Search

Water could also be variety one necessity of humans and each one residing beings. There is a number of water on the earth but it sincerely is not suitable for human use. Clean water is extra important and is used for a couple of purposes. The impurities observed in water can purpose dangerous diseases. Impurities in drainage water are often like empty bottles, polythene bags, papers etc. House drains empty themselves into the foremost drains which run beneath the foremost streets and beneath many lanes. Solid topics which is perhaps created thru human or animal activities, and which is perhaps disposed of due to the reality they’ll be dangerous or useless are mentioned as sturdy waste. Most of the sturdy wastes, like paper, plastic containers, bottles, cans, or even used motors and virtual gadgets aren’t biodegradable, this suggests that they’re not getting lessened through inorganic or herbal processes. Thus, after they collect they purpose a hazard to people. Decaying wastes moreover enchantment to have circle of relatives pests and convey about metropolis areas becoming unhealthy, dirty and unsightly places to be dwelling in. Moreover, it moreover motives damage to terrestrial organisms on the equal time as moreover reducing the uses of the land for specific extra useful purposes. Therefore, this problem goals immediately remedial measures. These impurities observed in drainage water can purpose blockage or the system.

A formal-semantic normative system (FSNS) is presented in this paper. The FSNS allows us to describe the links and functional units of typical information processes. The possibility of using the FSNS to automate graphical-analytical modelling and machine learning is shown. Properties of the FSNS are described. On its basis, a method is developed for specifying a formal alphabet of system connection nodes that has a specific subject content. The rules for manipulating the received alphabetic characters are also presented. The possibility and expediency of building a normative system with increased expressive capabilities is substantiated. This paper provides a brief description of the «Unit-Function-Object» system-object approach. Considered the possibility of using DL for the FSNS in an unambiguous, formalized form. An example of using the FSNS is presented.

To organize the network in an efficient way to minimize the risk of illegal node and to safeguard protected information, a security mechanism is required to secure communication. In addition, a security mechanism is also required to ensure that received information have not been tampered with. In this paper, a more efficient mechanism for Securing the Destination Sequenced Distance Vector Routing Protocol (SDSDV) is proposed. This paper comprehensively investigates the performance impacts by varying the number of maximum connections and mobility on securing the ad hoc network with Destination Sequenced Distance Vector Routing Protocol (DSDV) Routing Protocol. From simulation results, we explore the causes for performance degradation. Based on the investigation, we indicate that we have to impose restrictions on the maximum connections to acquire an expected performance. These results also reveal that the performance decreases with the increment of the mobility and maximum connections that is unequal to 60. If we want to obtain the optimal performance, the number of nodes in a network should be constrained to be 60 if the maximum connections are 60.

In This Paper Face Recognition has gain the more attention in the society of network multimedia for accessing information. Emerging Areas like network security, content indexing and extraction, and video compression benefits from face recognition technic because “people” are the center of attention in a lot of video footages. Face detection is advanced research area in the computer science vision. The research under this area is expanding in others areas like psychology. Localization of human face will be first and the initial stage as a study of face detection. In this paper the usage of Convolutional Neural Network (CNN) algorithm in detecting the criminal face and also the process of getting the location from image.

The subject of the paper is a vessel sensor network designed to collect data from wireless sensors for various purposes. The peculiarity of this network application is the presence of a large number of premises, wireless communication between which is complicated. One of the possible approaches to solving this problem is to use coordinators connected by a switch into a local network, and a large number of routers that provide data relaying along the chain. Studies of the proposed vessel wireless network in the OMNeT ++ simulation modeling environment using Castalia framework are carried out in the paper. The process of modeling both the network itself and its individual components, and various modes of their operation is shown. The interaction of network nodes through intermediate routers is considered. Estimation of losses during packet delivery along a chain of routers, the time spent on processing packets in routers and delays in packet delivery to the network coordinator from the sending node is based on the compiled model. It is concluded that with the increasing complexity of the network structure (growth in the number of routers), there is a proportional rise of the packets delivery delay over the wireless network to the vessel local network. However, all transmitted packets are delivered to the addressee.

Motion blur distortion is the most common type of image distortion in daily life. the research on motion-blurred image restoration technology has developed more mature. Classical algorithms such as Wiener filter and Kalman filter and various improved algorithms can achieve better results, but they take a long time and have great limitations in actual image restoration application scenarios. To solve this problem, this paper proposes an algorithm for fast restoration of image motion blur, an improved algorithm based on Randon transform to judge the image motion blur angle, and studies the algorithm for estimating the blur length under the condition that the blur angle is determined, and obtains two motion blur parameters of blurred image. Experimental results show that the fast image restoration method proposed in this paper has shorter time consumption, stronger anti-noise interference ability and better practicability.

