Taylor & Francis Group, LLC. -
Experimental investigation and influence of filling ratio on heat transfer performance of a pulsating heat pipe
Experimental investigation of the two-phase system of a pulsating heat pipe taken into account useful heat transfer In the field of thermal management, many new prospective concepts and techniques have been developed, one of which is the pulsating heat pipe, a classic heat transfer technique. The PHP is constructed from 8 turns of copper tubes with inner diameters of 2 mm, wall widths of 1 mm, and a total length of 5324 mm. The CLPHP uses ethylene glycol as the functioning liquid at different fill proportions of 45 %, 55 %, 65 %, 75 %, and 85 % of its amount. The evaporator section is heated electrically by a plate heater ranging from 120 W to 600 W, and the condenser section is cooled by a continuous flow of cooling water. The results thermal resistance decreases gradually with an increase in heat transfer rate. It is apparent that a lower rate of thermal resistance is by a fill ratio of 55 %. The evaporator temperature is 181.57 C and the condenser temperature is 41.06 C for ethylene glycol measured for calculating heat transfer performance at 600 W, thermal resistance is 0.136 C/W, heat transfer coefficient is 526.45 W/m2-C, and enhanced heat transfer is thus good, exhibiting good improvement at a full percentage of 55 % and when compared with CFD results. 2023 Elsevier Ltd -
Induction of radio frequency transmission in indian railway for smooth running of traffic during fog
Our railway system drives whole sole based on its electrical signaling but due to poor visibility it becomes impossible to run the traffic smoothly We are suggesting to use radio wave communication technology for running of train when conventional signaling cant be followed due to poor visibility. During winter season, due to heavy fog especially in North India and East India it becomes almost impossible to drive the train on time. Our idea can remove this problem permanently. A dedicated radio frequency band will be used by railway service and a specific frequency will be assigned to all tracks running to a specific direction. All trains will be equipped with a transmitter and a receiver. Train drivers will get notification of received radio frequency within a certain circumference (5 km). So if it receives the same frequency which it is transmitting then the driver will understand another train is there on the same track so signaling room and the driver will also be aware of the fact. Then the control room or the driver can take action considering speed and distance between this two accordingly. If another train will be running on the next track then also it will receive signal but in that case it will run at as usual speed. 2017 Taylor & Francis Group, London. -
Comparative Study Analysis on News Articles Categorization using LSA and NMF Approaches
Due to exponentially growing news articles every day, most of their important data goes unnoticed. It is important to come up with the ability to automatically analyse these articles and segregate them based on the context and related to their particular domain. This paper applies topic modelling which is one of the most growing unsupervised machine learning fields on a million headlines articles in order to produce topics to describe the context of the news article. There are various generative models but we specifically focusing on the non-negative matrix factorization (NMF) and Latent Semantic Analysis (LSA) for implementing and evaluating news dataset. Furthermore, the findings reveal that both NMF and LSA are useful topic modelling tools and classification frameworks, but based on the experimental results the LSA model performed well to identify the hidden data with better mean coherence values and also consumes lesser execution time than NMF. 2022 IEEE. -
An equal split triple-band wilkinson power divider employing extended cross shaped microstrip line /
Microwave and Optical Technology Letters, Vol.60, Issue 10, pp.2488-2492. -
Monitoring nyiragongo volcano using a federated cloud-based wireless sensor network
Current Nyiragongo Volcano observatory systems yield poor monitoring quality due to unpredictable dynamics of volcanic activities and limited sensing capability of existing sensors (seismometers, acoustic microphones, GPS, tilt-meter, optical thermal, and gas flux). The sensor node has limited processing capacity and memory. So if some tasks from the sensor nodes can be uploaded to the server of cloud computing then the battery life of the sensor nodes can be extended. The cloud computing can be used both for processing of aggregate query and storage of data. The two principal merits of this paper are the clear demonstration that the Cloud Computing model is a good fit with the dynamic computational requirements of Nyiragongo volcano monitoring and the novel optimization algorithm for seismic data routing. The proposed new model has been evaluated using Arduino-Atmega328 as hardware platform, Eucalyptus/Open Stack with Orchestra-Juju for Private Sensor Cloud connected to some famous public clouds such as Amazon EC2, ThingSpeak, SensorCloud and Pachube. 2017 IEEE. -
P-phase picker using virtual cloud-based Wireless Sensor Networks
Wireless Sensor Networks, mainly regarded as numerous resource-limited nodes linked via low bandwidth, have been intensively deployed for active volcano monitoring during the few past years. This paper studies the problem of primary waves received by seismic wireless sensors suffering from limited bandwidth, processing capacity, battery life and memory. To address these challenges, a new P-phase picking approach where sensors are virtualized using cloud computing architecture followed by a novel in-network signal processing algorithm, is proposed. The two principal merits of this paper are the clear demonstration that the Cloud Computing model is a good fit with the dynamic computational requirements of volcano monitoring and the novel signal processing algorithm for accurate P-phases picking. The proposed new model has been evaluated on Mount Nyiragongo using Eucalyptus/Open Stack with Orchestra-Juju for Private Sensor Cloud then to some famous public clouds such as Amozon EC2, ThingSpeak, SensorCloud and Pachube. The testing has been successful at 75%. The recommendation for future work would be to improve the effectiveness of virtual sensors by applying optimization techniques and other methods. 2015 IEEE. -
A critical review of anticancer properties of Withania somnifera (L.) Dunal with respect to the biochemical mechanisms of its phytochemical constituents
Cancer is a leading cause of mortality worldwide, the conventional chemotherapeutic drugs have been known for their toxicity and numerous side effects. A new approach to treat cancer involves phytochemical drugs. In the present review, anti-cancer activity of a class of steroidal lactones called withanolides obtained from Withania somnifera (L.) Dunal is discussed. The commonly studied bioactive compounds namely withaferin-A, withanoside IV, withanoside VI and withanolide-A among others obtained from methanolic and chloroform extract of the leaves and various alcoholic, aqueous and chloroform extract of roots have shown inhibition to various human cancer cell lines including skin, breast, colon, prostate, liver, ovary, cervical and lung. Prominent mechanisms of action include induction of apoptosis by NOS upregulation, ROS production and NBS2 or COX-2 inhibition; cytotoxicity by humoral and cell mediated immune response, activation of p53 and pRB and inhibition of various viral oncoproteins; cell cycle arrest by Cdc2 facilitated mitotic catastrophe, cyclin-D1 down-regulation and inhibition of transcription factors. Cancers are also controlled by inhibition of angiogenesis and metastasis of the tumor cells. In addition to anti-tumorogenic properties, W. somnifera also holds properties that make it a potential adjuvant in integrated cancer therapeutics and in enhancing the effectiveness of ongoing radiation therapy. Surya et al (2021).