In smart surveillance systems, event classification and detection are essential parts, on the other hand, violent event recognition is one of the most important key elements in that systems. The use of the transformer network for video action recognition has achieved very high results, On the other hand, the transformer network needs a large amount of data to gain good accuracy therefore, a new family of video transformer networks called Data-efficient video transformer (DEVTr) came to address these problems and shows that the use of the pre-trained convolution neural network in the embedding stage can improve accuracy with the use of a small dataset for the given task. In this study, we extend the data-efficient video transformer (DEVTr) for better event detection within a small dataset and with low hardware resources. We also introduced two new video data augmentations methods (random erase from frames and frame position shifting with blurring). The model achieved 98.25% accuracy on the Real-life violence dataset (RLVS), an accuracy of 96% on the NTU CCTV-fight dataset, and accuracy of 91.803% on the UBI-Fight dataset. A comparison with previous techniques illustrated that the proposed methods provide the best result among the other research for violence event detection within a small dataset and low hardware resources.

Oil refineries have high operating expenses and are often exposed to increased asset integrity risks and functional failure. Real-time monitoring of their operations has always been critical to ensuring safety and efficiency. We proposed a novel Industrial Internet of Things (IIoT) design that employs a text-to-speech synthesizer (TTS) based on neural networks to build an intelligent extension control system. We enhanced a TTS model to achieve high inference speed by employing HiFi-GAN V3 vocoder in the acoustic model FastSpeech 2. We experimented with our system on a low resources-embedded system in a real-time environment. Moreover, we customized the TTS model to generate two target speakers (female and male) using a small dataset. We performed an ablation analysis by conducting experiments to evaluate the performance of our design (IoT connectivity, memory usage, inference speed, and output speech quality). The results demonstrated that our system Real-Time Factor (RTF) is 6.4 (without deploying the cache mechanism, which is a technique to call the previously synthesized speech sentences in our system memory). Using the cache mechanism, our proposed model successfully runs on a low-resource computational device with real-time speed (RTF equals 0.16, 0.19, and 0.29 when the memory has 250, 500, and 1000 WAV files, respectively). Additionally, applying the cache mechanism has reduced memory usage percentage from 16.3% (for synthesizing a sentence of ten seconds) to 6.3%. Furthermore, according to the objective speech quality evaluation, our TTS model is superior to the baseline TTS model.

Traffic signs object detection has gained high interest in recent years, as one of the most significant object detector applications. The development of deep learning technologies gives support to traffic signs detector which it offers several advantages, including the benefit of high detection precision and the timely response to condition changes of traffic signs. Therefore, this paper shows an efficient method for detecting traffic signs. Hence, it implements a new Iraqi Traffic Sign Detection Benchmark (IQTSDB) dataset based on You Only Look Once version 5 (YOLOv5) algorithm. The experimental results show that the implementation of the IQTSDB dataset with YOLOv5 has high efficiency in different conditions such as sunny, cloudy, weak light, and rainy conditions. Besides, real images has been captured for the traffic signs in Baghdad. In addition, the results show that the YOLOv5 has high efficiency in detecting traffic signs of different sizes (small, medium, large), and mean Average Precision (mAP) compared to yolov2, and yolov3.

Traffic signs object detection has gained great interest in recent years, as one of the most important object detector applications. Traffic signs detection is based on deep learning, which gives it the benefit of high detection precision and timely response to condition changes of the traffic. Therefore, this paper shows an efficient method for detecting traffic signs in real-time. Hence, it implements a new Iraqi Traffic Sign Detection Benchmark (IQTSDB) dataset based on Mask Region-based Convolutional Neural Network (Mask R-CNN). The results show that the implementation of IQTSDB dataset with Mask R-CNN has a great efficiency in different conditions such as sunny, cloudy, weak light, and rainy conditions. In addition, the real video captured for traffic signs in Baghdad has been taken and compared to the German Traffic Signs Detection Benchmark (GTSDB) dataset. The IQTSDB dataset has a better performance than GTSDB dataset based on the performance parameters training loss and mean Average Precision (mAP).