The rapid development of deep learning has accelerated the progress of related technologies in the computer vision field and it has broad application prospects. Due to flower inter-class similarity and intra-class differences, flower image classification has essential research value. To achieve flower image classification, this paper proposes a deep learning method using the current powerful object detection algorithm YOLOv5 to achieve fine-grained image classification of flowers. Overlap and occluded objects often appear in the images of the flowers, so the DIoU_NMS algorithm is used to select the target box to enhance the detection of the blocked objects. The experimental dataset comes from the Kaggle platform, and experimental results show that the proposed model in this paper can effectively identify five types of flowers contained in the dataset, Precision reaching 0.942, Recall reaching 0.933, and mAP reaching 0.959. Compared with YOLOv3 and Faster-RCNN, this model has high recognition accuracy, real-time performance, and good robustness. The mAP of this model is 0.051 higher than the mAP of YOLOv3 and 0.102 higher than the mAP of Raster-RCNN.

In order to put an end to the product quality accidents caused by cutting tool breakage or severe wear in machining process, the paper explored an ELM model detection method based on voice recognition. In this paper, firstly it analysed the features of cutting sound signal in time-frequency domain, then discussed the extraction method of tool working state sensitive spectral energy statistical feature based on wavelet packet decomposition, and finally constructed an ELM fast detection model based on sound feature recognition. The experimental results demonstrated that the ELM detection model could achieve higher detection accuracy and faster response time. The simulation results show that the ELM model is effective and applicable in detecting tool wear with the help of sound recognition.

New technologies such as artificial intelligence have developed at a rapid pace in recent years and are increasingly being used in the process of managing news in bulk. The development of deep learning has facilitated unprecedented progress in the field of computing and has opened our eyes to the possibility of using AI for news text classification. In this paper, based on the system requirements analysis, we describe the process of functional modules arising from the requirements analysis, design the internal details of functional modules, including algorithms and detailed principles, and finally obtain a prototype of news text classification software, which results in the pre-design expectations. The research in this paper makes the system development work more concrete, while providing software users, software developers, and analysts and testers with a unified and comprehensive understanding of the system’s functional implementation.

Cloud computing not only provides convenience for users, but also brings certain information security threats to users. How to effectively protect the user's information security has become one of the core issues of network security. This paper analyzes the problems and reasons of network security in cloud computing environment, and points out the main ways to improve network security. This paper analyzes the network security problems in the cloud computing environment, and discusses the information security technology in the network. This paper studies the definition, characteristics, classification and core technology of cloud computing security, analyzes the security risk of cloud computing network, and puts forward the cloud computing network security model and security level evaluation method from different angles. Level experiment results show that the network security model in cloud environment is feasible, computing can fully meet the development requirements of the current network information age, and effectively standardize the network security operation environment. The results show that: in 2016, the number of articles related to cloud computing is at least 2653, and in 2020, the number of articles related to cloud computing is at most 6438.

Acoustics releaser plays an important role in the recovery of marine surveying system. This paper analyses and introduces present situation of the acoustics releaser in our country. Finally, main technology development direction and strategy of localization are put forward in the paper. The paper mainly includes research status quo outside and in China as well as key technical problems in design of underwater acoustic releasers.

This paper analyzes the electronic bill of lading technology of container shipping, and solves the key problems such as the loss of bill of lading during the circulation of paper bill of lading. Based on the optimization of the basic structure and core technology of electronic bill of lading, this study incorporates the blockchain technology, analyzes the fit between blockchain technology and electronic bill of lading, and constructs a new model of electronic bill of lading for container shipping based on blockchain technology, which improves the safety and stability of shipping transaction information and provides more effective solutions for the future practice of electronic bill of lading for container terminals.

When CPU enters the era of instruction level parallelism, the execution cycle of instructions has become shorter and shorter. Meanwhile, the processing speed of CPU has become faster and faster. However, only from the execution process of CPU instructions, there is a key factor that limits the speed of CPU processing instructions, namely, the branch instruction processing. The branch predictor is used to predict the execution result of the current branch instruction (taken/non-taken), which can make the program counter get the target instruction to continue to execute according to the prediction result before calculating the target jump address. If the prediction is correct, it will greatly improve the execution efficiency of CPU. This paper starts from the two basic categories of static branch prediction and dynamic branch prediction. Then analyse their prediction principle, prediction accuracy and component consumption used for prediction. For static branch predictor, its hardware consumption is less than that of dynamic branch predictor, and its accuracy is also lower than that of dynamic branch predictor. Moreover, their shortcomings are pointed out in this paper. At last, based on the original branch predictor, better branch predictors developed in recent years are introduced. In the future, considering the hardware consumption, I think the development of branch predictor will continue to optimize the branch predictor combining global history and local history, from the number of stored entries, the correlation between branch instructions and so on. On the premise of executing a large number of instructions, every little improvement in the efficiency of the predictor will bring huge benefits.

