Data Processing Layer Research Articles

Construction Method of a Digital-Twin Simulation System for SCARA Robots Based on Modular Communication.

Due to the high cost of robots, the algorithm testing cost for physical robots is high, and the construction of motion control programs is complex, with low operation fault tolerance. To address this issue, this paper proposes a low-cost, cross-platform SCARA robot digital-twin simulation system based on the concept of digital twins. This method establishes a 5D architecture based on the characteristics of different platforms, classifies data and integrates functions, and designs a data-processing layer for motion trajectory calculation and data storage for a virtual-reality robot. To address the complexity of data interaction under different cross-platform communication forms, an editable, modular, cross-platform communication system is constructed, and various control commands are encapsulated into simple programming statements for easy invocation. Experimental results showed that, based on modular communication control, users can accurately control data communication and synchronous motion between virtual and physical models using simple command statements, reducing the development cost of control algorithms. Meanwhile, the virtual-robot simulation system, as a data mapping of the real experimental platform, accurately simulated the physical robot's operating state and spatial environment. The robot algorithms tested using the virtual simulation system can be successfully applied to real robot platforms, accurately reproducing the operating results of the virtual system.

Improving ramification detection of St. Nicolas House Analysis

The St. Nicolas House Analysis (SNHA) is a new graph estimation method for detection of extensive interactions among variables. It operates by ranking absolute bivariate correlation coefficients in descending order thereby creating hierarchic association chains. The latter characterizes dependence structures of interacting variables which can be visualized in a corresponding network graph as a chain of end-to-end connected edges representing direct relationships between the connected nodes. The important advantage of this relatively new approach is that it produces less false positive edges resulting from indirect or transitive associations than expected with standard correlation or linear model-based approaches. Here we aim to improve the detection of ramifications in graphs by addition of different data processing layers to SNHA. They include the combinations of the extensions R-squared gaining(RSG) and linear model check(LMC). SNHA together with these so-called extensions were benchmarked against default SNHA and other reference methods available for the programming language R. In the end combinations of RSG, LMC and Bootstrapping improve SNHA performance across different network types, albeit at the cost of longer computation time.

Research on autonomous navigation system of greenhouse electric crawler tractor based on LiDAR.

The application of autonomous navigation technology of electric crawler tractors is an important link in the development of intelligent greenhouses. Aiming at the characteristics of enclosed and narrow space and uneven ground potholes in greenhouse planting, to improve the intelligence level of greenhouse electric crawler tractors, this paper develops a navigation system of electric crawler tractors for the greenhouse planting environment based on LiDAR technology. The navigation hardware system consists of five modules: the information perception module, the control module, the communication module, the motion module, and the power module. The software system is composed of three layers: the application layer, the data processing layer, and the execution layer. The developed navigation system uses LiDAR, Inertial Measurement Unit (IMU) and wheel speed sensor to sense the greenhouse environment and the crawler tractor's information, employs the Gmapping algorithm to build the greenhouse environment map, and utilizes the adaptive Monte Carlo positioning algorithm for positioning. The simulation test of different global path planning algorithms in Matlab shows that the A* algorithm obtains the optimal overall global path. In the scene of map 5, the path planned by the A* algorithm is the most significant, and the number of inflection points is reduced by 40.00% and 87.50%, respectively; meanwhile, the path length is the same as that of the Dijkstra algorithm, but the runtime is reduced by 68.87% and 81.49%, respectively; compared with the RRT algorithm, the path length is reduced by 7.27%. Therefore, the A* algorithm and the Dynamic Window Approach (DWA) method are used for tractor navigation and obstacle avoidance, which ensures global path optimality while also achieving effective local path planning for obstacle avoidance. The test results suggest that the maximum lateral deviation of the built map is 6cm, and the maximum longitudinal deviation is 16cm, which meets the requirement of map accuracy. Additionally, the results of the navigation accuracy test indicate that the maximum lateral deviation of navigation is less than 13cm, the average lateral deviation is less than 7cm, and the standard lateral deviation is less than 8cm. The maximum heading deviation is less than 14°, the average heading deviation is less than 7°, and the standard deviation is less than 8°. These results show that the developed navigation system meets the navigation accuracy requirements of electric crawler tractors in the greenhouse environment.

