Search

Paper artifacts are contaminated by external factors in the process of preservation such as foxing. For the problem of backward technology of rapid detection of foxing on paper artifacts, a method based on hyperspectral imaging technology is proposed to detect foxing spots on paper artifacts. After selecting the region of interest and obtaining the corresponding average reflectance, the difference in the average reflectance is found after comparing the healthy regions with the diseased regions. Using band operation and minimum noise fraction to observe the characteristics of foxing image, although there is overlap in different parts, the distribution distinction between moldy and healthy regions is obvious; K-nearest neighbor method and BP neural network are applied to establish the spectral discrimination model of paper artifacts with foxing spots, and the overall discrimination rate of the two methods is 73.3% and 85%, respectively. The results show that hyperspectral imaging can be used for the identification of foxing spots, but the distinction between different parts is not good, and the discrimination effect still needs to be improved.

In Today’s world technologies such as Internet of Things, Cloud Computing as well as Fog Computing are growing at an exponential rate which depend upon each other directly or indirectly. The Internet of Things can be described as a network of substantial matter such as cars, washing machines, refrigerator which can interact with each other through internet. Billions of devices will be IoT enabled in near future and generate enormous amount of data but IoT devices has some limitations like storage capabilities, processing capabilities and utilization of resources which can only be handled by integrating it with cloud technology. Cloud model provide environment in which software, Infrastructure, sharable pool of configurable resources, virtual environment, sensors, hardware and database is provided as a utility for IoT devices and users. In cloud computing paradigm some limitations exist for example distance of the data source from multi-hop, geological unified structure, latency, heterogeneity and many more. To address such limitations, Fog computing approach can be used to bring computing assets nearer to IoT devices. Fog computing is an enhancement of the cloud-based Network and computing services. It provides computational and storage services of cloud proximate to IoT devices. This paper provides an overview regarding the cloud computing uses in IoT devices and issues or problems that occur during integration. Handling of problems that occurs during integration of cloud with IoT can be done through fog computing. The purpose of this survey is to understand the concept of fog computing to improve the existing system of Integration of Cloud with IoT.

Wireless technology these days is very quickly becoming crescent. A network that was recently wired to get online was required. Just wired phones have been a thing of the past. In the past four decades, mobile networks have thrived immensely. The starting point was the 1G cellular concept where ‘G’ stances for generation linkages. This had fully developed very rapidly, generating 1G, 2G, 3G and gradually transferring into 4G from generation to generation. And now people are utilizing the 4G networks. 5G network will nearly stretch its wings to conquer this complex world of cell technology. Integrated 5G work is continuing, with complete service planned in 2020. The development of 5G technology is the perfect solution for the many problems facing us today with today’s innovations. 5G will become an intelligent technology that will limit to a single global uniform body the number of different innovations. This paper is mostly about the evolution of mobile wireless networks like 1G and 5G as well as how they vary and their benefits and drawbacks.

Light via our eyes influences visual performance, visual comfort and visual experience, but also affects several health related, non-image-forming (NIF) responses. New metrics have been developed to quantify the NIF effects of light. In order to incorporate these in lighting design practice, simulation tools are required that are able to process information about the spectral distribution of light sources and materials. However, most of the tools currently used for daylight and electric light simulations simplify the spectrum into RGB (Red, Green, Blue) colour values. This paper presents an overview of the currently used programs for simulating the NIF effects of light in building design and discusses the possibility of using existing spectral rendering software as an alternative. A review of literature shows that mostly Radiance or Radiance-based programs have been used so far, but new user-friendly tools could employ existing spectral rendering tools. As the NIF effects of light gain greater importance in lighting design, new simulation workflows are needed. This paper aims to support the development of future workflows by presenting the current state-of-the-art.

Under the pressure of energy and environmental protection, we will promote the technological progress and demonstration of electric vehicles, and the construction of charging facilities will continue. Charging facilities planning and orderly charging, as two major research directions of electric vehicle infrastructure, are of great significance for the future development of electric vehicles. The optimal charging of electric vehicles can effectively improve the safe and economic operation ability of distribution network, which is of great significance to its safe operation. Therefore, this paper proposes the outsourcing test experiment and processing of urban electric vehicle public charging network based on 5G and big data. In this paper, through the analysis of the development status of urban electric vehicles, this paper proposes to optimize the charging mode of electric vehicles by combining the charging network forward and backward algorithm. In the outsourcing test experiment, the electrical safety test shows that when the current reaches 1.1-37.1kw: 5000A, when the power factor is 0.8 ∼ 0.9, when the short-circuit current impact is tolerated, the connection device will not affect the breaking operation by contact fusion welding, and the insulation protection will not be invalid. Through investigation and analysis, the satisfaction degree of electric vehicle optimization algorithm is increasing year by year. Through the analysis of the test results, the research in this paper has achieved ideal results and made a contribution to the research of urban electric vehicle public charging network.

