Recent Advances in Computer Science and Communications - Volume 15, Issue 9, 2022

Mission planning is an integral process that enables earth observation missions and defines their success rate. This paper identifies key problems and opportunities in machine learning for earth observation satellite mission planning. Firstly, the description elements, classification methods, solution process and solution difficulties of the mission planning problem of earth observation satellite are described. Secondly, the current research status of machine learning for the earth observation satellite mission planning is summarized and analyzed. Finally, the problems of current research are analyzed, and the prospect of new field research is given in light of the development needs.

Background & Objectives: The global power system is in a state of continuous evolution, incorporating more and more renewable energy systems. The converter-based systems are void of inherent inertia control behavior and are unable to curb minor frequency deviations. The traditional power system, on the other hand, is made up of synchronous generators that have their inertia and governor response for frequency control. For improved inertial and primary frequency response, the existing frequency control methods need to be modified and an additional power reserve is to be maintained mandatorily for this purpose. Energy self-sufficient renewable distributed generator systems can be made possible through optimum active power control techniques. Also, when major global blackouts were analyzed for causes, solutions, and precautions, load shedding techniques were found to be a useful tool to prevent frequency collapse due to power imbalances. The pre-existing load shedding techniques were designed for traditional power systems and were tuned to eliminate low inertia generators as the first step to system stability restoration. To incorporate emerging energy possibilities, the changes in the mixed power system must be addressed and new frequency control capabilities of these systems must be researched. Discussion: In this paper, the power reserve control schemes that enable frequency regulation in the widely incorporated solar photovoltaic and wind turbine generating systems are discussed. Techniques for Under Frequency Load Shedding (UFLS) that can be effectively implemented in renewable energy enabled micro-grid environment for frequency regulation are also briefly discussed. The paper intends to study frequency control schemes and technologies that promote the development of self- sustaining micro-grids. Conclusion: The area of renewable energy research is fast emerging with immense scope for future developments. The comprehensive literature study confirms the possibilities of frequency and inertia response enhancement through optimum energy conservation and control of distributed energy systems.

Background: The smart grid communication network is constructed with three tiers, namely, Home Area Networks (HANs), Neighborhood Area Networks (NANs) and Wide Area Networks (WANs). These networks function with various communication protocols like table protocol, on-demand protocol, Wi-Fi, Zigbee, Z-Wave, Wi-MAX, GSM, LTE, Cognitive Radio Networks. The network interconnection is heterogonous and all appliances have to communicate through the IP gateways. A large amount of data is collected from various sensors placed in different locations. The analytics on “big data” is essential because these data are used to organize and plan an efficient control and management of the smart home, including secured data exchange in different sectors. Objective: This paper investigates broadly data rate, channel bandwidth, power consumption, and a coverage range of wired and wireless communication technologies used in residential buildings. A literature survey on optimization algorithms with various constraints to manage home appliances through scheduling is included. The paper also discusses the communication standards along with security and privacy requirements for smart metering networks. Conclusion: Investigation of IEEE standards for both wired and wireless communication protocols provide a reference in identifying an appropriate communication technique through a mathematical model for computing the communication channel bandwidth. A comparison of various optimization algorithms with multiple HEMS constraints has been made to achieve the minimum electricity cost and user comfort (with and without Renewable Energy Sources). As a result, the wireless communication protocols (Zig-Bee & Wi-Fi) are preferred mostly because of their reliability and low cost of use in HAN on both wired and wireless networks. Zigbee is the most appropriate technology used for data transmission between individual appliances and smart meters. Wi-Fi is a suitable technology for controlling and monitoring appliances because of its high data rate.

