In the context of India's evolving economy, where agriculture remains a vital yet limited sector, the challenge is to enhance productivity on finite cultivable land. This research addresses this imperative by introducing the Crop Yield Prediction Using Deep Learning (CYPBL) model, leveraging the Bi-Directional Long Short-Term Memory (Bi-LSTM) algorithm. Employing soil health and crop yield data from the Government of India, the CYPBL model is implemented through PySpark for scalability. Featuring 20 LSTM layers with a 12 × 1 input shape, including a bidirectional LSTM layer, the model achieves exceptional accuracy at 99.5 percent on test data. With a focus on real-time data, a batch size of 1 ensures optimal responsiveness. Beyond technological advancements, CYPBL emerges as a groundbreaking soil health monitoring system, bridging the gap between experts and farmers. By empowering farmers with insights into soil conditions, crop suitability, and improvement strategies, this research paves the way for data-driven, responsive agriculture in India and globally, contributing to the pressing issue of global food security.

In Mobile Adhoc Networks (MANETs), nodes are mobile and interact through wireless links. Mobility is a significant advantage of MANETs. However, due to the unpredictable nature of mobility, the link may fail frequently, degrading the Quality of Service (QoS) of MANETs applications. This paper outlines a novel Ad hoc On-Demand Distance Vector with Proactive Alternate Route Discovery (AODV-PARD) routing protocol that uses signal strength-based link failure time estimation. The node predicts the link failure time and warns the upstream node through a warning message about the failure. On the basis of this information, a mechanism for identifying alternate routes is started in order to reroute traffic to the alternate route prior to the link failure. It significantly reduces packet loss and improves all the QoS parameters. The suggested protocol is compared to the traditional Ad hoc On-Demand Distance Vector (AODV) routing protocol and shows that the outlined protocol results in an improvement in QoS.

Fake news on social media has become a growing concern due to its potential impact on shaping public opinion. The proposed Debunking Multi-Lingual Social Media Posts using Deep Learning (DSMPD) approach offers a promising solution to detect fake news. The DSMPD approach involves creating a dataset of English and Hindi social media posts using web scraping and Natural Language Processing (NLP) techniques. This dataset is then used to train, test, and validate a deep learning-based model that extracts various features, including Embedding from Language Models (ELMo), word and n-gram counts, Term Frequency-Inverse Document Frequency (TF-IDF), sentiments, polarity, and Named Entity Recognition (NER). Based on these features, the model classifies news items into five categories: real, could be real, could be fabricated, fabricated, or dangerously fabricated. To evaluate the performance of the classifiers, the researchers used two datasets comprising over 45,000 articles. Machine learning (ML) algorithms and Deep learning (DL) model are compared to choose the best option for classification and prediction.

Many industries, including the automobile industry, have seen inventive development in various application areas as a result of the Internet revolution. Autonomous vehicles aren't science fiction anymore; they are a reality. The transformation of existing Vehicular Networks (VANETs) into the Internet of Vehicles (IoV) resulted in numerous advantages, including im-proved traffic management and a safer driving experience. In the past, there have been reports of VANET cyberattacks involving vehicles that are not entirely autonomous. These attacks, however, are equally viable in a VANET with fully autonomous vehicles. Currently, available anti-virus tools are highly sophisticated, but malware writers are commonly one step ahead of the soft-ware, and new obfuscated viruses that current anti-virus software cannot recognize are constantly released. As a result, before adopting currently available anti-malware tools as a malware detection system in the Vehicular networks, it is necessary to evaluate their effectiveness against advanced malware. This research work investigates and presents the effectiveness of 72 publicly available anti-virus engines against 300 live malicious android applications and 70 benign applications. The experiment is conducted on Ubuntu 20.04, Intel i7 machine with 16 GB of memory to scan the malicious samples as well as benign samples from their respective local repositories through 72 anti-virus engines. A script is developed in python 3.5, which uses VirusTotal API to upload the malicious as well as benign samples to VirsuTotal and fetch the scanning report to our local log file. The results presented in the study show that majority of the malicious samples could not be detected. Out of 72 AV scanners considered in the study, the detection accuracy of only 5 scanners is in the range of 10% to the highest detection accuracy of 30.67 %, whereas the detection accuracy of the rest of the 67 AV scanners is below 6 %. Based on the literature review and experimental results derived in the study, the authors conclude that most of the known anti-virus tools can detect all known malwares but are in-efficient against highly dynamic, evolving, obfuscated mal wares and zero-day attacks.