Full power converter wind turbine is the main type of wind power, so the simulation calculation needs to establish accurate model parameters. This paper analyzes the model structure of PSASP program according to its low voltage ride through control and physical characteristics, and puts forward the parameter identification method of LVRT characteristics of full power converter wind turbine, and to use the LVRT data of 5. 5MW unit for parameter identification and simulation verification. This paper proposes that the electromechanical transient simulation can ignore the part of the generator model of the full power converter wind turbine, and simulates the grid side converter with the controlled current source. The main characteristics of LVRT are determined by the control system of the converter. In order to do the parameter identification, it is necessary to calculate and analyze the control characteristics of multiple measured data. First, determine the control mode, then determine the control parameters to complete the parameter identification. In this paper, the modeling conditions and model structure of the full power converter wind turbine are confirmed. The correlation between the parameters during the LVRT fault and the parameters during the LVRT recovery period and the LVRT characteristics is analyzed. In this paper, a parameter identification method is proposed to analyze the active current and reactive current during the LVRT fault, which has strong physical significance and operability. Based on the actual LVRT characteristics of 5. 5MW wind turbine, the parameter identification and simulation are carried out to verify the correctness of the method.

This paper deals with the new segmentation techniques for retinal blood vessels on fundus images. This technique aims at extracting thin vessels to reduce the intensity difference between thick and thin vessels. This paper proposes the modified UNet model by incorporating ResNet blocks into it which includes structured prediction. In this work we generate the visualization of blood vessels from retinal fundus image for two loss functions namely cross entropy loss and Dice loss where the network classifies several pixels simultaneously. The results shows higher accuracy by considering a much more expressive UNet algorithm and outperforms the past algorithms for Retinal Vessel Segmentation. The benefits of this approach will be demonstrated empirically.

As the core of the new monitoring system, the Internet of Things realizes the integration of wireless sensor networks and traditional communication networks, and provides a platform for remote management and monitoring of the underlying equipment. The intelligent transportation system framework built on this basis combines intelligent transportation technology and the organic combination of vehicle management technologies is conducive to the safety, speed and reliability of vehicle transportation, and plays an important role in further reducing transportation costs. Based on this, this article launched the research on the Internet of Things and intelligent transportation systems. This article first summarizes the concepts of the Internet of Things, intelligent transportation and wireless sensor network technology and the current research status at home and abroad. By analyzing and comparing the performance and characteristics of various communication methods, embedded core microprocessors and embedded operating systems, this paper proposes an overall design scheme of the Internet of Things transportation system based on embedded technology. This paper analyzes the path planning problems in the application of the transportation system, combining the shortest path algorithm simulation results and the actual characteristics of the transportation network, and proposes a simulation data fitting method based on two network parameters and Bellman-Ford, Dijkstra, and Floyd algorithms. The route optimization scheme, and the above-mentioned design scheme was implemented in the transportation system, and the scheme verification was carried out. Finally, this article describes in detail the overall debugging process and operating results of the transportation system, thereby fully verifying the feasibility and correctness of the design and implementation methods of the intelligent transportation system based on the Internet of Things. The research results show that when the INF-PROPORTION is small, the Dijkstra algorithm is better than the Bellman-Ford algorithm. When INF-PROPORTION=0.3, the two algorithms T overlap. Since then, the advantages of the Bellman-Ford algorithm gradually appear, but it is approaching in INF-PROPORTION. At 1 o’clock, the Dijkstra algorithm has a sharp decrease, which is again smaller than the Bellman-Ford algorithm. The second loop condition in the main loop of Dijkstra’s algorithm cannot be satisfied, resulting in a decrease in T.

Fire detection technology based on video images is an emerging technology that has its own unique advantages in many aspects. With the rapid development of deep learning technology, Convolutional Neural Networks based on deep learning theory show unique advantages in many image recognition fields. This paper uses Convolutional Neural Networks to try to identify fire in video surveillance images. This paper introduces the main processing flow of Convolutional Neural Networks when completing image recognition tasks, and elaborates the basic principles and ideas of each stage of image recognition in detail. The Pytorch deep learning framework is used to build a Convolutional Neural Network for training, verification and testing for fire recognition. In view of the lack of a standard and authoritative fire recognition training set, we have conducted experiments on fires with various interference sources under various environmental conditions using a variety of fuels in the laboratory, and recorded videos. Finally, the Convolutional Neural Network was trained, verified and tested by using experimental videos, fire videos on the Internet as well as other interference source videos that may be misjudged as fires.

Facial recognition is one of the main research directions in the field of artificial intelligence and image processing. It has been widely used in identity authentication, video surveillance and biological detection. Because it is non-contact, natural, convenient and reliable, facial recognition has become a popular choice for biometric systems. The accuracy of facial recognition still needs to be improved, the main goal of this paper is to improve the accuracy of face recognition. Based on the support vector machine method, the focus is on the feature extraction and feature matching of face images. In view of the particularity of face images, the pre-processing of face images is studied. In this paper, grayscale normalization and geometric normalization pre-processing methods are used. In order to reduce the interference factors of the image as much as possible, the features are high-lighted, and the non-featured parts are weakened, this paper adopts the Histogram of Oriented Gradient feature extraction method. Then we proposed a new method based on SVM, which uses a one-to-many method to construct multiple SVM classifiers, selects the optimal parameters through repeated experiments, and selects ORL face database for testing. The recognition rate can reach about 98.5%.

