Sanjay Kumar MBA,MS,PhD

Security and privacy are regarded as the greatest priority in any real-world smart ecosystem built on the Internet of Things (IoT) paradigm. In this study, a SqueezeNet model for IoT threat detection is built using Sine Cosine Sea Lion Optimization (SCSLnO). The Base Station (BS) carries out intrusion detection. The Hausdorff distance is used to determine which features are important. Using the SqueezeNet model, attack detection is carried out, and the network classifier is trained using… Show more

Security and privacy are regarded as the greatest priority in any real-world smart ecosystem built on the Internet of Things (IoT) paradigm. In this study, a SqueezeNet model for IoT threat detection is built using Sine Cosine Sea Lion Optimization (SCSLnO). The Base Station (BS) carries out intrusion detection. The Hausdorff distance is used to determine which features are important. Using the SqueezeNet model, attack detection is carried out, and the network classifier is trained using SCSLnO, which is developed by combining the Sine Cosine Algorithm (SCA) with Sea Lion Optimization (SLnO). BoT-IoT and NSL-KDD datasets are used for the analysis. In comparison to existing approaches, PSO-KNN/SVM, Voting Ensemble Classifier, Deep NN, and Deep learning, the accuracy value produced by devised method for the BoT-IoT dataset is 10.75%, 8.45%, 6.36%, and 3.51% higher when the training percentage is 90. Show less

Accurate and robust collection of plant phenotypic data offers theoretical as well as technical support to support the growth of crop science and to ensure ecological security, agricultural growth, and food security. Identifying phenotypic traits of crops refers to the detection of difference exists in plant features caused due to interaction of the environment and plant genetics. It is an important research discussed in plant breeding as it permits breeders to find a variety of crops with… Show more

Accurate and robust collection of plant phenotypic data offers theoretical as well as technical support to support the growth of crop science and to ensure ecological security, agricultural growth, and food security. Identifying phenotypic traits of crops refers to the detection of difference exists in plant features caused due to interaction of the environment and plant genetics. It is an important research discussed in plant breeding as it permits breeders to find a variety of crops with physical features, like stress resistance, and high yield. Manual measurement of phenotypic traits in the area is labor intensive and causes inaccurate results and these issues are resolved by developing a method based on the Taylor Coot algorithm for segmenting plant regions and biomass area to detect emergence counting and to estimate the biomass of crops. The process of counting emergence and estimating the biomass is performed in a parallel way using a Deep Residual Network (DRN) that is trained by developed optimization. The segmentation framework is done using Generative Adversarial Network (GAN) and U-Net to segment the plant regions and biomass area. For instance, the extraction of vegetation indices makes the process of biomass estimation to generate more optimal features using a deep learning model. Moreover, the proposed model obtains minimal Mean Absolute Difference (MAD), Standard Absolute Difference (SDAD), %Difference (%D) as 0.073, 0.074, and 16.45 for emergence counting. Moreover, the DRN shows higher performance by attaining minimum MAD, SDAD, and %D as 0.069, 0.096, and 14.85 for biomass estimation. Show less

An electrocardiogram (ECG) computes the electrical functioning of the heart, which is mostly employed for finding various heart diseases of its feasibility and simplicity. Moreover, some of the abnormalities that exist in the heart can be determined through investigating the electrical signal of the heartbeat. In this paper, Exponential Political optimizer (EPO)-based Deep Quantum Neural Network (QNN) is developed to categorize the heartbeat for arrhythmia detection. Here, the ECG signal is… Show more

An electrocardiogram (ECG) computes the electrical functioning of the heart, which is mostly employed for finding various heart diseases of its feasibility and simplicity. Moreover, some of the abnormalities that exist in the heart can be determined through investigating the electrical signal of the heartbeat. In this paper, Exponential Political optimizer (EPO)-based Deep Quantum Neural Network (QNN) is developed to categorize the heartbeat for arrhythmia detection. Here, the ECG signal is pre-processing using the wandering path finding technique to abolish the baseline wandering. In addition, the arrhythmia detection is done with Deep QNN in which the weights of Deep QNN are trained using Exponential Political optimizer (EPO). The developed EPO algorithm is devised using the combination of Exponentially Weighted Moving Average (EWMA) and Political Optimizer (PO). Generally, deep learning techniques offer only the best output with high dimensional features such that the mined features are treated under data augmentation to increase the dimensionality of features. Furthermore, the experimentation of the developed scheme is attained the maximum sensitivity, accuracy, and specificity of 0.92, 0.914, and 0.917. Show less

