Sameema Tariq¹, Ata-Ur- Rehman^2,3, Maria Abubakar², Waseem Iqbal⁴, Hatoon S. Alsagri⁵, Yousef A. Alduraywish⁵, Haya Abdullah A. Alhakbani^5,*

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2493-2515, 2024, DOI:10.32604/cmc.2024.055787 - 18 November 2024

Abstract In video surveillance, anomaly detection requires training machine learning models on spatio-temporal video sequences. However, sometimes the video-only data is not sufficient to accurately detect all the abnormal activities. Therefore, we propose a novel audio-visual spatiotemporal autoencoder specifically designed to detect anomalies for video surveillance by utilizing audio data along with video data. This paper presents a competitive approach to a multi-modal recurrent neural network for anomaly detection that combines separate spatial and temporal autoencoders to leverage both spatial and temporal features in audio-visual data. The proposed model is trained to produce low reconstruction error… More >

P. Shanmuga Prabha^*, S. Magesh Kumar

Intelligent Automation & Soft Computing, Vol.36, No.3, pp. 3101-3119, 2023, DOI:10.32604/iasc.2023.034885 - 15 March 2023

Abstract Today, securing devices connected to the internet is challenging as security threats are generated through various sources. The protection of cyber-physical systems from external attacks is a primary task. The presented method is planned on the prime motive of detecting cybersecurity attacks and their impacted parameters. The proposed architecture employs the LYSIS dataset and formulates Multi Variant Exploratory Data Analysis (MEDA) through Principle Component Analysis (PCA) and Singular Value Decomposition (SVD) for the extraction of unique parameters. The feature mappings are analyzed with Recurrent 2 Convolutional Neural Network (R2CNN) and Gradient Boost Regression (GBR) to More >

Yunping Zhao¹, Weixuan Liang¹, Jianzhuang Lu^1,*, Xiaowen Chen¹, Nijiwa Kong²

CMC-Computers, Materials & Continua, Vol.66, No.3, pp. 2709-2722, 2021, DOI:10.32604/cmc.2021.013389 - 28 December 2020

Abstract Late fusion multi-view clustering (LFMVC) algorithms aim to integrate the base partition of each single view into a consensus partition. Base partitions can be obtained by performing kernel k-means clustering on all views. This type of method is not only computationally efficient, but also more accurate than multiple kernel k-means, and is thus widely used in the multi-view clustering context. LFMVC improves computational efficiency to the extent that the computational complexity of each iteration is reduced from O(n³) to O(n) (where n is the number of samples). However, LFMVC also limits the search space of the… More >