The self weight of steel box girder is light, and the stability effect is smaller than that of concrete bridge. In this paper, the anti overturning research of the main line bridge and ramp bridge is carried out. It is found that for the variable cross-section continuous beam bridge with wind barrier along the whole line, when the pressure reserve of the side pier is small under the action of self weight, the compression of the bearing under the action of basic combination can not ensure that the bearing will not be empty under the action of standard value combination; Centrifugal force, wind load and temperature load caused by vehicle load have great influence on bridge overturning, which can not be ignored; Temperature load and foundation displacement may lead to stability or instability according to the stiffness distribution of the main beam. In this paper, it is proposed that both the basic combination and the standard value combination should be considered when checking the bearing void. It is recommended to adopt the calculation method of “the stability effect is the standard value effect that makes the superstructure stable, and the instability effect is the standard value effect that makes the superstructure unstable” as the stability coefficient.

Current discussions of art documentation and examination focus on improving the artifact documentation and examination process, constructing databases, applying new technology, and conducting technical training of staff. For curators, museum collections, private collectors, artifact surveyors, and art gallery workers, documentation and examination are a critical stage in the process of archiving, exhibiting, conserving, and repairing artwork. Workers understand the function of documentation and examination, but not all workers understand these processes’ value and purpose. Apart from revealing the current condition of artifacts, what is the real value and purpose of artifact documentation and the examination process? This research considers the international and domestic projects completed by the conservation center of Cheng Shiu university and explores problems arising in the documentation and examination process for curation, art exhibitions, and collaboration with other museums, along with resolutions provided by the process. This research also examines the key roles played by the documentation and examination process in those cases. This paper emphasizes the importance of the documentation and examination process; moreover, this paper’s study of real cases demonstrates the practical applications of the documentation and examination process.

Traditional action recognition algorithms often only pay attention to video RGB features or optical flow features. These methods do not make good use of the audio information in the video. Based on RGB and optical flow characteristics, this paper introduces the processing of audio information, and classifies videos based on element-level fine-grained multi-modal fusion. Through experimental comparison, the accuracy of the multi-modal fusion algorithm proposed in this paper is improved by 7.38% on the HMDB51 dataset and 3.18% on the UCF101 dataset compared to the simple modal splicing. At the same time, it is proved that the introduction of audio modes can effectively improve the performance of the model.

Semantic segmentation of parking lot scenes is the prerequisite of environment perception for automatic parking technology. It provides environmental semantic information for automatic parking of vehicles. However, due to the dim light of the parking lot environment, unclear ground signs, road reflections and other factors, semantic segmentation such as FCN The method is not yet able to segment ground signs such as background and lane lines to meet the perception needs of automatic parking. This paper proposes a parking lot scene semantic segmentation method based on a surround view system. The surround view system consists of 4 fisheye cameras. The images acquired by each camera are subjected to distortion correction, inverse perspective transformation and image stitching fusion to obtain a ring view. Based on the ring view, a semantic segmentation algorithm based on attention and feature fusion is proposed. Experiments are carried out on a self-made parking lot dataset with a size of 1280x960 pixels. The results show that the method proposed in this paper improves the mIoU of the FCN model by 12.3%.

this paper includes a study related to the concept of proximity congested sets and proximity not congested sets in i-topological proximity spaces which were defined using two concepts are the i-closure concept and nested set and then utilized it in studying a new type of concept namely cpc-congested set, cp-congested set, pc-congested set. Some of the characteristics and theories of these new sets were presented in this paper.

Traffic data encryption has been a trend in most Internet applications, and traditional protocol filtering based on fixed port and traffic classification based on Deep Packet Inspection are unable to Identify encrypted traffic. Recently, the traffic classification method based on the statistical characteristics of network traffic, which can solve the problem of encrypting data or user privacy protection, has been widely discussed. However, the traditional supervised learning method requires manual marking of a large amount of network traffic data, which is tedious and time-consuming. In this paper, a improved semi-supervised traffic classification framework based on BIRCH clustering method is proposed, and through experiments, the proposed algorithm, supervised learning algorithm and classical semi-supervised traffic classification algorithm are analyzed and compared. The results show that the algorithm proposed in this paper has higher overall accuracy and classification accuracy, and the algorithm can increase the accuracy on traffic classification.

With the rapid development of computer network technology, network applications have been very popular in people’s lives and work. The computer network technology includes many aspects, mainly including the communication technology and the computer technology. Although the network application has been relatively impeccable now, although people can contact anyone anywhere at any time through the network, it is still not perfect enough, and there are still great bottlenecks in the network technology. The network protocol plays an important role in the network technology. At present, the IPv4 protocol is more widely used in the Internet than others. Although the IPv6 protocol also has some applications, it is used less widely. For this reason, it is very necessary to research the application of the IPv6 network protocol. This paper mainly studies the main technical performance of the IPv6 network protocol, and introduces its application with specific examples. This paper analyzes the tunnel technology, network address translator technology and dual-stack technology of IPv6. And this paper introduces the basic configuration of the IPv6 address and of the static routing according to a specific type of router.

