<abstract xmlns="http://www.w3.org/1999/xhtml">

In order to solve the problem that irregular targets and dense targets are difficult to be detected in optical remote sensing images, this paper improved the YOLOV3 model Firstly, in order to further combine the feature information of different scales, the PaNet structure is introduced into the FPN part of the original YOLOv3, and the obtained effective feature layer is continued to be extracted for a round of feature. The feature is not only up-sampled to achieve feature fusion, but also down-sampled again to achieve enhanced feature fusion SimOTA method is introduced to dynamically match positive samples and set different positive sample numbers for different targets, which not only improves the speed of the algorithm, but also reduces the extra hyperparameters Experimental verification using richer DOIR data sets shows that the detection ability of the improved algorithm is significantly improved. Compared with the original YOLOv3, its mAP improves by 15.1 points, among which the detection accuracy of dense small targets is improved the most.
</abstract>

School of Computer Science and Engineering

Remote Sensing Image Object Detection Method Based On Improved YOLOv3

<abstract xmlns="http://www.w3.org/1999/xhtml">

Nowadays, we frequently use a lot of biometric identification technology means, such as: iris recognition, voice recognition and face recognition, but compared with other human biometric features, face information is easier to collect and more easily accepted by the public. According to the survey, in interpersonal contact, most people get information based on the first impression, even if there are changes in external conditions such as age, expression, makeup, etc., but the brain can still recognize these information, this phenomenon shows that face does have more feature information. From the information of a person's facial features, we can effectively distinguish each person. Face recognition is a technology that analyzes the face data and then uses it as an authentication mechanism. Generally, cameras are used to track and collect human faces, model theory and then analyze the collected binary data stream to extract relevant feature data. The research of human face recognition technology began in the middle of 1960s. After 1980s, due to the development of computer technology and the improvement of optical image processing technology, it gradually matured. The real use stage of face recognition is in the late 1990s, with Germany, Japan and the United States as the main technologies.
</abstract>

3D Face Feature Processing and Recognition Technology

<abstract xmlns="http://www.w3.org/1999/xhtml">

Traditional iris recognition has high recognition accuracy and low misrecognition rate. However, in the case of mobile terminal or distance, the image resolution and image quality decrease, and the recognition rate also decreases. To solve the above problems, this article is based on deep learning technology, on the basis of single mode state recognition, from different levels of multimodal integration, the iris and the eyes in the score level fusion recognition research, put forward the adaptive dynamic weighted score fusion method, to determine the weighing values can adaptive algorithm of the modal, without artificial specified, dynamic weighting algorithm more flexible, stronger applicability. Experimental results of casIA-Iris-LAMP and CasIA-Iris-Distance Iris database in Chinese Academy of Sciences show that the proposed fusion algorithm has higher recognition accuracy and better recognition performance than the single mode recognition algorithm and the traditional fractional fusion method, which proves the effectiveness of the algorithm.
</abstract>

Score Level Fusion for Iris and Periocular Biometrics Recogniton Based on Deep Learning

<abstract xmlns="http://www.w3.org/1999/xhtml">

With the continuous development and progress of the times, the ways of human-computer interaction have become more and more diverse. In order to reduce the spread of the new crown virus, gesture recognition has become a hot topic in the field of human-computer interaction in recent years. Traditional gesture recognition is affected by the environment and database, etc., with poor robustness and low accuracy. In order to improve the recognition rate of static gestures, this paper proposes to establish a deep learning model using CNN convolutional neural network, and a static gesture recognition method based on template matching. By establishing a palm template diagram, the gesture image to be recognized is matched with the template diagram based on the feature point, and the image is rotated after matching, and the template based on the grayscale value is matched again, so as to extract the gesture part. Through experimental proof, the algorithm can effectively improve the gesture recognition rate, the recognition accuracy rate reached 93.17%, and the recognition speed is faster.
</abstract>

Research on Static Gesture Recognition Based on Deep Learning

<abstract xmlns="http://www.w3.org/1999/xhtml">

For the traditional deep learning cannot solve the fog, coastal background interference, and the difficulty of small ships recognition, a multi-scale deep learning training model is proposed in this paper. Based on Faster R-CNN, this paper uses guided filtering to remove fog, as well as combined with negative sample enhancement learning to train the model, thus solving recognition of ship in complex sea conditions. And with multi-scale training strategy, the multi-scale ship samples are produced and sent to the network for training, so as to solve the problem of small target recognition. The experimental results show that compared with the Faster R-CNN, the precision and recall of our method increase by 6.43% and by 4.68% respectively. It solves the difficulty of ships recognition under complex sea conditions and small ship recognition that cannot be solved by traditional deep learning methods, the trained model has good generalization ability and robustness.
</abstract>