Lung cancer is a deadly condition that raises the death rate globally. Early identification and lung cancer are indispensable for improving the endurance proportion of patients. In this paper, Political Squirrel Search Optimization (PSSO)-based Deep learning scheme is developed for effectual lung cancer recognition and classification process. Here, Spine General Adversarial Network (Spine GAN) is applied for performing segmentation of lung lobe regions. The Deep Neuro Fuzzy Network (DNFN)… Show more

Lung cancer is a deadly condition that raises the death rate globally. Early identification and lung cancer are indispensable for improving the endurance proportion of patients. In this paper, Political Squirrel Search Optimization (PSSO)-based Deep learning scheme is developed for effectual lung cancer recognition and classification process. Here, Spine General Adversarial Network (Spine GAN) is applied for performing segmentation of lung lobe regions. The Deep Neuro Fuzzy Network (DNFN) classifier is used to forecast cancerous regions. Deep Residual Network (DRN) is also used to determine the various cancer severity levels. The Political Optimizer (PO) and Squirrel Search Algorithm(SSA)were combined to create the newly announced PSSO method. Using the dataset of images from the Lung Image Database Consortium, experimental outcomes are assessed. Show less

In today's business environment, corporate social responsibility (CSR) is becoming more and more significant. Companies should be concerned about the interests of their stakeholders, but they should also focus greater attention on areas other than just profit-making. Most individuals used to believe that firms exploited customers. This research work intends to find the impact of corporate social responsibility on the profitability of the selected Multinational Companies in India. Five… Show more

In today's business environment, corporate social responsibility (CSR) is becoming more and more significant. Companies should be concerned about the interests of their stakeholders, but they should also focus greater attention on areas other than just profit-making. Most individuals used to believe that firms exploited customers. This research work intends to find the impact of corporate social responsibility on the profitability of the selected Multinational Companies in India. Five multinational companies were randomly selected and relevant information was collected from the higher officials (n=263) of the selected companies. The study employed techniques including frequency analysis, f-test analysis, and correlation analysis. The results revealed that corporate social responsibility influences corporate reputation and corporate financial satisfaction. In addition, CSR impacts customer satisfaction and customer loyalty. Accordingly, the study suggested that multinational corporations step up their commitment to giving back to society by developing a framework for CSR spending to raise Indians' standards of living to the point where their good reputation will result in a positive and significant increase in profitability, as this is necessary for their continued operation in the nation. Show less

The Denial of Service (DoS) attack is a category of intrusion that devours various services and resources of the organization by the dispersal of unusable traffic, so that reliable users are not capable of getting benefit from the services. In general, the DoS attackers preserve their independence by collaborating several victim machines and following authentic network traffic, which makes it more complex to detect the attack. Thus, these issues and demerits faced by existing DoS attack… Show more

The Denial of Service (DoS) attack is a category of intrusion that devours various services and resources of the organization by the dispersal of unusable traffic, so that reliable users are not capable of getting benefit from the services. In general, the DoS attackers preserve their independence by collaborating several victim machines and following authentic network traffic, which makes it more complex to detect the attack. Thus, these issues and demerits faced by existing DoS attack recognition schemes in cloud are specified as a major challenge to inventing a new attack recognition method. Show less

In recent years, the use of credit cards has increased significantly due to digitization and the emergence of cashless transactions. There has been a huge jump in fraud in credit card transactions across banks, credit unions, and other financial institutions across the globe. Financial institutions and credit card companies are now required to detect credit card fraud in real time to prevent further losses.

This research proposed a method to improve fraud detection using unsupervised… Show more

In recent years, the use of credit cards has increased significantly due to digitization and the emergence of cashless transactions. There has been a huge jump in fraud in credit card transactions across banks, credit unions, and other financial institutions across the globe. Financial institutions and credit card companies are now required to detect credit card fraud in real time to prevent further losses.

This research proposed a method to improve fraud detection using unsupervised deep learning classifier autoencoders and deep neural networks. It is difficult to train machine learning models for credit card fraud detection because of the class imbalance.To build an effective classifier or predictive model, it is necessary to balance the number of legitimate and fraudulent transactions. Data resampling was applied to the dataset through random undersampling and random oversampling, specifically the synthetic minority oversampling technique (SMOTE) and adaptive synthetic (ADASYN) technique. Since resampling introduced noise in the data, an unsupervised deep learning– based autoencoder algorithm was used for denoising. Using the denoised dataset, a deepneural network was built to classify transactions in the sampled dataset as normal or fraudulent.