Dynamic trust security approach for edge computing-based mobile IoT devices using artificial intelligence

The Industrial Internet of Things (IIoT) encompasses various applications such as smart cities, healthcare, and agriculture, which rely on a multitude of interconnected devices. These applications demand specific performance requirements, including low latency and sufficient bandwidth. Edge computing has emerged as a promising solution to address the challenges associated with data flow processing. Particularly, in scenarios like smart cities, where a massive number of IIoT devices are deployed, edge computing serves as the primary data processing layer. However, the limited resources of edge computing, compared to cloud computing, pose significant security concerns for IIoT applications. In fact, this paper proposes a novel security system to secure the relation between the IIoT devices and edge computing. Dynamic Trust Security Approach (DTSA) leverages Artificial Intelligence to analyze, evaluate and enhance the security and privacy aspects of the IIoT devices’ interaction with edge computing. DTSA improve the security level of the IIoT system and improve the performance with more than 45% compare to the traditional method.

Enhancing Security in Internet of Things (IoT) Architecture through Defense-in-Depth Mechanism: A Comprehensive Study

The Internet of Things (IoT) has revolutionized various domains, offering connectivity and data sharing among diverse devices and services. However, this interconnectedness poses significant security challenges, primarily centered around confidentiality, integrity, and availability. This paper investigates the security issues embedded in the layers of IoT architecture, ranging from the perception layer to the application layer. By leveraging the Defense-in-Depth security mechanism, we propose a comprehensive approach to fortify IoT systems against cyber threats. The Defense-in-Depth strategy is illustrated through a layered model, addressing security concerns at the perimeter, host, OS/application, and data layers. The study explores various security measures applicable to each layer, emphasizing the need for a multi-faceted approach to ensure the robustness of IoT security. Keywords: Internet of Things (IoT), Security Issues, Defense-in-Depth Mechanism, Perception Layer, Network Layer, Data Processing Layer, Application Layer, Confidentiality, Integrity, Availability

Architecture, application and implementation of a digital twin of the RFID-enabled material flow in real-time for automotive intralogistics

RFID is used in logistics in the automotive industry to automate processes and optimise material flow. However, the data generated by RFID installations during operation offer more potential for further analyses to collect even more benefits from the technology. Therefore, in this paper, RFID data will be used to create a digital twin of the RFID-enabled material flow (DTRMF) in real-time and to programme various big data analyses. The architecture of the DTRMF must meet various qualitative requirements. Since the big data and digital twin architectures available in the literature either do not optimally fulfil all these requirements, or they are not described in enough detail to support real applications, this paper presents a new digital twin architecture for RFID-enabled material flow. This architecture consists of the data ingestion layer, data processing and analyses layer, data storage layer, visualisation layer, and the optional semantic layer. In addition, suitable technologies for the implementation of the architecture are described, and the feasibility of the architecture is demonstrated and verified by means of a case study.

Intermediate data fault-tolerant method of cloud computing accounting service platform supporting cost-benefit analysis

This study mainly aims at the intermediate data fault-tolerant method of cloud computing accounting service platform supporting cost-benefit analysis, which aims at providing cost-benefit analysis function for the platform and strengthening the fault-tolerant ability of the intermediate data of the platform. The invention discloses a method for constructing an enterprise cloud computing accounting service platform. Collect the internal and external accounting service system data of an enterprise by using an accounting service platform network environment provided by a cloud service provider. Transmit the data to a data processing and storage layer data warehouse for storage after data cleaning, extraction and processing. Then, call the collected data through the data processing and storage layer to analyze the transaction cost-benefit of the enterprise. The intermediate data fault-tolerant model is constructed. After being solved by the ant colony algorithm, the intermediate data generated in the process of cost-benefit analysis and other accounting services are fault-tolerant processed. Finally, the platform accounting service results are output to the interactive interface through the data output display layer. The highest data availability probability of the method proposed in this study is 0. 98, which indicates that the method has high data availability after fault-tolerant processing, and can effectively realize the interaction with users. The experimental analysis shows that the method proposed in this study can effectively analyze the transaction costs and benefits of enterprises. The probability of data availability after fault-tolerant processing is higher, and a load of reading and writing is lower.

Video Conference System in Mixed Reality Using a Hololens

The mixed reality conference system proposed in this paper is a robust, real-time video conference application software that makes up for the simple interaction and lack of immersion and realism of traditional video conference, which realizes the entire process of holographic video conference from client to cloud to the client. This paper mainly focuses on designing and implementing a video conference system based on AI segmentation technology and mixed reality. Several mixed reality conference system components are discussed, including data collection, data transmission, processing, and mixed reality presentation. The data layer is mainly used for data collection, integration, and video and audio codecs. The network layer uses Web-RTC to realize peer-to-peer data communication. The data processing layer is the core part of the system, mainly for human video matting and human-computer interaction, which is the key to realizing mixed reality conferences and improving the interactive experience. The presentation layer explicitly includes the login interface of the mixed reality conference system, the presentation of real-time matting of human subjects, and the presentation objects. With the mixed reality conference system, conference participants in different places can see each other in real-time in their mixed reality scene and share presentation content and 3D models based on mixed reality technology to have a more interactive and immersive experience.