Crop-related problems such as pests and diseases in India lead to yearly losses exceeding $500 billion. Leaf blight is identified as the principal factor responsible for the substantial financial losses amounting to $500 billion. Farmers engaged in the cultivation of forage and grain sorghum experience the greatest degree of hardship. This disease has a significant impact on various crops, including maize, rice, tomato, potato, millet, and onion. The timely detection and evaluation of disease in plants can contribute to mitigating the extent of associated losses. However, the task presents difficulties as a result of variations in crop species, varieteis of crop diseases, and environmental factors. The current methodologies lack generalizability in their ability to classify and predict diseases. All of the techniques employed in this study are applied to a dataset with predetermined input values and corresponding output values. The current methodologies involve preprocessing the images and performing segmentation for extracting the appropriate characteristics. The process of segmentation necessitates the implementation of pre-processing techniques, such as dilation and edge detection. As a consequence, the loss of crucial information occurs, which subsequently leads to inaccurate classification. Furthermore, the methodologies employed thus far have not been designed to evaluate the performance of the algorithm on specialised or specific datasets. Deep learning methodologies are susceptible to the issue of overfitting. This paper proposed an approach for extracting and analysing crop image data using the PySpark (MCIP) data frame. The MCIP framework employs Principal Component Analysis (PCA) as a method for selecting pertinent features. The PCA features that have been gathered are subsequently employed to identify homogeneous subgroups through the utilisation of the K-means algorithm. The utilisation of a categorised predictive output facilitates the identification and detection of diseases present in potato leaves. The utilisation of the Multispectral Crop Imaging Platform (MCIP) extends beyond the examination of potatoes exclusively, as it possesses the capability to identify diseases present in the foliage of various agricultural crops. In order to validate our assertion, we conducted an experiment utilising the MCIP algorithm on a dataset pertaining to rice diseases. In order to assess the robustness of MCIP, we conducted an evaluation of its Accuracy, Silhouette score, speed, and F1 score. The MCIP model demonstrated high performance in terms of both speed and accuracy compared to existed approaches. The level of accuracy is remarkably near 100 percent. Index Terms— Agriculture, clustering, data mining, k-means, pca, pySpark

WithBina Kotiyal Heman Pathak the continuous growth in the data and its use as a resource for analytic knowledge continues to help companies develop, the need for innovative approaches, tools, and strategies to extract actionable insights is becoming increasingly important. The data collected from myriad sources like social media, search engines, and the Internet of Things has developed substantial opportunities concerning the business to business industrial organizations. Big data (BD) computing is classified as batch and stream computing based on the processing types. Batch computing is performed when data is at rest, whereas real-time computing is performed when data is in motion. In the present era, real-time stream processing is in demand as the massive data generated has to be handled speedily to meet the business or organization requirements. BD analytics is used to get the big insight from this data. However, cleansing, interpreting, and analyzing such massive databases present hurdles in marketing, particularly in terms of making real-time decisions. This paper throws light on the various issues and challenges associated to BD. Most of the challenges are associated to the preprocessing phase of BD. It also presents the diverse applications of BD.

Mobile ad-hoc network (MANET) is an infrastructure-less network of mobile nodes, connected by wireless links. Although mobility is the key characteristic of MANETs, yet the frequent movement of nodes may lead to link failure. This frequent topology change due to evasive mobility is one of the primary reason of Quality of service (QoS) degradation in conventional MANETs. If link failure time of already established root is estimated in advance, data packet loss can be avoided by exploring alternate path well within time. Thus, accurate link failure time estimation is one of the key areas that have drawn the attention of researchers of the ad-hoc networking community. This paper outlines a least-square quadratic polynomial regression-based technique for estimating link failure time by using the signal strength of received data packets. The distance between the transmitting and receiving nodes is calculated from the received signal strength of data packets. The authors have generated an optimal error quadratic model between this node distance and data packet arrival time. After quadratic model formulation, the link failure time is estimated by finding the moment at which the maximum communication range will be achieved for considered transmitter–receiver pair. A detailed analysis has been done for observing the behaviour of link failure time estimation accuracy of the proposed technique with varying network parameters. The repercussion of mobility variation on estimated link failure time has also been analysed. The proposed technique has also been compared with an existing interpolation-based technique. Network Simulator 2.35 has been selected as the primary simulation tool along with BonnMotion and MOVE tool for various mobility scenarios generation.

In theYashi Chaudhary Dr. Heman Pathak present era, the use of the Internet has extended abruptly. With this abrupt increase, massive data is being created, resulting in big data. Big data means more diverse, more impetus, and more complex data streams. Data is being produced in abundance in exabytes and zettabytes by electronic devices, power grids, and modern software. This big data brings different challenges such as incompleteness, inconsistency, heterogeneity, and security with itself. The presented paper targets the security challenge as it is a very significant feature overseen by various data analysts; thus, data must be secured from dwindling in the wrong hands. This paper discusses the approaches and mechanisms mainly based on anonymization, access control, and encryption.