To implement the autoencoder, this research used Google’s TensorFlow library, which is part of the TensorFlow framework. Model performance was evaluated using metrics such as precision, recall, F1 score, and area under the curve–receiver operating characteristic. The study model outperformed existing models in the industry. Show less

The key difficulty is to develop creative techniques for portraying the material in a brief form known as a summary, especially with the advent of the internet and the availability of enormous amounts of textual data. The practice of condensing larger papers into a shorter version without losing their general information content is called text summarizing. Due to the lack of a corpus, automatic text summarization is still a difficult problem. A reliable and effective text summarization model… Show more

The key difficulty is to develop creative techniques for portraying the material in a brief form known as a summary, especially with the advent of the internet and the availability of enormous amounts of textual data. The practice of condensing larger papers into a shorter version without losing their general information content is called text summarizing. Due to the lack of a corpus, automatic text summarization is still a difficult problem. A reliable and effective text summarization model called the Chimp Water Wave Optimization-based Random Multimodal Deep Learning (ChWWO-based RMDL) method has been created to address the challenges in text summarization. The tokenization operation is carried out in this case using the Bidirectional Encoder Representations from Transformers (BERT) tokenization technique. Aspect Term Extraction (ATE) is carried out using the tokens to enhance summarization performance. Additionally, the established ChWWO method is used to train the RMDL model, which is then used for the text summarization process. However, the developed ChWWO combines the Water Wave Optimization and the Chimp Optimization Algorithm (ChOA) (WWO). The established method effectively raised the quality of the created summaries. The created ChWWO-based RMDL method performed better than several other approaches, with greater precision, recall, and F-measure values of 0.961, 0.971, and 0.966, respectively. Show less

Conventional recommendation techniques utilize various methods to compute the similarity among products. However, such conventional similarity computation techniques may produce incomplete information influenced by similarity measures in customers’ preferences, which leads to poor accuracy on recommendation. Hence, this paper introduced the novel and effective recommendation technique, namely Deep Embedded Clustering with matrix factorization (DEC with matrix factorization) for the… Show more

Conventional recommendation techniques utilize various methods to compute the similarity among products. However, such conventional similarity computation techniques may produce incomplete information influenced by similarity measures in customers’ preferences, which leads to poor accuracy on recommendation. Hence, this paper introduced the novel and effective recommendation technique, namely Deep Embedded Clustering with matrix factorization (DEC with matrix factorization) for the collaborative recommendation. In this method, the review data is utilized to generate the agglomerative matrix for the recommendation. The agglomerative matrix comprises customer series matrix, customer series binary matrix, product series matrix and product series binary matrix. The product grouping is carried out to group the similar products using DEC for retrieving the optimal product. Moreover, the bi-level matching generates the best group customer sequence in which the relevant customers are retrieved using tversky index and angular distance. In addition, the final recommendation of product is carried out using matrix factorization, such that the product with maximum rating is recommended to the customers. Additionally, according to the experimental results, the developed DEC with the matrix factorization approach produced better results with respect to F-measure values of 0.902, precision values of 0.896, and recall values of 0.908, respectively. Show less

Sentiment analysis is a vital and fast expanding field of study in natural language processing (NLP). A range of data-based techniques, including machine learning and deep learning models, are utilised to efficiently address categorization challenges. However, classification performance suffers whenever the input contains reviews for several tasks. Using the collection of reviews, this research develops a sentiment analysis method based on optimization. The established sentiment analysis… Show more

Sentiment analysis is a vital and fast expanding field of study in natural language processing (NLP). A range of data-based techniques, including machine learning and deep learning models, are utilised to efficiently address categorization challenges. However, classification performance suffers whenever the input contains reviews for several tasks. Using the collection of reviews, this research develops a sentiment analysis method based on optimization. The established sentiment analysis approach's two key steps are tokenization and sentiment categorization. The input reviews are initially extracted from the database and tokenized. The input review data is separated into discrete words, or tokens, for the tokenization procedure using Bidirectional Encoder Representations from Transformer (BERT). Sentiment is then categorised using the Attention-based Bidirectional CNN-RNN Deep Model (ABCDM), which was developed using the widely utilised Chimp Deer Hunting Optimization (CDHO) approach. In order to build the suggested CDHO approach, the Chimp Optimization Algorithm (ChOA) and the Deer Hunting Optimization Algorithm were combined (DHOA). The suggested CDHO-based ABCDM performed better than other methods with a maximum precision of 93.5%, recall of 94.5%. Show less