Research

19 pages, 18668 KiB

Open AccessArticle

A Post-Evaluation System for Smart Grids Based on Microservice Framework and Big Data Analysis

by Jie Wang, Ruiqi Ouyang, Wu Wen, Xin Wan, Wei Wang, Amr Tolba and Xingguo Zhang

Electronics 2023, 12(7), 1647; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics12071647 - 30 Mar 2023

Cited by 1 | Viewed by 1128

Wind energy, as a clean energy source, has been experiencing rapid development in recent years. However, there is often a significant difference between the designed electricity generation capacity and the actual electricity generation capacity during the construction of wind farms, making it difficult [...] Read more.

Wind energy, as a clean energy source, has been experiencing rapid development in recent years. However, there is often a significant difference between the designed electricity generation capacity and the actual electricity generation capacity during the construction of wind farms, making it difficult to assess the economic benefits of wind farms. Therefore, the development post-evaluation technology is required to support the renovation of old wind farms. In addition, traditional data analysis techniques are unable to handle and analyze massive data in a timely manner. Therefore, big data technology must be developed to improve processing efficiency. To address these issues and meet actual business needs, this paper designs an intelligent grid electricity generation post-evaluation platform for wind farms based on a microservice framework and big data analysis technology. The platform evaluates the operating status of wind farms by analyzing their operational and design data and visualizes relevant big data information. It provides technical support and improvement solutions for wind farm renovation and new wind farm construction. The platform has been tested and proven to meet the requirements for processing and analyzing massive data, post-evaluating electricity generation, and visualization. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

21 pages, 2247 KiB

Open AccessArticle

HIT-GCN: Spatial-Temporal Graph Convolutional Network Embedded with Heterogeneous Information of Road Network for Traffic Forecasting

by Haitao Xiong, Guojiang Shen, Xiang Lan, Haopeng Yuan and Xiangjie Kong

Electronics 2023, 12(6), 1306; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics12061306 - 09 Mar 2023

Cited by 2 | Viewed by 1487

Abstract

In road networks, attribute information carried by road segment nodes, such as weather and points of interest (POI), exhibit strong heterogeneity and often involve one-to-many or many-to-one relationships. However, research on such heterogeneity in traffic prediction is relatively limited. Our research examines how [...] Read more.

In road networks, attribute information carried by road segment nodes, such as weather and points of interest (POI), exhibit strong heterogeneity and often involve one-to-many or many-to-one relationships. However, research on such heterogeneity in traffic prediction is relatively limited. Our research examines how varying the network propagation pattern based on the degree of node-to-node heterogeneity of information affects the model prediction performance. Specifically, at the node level, we use knowledge embedding to generate knowledge vectors that quantify the heterogeneity among the attribute information of a node. At the road network level, we calculate a homogeneity adjacency matrix that captures both the topological structure of the road network and the similarity of node heterogeneity. This adjacency matrix assigns different weights to neighbors based on their homogeneity, guiding the propagation of graph convolutional networks (GCN). Finally, we separate the representation of propagation into self-representation and neighbor representation to extract multi-attribute information, including self, homogeneity, and heterogeneity. Experiments on real datasets demonstrate that the incorporation of our homogeneity adjacency matrix leads to a significant improvement in the accuracy of short-term and long-term prediction compared with previous work on homogeneous and single-dimensional information. Furthermore, our approach maintains its performance advantage over baseline models under different embedding dimensions and parameter settings. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

30 pages, 54337 KiB

Open AccessArticle

Reliable Data Transmission in Underwater Wireless Sensor Networks Using a Cluster-Based Routing Protocol Endorsed by Member Nodes

by Kaveripakam Sathish, Monia Hamdi, Ravikumar Chinthaginjala, Giovanni Pau, Amel Ksibi, Rajesh Anbazhagan, Mohamed Abbas and Mohammed Usman

Electronics 2023, 12(6), 1287; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics12061287 - 08 Mar 2023

Cited by 17 | Viewed by 2148

Abstract

Considering Underwater Wireless Sensor Networks (UWSNs) have limited power resources (low bandwidth, long propagation delays, and non-rechargeable batteries), it is critical that they develop solutions to reduce power usage. Clustering is one solution because it not only saves energy consumption but also improves [...] Read more.

Considering Underwater Wireless Sensor Networks (UWSNs) have limited power resources (low bandwidth, long propagation delays, and non-rechargeable batteries), it is critical that they develop solutions to reduce power usage. Clustering is one solution because it not only saves energy consumption but also improves scalability and data integrity. The design of UWSNs is vital to the development of clustering algorithms. The limited energy of sensor nodes, narrow transmission bandwidth, and unpredictable topology of mobile Underwater Acoustic Wireless Sensor Networks (UAWSNs) make it challenging to build an effective and dependable underwater communication network. Despite its success in data dependability, the acoustic underwater communication channel consumes the greatest energy at a node. Recharging and replacing a submerged node’s battery could be prohibitively expensive. We propose a network architecture called Member Nodes Supported Cluster-Based Routing Protocol (MNS-CBRP) to achieve consistent information transfer speeds by using the network’s member nodes. As a result, we use clusters, which are produced by dividing the network’s space into many minute circular sections. Following that, a Cluster Head (CH) node is chosen for each circle. Despite the fact that the source nodes are randomly spread, all of the cluster heads are linked to the circle’s focal point. It is the responsibility of the MNS-CBRP source nodes to communicate the discovered information to the CH. The discovered data will then be sent to the CH that follows it, and so on, until all data packets have been transferred to the surface sinks. We tested our techniques thoroughly using QualNet Simulator to determine their viability. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