Background: Trajectory planning is important to research in robotics. As the application environment changes rapidly, robot trajectory planning in a static environment can no longer meet actual needs. Therefore, a lot of research has turned to robot trajectory planning in a dynamic environment. Objective: This paper aims at providing references for researchers from related fields by reviewing recent advances in robot trajectory planning in a dynamic environment. Methods: This paper reviews the latest patents and current representative articles related to robot trajectory planning in a dynamic environment and introduces some key methods of references from the aspects of algorithm, innovation and principle. Results: In this paper, we classified the researches related to robot trajectory planning in a dynamic environment in the last 10 years, introduced and analyzed the advantages of different algorithms in these patents and articles, and the future developments and potential problems in this field are discussed. Conclusion: Trajectory planning in a dynamic environment can help robots to accomplish tasks in a complex environment, improving robots’ intelligence, work efficiency and adaptability to the environment. Current research focuses on dynamic obstacle avoidance, parameter optimization, real-time planning, and efficient work, which can be used to solve robot trajectory planning in a dynamic environment. In terms of the combination of multiple algorithms, multisensor information fusion, the combination of local planning and global planning, and multirobot and multi-task collaboration, more improvements and innovations are needed. It should create more patents on robot trajectory planning in a dynamic environment.

The ground space optical observation system considered as one of the main measurement methods to observe space object in Medium Earth Orbit (MEO), Highly Elliptical Orbit (HEO) and Geostationary Orbit (GEO) faces difficulties in forming high-solution images for objects located in GEO that only appears several light spots with limited pixels due to the impacts of observing distance, resolution ratio, and other atmospheric conditions. The light curve is the time history of an object’s observed brightness obtained from the ground-based optical observation system through light curves, right ascension, and declination of space objects. The characteristic of space objects such as position, velocity, size, shape, and material can be inverted. This paper has analyzed the principles, applications, merits, and demerits of several non-linear filtering methods in detail. Besides, the scientific description of inversion for characteristics of a non-resolved space object from ground photometric measurements and the essence of the non-linear filtering inversion method has also been clarified. A selection principle of the non-linear filtering inversion method for different space object characteristics is then proposed, and the developing direction of such inversion methods is also described in the end.

Background: The mobile robot navigation technology includes two key issues: the localization and the path planning, of which the localization is the most basic part of mobile robot navigation, because the target point is meaningful only when mobile robot's pose is clarified, and path planning can be done on this basis. Therefore, it is of great significance to have a good localization method for mobile robots. Objective: This study aimed to summarize the existing localization methods in mobile robot navigation technology and introduce their classifications, characteristics, as well as the stage and trends of development. Methods: A retrospective review of various patents and literature related to localization methods in mobile robot navigation technology was performed. The characteristics, differences, and applications of different localization methods were also introduced. Results: The existing localization methods were analyzed and compared, and their typical characteristics are summarized. The main applications, as well as the pros and cons in the current development stage, were summarized and analyzed. In addition, the development trend of patents related to positioning methods is also discussed. Conclusion: This paper summarized three localization methods and provided numerous cases. It can be seen that most of the existing localization methods are dedicated to improving the positioning accuracy and efficiency of mobile robots, while there is less research on the robustness of mobile robot localization, which is not conducive to the research on robots with the unknown working environment and long moving distances. Therefore, related research patents and documents should be proposed. Current and future development trends are also looking forward.

Objective: In recent years, with the large-scale construction of large venues, high-rise office buildings, residential quarters, and the development of networked UAV, the demand and complaints of users for air network coverage are increasing. The existing road test instruments are designed for ground coverage based on the mobile app and PC software, which is not suitable for low altitude signals. In order to shorten the test cycle of low altitude network signal and improve the test efficiency, a new low altitude network signal test method is proposed, and a test system suitable for low altitude network signal coverage and quality detection is developed. Methods: The present study investigated a system that uses airborne measuring instrument to complete data acquisition, and returns real-time data to the processing cloud platform through 5g cellular network. The signal quality and capacity of low altitude network are detected on the cloud platform. Results: The test results show that the proposed method and the developed airborne measuring instrument can complete the low altitude network signal test work and effectively improve the test efficiency. Conclusion: The research on test method for low altitude wireless network signal plays an important role in the optimization of low altitude network and fine management of tower base station information.