As a value-added service that improves the efficiency of online customer service, customer service robots have been well received by sellers in recent years. Because the robot strives to free the customer service staff from the heavy consulting services in the past, thereby reducing the seller’s operating costs and improving the quality of online services. The purpose of this article is to study the intelligent customer service robot scene understanding technology based on deep learning. It mainly introduces some commonly used models and training methods of deep learning and the application fields of deep learning. Analyzed the problems of the traditional Encoder-Decoder framework, and introduced the chat model designed in this paper based on these problems, that is, the intelligent chat robot model (T-DLLModel) obtained by combining the neural network topic model and the deep learning language model. Conduct an independent question understanding experiment based on question retelling and a question understanding experiment combined with contextual information on the dialogue between online shopping customer service and customers. The experimental results show that when the similarity threshold is 0.4, the method achieves better results, and an F value of 0.5 is achieved. The semantic similarity calculation method proposed in this paper is better than the traditional method based on keywords and semantic information, especially when the similarity threshold increases, the recall rate of this paper is significantly better than the traditional method. The method in this article has a slightly better answer sorting effect on the real customer service dialogue data than the method based on LDA.

In recent years, with the improvement of Internet of Things technology and the continuous improvement of economic level, people’s consumption consciousness has also changed, especially for the packaging of networked products put forward higher requirements. This paper mainly studies the visual expression of networked product based on Internet of Things technology. Starting from the increasing influence of Internet electronic consumption in China’s economic consumption system, this paper deeply discusses the systematic product logistics packaging design under the Internet consumption form. This paper analyzes and discusses the differences between Internet consumer commodity packaging and physical consumer commodity packaging in functional orientation, added value of packaging, systematic visual design and other aspects.

Based on the demand for smart grid 5G network, this paper studies 5G mobile communication technology and the industry's 5G private network construction mode. Combined with power grid requirements, this paper focuses on analyzing the uninterrupted 5G private network solution, the principal of the solution is also explained. Taking a 5G test network deployed at a converter station as an example, the construction, isolation, operation, and maintenance plans of the uninterrupted 5G private network solution in the power communication network is proposed, the actual tests verify the feasibility of the continuous 5G private network. This paper will provide reference for the promotion and application of 5G private network technology in the power grid.

Aiming at the series fault arc phenomenon in landscape lighting and the hidden dangers of electrical fires, in this paper, a landscape power supply series fault arc model is constructed and its model is simulated. The simulation results show that when a fault occurs, the arc current becomes smaller (almost zero) due to the increase in the impedance of the lighting circuit; this phenomenon is called the “current zero off” phenomenon of the fault arc current. The current zero off phenomenon of the fault arc current is the main fault feature in the landscape lighting circuit. In this paper, the wavelet algorithm is used to detect the fault current waveform. According to the fault characteristics, by judging whether the modulus maximum value of the wavelet coefficient has periodic characteristics with an interval of 100±15 sampling points, it is analyzed whether a series-type arc fault occurs. The built physical model verifies the feasibility and correctness of the arc detection algorithm. The research results of this paper have certain reference value for the detection and application of fault arc.

With advances in the mobile communications, many service-related tasks can be made quickly and easily. Mobile banking is one such service that has eliminated the need for a consumer to go to a branch to carry out many common transactions. In a country like India, where the last mile reach through brick-and-mortar banking facilities, mobile phones can complement the reach. This paper describes how mobile cloud architecture can be employed for banking and services to customers to enhance their banking experience as well as ensuring information security. This paper focuses on cloud-based risk architecture for banking solutions to address various issues related to mobile banking such as processing speed and storage capacity. Improved random forecast algorithm is used for the evaluation of the system. This proposed system achieves 99% of the system.

The implementation of training complexes based on virtual reality for the training of specialists in machine-building, chemical, mining and other industries is associated with the need to solve a number of tasks. These include simulating various physical processes (temperature, humidity, and air pressure), loads (speed of movement and angle of inclination of the surface), and other external factors that cannot be reliably simulated in virtual reality. Therefore, an urgent task is to integrate various simulation systems into the software and hardware platform of virtual training complexes, which will provide a realistic immersion in the subject area due to virtual reality, as well as simulate the necessary external influences on the student. The paper considers this process by the example of integration of a simulation system of physical loads into virtual training complexes. The basis of the simulation system under consideration is a controlled treadmill. The use of treadmills allows students to develop muscle memory, perform physical training and increase the degree of immersion in virtual reality, which positively affects the effectiveness of their training. However, their integration requires the solution of a number of practical tasks for the transfer of information between the individual subsystems of the virtual training complex. The paper considers algorithms and software for solving these problems. The described approaches can be used to integrate various simulation systems into the software and hardware platform of virtual training complexes for the organization of comprehensive training of specialists.

This paper takes the physical model of Radar Cat’s Eye as the research object, based on geomagicdesign software’s powerful reverse modeling function, the reverse modeling and design process of Radar Cat’s Eye is explained in detail. The detailed steps and main precautions of scanner calibration in the process of Radar Cat’s Eye reverse modeling are given. At the same time, the main contents of model scanning, data processing, reverse modeling, model comparative analysis and so on are also introduced and explained in detail. In short, the relevant contents of this paper provide reference and help for the reverse modeling and design of other models.

This paper discusses structuring of hardware and software for an autonomous social robot. It shows that the real-world social robot operations face the challenge of environmental variability and uncertainty of the objective parameters. Thus, a social robot must be capable of situation analysis for better autonomy. We propose a modular distributed structure of the control system. Separate modules monitor the status and control the subsystems of the robot. General coordination of subsystems is provided by the Supervisor module. For the robot to function autonomously, the Supervisor must be capable of situation analysis and its key functions: objective retrieval and analysis, situation description, configuring and strategizing the solution. The robot’s sensory inputs help acquire the objective and its parameters to describe the situation. Description relies on the database of a priori knowledge of the environment and its objects. Analysis is linked to a reduction in the uncertainty of the objective parameters and situation description. For a case study, the paper demonstrates a maze-solving strategy as affected by the situation.

