Search

Automatic meter reading is important for power billing in a smart city. Most SoTA (State-of-the-Art) vision-based methods can read only cyclometers and fail to handle dial meters due to their in-between problem and ambiguous patterns to interpret a digit and are not light enough to be run on an embedded platform. This paper focuses on the design and development of an Internet of Things (IoT)-assisted real-time Automatic Meter Reading (AMR) system for utility billing in a smart city. To enhance the accuracy of object detection, most SoTA methods use a very deep CNN-based architecture to create rich feature maps. However, this backbone also makes small objects in the last layer become one pixel or less. This paper proposes a novel BI-Fusion Mixed Stage Partial (BIF-MSP) network to hold the spatial information of a smaller object at the end of network architecture and also increase the efficiency while operating on an embedded system. It can accurately detect small digits not only from cyclometers but also from dial meters. It can automatically decide a rule (anticlockwise or clockwise) to accurately read digits on a dial-type meter. After that, a carry-out re-checking module is proposed to further improve the accuracy of this AMR system. The experiments show the superiorities of our ARM system in terms of accuracy and efficiency. The dataset can be publicly accessed from the following URL: https://140.113.110.150:5000/sharing/52HCvjly2

Gradient Descent, an effective way to search for the local minimum of a function, can minimize training and validation loss of neural architectures and also be incited in an appropriate order to decrease the searching cost of neural architecture search. In recent trends, the neural architecture search (NAS) is enormously used to construct an automatic architecture for a specific task. Mostly well-performed neural architecture search methods have adopted reinforcement learning, evolutionary algorithms, or gradient descent algorithms to find the best-performing candidate architecture. Among these methods, gradient descent-based architecture search approaches outperform all other methods in terms of efficiency, simplicity, computational cost, and validation error. In view of this, an in-depth survey is necessary to cover the usefulness of gradient descent method and how this can benefit neural architecture search. We begin our survey with basic concepts of neural architecture search, gradient descent, and their unique properties. Our survey then delves into the impact of gradient descent method on NAS and explores the effect of gradient descent in the search process to generate the candidate architecture. At the same time, our survey reviews mostly used gradient-based search approaches in NAS. Finally, we provide the current research challenges and open problems in the NAS-based approaches, which need to be addressed in future research.

Wearing a safety helmet is important in construction and manufacturing industrial activities to avoid unpleasant situations. This safety compliance can be ensured by developing an automatic helmet detection system using various computer vision and deep learning approaches. Developing a deep-learning-based helmet detection model usually requires an enormous amount of training data. However, there are very few public safety helmet datasets available in the literature, in which most of them are not entirely labeled, and the labeled one contains fewer classes. This paper presents the Safety HELmet dataset with 5K images (SHEL5K) dataset, an enhanced version of the SHD dataset. The proposed dataset consists of six completely labeled classes (helmet, head, head with helmet, person with helmet, person without helmet, and face). The proposed dataset was tested on multiple state-of-the-art object detection models, i.e., YOLOv3 (YOLOv3, YOLOv3-tiny, and YOLOv3-SPP), YOLOv4 (YOLOv4 and YOLOv4pacsp-x-mish), YOLOv5-P5 (YOLOv5s, YOLOv5m, and YOLOv5x), the Faster Region-based Convolutional Neural Network (Faster-RCNN) with the Inception V2 architecture, and YOLOR. The experimental results from the various models on the proposed dataset were compared and showed improvement in the mean Average Precision (mAP). The SHEL5K dataset had an advantage over other safety helmet datasets as it contains fewer images with better labels and more classes, making helmet detection more accurate.

The recent growth of the elderly population has led to the requirement for constant home monitoring as solitary living becomes popular. This protects older people who live alone from unwanted instances such as falling or deterioration caused by some diseases. However, although wearable devices and camera-based systems can provide relatively precise information about human motion, they invade the privacy of the elderly. One way to detect the abnormal behavior of elderly residents under the condition of maintaining privacy is to equip the resident’s house with an Internet of Things system based on a non-invasive binary motion sensor array. We propose to concatenate external features (previous activity and begin time-stamp) along with extracted features with a bi-directional long short-term memory (Bi-LSTM) neural network to recognize the activities of daily living with a higher accuracy. The concatenated features are classified by a fully connected neural network (FCNN). The proposed model was evaluated on open dataset from the Center for Advanced Studies in Adaptive Systems (CASAS) at Washington State University. The experimental results show that the proposed method outperformed state-of-the-art models with a margin of more than 6.25% of the F1 score on the same dataset.