IoT solutions for smart farming: A comprehensive review on the current trends, challenges and future prospects for sustainable agricultureIoT solutions for smart farming: A comprehensive review on the current trends, challenges and future prospects for sustainable agriculture

Agriculture is the most resource-intensive human activity. The goal to reduce agricultural input while producing more has been a primary driver of agricultural technology advancement since its inception. With recent advancements in supporting technologies, the usage of Internet-of-things (IoT) has become a trend in farming practice for agriculture management that use information technology to ensure that soil and plants receive their requirements for optimum health and productivity. It could be significant to summarize the trends and challenges of the application of IoT-based solutions in precision agriculture, more specifically smart crop production. Thus, the current review sought to give a complete overview of the use of IoT technology in smart farming. By surveying recent high-quality publications, IoT-based solutions applied to smart farming, with four basic layers, including data collection (perception), data transmission (transport), data processing, and application layers were summarized. The use of IoT solutions allows for resolving several issues in smart farming, such as the optimization of input resources, saving irrigation water, reducing the amount of fertilizer and pesticides, and optimizing energy resources. Accordingly, we discussed some notes about sensors, microcontroller systems, communication methods, and cloud platforms. In particular, a list of low-cost sensors and several typical single-board computers was provided. The IoT communication was discussed to get insight into the essential considerations. Since then, several key points have been noted for further directions of the application of IoT-based solutions for smart farming. Taken together, our mini-review could provide solid information for further construction and development of smart models of farming.

Smart Weather Data Management Based on Artificial Intelligence and Big Data Analytics for Precision Agriculture

Smart management of weather data is an essential step toward implementing sustainability and precision in agriculture. It represents an important input for numerous tasks, such as crop growth, development, yield, and irrigation scheduling, to name a few. Advances in technology allow collecting this weather data from heterogeneous sources with high temporal resolution and at low cost. Generating and using these data in their raw form makes no sense, and therefore implementing adequate infrastructure and tools is necessary. For that purpose, this paper presents a smart weather data management system evaluated using data from a meteorological station installed in our study area covering the period from 2013 to 2020 at a half-hourly scale. The proposed system makes use of state-of-the-art statistical methods, machine learning, and deep learning models to derive actionable insights from these raw data. The general architecture is made up of four layers: data acquisition, data storage, data processing, and application layers. The data sources include real-time sensors, IoT devices, reanalysis data, and raw files. The data are then checked for errors and missing values using a proposed method based on ERA5-Land reanalysis data and deep learning. The resulting coefficient of determination (R2) and Root Mean Squared Error (RMSE) for this method were 0.96 and 0.04, respectively, for the scaled air temperature estimate. The MongoDB NoSQL database is used for storage thanks to its ability to deal with real-world big data. The system offers various services such as (i) weather time series forecasts, (ii) visualization and analysis of meteorological data, and (iii) the use of machine learning to estimate the reference evapotranspiration (ET0) needed for efficient irrigation. To this, the platform uses the XGBoost model to achieve the precision of the Penman–Monteith method while using a limited number of meteorological variables (air temperature and global solar radiation). Results for this approach give R2 = 0.97 and RMSE = 0.07. This system represents the first incremental step toward implementing smart and sustainable agriculture in Morocco.

Design of intelligent operation inspection platform based on the multi-agent system for live line measurement of substation

At present, substations are developing vigorously in an intelligent direction. In this paper, an intelligent operation inspection platform based on a multi-agent system is designed. The platform’s design includes the design of its physical architecture and its operation architecture. The physical architecture of the platform includes a substation main control server, fixed live line measurement device, intelligent operation inspection software, intelligent data centralization device, intelligent interface conversion device, wireless communication channel, etc. In terms of platform operation architecture, an operation framework based on a multi-agent system is designed, including the “environment” layer, data sensing layer, data processing layer, and analysis and decision layer, and the whole platform is built based on the concept of edge computing. To solve the task allocation problem of edge computing, a Markov decision model is designed to minimize time consumption and maximize resource utilization, and the deep Q network (DQN) algorithm is used to solve the problem. The design aims at being effective, practical, safe, compatible, easy to upgrade, and extensible, and builds an intelligent operation inspection platform for live line measurement of substation equipment based on a multi-agent system, to improve the intelligent automation level of substation operation inspection.

