AUTOMATIC CONTROL AND COMPUTER SCIENCES最新文献

This paper presents a new method of localizing radio frequency (RF) source in non-line of sight (NLOS) using data collected using the anchor and map. The measurable observation in the unmanned aerial vehicle (UAV) is assumed to be the received signal strength indicator (RSSI), and a method is presented based on the RSSI observation of the reflected signal sent from the anchor to estimate the location of the reflecting obstacle, which is a two-step method for map estimation and localization. It is also assumed that the map of the obstacle location is also available; the location of the reflective obstacle can be obtained using the map with an error. And finally, by combining this data in a weighted and improved particle filter for the optimal use of the number of particles in a wide area, the location of the unknown RF source is estimated more accurately. It was revealed that the proposed method improved localization and had good precision.

In this study, the Tamarix chinensis forest in Changyi national marine ecological special protected area in Shandong province, China, was researched for forest fire monitoring based on thermal infrared remote sensing technology. We summarized the commonly monitoring methods for forest fire point based on remote sensing technology into two types: fixed threshold method (including its deformation model and extension model) and adjacent pixel analysis method (also known as background pixel correlation method). And we analyzed the advantages and disadvantages of these two methods. The BT (brightness temperature) data inverted from the remote sensing images of IRS sensor (HJ 1B satellite) and TIRS sensor (Landsat-8 satellite) indicated that there not had enough thermal radiation to form a fire point during the above phases in the protected zone. The research results and methods also confirmed that thermal infrared remote sensing technology can be used for forest fire monitoring and identification of macro forest fire point.

In this paper, on the basis of in-depth research on the key technology of binocular vision measurement; a set of multidimension online measurement system for image recognition is built. Canny operator is used as a tool to detect the contour features of parts, and the Canny operator is accelerated and improved from the aspects of mathematical reasoning and Gaussian pyramid. A synchronous external trigger circuit for a binocular camera and light source was designed. Finally, the improved algorithms in various aspects of visual measurement in this paper are applied to the measurement system. The experimental results show that the online measurement system has the advantages of high measurement accuracy and small repeatability errors.

Facial features extracted from deep convolutional networks are susceptible to background, individual identity and other factors. It interferes with facial expression recognition when mixed with useless features. Considering that different scale features have rich semantic and texture information respectively, this paper takes VGG-16 as the basic network structure and combines multiscale features to obtain richer feature information. In addition, the input feature map elements are enhanced or suppressed by the attention module in order to extract salient features more accurately. The proposed method was validated on two commonly used expression data sets CK+ and RAF-DB, and the recognition rates were 98.77 and 82.83%, respectively. Experimental results show the superiority of this method.

This paper deals with the problem of creating a keyword spotting (KWS) system with real-world audio data. The paper describes the different methods used to build KWS systems, deep learning models such as convolutional neural networks (CNN), transformers, etc. The paper also discusses the mainstream dataset for training and testing KWS models, Google Speech Commands. We conduct experiments on Google Speech Commands dataset and propose our method of creating a KWS dataset and that helps neural networks achieve better results in training on relatively small amounts of data. We also introduce an idea of a hybrid KWS inference system architecture that uses voice detection and light-weight speech recognition framework in attempt to boost its computational performance and accuracy. We conclude by noting that KWS is an important challenge in the field of speech recognition, and suggest that their method can be used to improve the performance of KWS systems in the circumstances of low amounts of training data. We also note that future research could focus on bettering the process of evaluating the models and improving the overall performance of KWS systems.

In recent years, the proliferating of IoT (Internet of things)-originated applications have generated huge amounts of data, which has put enormous pressure on infrastructures such as the network cloud. In this regard, scholars have proposed an architectural model for “cloud-fog” computing, where one of the obstacles to fog computing is how to allocate computing resources to minimize network resources. A heuristic-based TDCC (Time, distance, cost and computing-power) algorithm is proposed to optimize the task scheduling problem in this heterogeneous system for genetic algorithm-based “cloud-fog” computing, including execution time, operational cost, distance and total computing power resources. The algorithm uses evolutionary genetic algorithms as a research tool to combine the advantages of cloud computing, fog computing and genetic algorithms to achieve a balance between latency, cost, link length and computing power. In the hybrid computing task scheduling, this algorithm has a better balance than TCaS algorithm which only considers a single metric; this algorithm has a better adaptation value than traditional MPSO algorithm by 2.61%, BLA algorithm by 6.92% and RR algorithm by 33.39%, respectively. The algorithm is also flexible enough to match the user’s needs for high performance distance-cost-computing power, enhancing the effectiveness of the system.