The development of music is a tortuous process, and the network relationship between each genre and each artist is intricate. In order to have a better understanding of the history of music, this paper tells the stories hidden in the history of music by means of data processing. Firstly, this paper establishes a model to evaluate the similarity between music by using ISOMAP algorithm. At the same time, the forest evolution model was established to mark the most revolutionary musical characters. Finally, using the Page-Rank algorithm, we get the founders of several music genres. It turns out that the figures who led the development of music don’t coincide with the figures who revolutionized music. Through the analysis of this paper, we can more clearly understand the development of music and the evolution of genres.

A signature is a mark or name that represents the identity of the people and the Signature Verification System (SVS) is used to validate the identity of people. The signature verification system is mostly used for bank cheques, vouchers, intelligence agencies and others. There are two types of SVS which are online and offline signature verification systems. The paper deals with an offline signature verification system. The proposed system consists of four main stages, (i) image acquisition, (ii) image pre-processing, (iii) feature extraction and (iv) classification. The image pre-processing steps involved binarization, noise removal using Gaussian filter and image resizing and thinning. In the feature extraction stage, Bag-of-Features with the Speeded Up Robust Features (SURF) extractor was utilized. In the third stage, the Support Vector Machine (SVM) classifier is used. Lastly, the confusion matrix and the verification rate were used to evaluate the performance of the classifier. In this paper, we implement and compare the performance of the signature verification system without entering the user ID and the signature verification system entering the user ID. For the ratio of 75% and 25% of the training and testing, respectively, the average accuracy for the signature verification system without entering the user ID is 71.36%, whereas the average accuracy for the signature verification system entering the user ID is 79.55%.

This paper presents an adaptive frequency Phase locked loop (PLL) based approach for grid connected multifunctional inverter is presented for residential applications. The proposed control structure deals with non-linear loads and also non ideal grid voltages like magnitude variation, frequency variation, unbalance harmonics, etc. and can effectively address the DC offset in a voltage signal which in turn improves the power quality. A third order generalized integrator based PLL with adaptive frequency and DC offset elimination blocks will effectively deal with the power grid voltage fluctuations, frequency variations and eliminate the phase difference between PLL output. This approach is implemented as control algorithm for single-stage single-phase grid connected multifunctional inverter topology for PV applications which feeds energy to the grid. The Maximum Power Point Tracking is obtained by Perturb & Observe method for extracting maximum power from a Photovoltaic system. A detailed analysis with the proposed control technique is presented in this paper. Experimental tests are conducted at various operating conditions to describe and verify the performance of the proposed control using MATLAB / Simulink.

The traditional hepaticcell carcinoma (HCC) pathological grading depends on biopsy, which will cause damage to the patient's body and is not suitable for everyone's pathological grading diagnosis. The purpose of this paper is to study the pathological grading of liver tumors on MRI images by using deep learning algorithm, so as to further improve the accuracy of HCC pathological grading. An improved network model based on SE-DenseNet is proposed. The nonlinear mapping relationship between feature channels is modeled and recalibrated using attention mechanism, and rich deep-seated features are extracted, so as to improve the feature expression ability of the network. The method proposed in this paper is verified on the data set including 197 patients, including 130 training sets and 67 test sets. The experimental results are evaluated by receiver operating characteristic (ROC) and area under the ROC curve (AUC). The improved SE-Densenet network achieves good results, and AUC 0.802 is obtained on the test set. The experimental results show that the method proposed in this paper can well predict the pathological grade of HCC.

with the rise and rapid development of mobile communication, intelligent terminal and data system, we are entering the era of mobile Internet. In recent years, more and more data need to be processed and transmitted in daily life, and structured data is becoming more and more important. Among them, multi-mode matching technology can search data in a wider range. Matching for multiple patterns at a time avoids unnecessary matching, accelerates the matching process, and helps to find longer matching information and obtain higher accuracy. This paper mainly introduces the high camouflage intrusion detection method of structured database based on multi-mode matching. This paper uses the high disguised intrusion detection method of structured database based on multi-mode matching, collects sensitive information of wireless access points and stations through the communication of WLAN in multimodal matching, then intercepts and forges data packets to initiate replay attack. Replay attack is characterized by abnormal traffic in the network, which can be detected by statistical analysis. The experimental results show that the high camouflage intrusion detection method based on multi-mode matching makes the camouflage intrusion detection rate increase by 23%. The limitations of the design and research of camouflage intrusion detection are analyzed, discussed and summarized, so as to enrich the academic research results.

In this paper, a MATLAB Simulink model of a Quadruped Robot is presented alongside its remote, control and monitor user interface that has been developed by using the fundamentals of Internet of Things on a Node-Red Flow and the FRED-Cloud Server. Robotics and Automation over the recent years have developed exponentially and hence have been a key factor in the rise of Industry 4.0 which has usurped manual supervision and operation in industrial and manufacturing processes around the globe. The design and creation of technologically advanced robots integrated with computer-based software for their automation has not only successfully made the tasks facile to manage within short spans of time, but also has increased the efficiency notably. The stability and mobility of quadruped robots is considered to be ideal on differing terrains with minimal subtle changes, thereby making it an asset. Internet of Things on the other hand, has paved its way over the control of robots as well, with its unparalleled benefits. This paper is focused on the design and execution of the Quadiuped model which includes the observation of the various significant graphs achieved post simulation with respect to electrical values such as power and current consumption, and a visual animation of the robot running in the workspace. Furthermore, a single platform is developed and displayed that allows a user to log in for security puiposes and thereby, operate and monitor the functions and conditions of the bot easily, ranging from remote visual support, directional integrity, damage control and more, without the need of multiple platforms to carry out varying tasks with respect to control.