Background: Localization is an important area of implementation of the internet of things based on Wireless Sensor Networks. Outdoor user tracking is possible using the global positioning system; however, the global positioning system accuracy decreases in indoor environments. To overcome this problem, the wireless sensor network is used in internet of things-based technology for localization. Objective: The wireless sensor network-based indoor localization is categorized into two categories; rangebased and range-free localization. In range-based localization, it first computes the relative distance and then calculates relative coordinates. In range-based techniques, distance and position are calculated. The internet of things-based localization uses the range-based and range-free techniques of a wireless sensor network to localize any object. The Light Dependent Resistor-based localization work has been proposed in previous research. In this research, the light-dependent resistor traces a person’s entry /exit event as the person switches ON/OFF lights of the building. However, it was not a sufficient effort to localize a person using light dependent resistor. To overcome the problem of light dependent resistor, the two PIR sensors have been used in each room along with one RFID based approach in this study. Methods: An indoor scenario has been considered in this study. The hardware setup has been configured to trace the user. When a user enters inside a building, he will switch on the lights, and the light sensor records the light intensity and gives some reading. The difference in the reading of the light sensor (before switching ON the light and after switching OFF the light) gives some clue about a user in an indoor scenario. Nevertheless, if the lights of many rooms remain switched ON, then the user cannot be localized using the above method. In order to sort out this ambiguity of light sensors, two passive infrared sensors in each room along with one radio frequency identification-based model have been proposed in the present study. Implementing the single-user localization using a light-dependent resistor sensor becomes erroneous if a person moves from one room to another and the lights get turned ON/OFF. Moreover, the LDR-based model is affected by sunlight during the daytime. Results: As the implementation of passive infrared sensors along with one RFID-based localization technique gives 93% efficiency, the light-dependent resistor-based localization system gives an efficiency of 35%. Conclusion: The light-dependent resistor-based approach is prone to more errors because the user may enter multiple rooms while the lights of each room remain ON. To overcome this problem, a passive infrared sensor and radio frequency identification-based approach for a single user indoor localization has been proposed. The proposed techniques are easy and cost-effective for implementation. The results show that the proposed technique provides better localization accuracy than a light-dependent sensor-based technique for single-user indoor localization.

Background: With the development of network technology and the continuous increase in user-generated content on the Internet, the protection of digital copyright is particularly important. Objective: In order to better protect the copyright of digital works, this paper proposes a Polkadot scheme based on the advantages of blockchain cross-chain technology. Methods: The scheme sets up three parallel chains, including digital work chain, copyright management chain, and dispute arbitration chain, and shows the information interaction process of Validators, Fishermen, Collators, and Nominators. Results: The research shows that the scheme has more advantages than a single chain or alliance chain. It has a shorter block creation time, better security, and availability. Conclusion: The findings provide new ideas for copyright registration, copyright trading, and infringement maintenance of digital works and also broadens the application of cross-chain technology of blockchain.

Background: Energy conservation has always been a major issue in our country, and the air conditioning energy consumption of buildings accounts for the majority of the energy consumption of buildings. If the building load can be predicted and the air conditioning equipment can respond in advance, it can not only save energy but also extend the life of the equipment. Introduction: The neural network proposed in this paper can deeply analyze the load characteristics through three gate structures, which helps improving the prediction accuracy. Combined with the grey relational degree method, the prediction speed can be accelerated. Method: This paper introduces a grey relational degree method to analyze the factors related to air conditioning load and selects the best ones. A Long Short-Term Memory Neural Network (LSTMNN) prediction model was established. In this paper, grey relational analysis and LSTMNN are combined to predict the air conditioning load of an office building, and the predicted results are compared with the real values. Results: Compared with the Back Propagation Neural Network (BPNN) prediction model and Support Vector Machine (SVM) prediction model, the simulation results show that this method has a better effect on air conditioning load prediction. Conclusion: Grey relational degree analysis can extract the main factors from the numerous data, which is more convenient and quicker without repeated trial and error. LSTMNN prediction model not only considers the relation of air conditioning load on time series but also considers the nonlinear relation between load and other factors. This model has higher prediction accuracy, shorter prediction time, and great application potential.

