Chronic kidney disease (CKD) is among the top 20 causes of death worldwide and affects approximately 10 of the world adult population. CKD is a disorder that disrupts normal kidney function. Due to the increasing number of people with CKD, effective prediction measures for the early diagnosis of CKD are required. The novelty of this study lies in developing the diagnosis system to detect chronic kidney diseases. This study assists experts in exploring preventive measures for CKD through early diagnosis using machine learning techniques. This study focused on evaluating a dataset collected from 400 patients containing 24 features. The mean and mode statistical analysis methods were used to replace the missing numerical and the nominal values. To choose the most important features, Recursive Feature Elimination (RFE) was applied. Four classification algorithms applied in this study were support vector machine (SVM), k-nearest neighbors (KNN), decision tree, and random forest. All the classification algorithms achieved promising performance. The random forest algorithm outperformed all other applied algorithms, reaching an accuracy, precision, recall, and F1-score of 100 for all measures. CKD is a serious life-threatening disease, with high rates of morbidity and mortality. Therefore, artificial intelligence techniques are of great importance in the early detection of CKD. These techniques are supportive of experts and doctors in early diagnosis to avoid developing kidney failure.

The growth of internet era leads to a major transformation in a storage of data and accessing the applications. One such new trend that promises the endurance is the Cloud computing. Computing resources offered by the Cloud includes the servers, networks, storage, and applications, all as services. With the advent of Cloud, a single application is delivered as a metered service to numerous users, via an Application Programming Interface (API) accessible over the network. The services offered via the Cloud are such as the infrastructure, software, platform, database and web services. The main motivation of this application model is to provide computationally secure key generation to protect the data via encryption. This key generation in the cryptography process falls into three categories in this research work. In the first part, SVM based encryption service model is constructed for which the key generation is from the conventional encryption operation mode with some improvements. To make the process more complex, the optimization techniques are taken into account for the key generation in descendant two methods application model that acts computationally more secure specifically for Cloud environment. The results of security analysis confirm the effectiveness of the proposed application model withstands potentially against various attacks such as Chosen Cipher Attack, Chosen Plain text Attack indistinguishable attacks for files. In case of images, it resists well against statistical and differential attacks. Comparative Analysis shows evidence of the efficiency of the developed pioneering application model quality and strength compared with that of the existing services.

IT services and resources on-demand through Internetwork are offered by Cloud Computing (CC), including the pay-for-you-go aspect. A lot is offered by the CC paradigm, such as Infrastructure related services, computing services, storage, and environments for deployment are also provided. The objective of this study is to survey one of the significant challenges in cloud computing, which is a multi-variant, multi-constraint issue termed Load unbalancing, resulting in the demising of the scalability, efficiency, and performance of the system. Equilibrium in the server workload distribution is still strived for by cloud service providers. The unbalancing issue is resolved by load balancing solutions in two ways: overloading and underloading. An extensive structural literature analysis of Load balancing and its constituent domains with the inclusion of various parameters, such as scalability, make-span, and throughput, are depicted in this research paper to enhance the QoS. A detailed and organized taxonomy of all the Load balancing algorithms based on nature system state, techniques, functionality, and types is also presented. The major focus of the survey is around the Static, dynamic, hybrid, and nature-inspired Load-Balancing algorithms.

Increasing prevalence and simplicity of using Artificial Intelligence (AI) techniques, Steganography is shifting from conventional model building to AI model building. AI enables computers to learn from their mistakes, adapt to emerging inputs, and carry out human-like activities. Traditional Linguistic Steganographic approaches lack automation, analysis of Cover text and hidden text volume and accuracy. A formal methodology is used in only a few Steganographic approaches. In the vast majority of situations, traditional approaches fail to survive third-party vulnerability. This study looks at evaluation of an AI-based statistical language model for text Steganography. Since the advent of Natural Language Processing (NLP) into the research field, linguistic Steganography has superseded other types of Steganography. This paper proposes the positive aspects of NLP-based Markov chain model for an auto-generative cover text. The embedding rate, volume, and other attributes of Recurrent Neural Networks (RNN) Steganographic schemes are contrasted in this article between RNN-Stega and RNN-generated Lyrics, two RNN methods. Here the RNN model follows Long Short Term Memory (LSTM) neural network. The paper also includes a case study on Artificial Intelligence and Information Security, which discusses history, applications, AI challenges, and how AI can help with security threats and vulnerabilities. The final portion is dedicated to the study’s shortcomings, which may be the subject of future research.

In the twenty-first century, storing and managing digital documents has become commonplace for all corporate and public sectors around the world. Physical documents are scanned in batches and stored in a digital archive as a heterogeneous document stream, referred to as a digital package. To make Robotic Process Automation (RPA) easier, it’s necessary to automatically segment the document stream into a subset of independent, coherent multi-page documents by detecting the appropriate document boundary. It’s a common requirement of a TI company’s Automated Document Management Systems (ADMS), where business operations are automated using RPA and the goal is to extract information from digital documents with minimal user intervention. The current study proposes, evaluates, and compares a multi-modal binary classification network incorporating text and picture aspects of digital document pages to state-of-the-art baseline methodologies. Image and textual features are extracted simultaneously from the input document image by passing them through Visual Geometry Group 16 -Convolutional Neural Network (VGG16-CNN) and pre-trained Bidirectional Encoder Representations from Transformers (Legal-BERTbase) model through transfer learning respectively. Both features are finally fused and passed through a fully connected layer of Multi Layered Perceptron (MLP) to obtain the binary classification of the pages as the First Page (FP) and Other Page (OP). Real-time document image streams from production business process archive were obtained from a reputed Title Insurance (TI) company for the study. The obtained F1 score of 97.3797.15the expected Straight Through Pass (STP) threshold defined by the process admin.