Fine-grained Recognition of Ships Under Complex Sea Conditions

<abstract xmlns="http://www.w3.org/1999/xhtml">

TOC, as a new type of computer, uses the state of light: it uses the non light state and two polarized light states with orthogonal polarization directions to represent information, and uses a rotator and polarizer to change the three light states, thus completing ternary logic operations. This new type of computer has the advantages of numerous processor bits, independent use of processor bits in groups, and reconfigurable computing functions of processor bits; After more than 20 years of development, we have achieved fruitful results. In this paper, the research progress of ternary optical computer is comprehensively and thoroughly analyzed and summarized, from the concept of TOC theory to the kilobit processor being studied so far. Firstly, the theory of ternary optical computer is summarized. Secondly, according to the core theory of ternary optical computer and the achievements that have been made, ternary optical computer has also made some progress in software and data calculation, such as operation result file generation software, addition routine, multiplication routine, etc. Finally, the future research directions of ternary optical computer are analyzed and prospected. Firstly, the structure of ternary optical computer is introduced, and the existing research results are summarized. Finally, the future research directions of ternary optical computer are analyzed and prospected.
</abstract>

A Survey of Ternary Optical Computer Research

<abstract xmlns="http://www.w3.org/1999/xhtml">

This study presents a novel control strategy of discrete variable frequency (DVF) based on space voltage vectors for a three-phase induction motor (IM) soft-starting. The proposed strategy is developed in four steps. First, conducting states of the three-phase thyristor circuits are analysed, and the formation mechanism of space voltage vectors is also demonstrated. Then, DVF control strategy of IM based on hexagon flux linkage loci is expounded categorically, which contains frequency f/7 control, frequency f/4 control, frequency f/3 control and ramp voltage control. Next, under two-phase stationary coordinate system, stator flux equation of IM is derived, and the decrease in stator flux when zero-vector voltage working is calculated accurately. In the end, an experimental system of IM based on three-phase thyristor circuits is constructed, and the experimental results are dealt with and compared with the usual ramp voltage technique. The study results show that IM driven by the proposed strategy can steadily operate at the preset discrete frequency, and the effective value of starting current of IM can be decreased by nineteen percent. The experimental results verify the conclusions.
</abstract>

School of Electrical and Control Engineering

Shaanxi University of Science and Technology

One Novel Soft-Starting Control Strategy for Induction Motor Based on Space Voltage Vectors

<abstract xmlns="http://www.w3.org/1999/xhtml">

Using each part of the image's spatial information to generate better local details of the image is a key problem that super-resolution reconstruction has been facing. At present, mainstream super-resolution reconstruction networks are all built based on convolutional neural networks (CNN). Some of these methods based on Generative Adversarial Networks (GAN) have good performance in high-frequency details and visual effects. However, because CNN lacks the necessary attention to local spatial information, the reconstruction method is prone to problems such as excessive image brightness and unnatural pixel regions in the image. Therefore, using the capsule network's excellent perception of hierarchical spatial information and local feature relationships, the author proposes a super-resolution reconstruction based on capsule network CSRGAN. The experiment's final result shows that compared with the pure convolution method RDN, the PSNR value of CSRGAN is increased by 0.14, which is closer to the original image.
</abstract>

Super-resolution Reconstruction Based on Capsule Generative Adversarial Network

<abstract xmlns="http://www.w3.org/1999/xhtml">

By learning nonlinear mapping functions from low resolution (LR) images to high resolution (HR) images, deep neural networks show good performance in image super-resolution (SR). However, the existing SR approach has two potential limitations. First, learning the mapping function from LR to HR images is usually an ill-conditioned problem, since there exist an infinite number of HR images that can be down-sampled to the same LR image. Thus, the space of possible functions can be very large, making it difficult to find a good solution. Second, paired LR-HR data may not be available in real-world applications, and the underlying degradation method is often unknown. For this more general case, existing SR models tend to generate adaptive problems and produce poor performance. To solve the above problem, we propose a dual regression scheme that reduces the space of possible functions by introducing additional constraints on LR data.
</abstract>