With the advent of sensor technology, the exertion of multispectral image (MSI) is comely omnipresent. Denoising is an essential quest in multispectral image processing which further improves recital of unmixing, classification and supplementary ensuing praxis. Explication and ocular analysis are essential to extricate data from remote sensing images for broad realm of supplications. This paper describes curvelet transform based denoising of multispectral remote sensing images. The implementation of curvelet transform is done by using both wrapping function and unequally spaced fast Fourier transform (USFFT) and they diverge in selection of spatial grid which is used to construe curvelets at every orientation and scale. The coefficients of curvelets are docket by a scaling factor, angle and spatial location criterion. This paper crisps on denoising of Linear Imaging Self Scanning Sensor (LISS) III images. The proposed denoising approach has also been collated with some existing schemes for assessment. The efficacy of proposed approach is analyzed with calculation of facet matrices such as Peak signal to noise ratio and Structural similarity at distinct variance of noise..

With the rapid development of informatization, computer database software systems have entered various fields of society, which has brought about the explosive growth of industry data. Faced with massive amounts of data, computers with limited storage capacity have to abandon some outdated data, and the application of various data mining technologies related to it has gradually matured. The purpose of this article is to discuss the application research of data mining technology in software engineering. This article analyzes the correlation analysis of a large number of bug repair source code update data and bug defect reports in the version control system SVN and the defect tracking system Bugzilla in the software engineering project development process, and tries to classify the bug report by data mining technology: defect changes and potential defects change. Starting from large-scale software engineering projects, apply data mining technology to the huge software engineeri ng knowledge base. Especially the software development and maintenance are explained, as well as the more challenging problems in the future. This paper uses data mining technology to study the dependency of the source code files of each module of the software system, and helps software developers quickly understand the software architecture by understanding the interrelationships between the modules, and provides suggestions for modification paths. Experimental research shows that this paper compares with F-measure and concludes that FL-M-GSpan algorithm is better than TS-M-GSpan algorithm. At the same time, it is found that the FL-M-GSpan algorithm always has a better accuracy rate close to 95%, while the TS-M-GSpan algorithm always has a better recall rate.

With the rapid development of today’s technological society, recognition algorithms have received more and more attention. In addition, in recent years, deep learning algorithms have developed rapidly at the theoretical level, and related new technologies have also been applied to various industries. TensorFlow is a deep learning framework that performs well in all aspects. The purpose of this article is to study the realization of recognition algorithms based on TensorFlow’s deep learning mechanism and their optimization techniques. The target detection algorithm used in the system in this paper combines deep learning technology to replace the traditional method based on convolutional filtering. The paper is based on the TensorFlow deep learning framework. TensorFlow is an open source software library for machine intelligence. The learning software library of the network learning framework. This article uses a semi-automatic labeling method combined with an incremental learning algorithm to label the data set. After labeling the data, the parameters are set, the model is trained, and the model is finally trained and applied to the detection system. Studies have shown that: in the recognition algorithm, only the single sub-analysis stream is considered, and the short video sequence analysis stream can get the most excellent accuracy. Compared with the second best long video sequence analysis stream, it can also increase by about 3%.

The power consumption readings of sub meter and total meter of distribution transformer of low-voltage users follow the law of conservation of energy. The meter power loss rate of abnormal low-voltage users must also be abnormal. This paper studies the solution of the meter power loss rate under the four abnormal power consumption scenarios of single (multi) user and full (partial) period. The traditional linear solution method has accurate identification effect for the abnormal power consumption scenario of full period, but it cannot identify the abnormal power consumption scenario of partial period. In this paper, an improved artificial fish swarm algorithm is proposed. By adjusting the fixed step to the adaptive step, the power loss rate of each sub meter is obtained, and the abnormal power users are pinpointed. The research results are verified by simulation examples on IEEE European Low Voltage Test Feeder. The results show that the improved artificial fish swarm algorithm in this paper can identify abnormal power users for the above four abnormal electric field scenarios. The algorithm provides a new alternative for the identification of abnormal low voltage users.

Livestock plays very important economic, social and cultural roles in the well being of rural communities across the world. Quality environmental conditions, automation and monitoring are the key necessities of running a good and profitable livestock farm. Air quality, temperature of the surroundings and humidity play a major role while deciding the fan speeds of the exhaust System used in all aspects of livestock farming. Another important part of livestock production is increasing incubation speeds of eggs by performing artificial incubation. It is a requirement to maintain the temperature at a constant value in this system. This paper describes two mutually exclusive Fuzzy Logic algorithm-based systems to automate the exhaust system and an artificial egg incubator. The other important part of a livestock farm is production of milk and milk products. It is required to monitor the health of cows by overseeing their activities at any point of time. This can be done by determining and monitoring the activities performed by the cow. This paper describes a simple Deep Learning Model to classify the activities of a cow broadly as standing, walking or grazing. The Exhaust and the Incubator system are controlled and monitored using Internet of Things (IOT) System using a native web application developed using the Flask framework.