In order to improve the accuracy of the super-resolution network and reduce the number of model parameters, this paper improves its RCAB module on the basis of RCAN, and builds a reconstruction network RSAN that can improve the quality and efficiency of image super-resolution reconstruction. By replacing the original channel attention module with a more efficient and lightweight shuffle attention, it is mainly used to reduce the number of parameters, supplemented by improving the accuracy; and replacing part of the ordinary convolution in RCAN with split convolution is mainly used to improve accuracy, supplemented by reducing feature redundancy and parameters. The experimental results show that RSAN in this paper can not only obtain better subjective visual evaluation and objective quantitative evaluation, but also reduce the number of network model parameters and improve the efficiency of the network to a certain extent.

An important structural material in civil engineering construction is concrete. Concrete is widely used in various building structures. Concrete construction technology directly determines the construction quality of the concrete structure itself, which plays a very important role in the stability of the building structure. This paper mainly summarizes the current construction situation of concrete, and deeply analyzes some problems and technical points in the construction process, which is of great significance to improving the construction quality of concrete and optimizing the construction management of concrete. On this basis, this paper expounds the maintenance ideas of concrete pouring from the aspects of concrete mold removal, later repair and concrete maintenance operation, so as to provide a reference for the technical improvement of concrete construction.

Aiming at the congestion control problem of SDN, this paper designs a network congestion control scheme based on Q-learning algorithm of reinforcement Learning. According to the usage of link bandwidth in the network, the algorithm adjusts the transmission rate of the source data stream continuously, and finally obtains the optimal data stream allocation scheme. Experimental simulation evaluates the performance of the algorithm, the proposed control algorithm based on reinforcement learning congestion, can effectively improve the link utilization, reduce network congestion. The experimental results show that the congestion control algorithm proposed in this paper can allocate the optimal rate for each data stream, reduce network congestion, and has better performance than the traditional SDN algorithm.

Handwritten digit recognition refers to the recognition of handwritten digits written and printed on paper, and the recognition results are stored in the computing machine in the form of text. According to the characteristics of a handwritten digital image, based on the multi-layer perceptron method, this paper introduces the source and principle of handwritten digital image recognition in detail, and analyzes the steps, related functions and theories of handwritten digital image recognition in sequence. The proposed algorithm was validated on the handwritten dataset MNIST, and the model was evaluated and adjusted. Eventually, the trained model was migrated to Android.

New Coronavirus pneumonia is eroding the world, and digital libraries are even more important. How to control the network security of digital library system? According to the requirements of equal protection 2.0, this paper analyzes the security requirements of digital library network, and puts forward the security protection technology of digital library system under equal protection 2.0 system from the four perspectives of secure communication network, secure area boundary, secure computing environment and security management center. Based on the security protection technology framework of equal protection 2.0, this paper studies the security evaluation method of digital library, and puts forward the security protection technology solution.

All the small disturbance equation (SDE) methods, which are a useful technique to enhance the stability and security of the aircraft, play a significant role in the development of the aviation area. This review paper briefly introduces the development of the SDE and summarizes the two calculation methods combining with the SDE and application of the SDE method in the aviation area. The calculation methods mainly focus on the approximate factorization (AF) algorithm with the SDE and Newton-Orthomin method with the SDE. AF algorithm with the SDE is robust enough, and it can choose the calculation methods according to accuracy rather than stability that significantly saves the calculation cost. The newton-Orthomin method with the SDE can improve computing efficiency by 2.1 to 4.5 times compared with the monotone AF method. The direction of application focus on the flutter analysis, gust analysis and resizing of some component in the aircraft and the disadvantages are explored for each type. In conclusion, the combination of the SDE with the other algorithms can increase calculation efficiency, and the SDE has a wide range of applications in the aviation area. This paper can provide relevant references for the subsequent combination of the SDE and other algorithms development or practical application of SDE.

In the massive mechanical fault data, the value density of fault information is low, and the data quality is uneven. What’s more, the multi-source signals collected by different sampling methods are different. At present, the expert system or shallow neural network model with weak self-learning ability cannot meet the requirements. Therefore, aiming at the characteristics of coupling, uncertainty and concurrency of mechanical faults, this paper constructs two kinds of 2D-CNN fault feature data sets, and uses Convolutional Neural Network (CNN) with strong self-learning ability to build two kinds of fault diagnosis models: CNN-Z and CNN-F. With CNN-Z and CNN-F models as base learners, this paper utilizes the ensemble algorithm Gradient Boosting Decision Tree (GBDT) to combine multiple bases. Compared with the results of the single base learner, the outcomes have higher accuracy and lower generalization error. Through the analysis and comparison of the performance indicators of the algorithm, this paper concludes that the diagnosis error of the fault diagnosis algorithm based on CNN and GBDT is the lowest with 1.79%, and the effectiveness, reliability and accuracy of the proposed algorithm in mining hidden fault state information are verified.