Collaborative Damage Detection Framework for Rail Structures Based on a Multi-Agent System Embedded with Soft Multi-Functional Sensors.

With the rapid growth of railways in China, the focus has changed to the maintenance of large-scale rail structures. Multi-agent systems (MASs) based on wireless sensor network (WSNs) with soft multi-functional sensors (SMFS) are adopted cooperatively for the structural health monitoring of large-scale rail structures. An MAS framework with three layers, namely the sensing data acquisition layer, sensor data processing layer, and application layer, is built here for collaborative data collection and processing for a rail structure. WSN nodes with strain, temperature, and piezoelectric sensor units are developed for the continuous structural health monitoring of the rail structure. The feature data at different levels are extracted for the online monitoring of the rail structure. Experiments carried out at the Rail Transmit Base at East China Jiaotong University verify that the WSN nodes with SMFS are successfully assembled onto a 100-m-long track for damage detection. Based on the sensing data and feature data, a neural network data fusion agent (DFA) is applied to calculate the damage index value of the track for comprehensive decisions regarding rail damage. The use of WSNs with multi-functional sensors and intelligent algorithms is recommended for cooperative structural health monitoring in railways.

KFIML: Kubernetes-Based Fog Computing IoT Platform for Online Machine Learning

The massive onsite data produced by the Internet of Things (IoT) can bring valuable information and immense potentials, thus empowering a new wave of emerging applications. However, with the rapid increase of onsite IoT data streams, it has become extremely challenging to develop a scalable computing platform and provide a comprehensive workflow for processing IoT data streams with lower latency and more intelligence. To this end, we present a Kubernetes-based scalable fog computing platform (KFIML), integrating big data streaming processing with machine learning (ML)-based applications. We also provide a comprehensive IoT data processing workflow, including data access and transfer, big data processing, online ML, long-term storage, and monitoring. The platform is feasibly validated on a clustered testbed, which comprises a master node, IoT broker servers, worker nodes, and a local database server. By leveraging the lightweight orchestration system, namely Kubernetes, we can readily scale and manage containerized software frameworks on our testbed. The big data processing layer utilizes the advanced data flow frameworks such as Apache Flink, to support both streaming processing and statistical analysis with low latency. In addition, the specified long short-term memory (LSTM)-based ML pipelines are employed on the online ML layer, to enable the real-time predictive analysis of IoT data streams. The experiments on a real-world smart grid use case demonstrate that the container-based KFIML platform can be well-scaled with Kubernetes to efficiently perform big data processing increased onsite IoT data streams with lower latency and conduct ML-based applications.

Artificial intelligence technology in electronic communication engineering for medical applications

In order to solve the problem of high frame error rate in electronic communication engineering, the application of artificial intelligence technology in electronic communication engineering is proposed. Taking LPWAN technology in artificial intelligence technology as an example, a new architecture is proposed to improve the security of wireless communication system of internet of things. The architecture is mainly composed of business layer, data processing layer, terminal access layer and communication technology layer. The experimental results show that the system configuration sends four kinds of information transmission instructions of “temperature, light, air pressure and humidity” every 30 s, and the receiving port collects the above command data continuously for 4 h, compared with the traditional architecture (15.6%), and the packet loss rate is 4%, which can effectively improve the throughput and processing efficiency of the system. The designed architecture runs stably, has low bit error rate, and can better support the wireless communication. It is proved that the new architecture with LPWAN technology as an example has large overall capacity and excellent performance of its electronic communication engineering interface. The frame number error rate is greatly reduced and the result of signal frame number is more accurate.

Energy efficient IoT‐based informative analysis for edge computing environment

AbstractInternet of Things (IoT) is an intelligent technology that interconnection of everything at any time over an edge computing network. Because of pervasiveness and ubiquity, IoT technology is exhausting energy resources over edge computing platforms. As a result, IoT energy efficiency has become a prominent research domain. Conspicuously, an energy‐efficient IoT framework for the edge computing paradigm has been proposed in the present research. Specifically, the proposed framework comprises three layers including perception and control layer, data processing layer, and application and visualization layer. The presented framework predicts inactive sensor intervals based on respective battery percentage, historical utility, and data accuracy needed for edge‐based service delivery. Specifically, when the sensing nodes are in inactivity mode, the predicted value increases edge resource usage by re‐provisioning the allotted resources. Moreover, the presented technique enables energy‐efficient utilization of IoT resources. For validation purposes, the performance comparison is performed with state‐of‐the‐art techniques. It shows that the presented framework is significantly enhanced in terms of energy consumption efficacy (30.45 mJ/K nodes), packet loss ratio (0.51%), statistical performance, and system stability (84.69%).