With the continuous development of computer vision, the application of image recognition technology is becoming increasingly widespread. An edge detection image recognition model based on improved artificial bee colony algorithm has been proposed. Firstly, the identification process of artificial bee colonies is designed. To solve the algorithm easily falling into local optima, a GA with a global search strategy is further improved, achieving an improvement in model operation speed and coherence. Moreover, the target detection and localization methods are selected. The Canny operator and line fitting method are ultimately determined for image search and localization. To further verify the reliability of the improved artificial bee colony algorithm, simulation experiments are conducted on the MATLAB platform. The experimental results show that under 0.1 noise, the improved artificial bee colony algorithm has better recognition accuracy, compared to the particle swarm algorithm. The calculation time is reduced by 7.35s. In summary, the improved artificial bee colony algorithm has the best recognition accuracy and noise resistance performance.

Design of interleavers with a compromise between reliability and complexity of implementation is a challenging code design problem. This paper deals with the design of chaotic interleavers for secure turbo codes using a novel generalized 2D chaotic map. Compared with random interleavers, the proposed interleavers improve the performances while reducing the complexity of implementation. Furtheremore, parameters of chaotic maps can be used to jump from a map to the other which improve the security against decoding attacks. The proposed interleavers enhance the reliability and physical layer security.

In contemporary society, individuals have elevated expectations for visual communication. Low-resolution images can negatively impact image quality and viewing experience. As a result, enhancing the visual communication of multiframe, low-resolution image sequences has become a primary focus of current research. This study optimized the visual communication effect of multiframe, low-resolution photo sequences using deep photo superresolution reconstruction technology based on low-resolution, color-guided photos. Meanwhile, the visual communication effect of multiframe low-resolution image sequences has also been improved. The experimental results indicated that from the perspective of infrared spectroscopy, multiframe video photo visual communication resources could have a harvest probability of 99% and a tracking efficiency of 96%. The reconstruction results of deep photos from various sources indicated that sparse encoding-based superresolution resources are suitable for doll images. Among different color photo superresolution algorithms, gradient-based upsampling network and adaptive separable data-specific transformation resources can better recover guided photos. Optimization algorithms can effectively enhance the visual communication of multiframe low-resolution image sequences by removing noise and improving image details while maintaining the natural style of the image and enhancing clarity. The proposed image strength enhancement method can address the issue of poor visual communication performance in multiframe low-resolution image sequences. The resources for optimizing visual connection effects in multiframe, low-resolution photo sequences can solve the problem of multiframe and low-resolution simultaneously. This approach has greater potential for development compared to a single solution. Therefore, this application holds significant reference value.

In identifying crop leaf diseases, Due to the complex nature of the disease symptoms. There may be variations in disease symptoms with similar characteristics and similarities in disease symptoms with different elements. This can make it challenging to differentiate between various diseases. CSASNet is a hybrid classification model proposed in this paper that combines the attention and multiscale feature fusion mechanisms. The model first incorporates the multiscale feature fusion module atrous spatial pyramid pooling (ASPP) into the ShuffleNetV2 network structure. This enriches the network with disease-specific multiscale feature information. Additionally, the model combines the special group-wise enhance (SGE) attention mechanism module to enhance the weight of disease spot feature information. Lastly, the leaky ReLU function replaces the original ReLU activation function. This allows the model to reduce damaging feature loss during training. The paper presents a design of multiple cross-validation experiments for comparison. The experimental results suggest that the improved model was used for disease leaf identification and showed an accuracy improvement on different crops. Compared to Convnext and MobileNetV2, the CSASNet model demonstrates higher recognition accuracy.