Nowadays, investigators of phrases and text sentimental orientation identification mainly divided into two ways: semantic comprehension and machine learning. Machine learning needs a lot of training corpus and also cannot handle general field words effectively, meanwhile, semantic comprehension cannot get high scores at precision and recall. Therefore, in this paper, we propose a new fusion method based on our semantic comprehension for judging phrases’ polarity. In this paper, firstly, we modify the knowledge of Hownet, on the basis of its four primitives, the fifth primitive—sentimental primitive was proposed by our research, and annotated it into Hownet manually; secondly, we propose a new phrase sentimental similarity calculation method to compute word’s sentimental value; at last, we integrate transductive learning into this method to identify phrases’ sentimental orientation. The performance of experiment show that, compared with SVM or traditional semantic comprehension, it can get better results.

In the safety monitoring of bridge stress structure, the influence of surrounding environment and noise interference will cause the change of monitoring node coverage and affect the monitoring accuracy. Based on wireless sensor technology, a safety monitoring method of vehicle bridge stress structure is proposed. The interpolation fitting method is used to calculate the stress value of the sensor, and the optimal layout of the sensor is determined with the minimum deflection transfer error as the objective function. Probability sensing model is used to establish wireless overlay network, and wireless sensing technology is used to collect monitoring data. Based on the monitoring data, the static and dynamic response equation is established to establish the finite element model of bridge stress structure. The first level early warning threshold is determined according to the monitoring data under the normal operation state of the bridge, and the second level early warning threshold is determined according to the most unfavorable load distribution of the finite element model, so as to complete the bridge safety monitoring. The experimental results show that the average deformation deviation of the monitoring method proposed in this paper is 0.26mm, which is 0.77mm and 1.22mm smaller than the monitoring methods based on machine vision and GPS differential positioning technology, indicating that the monitoring method in this paper is more accurate and meets the safety requirements of bridge engineering.

Aiming at covering the shortage of single source sensor imaging and improving the contrast between the target and the background in image, this paper proposes an adaptive weight fusion algorithm of infrared and visible image based on a High-frequency Domain Convolutional Neural Network (HDCNN). Firstly, the high and low frequency components of the original image are obtained by using the Daubechies wavelet transform, and then a high-frequency domain convolutional neural network which can detect the frequency information ratio of infrared and visible light in the high-frequency subband is trained. Secondly, the network is used to perform adaptive weight fusion for the high frequency components and regional energy is used for fusion of the low frequency components. Finally, the fusion image is obtained by inverse wavelet transform. A large number of experiments have proved that the algorithm in this paper has a greater improvement over similar comparison algorithms in objective evaluation metrics such as standard deviation, spatial frequency and average gradient. The algorithm enhances the contrast between the target and the background in the fusion image, and enriches the characteristic information of the target itself.

In the fingertip intelligent blood collection robot, we need to move the blood collection needle to the designated position quickly and accurately, but it is difficult to meet the two indicators of speed and accuracy at the same time. This paper proposes a fast navigation method based on binocular vision. This method obtains the coordinates of the fingertip blood sampling point through three-dimensional reconstruction and contour extraction, and guides the robotic arm to quickly move the blood sampling needle to a position near the blood sampling point according to the coordinate position. The method in this paper is used for the rough navigation of blood collection robots, and it is verified by experiments that this method can meet the needs of blood collection robots.

According to the relevant provisions of the "Election Law of the People's Republic of China", the engineering software required for the implementation of large-scale conference elections can set voting regulations for "differential elections", "equal elections", and "alternative elections". This paper proposes an automatic ballot recognition system based on image processing, which is suitable for all levels of people’s congresses, party and government meetings or other meetings. It has complete functions and stable recognition. It can automatically count and summarize the voting results and display the voting results on the big screen. Show on the display system. Firstly, the paper ballot is scanned by a scanner to obtain the image of the ballot. Secondly, the system will preprocess the image of the ballot and segment the image into regions.Thirdly, according to the handwritten character recognition algorithm based on image processing and Shen filter proposed in this paper, the handwritten characters "√" and "×" in the subregion are recognized.The final experimental results show that the recognition accuracy of the system is as high as 99.82%, which has an absolute advantage over the traditional manual voting, and can meet the performance requirements of high efficiency, accuracy, objectivity and security of large-scale conference election.

In this paper, the electric field intensity of the electrode structure of the thermally emitted electron gun of UTEM is simulated, and the relation between the electric field intensity distribution and the electrode plate is analyzed. Using the electronic optics software, the optical system of the electron gun is simulated, the performance parameters of the electron gun are obtained, and the advantages and disadvantages of the whole optical system are analyzed. The research results of this paper can provide a reference for the design and simulation of similar electron gun.

The LDA model is a total probability generation model for analyzing a large number of documents. It extends PLSA, another text analysis model. In this model, each document is treated as a topic hybrid model, and the topic’s proportional prior distribution is a Dirichlet distribution. The LDA model does not reflect complex dependencies between underlying topics. Based on LDA, this paper introduces a new topic generation model, DMA (Dirichlet Mixture Allocation), which models document collections more accurately than LDA when documents are obtained in multiple classes. In this paper, we build a probabilistic topic model of DMA, use the method of variational inference to approximate each parameter of the model, study the model, and finally solve the estimation of each parameter.