Diabetic Retinopathy is a significant complication of diabetes, caused by a high blood sugar level, which damages the retina. In its earliest stages, diabetic retinopathy is asymptomatic and can lead to blindness if not discovered and treated promptly. As a result, there is a need for a reliable screening method. According to studies, this problem affects a large section of the population, and it is thus linked to Big Data. There are several obstacles and issues with Big Data, but Deep Learning is providing solutions to these issues. As a result, academics are extremely interested in Big Data with Deep Learning. It has been our goal in this study to employ effective preprocessing and Deep Learning approaches to accomplish binary classification of Diabetic Retinopathy. The experiment is done out using a dataset from Kaggle that was collected from India. The peculiarity of the paper is that the work is implemented on the Spark platform, and the performance of three models, InceptionV3, Xception, and VGG19 with the Logistic Regression classifier is compared. The accuracy of the models is used as a comparison criterion. Based on the results of the trial, the accuracy of InceptionV3 is 95 percent, the accuracy of Xception is 92.50 percent, and the accuracy of VGG19 is 89.94 percent. Consequently, InceptionV3 outperforms the other two models.

Ad-hoc networks in which nodes are mobile as well as communicate via wireless links fall under the category of mobile ad-hoc networks (MANETs). Evasive mobility and the limited battery life of MANET nodes make routing a difficult problem. Most of the conventional routing protocols recommend the shortest path without considering route stability into account. A Cross-Layer Design and Fuzzy Logic based Stability Oriented (CLDFL-SO) routing protocol is proposed in this research, which offers a solution for stable route formation by eliminating unstable links and low-quality nodes. Cross-layer interaction parameter based link residual lifetime calculation is used to assess the link's stability. The fuzzy logic is being used to evaluate the node quality by providing node metrics like node speed, residual energy and node degree. The simulations illustrate the efficacy of the suggested protocol in comparison to the popular Ad-hoc On-Demand Distance Vector (AODV) protocol.

Mobile ad-hoc network (MANET) is an infrastructure-less, rapidly deployable and self-organizing distributed network with mobile autonomous terminals. Due to these characteristics, MANETs have always been important for defence applications especially for countries like India having boundaries and regions with large geographical diversity. Mobility is one of the defining features of MANET and has a major impact on the performance of routing protocols. In the present work, the performance of the AODV routing protocol is characterised for various mobility scenarios including random movement-based, controlled movement-based and realistic mobility models. A rigorous mobility and scalability analysis of AODV has been presented in graphical form considering transmission delay, number of received packet, control overhead, normalized routing overhead, packet delivery ratio and throughput as the performance measure. Network Simulator 2.35 is chosen as the primary simulator along with BonnMotion as well as the MOVE tool, for the generation of various mobility scenarios.

The change in the behavior of humans in the past decade has shown a tremendous generation in the data. The various researchers have given various definitions and discussed the different characteristics of big data. In the present study, we emphasize on the less focused areas of big data. One such zone is big data preprocessing. Extracting valuable information from big data has broadly three phases: first is acquisition and storage, second is data preprocessing, third is applying data mining and, at last, analysis of data. The contribution of this paper is that it shows generating the valuable information from big data not dependent on opting an advanced algorithm or novel algorithm but more than that it depends on acquisition of relevant data and preprocessing phase. The preprocessing phase plays a significant role in generating valuable data which serves as a great input in decision-making. At last, this paper gives a brief survey and analysis on big data preprocessing techniques used to handle imperfect data, reduction of data size and imbalanced data. It also theoretically discusses the different problems associated with the various phases and gives future directions where the researchers can work.

In this digital era, technology is upgrading day by day and becoming more agile and intelligent. Smart devices and gadgets are now being used to find solutions to complex problems in various domains such as health care, industries, entertainment, education, etc. The Transport system, which is the biggest challenge for any governing authority of a state, is also not untouched with this development. There are numerous challenges and issues with the existing transport system, which can be addressed by developing intelligent and autonomous vehicles. The existing vehicles can be upgraded to use sensors and the latest communication techniques. The advancements in the Internet of Things (IoT) have the potential to completely transform the existing transport system to a more advanced and intelligent transport system that is the Internet of Vehicles (IoV). Due to the connectivity with the Internet, the Internet of Vehicles (IoV) is exposed to various security threats. Security is the primary issue, which requires to be addressed for success and adoption of the IoV. In this paper, the applicability of machine learning based solutions to address the security issue of IoV is analyzed. The performance of six machine-learning algorithms to detect Bot threats is validated by the k-fold cross-validation method in python.