Deep learning requires training on massive data to get the ability to deal with unfamiliar data in the future, but it is not as easy to get a good model from training on massive data. Because of the requirements of deep learning tasks, a deep learning framework has also emerged. This article mainly studies the efficient distributed image recognition algorithm of the deep learning framework TensorFlow. This paper studies the deep learning framework TensorFlow itself and the related theoretical knowledge of its parallel execution, which lays a theoretical foundation for the design and implementation of the TensorFlow distributed parallel optimization algorithm. This paper designs and implements a more efficient TensorFlow distributed parallel algorithm, and designs and implements different optimization algorithms from TensorFlow data parallelism and model parallelism. Through multiple sets of comparative experiments, this paper verifies the effectiveness of the two optimization algorithms implemented in this paper for improving the speed of TensorFlow distributed parallel iteration. The results of research experiments show that the 12 sets of experiments finally achieved a stable model accuracy rate, and the accuracy rate of each set of experiments is above 97%. It can be seen that the distributed algorithm of using a suitable deep learning framework TensorFlow can be implemented in the goal of effectively reducing model training time without reducing the accuracy of the final model.

The primary objective of this particular paper is to classify the health-related data without feature extraction in Machine Learning, which hinder the performance and reliability. The assumption of our work will be like, can we able to get better result for health-related data with the help of Tree based Machine Learning algorithms without extracting features like in Deep Learning. This study performs better classification with Tree based Machine Learning approach for the health-related medical data. After doing pre-processing, without feature extraction, i.e., from raw data signal with the help of Machine Learning algorithms we are able to get better results. The presented paper which has better result even when compared to some of the advanced Deep Learning architecture models. The results demonstrate that overall classification accuracy of Random Forest, XGBoost, LightGBM and CatBoost, Tree-based Machine Learning algorithms for normal and abnormal condition of the datasets was found to be 97.88%, 98.23%, 98.03% and 95.57% respectively.

With the rapid development and improvement of information technology, information system construction has new requirements and goals. Cloud computing technology is an inevitable choice in the construction of information system. By taking cloud computing technology as the basic structure framework, the phenomenon of data information island can be broken. The purpose of this paper is to study the application of cloud computing in the construction of information system. Taking the management mode of university campus as an example, based on the research of cloud computing technology, virtual machine technology and Internet of things technology, this paper discusses the data resource management algorithm of smart campus. Aiming at the scheduling model, strategy and research objectives of cloud computing resources in data center, this paper proposes a method of initial allocation and adaptive dynamic scheduling of virtual machine resources. According to the multi-dimensional vector characteristics of virtual machine, this paper proposes a resource allocation algorithm based on multi-objective evolution, and gives four important strategies. The experimental results show that the four advantages and strategies can effectively reduce the number of virtual machine migration and reduce the adverse impact on the overall performance of cloud computing core network.

Considering the problems of low communication rate and large communication delay of the traditional single-lamp monitoring system for airfield lighting based on narrow-band power line carrier communication technology, a solution of single-lamp monitoring system for airfield lighting based on broadband power carrier communication technology is proposed. Firstly, this paper has made a comparison of advantages and disadvantages between narrow-band power line carrier communication technology and broadband power line carrier communication technology, and briefed the problems faced by traditional single-lamp monitoring system based on narrow-band power line carrier communication. Taking technical characteristics into consideration, broadband power line carrier communication technology is selected for the development of a new single-lamp monitoring system for airfield lighting. Secondly, this paper articulated the design and development process of new airfield lighting single-lamp monitoring system based on broadband power line carrier communication technology, from the formulation of the overall architecture scheme of the system to the realization of local convergent equipment, and focused on the analysis of hardware and software development process of single-lamp monitoring module. Finally, this paper set up a test environment, and verified the performance index by experiments. The test results show that the system meets the design index requirements, can improve the performance of the single-lamp monitoring system for airfield lighting, effectively solves the problems faced by the traditional system, and can further meet the needs of the airport for airfield lighting monitoring and control.

Conveyor belt transfer is a widely used transportation means in industry and agriculture, with the help of the robot arms the workpiece on the belt can be picked and placed, replacing human sorters for production lines work. The position and orientation of the workpiece are important for grabbing by the robot arms. The goal of the paper was to investigate the acquisition of the position and orientation of the conveyor belt workpiece by means of the camera video overhead looking down the belt. The proposed method is the inter frame difference in nature, using the conveyor belt background as the first frame, but the other frames were not used wholly as usually, only an ROI all around the conveyor belt in the camera video was chosen, and the inter frame difference was carried out in the ROI. The ROI was of the same width as that of the belt in the video which was known in advance, while the length of the ROI was arbitrary, so one pixel in the frame was scaled to the actual length conveniently. Every read frame behind the background was computed the difference with the background in such ROI, and the four vertexes coordinates of the rectangle workpiece image on the belt were obtained when it passed the ROI, and then the distance apart from the right belt boundary was calculated due to the proportional relation between the width of workpiece and that of the ROI. Two kind workpiece orientation on the belt toward the left and right were judged using the same obtained four vertexes coordinates by means of Euclidian length, and the tilt angle was calculated by arc tangent function in favour of two narrow sides of rectangle workpiece grab. The actual test showed that the method of obtaining the position and orientation of workpiece on the belt proposed in the paper could be realized correctly.