This paper constructs a deep learning method for detecting network traffic anomalies to enhance the secure transmission of data in networks due to the complex, diverse and numerous types of anomalous traffic in current networks. The method combines multiple convolutional auto-encoders (Multi-CAE) with a long short-term memory network. The convolutional auto-encoders are obtained by combining stacked auto-encoders with convolutional layers, which can not only reduce feature loss but also effectively extract the spatial structure of samples. The use of Multi-CAE greatly improves the feature extraction capability, and combined with the long short-term memory network to extract temporal features, the effective features extracted in this paper are more comprehensive and less losses compared to the models used in other researches. A comparison of the loss values in the training of CAE (Convolutional Auto-Encoders) and SAE (Stacked Auto-Encoders) in the experiments shows that the loss values of CAE are about one-tenth lower than those of SAE, and the method consisting of Multi-CAE and LSTM for the USTC- TFC2016 dataset was trained with accuracy values up to 99.98%, and the precision, recall and f1-score parameters were also above 99%, outperforming other studies.

Applying deep learning methods to achieve synthetic aperture radar (SAR) image ship target detection has become a current hot research topic. However, most of the existing detection networks are designed based on optical images, so when they are directly applied to SAR image target detection, there will be the following two problems: 1) There are big differences between SAR image and optical image in imaging mechanism, geometric characteristics and radiation characteristics, etc, which makes the detection network have more redundant imformation; 2) Real-time performance and accuracy are both very important in SAR image target detection task, and applying a network designed based on optical image cannot balance the performance of the two well. In response to the above problems, this paper proposes a lightweight network LSSNet specially designed for SAR image ship detection task. In earlier layers, we use depthwise separable convolution instead of conventional convolution to design dense block; in deeper layers, stacked dense blocks with shortcuts are used to enhance deep supervision, and finally achieve high-speed and high-accuracy detection. This paper uses SSDD dataset as baseline for expeiment and results show that LSSNet have higher accurracy and detecition speed. Its lightweight structure will also help transplant to hardware devices in the future.

The traditional swarm intelligence optimization K-means algorithm has some problems, such as poor global search ability and blind area selection of initial center points, which leads to the reduction of clustering availability. In order to avoid the above limitations, this paper proposed IABC k-means algorithm. Firstly, the employed bees stage in the traditional artificial bee colony ABC algorithm uses the current colony optimal solution information to guide its optimization search. Secondly, this paper wanted to solve the search ability of the employed bees and expand the information sharing range between various individuals, a random guidance mechanism is proposed in the onlookers bees stage. Finally, chaotic sequence is introduced in the scout bee stage to accelerate the convergence speed of the algorithm. IABC algorithm is proposed and applied to K-means clustering algorithm to improve the poor global search ability of K-means algorithm and the random selection of initial center points. Experiments show that the IABC and IABCK-means proposed in this paper effectively improves the clustering availability.

Targeting at the problem that the existing hybrid database solutions can not simultaneously realize the client’s verification and access function to the encrypted data in the public cloud database and the cross database query function in the heterogeneous database environment, this paper designs an access and integration middleware to realize the client’s verification and access function to the heterogeneous hybrid database in the public cloud and the cross database query function. Access and integration middleware is composed of verification access component and heterogeneous database data integration method. The verification and access component reconstructs the protocol interaction process based on MySQL protocol, and encrypts and decrypts the encrypted data in the public cloud database through the existing hybrid database scheme, so as to realize the client’s verification and access to the encrypted data in the cloud database. The heterogeneous database data integration method unifies the data from different types of databases, and then integrates them into the same database, and uses this database for query operation to realize cross database query. This paper first analyzes the hybrid database system model, then designs from the aspects of MySQL protocol analysis, verification access, data integration, and finally analyzes the access and integration middleware from the aspects of functionality and security.