Mobile ad-hoc network (MANET) is a collection of mobile terminals forming an infrastructure-less and quickly deployable network, in which nodes can communicate to each other via multiple hops. Mobility attribute is a notable one in MANET, as this leads to frequent topology changes, so this is the primary cause of link failure. Link failure time estimation has always remained an active area of research among researchers of the networking community. This paper explores various link failure time prediction techniques and proposes a novel least-squares polynomial regression-based statistical technique to estimate the link failure time in MANET. Each node in the network periodically broadcasts hello packets to register its presence with neighbouring nodes. A neighbour node receives these packets and uses its signal strength to estimate the link failure time with help of quadratic least-squares regression. The outlined technique is simulated using Network Simulator 2.35. The performance of the estimation accuracy of the suggested technique and existing interpolation-based technique has been examined for numerous mobility and scalability scenarios.

Location management of a Mobile Agent (MA) is necessary for a Mobile Agent System (MAS), in which many significant services are accomplished using MA communications that require specific location information. This paper gives the performance analysis of a Hierarchical Location Management System (HLMS) for mobile Multi Agent System (MUS) with the objectives to reduce the search and update cost. This work also discusses a mailbox-based approach to provide communication among MAs. Mailbox is a data structure which is used to store the messages for MAs. There are two different communication mechanisms (jump and full migration) with mailbox have been used. In jump migration MA's mailbox always resides at the local router and in full migration MA always carries its mailbox with it at the host it is executing. For jump migration MA periodically checks its mailbox to get the message. HLMS has been modelled using the timed Coloured Petri Net (CPN) tool. Performance of HLMS is then observed for identified parameters such as Trip Time (TT), Migration Rate (MR), Search Rate (SR), Network Overhead (ND) and Communication Time (COT). Simulation results show that HLMS can locate the MAs in a fault free environment but TT and ND decrease as intra-region MR increases.

With the fast expansion in wide area networks leading to availability of low cost fundamental computational resources, the popularity of computational grids has increased. Effective dynamic load balancing (DLB), scheduling and fault tolerance collectively determine the QoS requirements of users from computational grids. In an effort to enhance the previously proposed and implemented DLB algorithms for hierarchical and distributed computational grids viz. DLBCGBH – H / G, Fuzzy Min-Max Scheduling (FMiMaS) was proposed and integrated with the Local scheduling proposed in DLBCGBH – H / D, to result into two resource management schemes viz. Fuzzy Hierarchical & Fuzzy Distributed approaches, based on hybrid scheduling demonstrating tremendous improvements against the performance metrics viz. Average Consumed Time, Average Waiting Time and Number of Tasks Migrated. In this paper, these two approaches are tested for fault tolerance against various possibilities of node failure to assess their robustness for the domain of computational grids.

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

Grid computing is an infrastructure for supporting complex computing.That is organized with the different scale of computational and network resources.In addition of that it is capable to process the request of multiple users.In this context the effective scheduling of resources according to the submitted tasks are required for efficient computational outcome.This paper provides an experimental study for the three popular load balancing techniques i.e. space shared, distributed and Hierarchical.The experiments are performed using GridSim technology and with help of JAVA based implemented scripts.The two kinds of experiments are reported in this work first with the increasing workload and secondly with the varying number of resources i.e. number of machines and number of processing elements.The different experiments show that the space shared is a promising algorithm for load balancing but the hierarchical load balancing algorithm comparatively enhances the performance of grid.Finally, the distributed load balancing algorithm demonstrates its superiority among all of them.

Mobile Agent technology has become a new paradigm for distributed real-time systems because of their inherent advantages. In any distributed system, along with other issues, survivability and fault tolerance are vital issues for deploying Mobile Agent for real applications. All Mobile Agent based applications face reliability problems due to the failure of agent platform, host and communication link etc. Mobile Agent technology has drawn attention of various researchers working in the area of distributed computing. Researchers have realized the benefits of using Mobile Agents over other existing technology and explore various area of application for Mobile Agents such as Electronic Commerce, Network Management, and Distributed Applications etc. However to fully deploy Mobile Agents in practice a number of challenging issues especially security, fault tolerance and privacy need to be addressed. The scope of this paper is limited to address fault tolerance problem of Mobile Agents in a multi agent environment. This paper identifies various faults in life cycle of Mobile Agent and proposes a comprehensive solution to tolerate all these faults. Paper also identifies the situations when Mobile Agent gets blocked and suggests several ways to avoid these blocks and continues its execution. Proposed solutions combine various existing fault tolerant mechanism to tolerate different kinds of faults. Proposed approach is hierarchical in nature, which combines both centralized and distributed approaches to take advantages of both. Thread base mechanism has been used to detect the failure of Mobile Agent and its executing environment. Heart-beat message passing and Ping command based techniques have been suggested to detect failure of Agent servers. Mobile agent system places have been introduced in this paper for Mobile agent execution. Modified itinerary options have also been explored for tolerating faults and to avoid blocking. Rear guard and acknowledgement based mechanism has been used to tolerate link failure and to ensure fault free migration of Mobile Agents across the networks. Keywords-Agent (MA), Mobile Agent System (MAS), Multi Agent System (MUS), Fault Tolerance, Ping Method.