An efficient learning based approach for automatic record deduplication with benchmark datasets.

With technological innovations, enterprises in the real world are managing every iota of data as it can be mined to derive business intelligence (BI). However, when data comes from multiple sources, it may result in duplicate records. As data is given paramount importance, it is also significant to eliminate duplicate entities towards data integration, performance and resource optimization. To realize reliable systems for record deduplication, late, deep learning could offer exciting provisions with a learning-based approach. Deep ER is one of the deep learning-based methods used recently for dealing with the elimination of duplicates in structured data. Using it as a reference model, in this paper, we propose a framework known as Enhanced Deep Learning-based Record Deduplication (EDL-RD) for improving performance further. Towards this end, we exploited a variant of Long Short Term Memory (LSTM) along with various attribute compositions, similarity metrics, and numerical and null value resolution. We proposed an algorithm known as Efficient Learning based Record Deduplication (ELbRD). The algorithm extends the reference model with the aforementioned enhancements. An empirical study has revealed that the proposed framework with extensions outperforms existing methods.

Hybrid deep learning model with enhanced sunflower optimization for flood and earthquake detection.

Natural catastrophes may strike anywhere at any moment and cause widespread destruction. Most people do not have the necessary catastrophe preparedness knowledge or awareness. The combination of a flood and an earthquake can cause widespread destruction. Natural catastrophes have a domino effect on a country's economy, first by damaging infrastructure and then by taking human lives and other resources. The mortality tolls of both humans and animals have decreased as a result of recent natural disasters. So, we need a mechanism to identify and monitor floods and earthquakes. The suggested system uses a hybrid deep learning analysis to keep an eye on earthquake- and flood-affected areas. In order to boost the efficiency of the presented model, this research presents the improved sunflower optimisation (ESFO). In polynomial time, it determines the best time to schedule events. In view of the need for real-time monitoring of regions vulnerable to flooding and earthquakes, as well as the associated costs and precautions, this study focuses on systems. The suggested technology also sends a notification to the proper authorities whenever a person is detected in the area. In the event of an emergency, it can be used as a backup source of solar power. We then offer the best suitable depth and enable real-time earthquake detection with reduced false alarm rates through practical evaluation. Finally, we demonstrate that the projected model can be successfully deployed in a real-world, dynamic situation after being trained on a range of datasets.

Prediction of DDoS attacks in agriculture 4.0 with the help of prairie dog optimization algorithm with IDSNet.

Integrating cutting-edge technology with conventional farming practices has been dubbed "smart agriculture" or "the agricultural internet of things." Agriculture 4.0, made possible by the merging of Industry 4.0 and Intelligent Agriculture, is the next generation after industrial farming. Agriculture 4.0 introduces several additional risks, but thousands of IoT devices are left vulnerable after deployment. Security investigators are working in this area to ensure the safety of the agricultural apparatus, which may launch several DDoS attacks to render a service inaccessible and then insert bogus data to convince us that the agricultural apparatus is secure when, in fact, it has been stolen. In this paper, we provide an IDS for DDoS attacks that is built on one-dimensional convolutional neural networks (IDSNet). We employed prairie dog optimization (PDO) to fine-tune the IDSNet training settings. The proposed model's efficiency is compared to those already in use using two newly published real-world traffic datasets, CIC-DDoS attacks.