Internet of Things (IoT) is the most considerable medium for all smart applications, in which it provides a huge support to agricultural industry in fine manner. In literature, there are lots of smart devices are available for monitoring the crops and agricultural field, but all are strucked under certain limitations such as power problem, cost expensiveness and so on. This paper is intended to design a new machine learning enabled Smart Internet of Things medium to support agricultural field in proper way. In this paper, a Intelligent Crop Monitoring Device (ICMD) is introduced to monitor the crops over the agricultural field in 24x7 manner. This kind of monitoring devices enhances the production and quality-of-service of the agriculture as well as related products. This paper associates an innovative technology to the Smart Device called Machine Learning, but instead of using the classical learning schemes, this approach introduced a new scheme called Modified Learning based Field Analysis Strategy (MLFAS). This approach is inspired from the classical machine learning scheme called Convolutional Neural Network (CNN), in which the proposed Smart Device called ICMD accumulates the real-time agricultural field details and pass it to the monitoring unit for manipulation. The manipulation end maintains the data into the server unit, in which the machine learning model called MLFAS acquires the received field data and process it based on the training samples. The training samples are nothing but data collected from the agriculture field, the collection of received data are maintained into the server end for processing, the proposed MLFAS model manipulates the data and created as a model for further testing. The newly arrived data from the field is considered as a testing data and cross-validate that data into the trained model. The data acquired from the agriculture fields are temperature, humidity and soil moisture level, in which these records are passed to the server unit by using IoT module associated with the ICMD. The data available into the server can easily be monitored by the farmer from anywhere at any time. The learning model predicts the status of the crop in the field by means of analyzing the input acquired from the real-time testing input and report that to the respective farmer for taking an appropriate action. For all this system is useful to the agricultural field and provides good support to farmers to monitor the crops over the agricultural field from the remote place even. By using this proposed scheme, the farmers can make accurate and efficient crop management decisions with the use of results obtained by using the Smart Device called ICMD.

For the purpose of faster and more accurate anomalous traffic detection with increasing classes of data traffic in the network, this paper proposes a new anomalous traffic detection method based on stacked auto-encoders and a long short-term memory network model. The method uses Multi-SAE to extract the effective features of sequential traffic, which is obtained by concatenating multiple stacked auto-encoders, and a long short-term memory network to extract the temporal structure of the effective features, with the Multi-SAE and the long short-term memory network in a back-and-forth tandem structure. To further improve the efficiency of the detection, redundant MAC addresses are also removed in the pre-processing. From the experimental results, this paper achieves effective detection of twenty types of data traffic with an accuracy rate of 98.25%, which is higher than that of the same category of research by nearly 2 percentage points, and the parameters of precision, recall and f1-score also reach over 96%, improving the detection results.

The Quasi-Newton method (QN) is widely used in solving large-scale optimization problems due to its high efficiency. However, this algorithm requires a large number of iterative calculations, which is more time-consuming to compute in software. The Davidon-Fletcher-Powell (DFP) algorithm has been implemented on field-programmable gate array (FPGA) in order to speed up the computation. The number of iterations in the online search part of the algorithm is excessive, which affects the speed of the calculation. In order to solve this problem, this paper proposes a hardware implementation of DFP algorithm using inexact linear search. The results show that the calculation speed of the DFP algorithm implemented in this paper on the software side and FPGA platform is increased by 7.59 times and 3.08 times, respectively. And resource consumption and accuracy have little effect on the results.

For distance education, the application of computer network and software technology is very important to open teaching and management. This paper mainly studies the application of blockchain technology in the field of Open University distance education. Blockchain technology, as a new type of decentralized trust structure technology, provides necessary support for distance open education in teaching resource utilization, teaching process control, teaching effect evaluation and teaching management, and provides an effective foundation for teachers and students to participate in distance teaching practice together. This paper adopts a hierarchical network architecture and hierarchical storage structure, which has good scalability and node transparency, provides support for user service strategy in large-scale applications.

In this paper, based on the research focus of the current logistics field, a deep learning based express single-side bar code extraction algorithm is designed. This algorithm can recognize the original image and read out the information of the package. The algorithm is divided into two parts: bar code localization algorithm and bar code recognition algorithm. To avoid high delay, we use the YOLOV5S network to complete the barcode localization algorithm. First, the YOLOV5S algorithm is used to frame out the barcode, and the bounding Box is cut off. Then, OpenCV's method is used to obtain the deflection Angle of the image. Finally, affine transformation is used to correct the images with deflection. The bar code recognition algorithm is to use ZBAR algorithm to decode the bar code and output the decoded content in the form of string, and finally realize the location and recognition of the bar code on the single side of the express. Finally, through the test of the data set, it can be seen from the experimental results that this paper has accomplished the goal well.

With the continuous innovation of artificial intelligence technology, the teaching level of mechanical education courses in colleges and universities is also constantly improving. In the context of the era of big data, the teaching of mechanical education courses in colleges and universities has become more intelligent and informatized. This article mainly introduces BP neural network method and hill climbing algorithm. This paper uses BP neural network method to analyze the application of artificial intelligence technology in the teaching of mechanical education courses in colleges and universities, and establishes a potential mathematical model of BP neural network method. The model is solved by BP neural network method, and the current situation analysis and application status of the teaching mode of mechanical education courses in colleges and universities are analyzed, and the model is revised using historical data to improve the application research of artificial intelligence technology in the teaching of mechanical education courses in colleges and universities Accuracy. The experimental results of this paper show that the BP neural network method has increased the effect of artificial intelligence technology in the teaching of mechanical education courses in colleges and universities by 33%. Finally, by comparing the value analysis of the application of artificial intelligence technology in the teaching of mechanical education courses in colleges and universities, and the data analysis of artificial intelligence technology in the teaching of mechanical education courses in colleges and universities, the system shows that artificial intelligence technology is used in mechanical education courses in universities. Application in teaching.