Super-resolution Image Reconstruction Based on Double Regression Network Model

<abstract xmlns="http://www.w3.org/1999/xhtml">

The line of sight reflects the focus of human attention. Gaze estimation technology has a wide range of application prospects in human-computer interaction, human emotion analysis, commercial advertising, and so on. Gaze estimation needs to be jointly determined by eye movement and head movement because the human gaze is often with the head movement. In this paper, a gaze estimation system with head movement is implemented by a monocular camera, using eye movement features and head movement posture changes to estimate the gaze point. A camera is used as the information acquisition device to extract the eye movement feature information, and the offset of head movement is estimated at the same time. The final fixation point position coordinates are obtained by compensating the fixation point position in the case of head movement, and then the fixation point position coordinates are estimated. For the compensated gaze drop point, the average pixel error on the X-axis is estimated to be 118 pixels, and the average pixel error on the Y-axis is estimated to be 136 pixels.
</abstract>

Research on Gaze Estimation Method Combined with Head Motion Changes

AHEAD OF PRINT

Volume 9 (2024): Issue 1 (January 2024)

Volume 8 (2023): Issue 4 (December 2023)

Volume 8 (2023): Issue 3 (September 2023)

Volume 8 (2023): Issue 2 (June 2023)

Volume 8 (2023): Issue 1 (January 2023)

Volume 7 (2022): Issue 4 (January 2022)

Volume 7 (2022): Issue 3 (January 2022)

Volume 7 (2022): Issue 2 (January 2022)

Volume 7 (2022): Issue 1 (January 2022)

Volume 6 (2021): Issue 4 (January 2021)

Volume 6 (2021): Issue 3 (January 2021)

Volume 6 (2021): Issue 2 (January 2021)

Volume 6 (2021): Issue 1 (January 2021)

Volume 5 (2020): Issue 4 (January 2020)

Volume 5 (2020): Issue 3 (January 2020)

Volume 5 (2022): Issue 2 (January 2022)

Volume 5 (2020): Issue 1 (January 2020)

Volume 4 (2019): Issue 4 (January 2019)

Volume 4 (2019): Issue 3 (January 2019)

Volume 4 (2019): Issue 2 (January 2019)

Volume 4 (2019): Issue 1 (January 2019)

Volume 3 (2018): Issue 4 (January 2018)

Volume 3 (2018): Issue 3 (January 2018)

Volume 3 (2018): Issue 2 (January 2018)

Volume 3 (2018): Issue 1 (January 2018)

Volume 2 (2017): Issue 4 (January 2017)

Volume 2 (2017): Issue 3 (January 2017)

Volume 2 (2017): Issue 2 (January 2017)

Volume 2 (2017): Issue 1 (January 2017)

Volume 1 (2016): Issue 2 (January 2016)

Volume 1 (2016): Issue 1 (January 2016)

International Journal of Advanced Network, Monitoring and Controls

The International Journal of Advanced Network, Monitoring and Controls (ISSN:2470-8038）is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills, especially in the fields of advanced network, monitoring, sensors and controls. It is also the Journal's objective to promote engineering and technology education.  All papers submitted to the Journal will be blind peer-reviewed. Every paper is reviewed by two Professors and blind. All reviewers are independent of the editorial board. Only original articles will be published.  Open Access Policy  This journal provides immediate open access to its content under the Creative Commons CC BY-NC-ND 4.0 license on the principle that making research freely available to the public supports a greater global exchange of knowledge. Under the CC BY-NC-ND 4.0 license users are free to share the work (copy and redistribute the material in any medium or format), if the contribution is properly attributed and used for non-commercial purposes. The material published in the journal may not be altered or build upon.  Rejection rate: 50%  All submitted papers will be reviewed by more than two expert referees in their relevancy to the call for paper. After refereeing process, all accepted papers will be published and the full text is online available.   The acceptance process is as follows:   First of all, check the paper format and theme, and then entering the technical review process according to the quality standards.   The paper will be submitted to two reviewers for review according to the content of the paper; two blind reviewers will make comments and revisions to the paper, and then give an acceptance or rejection.   ABOUT SOCIETY  Xi'an Technological University has over 20,000 students and is authorized by Chinese government to award Ph.D. degrees. The State and Provincial Joint Engineering Laboratory of Advanced Network and Monitoring Control is located within the School of Computer Science and Engineering, Xi'an Technological University. The Lab.is mainly focused on researches in theoretical researches and practical applications of computing technologies, advanced networks, system simulations, artificial intelligence, automated monitoring and controls.  Archiving  Sciendo archives the contents of this journal in Portico - digital long-term preservation service of scholarly books, journals and collections.  Plagiarism Policy  The editorial board is participating in a growing community of Similarity Check System's users in order to ensure that the content published is original and trustworthy. Similarity Check is a medium that allows for comprehensive manuscripts screening, aimed to eliminate plagiarism and provide a high standard and quality peer-review process. 