International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
Secure Data Transactions based on Hash Coded Starvation Blockchain Security using Padded Ring Signature-ECC for Network of Things
Get PDFBlockchain is one of the decentralized processes in a worldview that works with parallel and distributed ledger technology, the application process, and service-oriented design. To propose a Secure data Transaction based on Hash coded Starvation Blockchain security using Padded Ring signature-ECC for Network of Things. Initially, the crypto policy is authenticated based on the user-owner shared resource policy and access rights. This creates a Public blockchain environment with a P2P Blockchain network. The owner encrypts the data using optimized ECC through Hash-coded Starvation Blockchain security (HCSBS). This makes the encrypted block's provable partition chain Link (P2CL). The encrypted blocks are transmitted into the network of nodes monitored by NoT. During the data transmission, the Network of Things monitors the transaction flow to verify the authenticity over the network of nodes. The monitored data be securely stored in transaction Block storage with the hash-indexed block with chain ring policy (HICLP). This creates controller node aggregation over the transaction environment to securely transfer the data to the peer end. The User gets the access Key to decrypt the data with policy aggregated shared resource policy to access the data. The proposed system produces high security as well compared to the previous design
Context-Aware Clustering and the Optimized Whale Optimization Algorithm: An Effective Predictive Model for the Smart Grid
Get PDFFor customers to participate in key peak pricing, period-of-use fees, and individualized responsiveness to demand programmes taken from multi-dimensional data flows, energy use projection and analysis must be done well. However, it is a difficult study topic to ascertain the knowledge of use of electricity as recorded in the electricity records' Multi-Dimensional Data Streams (MDDS). Context-Aware Clustering (CAC) and the Optimized Whale Optimization Algorithm were suggested by researchers as a fresh power usage knowledge finding model from the multi-dimensional data streams (MDDS) to resolve issue (OWOA). The proposed CAC-OWOA framework first performs the data cleaning to handle the noisy and null elements. The predictive features are extracted from the novel context-aware group formation algorithm using the statistical context parameters from the pre-processed MDDS electricity logs. To perform the energy consumption prediction, researchers have proposed the novel Artificial Neural Network (ANN) predictive algorithm using the bio-inspired optimization algorithm called OWOA. The OWOA is the modified algorithm of the existing WOA to overcome the problems of slow convergence speed and easily falling into the local optimal solutions. The ANN training method is used in conjunction with the suggested bio-inspired OWOA algorithm to lower error rates and boost overall prediction accuracy. The efficiency of the CAC-OWOA framework is evaluated using the publicly available smart grid electricity consumption logs. The experimental results demonstrate the effectiveness of the CAC-OWOA framework in terms of forecasting accuracy, precision, recall, and duration when compared to underlying approaches
Machine Learning Approach for Prediction of the Online User Intention for a Product Purchase
Get PDFThe deployment of self-learning computer algorithms that can automatically enhance their performance via experience is referred to as machine learning in ecommerce and is a crucial trend of the retail digital transformation. Machine learning algorithms can be unambiguously trained by analysing big datasets, identifying repeating patterns, relationships, and anomalies among all of this data, and creating mathematical models resembling such associations. These models are improved when the algorithms analyse ever-increasing amounts of data, providing us with useful insights into specific ecommerce-related events and the links between all the variables that underlie them. A tool that has been quite effective in studying current affairs, predicting future trends, and making data-driven decisions. The present work investigates the implementation of machine learning algorithms to predict the user intention for purchasing a product on a specific store's website. An Online Shoppers Purchasing Intention data set from the UC Irvine Machine Learning Repository was used for this investigation. In this study, two classification-based machine learning algorithms i.e. Stochastic Gradient Descent (SGD) algorithm and Random Forest algorithm were used. SGD algorithm was used for first time in prediction of the online user intention. The results showed that the Random Forest resulted in the highest F1-Score of 0.90 in contrast to the Stochastic Gradient Descent algorithm
