Surveillance systems regularly create massive video data in the modern technological era, making their analysis challenging for security specialists. Finding anomalous activities manually in these enormous video recordings is a tedious task, as they infrequently occur in the real world. We proposed a minimal complex deep learning-based model named EADN for anomaly detection that can operate in a surveillance system. At the model’s input, the video is segmented into salient shots using a shot boundary detection algorithm. Next, the selected sequence of frames is given to a Convolutional Neural Network (CNN) that consists of time-distributed 2D layers for extracting salient spatiotemporal features. The extracted features are enriched with valuable information that is very helpful in capturing abnormal events. Lastly, Long Short-Term Memory (LSTM) cells are employed to learn spatiotemporal features from a sequence of frames per sample of each abnormal event for anomaly detection. Comprehensive experiments are performed on benchmark datasets. Additionally, the quantitative results are compared with state-of-the-art methods, and a substantial improvement is achieved, showing our model’s effectiveness.

We present a novel system for anomaly detection in surveillance videos, specifically focusing on identifying instances where individuals deviate from public health guidelines during the pandemic. These anomalies encompassed behaviours like the absence of face masks, incorrect mask usage, coughing, nose-picking, sneezing, spitting, and yawning. Monitoring such anomalies manually was challenging and prone to errors, necessitating automated solutions. To address this, a multi-attention-based deep learning system was employed, utilizing the EfficientNet-B0 architecture. EfficientNet-B0, featuring the Mobile Inverted Bottleneck Convolution (MBConv) block with Squeeze-and-Excitation (SE) modules, emphasizes informative channel characteristics while disregarding irrelevant ones. However, this approach neglected crucial spatial information necessary for visual recognition tasks. To improve this, the Convolutional Block Attention Module (CBAM) was integrated into EfficientNet-B0 to improve feature extraction. The baseline EfficientNet-B0 model’s SE module was replaced with the CBAM module within each MBConv module to retain spatial information related to anomaly activities. Additionally, the CBAM module, when embedded after the second convolutional layer, was observed to significantly enhance the classification ability of the model across different anomaly classes, resulting in a significant accuracy boost from 87 to 96%. In conclusion, we demonstrated the efficacy of the CBAM module in refining feature extraction and improving the entire classification performance of the proposed method, showcasing its potential for robust anomaly detection in surveillance videos.

Precise and timely diagnosis of Covid-19 and pneumonia is crucial for effective treatment. However, the traditional RT-PCR method is time-consuming, costly, and prone to incorrect results. To address these limitations, a deep ensemble strategy is proposed as a promising alternative to provide more accurate and reliable outcomes. The strategy comprises three main stages: i) pre-processing, ii) salient feature extraction, and iii) training and classification. In the pre-processing step, the authors resize the images to the desired input shape. Data augmentation techniques, such as zooming, nearest full mode, rotation, and flipping, are employed to augment the dataset, thereby improving the training accuracy of the proposed approach. Additionally, the proposed method leverages the capabilities of VGG-16, DenseNet-201, and Efficient-B0 models using transfer-learning techniques to extract deep features from the images. These salient features are then passed through proposed fully connected layers and ensemble classifiers to predict the probability of the given classes. Extensive experiments were conducted on a chest X-ray image dataset, demonstrating that the proposed system outperforms contemporary techniques in terms of precision, recall, F1-score, and accuracy (acc). The proposed method obtained 97% of acc, while 96%, 95%, and 97% pre, rec, and F1-score respectively. In conclusion, this study presents a valuable contribution to medical image diagnosis using an AI-based deep ensemble strategy. The proposed approach offers a promising solution for accurate and efficient diagnosis of Covid-19 and pneumonia, assisting healthcare professionals in making informed decisions for optimal treatment outcomes.