Large scale Neural Network (NN) accelerators typically have multiple processing nodes that can be implemented as a multi-core chip, and can be organized on a network of chips (noise) corresponding to neurons with heavy traffic. Portions of several NoC-based NN chip-to-chip interconnect networks are linked to further enhance overall nerve amplification capacity. Large volumes of multicast on-chip or cross-chip can further complicate the construction of a cross-link network and create a NN barrier of device capacity and resources. In this paper, this refer to inter-chip and inter-chip communication strategies known as neuron connection for NN accelerators. Interconnect for powerful fault-tolerant routing system neural NoC is implemented in this paper. This recommends crossbar arbitration placement, virtual interrupts, and path-based parallelization strategies in terms of intra-chip communications for the virtual channel routing resulting in higher NoC output at lower hardware costs. A lightweight NoC compatible chip-to-chip interconnection scheme is proposed regarding to inter-chip communication for multicast-based data traffic to enable efficient interconnection for NoC-based NN chips. Moreover, the proposed methods will be tested with four Field Programmable Gate Arrays (FPGAs) on four hard-wired deep neural network (DNN) chips. From the experimental results it can be illustrate that a high throguput can obtained effectively by the proposed interconnection network in handling thedata traffic and low DNN through advanced links.

The major challenges, which come across face recognition system, are to find the age and gender in 2D/3D image of the person specifically in cloud environment. This paperis centered on face detection with MAC (Media Access Control) and biometric technology. Face scanning along with machine’s MAC address and biometric technologies has been shown to improve security controls. Face recognition can be used to search and label users and their assigned machines for sensitive purposes. Following that, it was stored in a specific database with their unique ID. In addition, the verification process has begun by comparing the models in the database. Face scanning along with speech and biometric technologies is used to improve security controls. Face recognition system may also be set up in high security machines to improve protection by allowing only registered individuals or others users. Related strategies for determining the age and gender and 2D/3D image from a specific picture are explored, as well as several modern methods for preserving protection. In this paper, the full model is explored independently with security implemented in cloud environment. The proposed model of the paper provides the integrated security features using MAC address of machine and face recognition of the machine user.

In view of the wide variety of telecom packages and the difficulty of adapting to the needs of users, this paper introduces a recommendation model for telecom packages based on deep forests. This paper first analyzes the telecom package data, and then optimizes the deep forest according to its characteristics such as discrete, continuous attribute interleaving and high coupling characteristics, including the use of decision trees to discretize continuous features and design continuous window sliding mechanism. These methods can improve the ability of deep forest combination high coupling features. Finally, the model optimization measures were verified by detail experiments. The experimental results show that the optimized deep forest can be applied to the telecom package recommendation field. Compared with other shallow models and unoptimized deep forest models, the deep forest model has increased the F1 score by 5%; after adjusting the deep forest hyper parameters, the F1 score can be increased by 2%.

The parallel connection of IGBTs has been being applied in high power neutral point clamped (NPC) three level converters. This paper investigates the impact of gate parameters (gate resistor and capacitance) on dynamic current imbalance of parallel connected IGBT for NPC three level converter. A gate parameters calculation method is proposed in the paper, and the delay time and collector current difference can be analysed quantitatively. Experimental results have shown the effectiveness of the method.

the paper introduces IRS to assist offloading, and the propagation Environment can be intelligently changed by changing the reflection unit of the IRS, This article proposes an IRS-assisted MEC power distribution Internet of Things system, and studies the gain effect of IRS in the MEC system. In this system, the single antenna equipment can choose to unload a small part of its computing task to the edge computing node of the distribution Internet of things through the multi antenna access point with the help of IRS. In this paper, the delay minimization problem of the whole system is established, the DNQ reinforcement learning algorithm is used to solve the problem, which can effectively change the coverage of smart substations.

As a large, complex system with wide distribution and high real-time, the safe, stable and reliable operation of the power system is inseparable from the power automation system. In this paper, an in-depth study is conducted on the key issues of this solution in the process of software cross-platform integration around the EPRI graphic center method, combined with the power data interface standard. The dispatch center graphics system and the dispatch center power graphics application method are discussed in detail in the paper. In addition, the paper also explains the online calibration system for relay protection ratings with smart grid dispatching technology support system. The methods and sample systems in this paper have been practically applied in large scale power grid dispatching centers, providing a reliable guarantee for the safe and stable operation of the power grid.

The rapid development of the high frequency power conversion techniques makes great demands on the methods that can reduce the execution time of the program effectively. This paper is aiming at reducing the execution time of the program in several aspects such as sampling, complex expressions, and so on. As one of the most widely applied methods, reducing the execution time of the program at the cost of the memory space is adopted in this paper. Furthermore, in order to confirm the feasibility and superiority of programs that are proposed in this paper, they are compared with other programs that can realize the same function in terms of the execution time.

Steganography can be described as approach of masking an undisclosed message with a normal message which is known as the Carrier message signal. DSP techniques, such as LSB encoding, have historically been implemented for secret information hiding. Utilization ofsteganography functions of deep neural networks for voice data is something this paper will present. This paper also demonstrate that the steganography techniques suggested for vision are less suitable for speech signals this paper present a implementation technique that involves the use of ISTFT and STFT as differentiablelayers in the network. Empirically, the efficacy of the proposed methods based on multiple datasets of speech should be demonstrated and the outcome are examined quantitatively and qualitatively. Using of multiple decoders or a single conditional decoder helps to hide multiple signals in a single carrier signal. Finally, under various channel distortion situations, this model Qualitative studies indicate that human listeners cannot detect changes made to the carrier and hence the decoded messages are highly intelligible.