Developing the Computational Building Blocks for General Intelligent in SOAR
Get PDFCognitive architecture's purpose is to generate artificial agents with capacities similar to the human mind. Soar Cognitive Architecture is to produce the fixed computational building blocks needed for generally intelligent agents— agents that can outright a variety of tasks and encode, use, and learn all types of knowledge to realize the broad cognitive abilities present in humans. This paper introduced an arithmetic agent that does multicolumn, two-digit addition in SOAR. Here, we show the entire calculating procedure, including all of its operators. We are using episodic memory assistance to enhance the set of cognitive abilities that let the agent learn and reason
Deep learning based Brain Tumour Classification based on Recursive Sigmoid Neural Network based on Multi-Scale Neural Segmentation
Get PDFBrain tumours are malignant tissues in which cells replicate rapidly and indefinitely, and tumours grow out of control. Deep learning has the potential to overcome challenges associated with brain tumour diagnosis and intervention. It is well known that segmentation methods can be used to remove abnormal tumour areas in the brain. It is one of the advanced technology classification and detection tools. Can effectively achieve early diagnosis of the disease or brain tumours through reliable and advanced neural network classification algorithms. Previous algorithm has some drawbacks, an automatic and reliable method for segmentation is needed. However, the large spatial and structural heterogeneity between brain tumors makes automated segmentation a challenging problem. Image tumors have irregular shapes and are spatially located in any part of the brain, making their segmentation is inaccurate for clinical purposes a challenging task. In this work, propose a method Recursive SigmoidNeural Network based on Multi-scale Neural Segmentation (RSN2-MSNS) for image proper segmentation. Initially collets the image dataset from standard repository for brain tumour classification. Next, pre-processing method that targets only a small part of an image rather than the entire image. This approach reduces computational time and overcomes the over complication. Second stage, segmenting the images based on the Enhanced Deep Clustering U-net (EDCU-net) for estimating the boundary points in the brain tumour images. This method can successfully colour histogram values are evaluating segment complex images that contain both textured and non-textured regions. Third stage, Feature extraction for extracts the features from segmenting images using Convolution Deep Feature Spectral Similarity (CDFS2) scaled the values from images extracting the relevant weights based on its threshold limits. Then selecting the features from extracting stage, this selection is based on the relational weights. And finally classified the features based on the Recursive Sigmoid Neural Network based on Multi-scale Neural Segmentation (RSN2-MSNS) for evaluating the proposed brain tumour classification model consists of 1500 trainable images and the proposed method achieves 97.0% accuracy. The sensitivity, specificity, detection accuracy and F1 measures were 96.4%, 952%, and 95.9%, respectively
An Imperceptible Method to Monitor Human Activity by Using Sensor Data with CNN and Bi-directional LSTM
Get PDFDeep learning (DL) algorithms have substantially increased research in recognizing day-to-day human activities All methods for recognizing human activities that are found through DL methods will only be useful if they work better in real-time applications. Activities of elderly people need to be monitored to detect any abnormalities in their health and to suggest healthy life style based on their day to day activities. Most of the existing approaches used videos, static photographs for recognizing the activities. Those methods make the individual to feel anxious that they are being monitored. To address this limitation we utilized the cognitive outcomes of DL algorithms and used sensor data as input to the proposed model which is collected from smart home dataset for recognizing elderly people activity, without any interference in their privacy. At early stages human activities the input for human activity recognition by DL models are done using single sensor data which are static and lack in recognizing dynamic and multi sensor data. We propose a DL architecture based on the blend of deep Convolutional Neural Network (CNN) and Bi-directional Long Short-Term Memory (Bi-LSTM) in this research which replaces human intervention by automatically extracting features from multifunctional sensing devices to reliably recognize the activities. During the entire investigation process we utilized Tulum, a benchmark dataset that contains the logs of sensor data. We exhibit that our methodology outperforms by marking its accuracy as 98.76% and F1 score as 0.98
