Improved Arabic Alphabet Characters Classification Using Convolutional Neural Networks (CNN)

Handwritten characters recognition is a challenging research topic. A lot of works have been present to recognize letters of different languages. The availability of Arabic handwritten characters databases is limited. Motivated by this topic of research, we propose a convolution neural network for the classification of Arabic handwritten letters. Also, seven optimization algorithms are performed, and the best algorithm is reported. Faced with few available Arabic handwritten datasets, various data augmentation techniques are implemented to improve the robustness needed for the convolution neural network model. The proposed model is improved by using the dropout regularization method to avoid data overfitting problems. Moreover, suitable change is presented in the choice of optimization algorithms and data augmentation approaches to achieve a good performance. The model has been trained on two Arabic handwritten characters datasets AHCD and Hijja. The proposed algorithm achieved high recognition accuracy of 98.48% and 91.24% on AHCD and Hijja, respectively, outperforming other state-of-the-art models.

A convolution neural network approach for fall detection based on adaptive channel selection of UWB radar signals

According to the World Health Organization and other authorities, falls are one of the main causes of accidental injuries among the elderly population. Therefore, it is essential to detect and predict the fall activities of older persons in indoor environments such as homes, nursing, senior residential centers, and care facilities. Due to non-contact and signal confidentiality characteristics, radar equipment is widely used in indoor care, detection, and rescue. This paper proposes an adaptive channel selection algorithm to separate the activity signals from the background using an ultra-wideband radar and to generalize fused features of frequency- and time-domain images which will be sent to a lightweight convolutional neural network to detect and recognize fall activities. The experimental results show that the method is able to distinguish three types of fall activities (i.e., stand to fall, bow to fall, and squat to fall) and obtain a high recognition accuracy up to 95.7%.

Design and Implementation of Intelligent EOD System Based on Six-Rotor UAV

Explosive ordnance disposal (EOD) robots can replace humans that work in hazardous environments to ensure worker safety. Thus, they have been widely developed and deployed. However, existing EOD robots have some limitations in environmental adaptation, such as a single function, slow action speed, and limited vision. To overcome these shortcomings and solve the uncertain problem of bomb disposal on the firing range, we have developed an intelligent bomb disposal system that integrates autonomous unmanned aerial vehicle (UAV) navigation, deep learning, and other technologies. For the hardware structure of the system, we design an actuator constructed by a winch device and a mechanical gripper to grasp the unexploded ordnance (UXO), which is equipped under the six-rotor UAV. The integrated dual-vision Pan-Tilt-Zoom (PTZ) pod is applied in the system to monitor and photograph the deployment site for dropping live munitions. For the software structure of the system, the ground station exploits the YOLOv5 algorithm to detect the grenade targets for real-time video and accurately locate the landing point of the grenade. The operator remotely controls the UAV to grasp, transfer, and destroy grenades. Experiments on explosives defusal are performed, and the results show that our system is feasible with high recognition accuracy and strong maneuverability. Compared with the traditional mode of explosives defusal, the system can provide decision-makers with accurate information on the location of the grenade and at the same time better mitigate the potential casualties in the explosive demolition process.

A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network

This paper proposed an improved U-Net fully convolutional neural network to automatically extract a single landslide deformation information under time series based on the physical model experiments. This method extracts time series information for three different landslide deformation ranges. Compared to U-Net and mainstream superpixel method, evaluation indicators of DSC, VOE and RVD verify the high recognition accuracy and strong robustness of our method.

An Adaptive Operational Modal Analysis Method Using Encoder LSTM with Random Decrement Technique

A new parameter identification method under non-white noise excitation using transformer encoder and long short-term memory networks (LSTMs) is proposed in the paper. In this work, the random decrement technique (RDT) processing of the data is equivalent to eliminating the noise of the raw data. In general, the addition of the gate in LSTM allows the network to selectively store data, which avoids gradient disappearance and gradient explosion to a certain extent. It is worthwhile mentioning that the encoder can learn the essence of data, which reduces the burden for the LSTM. More specifically, establish as simple LSTM structure as possible to learn the data of this essence to achieve the best training effect. Finally, the proposed method is used for simulation and experimental verification, and the results show that the method has the advantages of high recognition accuracy, strong anti-noise ability, and fast convergence rate. Specially, the results indicated appropriate accuracy proposed by deep learning combined with traditional method for parameter identification as well as proper performance of the proposed method.