Research on Multi-party Data Secure Interaction Technology for Energy Internet

Aiming at the problems of the energy Internet interaction process, which involves more users and intermediate links, and each participant is independent of each other, information asymmetry, and participants do not trust each other, this paper proposes a blockchain-based energy Internet multiparty data interaction model to build a data circulation architecture, including four layers, which are data sensing layer, network transmission layer, data processing layer and application service layer, to realize identity association, cross-domain access, It can realize the basic functions such as identity association, cross-domain access, trust evaluation and privacy protection, and effectively guarantee the secure interaction of multi-party data in the energy Internet.

KMFA2 based QoS improvement for multi‐channel IoT networks

AbstractInternet of Things (IoT) networks are designed to obtain the best possible end‐user experience. This experience is measured in terms of security and speed of operation. In order to achieve high security, encryption, and authentication algorithms are proposed by researchers. The speed of operation is generally measured using the network's response time, and it can be improved using light‐weighted algorithms for data processing and actuation. Most of these techniques are applied at the application level, making the network ineffective in its originally deployed form. Moreover, due to the addition of security and data processing layers, the overall IoT network's QoS reduces, reducing the end user's experience. In order to remove these issues, this work proposes a novel kernel‐level multi‐channel fuzzy‐authentication and aggregation framework (KMFA2). The KMFA2 framework can solve authentication issues by using a kernel‐level lightweight and secure authentication protocol for all IoT devices. KMFA2 also enables the IoT devices to possess multi‐channel capabilities, with inbuilt aggregation capabilities. The overall implementation is carried out on the NS2 tool. The proposed KMFA2 protocol is tested on different IoT networks, and it is observed that the protocol improves the QoS by almost 10% and simplifies security using the authentication framework. The comparisons were performed with state‐of‐the‐art IoT deployments.

Ecosphere Management Model of Farmer Cooperatives Based on Intelligent Data Sampling Technology.

In order to improve the operation effect of farmer cooperatives, this paper combines the intelligent data sampling technology to analyze the ecological circle operation mode of farmer cooperatives. Moreover, this paper strives to promote the ecosphere business model, accelerate regional development, build agricultural pastoral complex projects and in-depth study TI-ADC modeling, error estimation, mismatch compensation, and other technologies, and carry out engineering realization. In addition, this paper uses technology to analyze intelligent data and builds a system structure based on the actual needs of the farmer cooperative ecosphere management. Finally, this paper analyzes the structure and flow of the data processing layer. The test results show that the ecosystem business model of farmer cooperatives based on intelligent data sampling technology proposed in this paper has good results.

Predicting Airline Additional Services Consumption Willingness Based on High-Dimensional Incomplete Data

Prediction of the purchase willingness of passengers has great benefits for airlines to promote auxiliary services, however, the datasets stored in passenger travel information systems are often high-dimensional and incomplete. This study develops a prediction method of airline additional service consumption willingness based on high-dimensional and incomplete datasets with a triple-layer hybrid PSO-XGBoost model, which consists of an incomplete data processing layer, a high-dimensional data processing layer, and a predicting layer. The raw dataset is converted into a complete and low-dimensional dataset through the first two layers and inputted into the predicting layer to train and optimize the XGBoost model together with the PSO algorithm and 10-fold cross-validation. The experimental results show that the proposed method outperforms other traditional machine learning models, presenting the highest prediction score with 0.9879 in terms of AUC. The findings help predict airline additional services consumption intentions of passengers and are beneficial to efficient and low-cost precise marketing for airlines.

Importance of Memory Management Layer in Big Data Architecture

The generation of daily massive amounts of heterogeneous data from a variety of sources presents a challenge in terms of storage and analysis capabilities and brings new problems into high-performance computing clusters. To better utilize this huge and heterogeneous data, the continuous development of advanced Big Data platforms and Big Data analytic techniques are required. One of the significant issues with in-memory Big Data processing platforms, such as Apache Spark, is the user’s responsibility to decide whether the intermediate data should be cached or not. In addition, the data may be kept in several storage systems and physically scattered over different racks, regions, and clouds. Data need to be close to the computation nodes and hence data locality issue is a challenge. In this paper, using a distinct memory management layer between the data processing layer and the data storage layer, which automatically caches data without the need for any interaction from the applications’ developers, is evaluated. K-means, PageRank and WordCount workloads from the HiBench benchmark beside a real case to predict the price of Real Estate that is implemented using Gradient Boosting Regression Tree model, are used to evaluate this framework. Experiments show that the memory management layer outperforms the Apache Spark in reducing the execution time.