Resources Efficient Dynamic Clustering Algorithm for Flying Ad-Hoc Network
Get PDFUnmanned Aerial Vehicles, often known as UAVs, are connected in the form of a Flying Ad-hoc Network, or FANET, and placed to use in a variety of applications to carry out efficient remote monitoring. Their great mobility has an adverse effect on their energy consumption, which in turn has a detrimental effect on the network's stability and the effectiveness of communication. To manage the very dynamic flying behavior of UAVs and to keep the network stable, novel clustering algorithms have been implemented. In this context, a novel clustering technique is developed to meet the rapid mobility of UAVs and to offer safe inter-UAV distance, reliable communication, and an extended network lifespan. It also provides a detailed analysis of the similarities and distinctions between AODV, AOMDV, DSDV, and DumbAgent.The performance of these protocols is analyzed using the NS-2 simulator. The simulation results are shown in our study with AODV, AOMDV, DSDV, and DumbAgent. The results of the simulation make it abundantly evident that the AODV routing protocol outperforms the other routing protocols DSDV, AOMDV, and DumbAgent in terms of the number of packets lost, the amount of throughput achieved, the amount of routing overhead generated, and the amount of delay
A VOS analysis of LSTM Learners Classification for Recommendation System
Get PDFIn response to the growing popularity of social web apps, much research has gone into analyzing and developing an AI-based responsive suggestion system. Machine learning and neural networks come in many forms that help online students choose the best texts for their studies. However, when training recommendation models to deal with massive amounts of data, traditional machine learning approaches require additional training models. As a result, they are deemed inappropriate for the personalized recommender generation of learning systems. In this paper, we examine LSTM-based strategies in order to make useful recommendations for future research
EECLA: A Novel Clustering Model for Improvement of Localization and Energy Efficient Routing Protocols in Vehicle Tracking Using Wireless Sensor Networks
Get PDFDue to increase of usage of wireless sensor networks (WSN) for various purposes leads to a required technology in the present world. Many applications are running with the concepts of WSN now, among that vehicle tracking is one which became prominent in security purposes. In our previous works we proposed an algorithm called EECAL (Energy Efficient Clustering Algorithm and Localization) to improve accuracy and performed well. But are not focused more on continuous tracking of a vehicle in better aspects. In this paper we proposed and refined the same algorithm as per the requirement. Detection and tracking of a vehicle when they are in larges areas is an issue. We mainly focused on proximity graphs and spatial interpolation techniques for getting exact boundaries. Other aspect of our work is to reduce consumption of energy which increases the life time of the network. Performance of system when in active state is another issue can be fixed by setting of peer nodes in communication. We made an attempt to compare our results with the existed works and felt much better our work. For handling localization, we used genetic algorithm which handled good of residual energy, fitness of the network in various aspects. At end we performed a simulation task that proved proposed algorithms performed well and experimental analysis gave us faith by getting less localization error factor
An Approach for Mining Top-k High Utility Item Sets (HUI)
Get PDFItemsets have been extracted by utilising high utility item (HUI) mining, which provides more benefits to the consumer. This could be one of the significant domains in data mining and be resourceful for several real-time implementations. Even though modern HUI mining algorithms may identify item sets that meet the minimum utility threshold, However, fixing the minimum threshold utility value has not been a simple task, and often it is intricate for the consumers when we keep the minimum utility value low. It might generate a massive amount of itemsets, and when the value is at its maximum, it might provide a smaller amount of itemsets. To avoid these issues, top-k HUI mining, where k represents the number of HUIs to be identified, has been proposed. Further, in this manuscript, the authors projected an algorithm called the top-k exact utility (TKEU) algorithm, which works without computing and comparing transaction weighted utilisation (TWU) values and deliberates the individual utility item values for deriving the top-k HUI. The datasets are pre-processed by the proposed algorithm to lessen the system memory space and to provide optimal outcomes for condensed datasets