Background: Detecting occluded objects in images remains a challenging problem since the occluded objects often occlude each other or are occluded by other objects. It is hard to identify the occluded objects in an image, especially when the occlusion is significant. Methods: In this work, a two-stage object detection method has been proposed. The proposed method is based on the Faster RCNN model and uses ResNet50 as the backbone network. In addition, the method uses the feature pyramid network to reuse the higher-resolution maps of the feature hierarchy. The dilated convolution in the architecture of the proposed network has been added to expand the receptive field of the feature maps and the loss function and gradient learning rate are optimized. Results: The proposed detector is trained in an end-to-end fashion, which achieves state-of-theart results on two datasets, i.e., MAFA and WIDER FACE, particularly for WIDER FACE (with the highest mAP, 66.4%). Conclusion: In conclusion, by adding dilated convolution and optimizing gradient learning rate to the object detection model, the precision of the occlusion object detection can be improved effectively.

Background: With the development of the Internet of things, WSN node positioning is particularly important as its core technology. One of the most widely used algorithms, the DV-hop algorithm, has many advantages, such as convenient operation, use of no additional equipment, etc. At the same time, it also has some disadvantages, like large location error and insufficient robustness. Particle swarm optimization algorithm is advantageous in dealing with nonlinear optimization problems. Therefore, the improved particle swarm optimization algorithm is introduced to solve the problem of inaccurate positioning. Objective: Aiming at the problem of large positioning error in the three-dimensional node localization algorithm, the paper proposes an intelligent node localization algorithm based on hop distance adjustment. The algorithm is used to optimize the hop number of nodes and make the distance calculation more accurate. At the same time, particle swarm optimization is used to intelligently solve the problem of choosing the most valuable node position. Methods: Firstly, this paper analyzed the errors caused by the 3D DV-hop localization algorithms. Then, a new method of distance estimation and coordinate calculation is provided. At the same time, mutation factors and learning factor based on the particle swarm optimization algorithm are introduced. Then, a three-dimensional node localization algorithm based on ranging error correction and particle swarm optimization algorithm is proposed. Finally, the improved algorithm is simulated and compared with similar algorithms. The simulation results show that the proposed algorithm has good convergence and improves the positioning accuracy without additional hardware conditions, and effectively solves the problem of inaccurate node positioning. Results: The proposed algorithm creatively combines the hop number correction and particle swarm optimization algorithm to improve the accuracy of node positioning and robustness. However#140;the amount of computation is increased. Conclusion: Overall, it is within acceptable limits. It is worthwhile to improve the performance with a little increase in the amount of computation. The algorithm is worth popularizing.

Objective: With the development of Internet finance, the scale of peer-to-peer (P2P) online lending platforms have rapidly expanded. Additionally, the phenomenon of losses among online lending platforms and the problem of default by borrowers have emerged, greatly restricting the healthy development of online lending platforms. Therefore, it is necessary to dynamically set the credit rating of the borrowers according to the performance of the borrowers, and establish a default risk evaluation model for the borrowers of the online lending platform to promote the healthy development of the online lending platform. Methods: This paper uses web crawler technology to obtain borrower information as the sample data, selects 17 core variables as explanatory variables, and utilizes project status as the target variable. First, according to the performance of the borrower, we use K-means to cluster, obtain a dynamic credit rating by calculation and reset the rating to obtain new borrower information. Second, we determine the optimal parameters of the support vector machine algorithm through cross-validation and establish the best evaluation model for online loan borrowers' default risk. Finally, we conduct experimental verification. Results: The classification accuracy of the proposed algorithm is better than that of decision trees and random forest, and the classification effect is the strongest. Conclusion: The experimental results show that the model has good stability and generalizability, and the research results provide dynamic decision support for early warnings of online lending platform risk and risk prevention and control; they can thus help promote the healthy development of online lending platforms.