In the past few decades, Cognitive Radio network (CRN) has been regarded in the literature as the most promising technology for performing dynamic spectrum management. One of the major aspects of spectrum management is referred to as the spectrum-reconfiguration decision-making ability of CR users. Dynamic spectrum reconfiguration has previously been reported to improve the spectrum utilisation in CRN. In exploiting spectrum reconfiguration to improve spectrum utilisation, various approaches have been adopted to develop models. However, none of these research works has been evaluated in the urban and rural settlement context. In a CRN environment, the frequency availability is not static like that of traditional networks. There are resource-rich regions such as in rural areas, where many frequencies are available for the Secondary Users (SUs) and resource-poor regions such as urban areas, where there are only a few frequencies available for SUs. Hence, this paper proposed a novel Foraging Inspired Spectrum Selection and Reconfiguration (FISSER) model. The performance of the FISSER model has been analysed through computer simulations both in the rural and urban CRN, using high and low perceptual radii. A high perceptual radius has been shown in the literature to improve energy efficiency and data communication performance in ad hoc networks. However, the simulation results reported in this paper show that even though the high perceptual radius improves the nodes’ energy efficiency it does not achieve optimal data communication performance compared to when the nodes use a low perceptual radius. Also, the efficacy of FISSER model was tested by comparing it against the reinforcement learning model. Based on the obtained results, it was shown that the FISSER model achieved better results in both the network throughput and the channel switching time.

The fourth-order dispersive nonlinear Schrödinger (FODNLS) equation can simulate the nonlinear propagation and interaction of ultrashort pulses in high-speed optical fiber transmission systems in optics. In this paper, all traveling wave solutions of the envelope are obtained by means of the polynomial complete discriminant system and the elementary integral method. Under specific parameters, the propagation modes of all solutions are given. In this paper, by using the direct integration method, all traveling wave solutions of the envelope of the equation are given, including the singular rational solution, the singular periodic solution, the solitary wave solution and the double periodic solution.

With the rapid growth of IoT devices, machine communication is becoming more and more popular in 5G wireless communication systems. This paper proposes a novel MAC protocol for the Internet of Things (IoT) in a scenario with a gateway and multiple IoT devices. The IoT devices with packets (active IoT devices) send independent double-pilot(IDP). The gateway takes the number and ID of IoT devices and allocates appropriate power to IoT devices. These IoT devices adjust the power and transmit packets using the Power domain Non-Orthogonal Multiple Access Protocol (PD-NOMA). Compared with the traditional single pilot scheme (TSP), the independent double-pilot can dramatically reduce the pilot collision probability, although it will probably bring a moderate increase in detection workload. Furthermore, the IDP-NOMA protocol proposed in this paper dramatically improves the system throughput and the probability of transmission success.

With the development of computer technology and network technology, various digital learning methods have seriously impacted the traditional education and teaching mode, among which gameplay learning represented by teaching games has attracted wide attention of educators. It is considered to be the most effective way to stimulate learners’ learning motivation. Mobile game is an important part of mobile phone value-added service. The research of mobile game engine has extremely important application value for the development of mobile phone game. This paper mainly studies how to realize a high-performance mobile game engine. Through the analysis of mobile phone operating system, mobile game market, mobile phone game user needs, the technology selection and main function modules of the engine are determined. Through the research of java technology, the technical architecture of engine server and client is determined. Performance and algorithm optimization are the focus of this paper, because performance issues are the biggest bottleneck in developing games on java phones.

Recover the high-resolution image from a single low-resolution image is known as single image super-resolution reconstruction (SISR). SSIR is currently a research hotspot in computer vision. In this paper, we study the feature learning module of the magnification-arbitrary network for Super-Resolution(Meta-SR), and propose an improved method of image feature learning. Its idea is multi-scale residual dense block (MRDB). We integrate it into the existing structure of the Meta-SR network. As a result, the same network has increased the receptive field, and it can obtain more detailed features of the image. This structure can be extended to other existing SISR network models. In the published and standard test set Set14, compared with the interpolation method, the average PSNR value of the algorithm in this paper increases by 3.79dB, 3.01dB and 2.85dB at amplification factors 2, 3 and 4, respectively. Through the analysis of SISR results, it can be obtained that the improved method proposed in this paper has a significant improvement in all indicators, and can more fully extract the image detail features, thereby improving the quality of the reconstructed image.

The link of traditional architectural design is very complicated. It costs a lot of human and financial resources. The traditional architectural design drawing error is also very big. Engineers can only measure some errors with their own experience. On this basis, experts believe that computer-aided systems can help architectural design. In recent years, the pollution caused by building materials is becoming more and more serious [1]. This situation has attracted the attention of environmental protection departments. Experts put forward the theoretical research of green building. This paper briefly summarizes the characteristics of computer-aided architectural design. This paper describes the application of computer technology in green building. Finally, this paper puts forward the research on the combination of the two.