Received Sep 7, 2022 Revised Oct 18, 2022 Accepted Oct 24, 2022 In the digital world, classifying real sensed data in huge volumes derived from numerical problems is a challenging task due to the computational complexity of the metaheuristic searching process. The deep learning approach includes convolutional neural network (CNN), long short-term memory (LSTM), and Bidirectional (BI)-LSTM, suitable for an optimistic processing time of analyzing XML datasets (i.e., social media, trade center, and surveillance data exchanged in the internet world). However, it faces process deviation when datasets extend their range beyond the expected volume. This paper proposes a novel deep learning formwork referred to as archimed improved numerical optimization deep learning (AINODL) to improve the classification of XML datasets. The proposed AINODL framework first extracts feature from XML documents using the vector space model. Secondly, it classifies the XML data using the inbuilt function of the AINODL framework. The experiments demonstrate that the performance parameters accuracy (90%), sensitivity (93%), and specificity (94%) of the proposed AINODL framework are significantly enhanced compared with the existing approaches CNN, LSTM, and BI-LSTM.

Indonesian Journal of Electrical Engineering and Computer Science

A Survey on Web Service approaches targeting network traffic reduction

Web extensible markup language (XML) data quality analysis using clustering is necessary in many real time web applications. In huge applications XML is the standard format to explore the web data. In existing approaches the XML web data is clustered by using Weighted Fuzzy C means (WFCM),LSI(Latent Semantic Indexing),LSI*(Enhanced Latent Semantic Indexing) and K-means clustering approach. The existing approach generates degrades the efficiency of the performance. The performance of the clustering is increased by the novelty technique Improved Fuzzy Clustering Method (I-FCM)in this article. I-FCM is the machine learning method that clusters the XML data better than the other existing methods. First, using keyword the features are extracted from the XML web repository. Next, cluster the extracted features using I-FCM approach. Finally, necessary performance parameters in the clustering of XML data are analyzed. This article used the platform MATLAB to demonstrate the proposed approach. For the experimental purpose the LF-AMAZON dataset is utilized. The parameters accuracy, purity, entropy, and search time is utilized to measure the performance of the novelty technique. This performance is compared with the existing approach. The output of the novelty work shows the better performance and robust result is generated than the existing method. 

An Improved Fuzzy Clustering Method for Analyzing Clustering Quality in XML Web Data

The affinity propagation (AP) clustering can accurately and effectively process complex data and has been widely used in various data clustering analysis fields, especially in computer vision and computational biology. However, the dataset usually contains sensitive information. To prevent the leakage of users’ privacy during the clustering process, this paper proposes an affinity propagation clustering with differential privacy algorithm. Based on the affinity propagation clustering, we first adjust the corresponding preference value by calculating the density value of each sample and then add Laplace noise to the responsibility matrix to protect the data privacy. Experimental results show that the adjusted preference value with the sample density can effectively reduce the running time of the algorithm and the loss of data accuracy caused by differential privacy.

DP-AP: Differential Privacy-Preserving Affinity Propagation Clustering

Received Aug 30, 2021 Revised Jun 15, 2022 Accepted Jun 23, 2022 The current paper proposes a novel type of decision tree, which is never used for software development cost prediction (SDCP) purposes, the clusterbased fuzzy regression tree (CFRT). This model uses the fuzzy k-means (FKM), which deals with data uncertainty and imprecision. The tree expansion is based on the variability measure by choosing the node with the highest value of granulation diversity. This paper outlined an experimental study comparing CFRT with four SDCP methods, notably linear regression, multi-layer perceptron, K-nearest-neighbors, and classification and regression trees (CART), employing eight datasets and the leave-one-out cross-validation (LOOCV). The results show that CFRT is among the best, ranked first in 3 datasets according to four accuracy measures. Also, according to the Pred(25%) values, the proposed CFRT model outperformed all the twelve compared techniques in four datasets: Albrecht, constructive cost model (COCOMO), Desharnais, and The International Software Benchmarking Standards Group (ISBSG) using LOOCV and 30-fold crossvalidation technique.

An effective quality analysis of XML web data using clustering and classification approach is used in our proposed method. XML is turning into a standard in representation of data, it is attractive to support keyword search in XML database. A keyword search searches for words anyplace in record. It is developed as best worldview for finding data on web. The most imperative prerequisite for the keyword search is to rank the consequences of question so that the most pertinent outcomes show up. Here, we gather more XML documents. Followed by that, feature extraction occurs. Since the selected feature contains both relevant as well as irrelevant features it is essential to filter the irrelevant features. For the purpose of selecting, the relevant features probability-based feature selection method is used. Then for clustering the relevant features on the basis of keywords weighted fuzzy c means clustering algorithm is used. In order to assess the XML data quality, optimal neural network (ONN) classifier is utilized. In this ONN classifier in order to select the optimal weights, whale optimization algorithm is used. Thus, the web pages are effectively ranked. The efficiency of the proposed method is assessed using clustering and classification accuracy, RMSE, and search time. The proposed method is implemented in JAVA.

An effective quality analysis of XML web data using hybrid clustering and classification approach

Blockchain security via the Internet of Things (IoT) will reshape the decision-making function of the data-driven incumbent smart enterprise, providing the vision of the connected world of things. Enterprise IoT development of devices, personnel, and systems in such a way that they may connect and communicate with each other through the Internet. Blockchain is an enterprise financial transaction, and its digital network is distributed transaction ledger. Today, enterprises need the massive global data management and rapid trading volume to keep things going and growing. It creates enterprise business challenges of different types of security, transparency, and complexity of the problem. Enterprise architecture offers several advantages for the thief to obtain a specific user account,   application, and access to the device. This is, will doesn't be to provide the necessities of security. The proposed Digital Hash Data Encryption (DHDE) is used to secure the transaction data-based embedded system people and blockchain. Blockchain and IoT technology integration may bring numerous benefits to mention. Therefore, the proposed DHDE algorithm comprehensively discusses the blockchain technology integration system. The proposed DHDE algorithm encrypts the transaction data for an unauthorized person who cannot access the enterprise transaction data based on embedded system people and blockchain.

/pdf/digital-hash-data-encryption-for-iot-financial-transactions-2q7crxcp.pdf

Digital Hash Data Encryption for IoT Financial Transactions using Blockchain Security in the Cloud

Data storage presents substantial issues due to concerns about data security and privacy. In this study, we provide a search-based, interoperable, verified public key cryptography system. The searchability is significantly improved by our recommended method, which allows the cloud servers to create invert crypto indexes while needing a query trap and leveraging asymmetric cryptography developed by van Vries, Miller, Showing different, and Vaikuntanathan. Contrarily, the recommended method offers a brand-new permitted dataset built on the inversion decryption scheme and shows how it may be used to evaluate the thoroughness and correctness of serps. Additionally, using the provided method, many users may do encrypted searches on cryptography. Finally, it is shown that the offered technique is secure utilizing the approximate-GCD problem. The experiment's results showed that the proposed technique had less computational complexity than the methods currently in use.

M. Gopianand

Papers

An effective quality analysis of XML web data using hybrid clustering and classification approach

Digital Hash Data Encryption for IoT Financial Transactions using Blockchain Security in the Cloud

Accessible Authentication Using Keyword Search through Homomorphic Encryption