Tailings Settlement Velocity Identification Based on Unsupervised Learning

In order to reasonably and accurately acquire the settlement interface and velocity of tailings, an identification model of tailing settlement velocity, based on gray images of the settlement process and unsupervised learning, is constructed. Unsupervised learning is used to classify stabilized tailing mortar, and the gray value range of overflow water is determined. Through the identification of overflow water in the settlement process, the interface can be determined, and the settlement velocity of tailings can be calculated. Taking the tailings from a copper mine as an example, the identification of tailings settling velocity was determined. The results show that the identification model of tailing settlement speed based on unsupervised learning can identify the settlement interface, which cannot be manually determined in the initial stage of settlement, effectively avoiding the subjectivity and randomness of manual identification, and provide a more scientific and accurate judgment. For interfaces that can be manually recognized, the model has high recognition accuracy, has a rapid and efficient recognition process, and the relative error can be controlled within 3%. It can be used as a new technology for measuring the settling velocity of tailings.

Research and Implementation of Fast-LPRNet Algorithm for License Plate Recognition

The license plate recognition is an important part of the intelligent traffic management system, and the application of deep learning to the license plate recognition system can effectively improve the speed and accuracy of recognition. Aiming at the problems of traditional license plate recognition algorithms such as the low accuracy, slow speed, and the recognition rate being easily affected by the environment, a Convolutional Neural Network- (CNN-) based license plate recognition algorithm-Fast-LPRNet is proposed. This algorithm uses the nonsegment recognition method, removes the fully connected layer, and reduces the number of parameters. The algorithm—which has strong generalization ability, scalability, and robustness—performs license plate recognition on the FPGA hardware. Increaseing the depth of network on the basis of the Fast-LPRNet structure, the dataset of Chinese City Parking Dataset (CCPD) can be recognized with an accuracy beyond 90%. The experimental results show that the license plate recognition algorithm has high recognition accuracy, strong generalization ability, and good robustness.

ZnO nanowire optoelectronic synapse for neuromorphic computing

Artificial synapses that integrate functions of sensing, memory and computing are highly desired for developing brain-inspired neuromorphic hardware. In this work, an optoelectronic synapse based on the ZnO nanowire (NW) transistor is achieved, which can be used to emulate both the short-term and long-term synaptic plasticity. Synaptic potentiation is present when the device is stimulated by light pulses, arising from the light-induced O2 desorption and the persistent photoconductivity behavior of the ZnO NW. On the other hand, synaptic depression occurs when the device is stimulated by electrical pulses in dark, which is realized by introducing a charge trapping layer in the gate dielectric to trap carriers. Simulation of a neural network utilizing the ZnO NW synapses is carried out, demonstrating a high recognition accuracy over 90% after only 20 training epochs for recognizing the Modified National Institute of Standards and Technology (MNIST) digits. The present nanoscale optoelectronic synapse has great potential in the development of neuromorphic visual systems.

Research on CNN-based intelligent recognition method for negative images of weld defects

The existing technology of automatic classification and recognition of welding negative images by computer is difficult to achieve a multiple classification defect recognition while maintaining a high recognition accuracy, and the developed automatic recognition model of negative image defect cannot meet the actual needs of the field. Therefore, the convolutional neural network (CNN)-based intelligent recognition algorithm for negative image of weld defects is proposed, and a B/S (Browser/Server) architecture of weld defect feature image database combined with CNN is established subsequently, which converted from the existing CNN by the migration learning method. It makes full use of the negative big data and simplifies the algorithm development process, so that the recognition algorithm has a better generalization ability and the training algorithm accuracy of 97.18% achieved after training. The results of the comparison experiments with traditional recognition algorithms show that the CNN-based intelligent recognition algorithm for defective weld negatives has an accuracy of 92.31% for dichotomous defects, which is significantly better than the traditional recognition algorithm, the established recognition algorithm effectively improving the recognition accuracy and achieving multi-category defect recognition. At the same time, the CNN-based defect recognition method was established by combining the image segmentation algorithm and the defect intelligent recognition algorithm, which was applied to the actual negative images in the field with good results, further verifying the feasibility of CNN-based intelligent recognition algorithm in the field of defect recognition of welding negative images.

Research on Automated Information System of Non-sense Attendance Using Face Recognition and Large Database

In order to meet the needs of today’s large-scale enterprise human resource management attendance business, this paper designs an embedded face recognition attendance system, and designs and analyses the implementation method of the system in detail. The system consists of two parts: face-swiping attendance and attendance management. Among them, face-swiping time attendance uses the Face Boxes model to detect faces, and the Face Net model to identify the person who punches in. Tests have found that the system is simple to operate, has high recognition accuracy, and has a certain practical value.