Aiming at the problem that the current feature selection algorithm can not adapt to both supervised learning data and unsupervised learning data, and had poor feature interpretability, this paper proposed a hybrid feature selection model based on machine learning and knowledge graph. By the idea of hybridization, this model used supervised learning algorithms, unsupervised learning algorithms and knowledge graph technology to model from the perspective of data features and text features. Firstly, the data-based feature weights were obtained through the machine learning model, and then the text-based weights were obtained by using the knowledge graph technology, and the weight sets are combined to obtain a feature matrix with good explanatory properties that meets both the data and text features. Finally, the case analysis proves that the method proposed in this paper has good effects and interpretability.

This paper presents a design and development of an Ankle Foot Orthosis (AFO) printed with a multi-extrusion Fused Deposition Modelling (FDM) printer. AFO is crucial in the healing of patients with ankle joint displacement. It helps to heal the foot easily. The model is designed to print with dual materials such as flex and polylactic acid (PLA). The critical problem in building a prototype is to obtain excellent bonding properties between the layers of different materials. The Flex material is softer than the PLA and both have different melting temperatures. Thus, successfully printing with an excellent adhesive is the key concern in multimaterial applications. The paper also presents the simulation results of an AFO to justify the mechanical properties and required materials for sustainable development.

Fault-tolerant design of cache is a key aspect of highly reliable processor design. In this paper, based on the key metrics in Cache architecture design: reliability, power consumption, latency and area, we divided the related research into two categories: one is to maximize reliability with guaranteed latency, power consumption and area, the other is to minimize latency, power consumption and area loss while ensuring fault tolerance reliability. Based on the classification, by analyzing different studies of Data and Tag in Cache, this paper gives the characteristics of these methods and the future development trend.

Dissolved Gas Analysis (DGA) for oil samples has been the most widely used diagnosis tool for transformer condition assessment for many years. However, DGA use to oil-filled transformers with a voltage class up to 100 kV. The aim of this paper is to address the issue of DGA interpretation to oil-filled transformers with a voltage class of 10 kV. This paper will present DGA tests results from 57 power transformers and will propose a maintenance decision making procedure using the IEC 60599-2015 Ratio Method, IEEE Std C57.104-2008 include Dornenberg Ratio Method and Rogers Ratio Method, and Russian Std CTO 56947007-29.180.010.094-2011 and Russian Std RD 153-34.0-46.302-00.

Abstract.This paper aims at the high efficiency of field balancing for turbo-generator with large capacity currently, and introduces the strategies and key techniques of the rotor system balancing with practical cases of power plant in field. The acquisition, analysis and former processing of the original vibration data for balance calculation are included. Furthermore, they involve complete measuring points and conditions, accurate judgment for the types of unbalance exciting force and selection of stable vibration data, all these could reduce the blindness of balancing effectively. The strategies and techniques also contain the determination for axial plane of unbalance by the modal method, then the optimal steps and the plane of adding weight are chosen during the implementation of balancing. Besides, this paper also introduces the analysis and selection of influence coefficients and the phase of trial weight, these can help determine the final correction weight accurately in order to guarantee the balancing process prompt and efficient. Meanwhile, the restriction of practical location for adding weight and construction period of maintenance and production for the units should be considered during the high efficiency balancing in field. These strategies and techniques of high efficiency balancing have practical application value in promoting the technology of field balancing for turbo- generator units with large capacity.

Unmanned aerial vehicle (UAV) has been widely used in power system inspection. Most of the existing UAVs are equipped with visible and infrared cameras for fast full spectrum photography and fault monitoring of transmission lines. When the transmission line has defects such as aging, broken strand and serious corrosion, the traditional image recognition, infrared and other observation methods can not identify these defects well. In order to realize the rapid detection and judgment of broken strand, this paper analyzes the characteristics of electromagnetic interference of transmission line, and constructs the electromagnetic interference measurement system based on patrol UAV. The research results of this paper can realize the real-time detection and alarm of broken strand, and provide technical support for line inspection.

In recent years, with the rapid development of artificial intelligence technology, people’s demand for wireless spectrum resources is increasing, which poses a huge challenge to the originally tight and limited wireless spectrum resources. On the other hand, the traditional fixed spectrum cooperative sensing and allocation algorithms result in extremely low spectrum utilization for a considerable part of the licensed spectrum. The purpose of this paper is to study the cooperative sensing and allocation algorithm of cognitive RS (radio spectrum) based on artificial intelligence. This dissertation focuses on cooperative perception and cognitive radio systems, respectively, from the aspects of cooperative perception of user fairness, maximization of system energy efficiency, and user detection when user access is busy. Firstly, a joint optimization model of fairness cooperative spectrum sensing and allocation is established to compensate the sensing overhead of cooperative users to ensure its fairness; then, define and analyze the energy efficiency of the cognitive system, and establish a joint optimization model of cooperative spectrum sensing and allocation based on artificial intelligence to maximize energy efficiency, and optimize wireless sensing and allocation parameters while ensuring maximum system energy efficiency. The experimental results show that when = 0.7, the algorithm proposed in this study has reached 100% of the RS perception performance, while the traditional algorithm only has 93%. The algorithm proposed in this paper has greater advantages in perception and distribution performance.