18 pages, 1325 KiB

Open AccessArticle

A Big Data Platform for International Academic Conferences Based on Microservice Framework

by Biao Yang, He Liu, Xuanrui Xiong, Shuaiqi Zhu, Amr Tolba and Xingguo Zhang

Electronics 2023, 12(5), 1182; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics12051182 - 01 Mar 2023

Viewed by 1534

Abstract

In the era of the information explosion, big data are always around us. Academic big data are defined as a large amount of data generated in the life cycle of all academic activities, which usually contains a large amount of academic information. Academic [...] Read more.

In the era of the information explosion, big data are always around us. Academic big data are defined as a large amount of data generated in the life cycle of all academic activities, which usually contains a large amount of academic information. Academic conferences can effectively promote academic exchanges among scholars. In recent years, academic conferences in various fields have been held around the world. However, with the increase in the number of academic conferences, the quality of conferences and the efficiency of hosting and participating in conferences are uneven. In today’s fast-paced life, high-quality and efficient academic conferences have become the first choice of scholars. In this paper, a conference recommendation method based on a big data analysis of users’ interests and preferences is proposed to help users choose high-quality academic conferences and to help organizers reduce conference costs and improve the conference operation efficiency. The method first divides the research fields of user-related academic conferences into three categories: the fields that users are interested in, the fields that users attend, and the research fields that users follow up. Then, the weights of these three categories are set, and the importance of each category recommendation related to the user is calculated. Finally, the conference recommendation index is calculated and several conferences with a high recommendation value are recommended to users. The experimental results show that the proposed conference recommendation method provides a convenient and fast service to conference participants and conference organizers. The developed big data platform can significantly improve the operation and participation efficiency of academic conferences, reduce the costs, and give full play to the role and value of academic conferences. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

11 pages, 2216 KiB

Open AccessArticle

Dense Vehicle Counting Estimation via a Synergism Attention Network

by Yiting Jin, Jie Wu, Wanliang Wang, Yibin Wang, Xi Yang and Jianwei Zheng

Electronics 2022, 11(22), 3792; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics11223792 - 18 Nov 2022

Cited by 2 | Viewed by 1134

Abstract

Along with rising traffic jams, accurate counting of vehicles in surveillance images is becoming increasingly difficult. Current counting methods based on density maps have achieved tremendous improvement due to the prosperity of convolution neural networks. However, as highly overlapping and sophisticated large-scale variation [...] Read more.

Along with rising traffic jams, accurate counting of vehicles in surveillance images is becoming increasingly difficult. Current counting methods based on density maps have achieved tremendous improvement due to the prosperity of convolution neural networks. However, as highly overlapping and sophisticated large-scale variation phenomena often appear within dense images, neither traditional CNN methods nor fixed-size self-attention transformer methods can implement exquisite counting. To relieve these issues, in this paper, we propose a novel vehicle counting approach, namely the synergism attention network (SAN), by unifying the benefits of transformers and convolutions to perform dense counting assignments effectively. Specifically, a pyramid framework is designed to adaptively utilize the multi-level features for better fitting in counting tasks. In addition, a synergism transformer (SyT) block is customized, where a dual-transformer structure is equipped to capture global attention and location-aware information. Finally, a Location Attention Cumulation (LAC) module is also presented to explore the more efficient and meaningful weighting regions. Extensive experiments demonstrate that our model is very competitive and reached new state-of-the-art performance on TRANCOS datasets. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

9 pages, 2690 KiB

Open AccessArticle

A Generative Learning Steganalysis Network against the Problem of Training-Images-Shortage

by Han Zhang, Zhihua Song, Qinghua Xing, Boyu Feng and Xiangyang Lin

Electronics 2022, 11(20), 3331; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics11203331 - 16 Oct 2022

Cited by 2 | Viewed by 1253

Abstract

In recent years, several steganalysis neural networks have been proposed and achieved satisfactory performances. However, these deep learning methods all encounter the problem of Training-Images-Shortage (TIS). In most cases, it is difficult for steganalyses to obtain enough signals about steganography from a game [...] Read more.

In recent years, several steganalysis neural networks have been proposed and achieved satisfactory performances. However, these deep learning methods all encounter the problem of Training-Images-Shortage (TIS). In most cases, it is difficult for steganalyses to obtain enough signals about steganography from a game opponent. In order to solve the problem of TIS for steganalysis, we propose a novel steganalysis method based on generative learning and deep residual convolutional neural networks. Comparative experiments show that the proposed architecture can achieve promising performance in response to spatial domain steganalysis despite a lack of training images. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

22 pages, 3312 KiB

Open AccessArticle

Behavior Analysis Using Enhanced Fuzzy Clustering and Deep Learning

by Arwa A. Altameem and Alaaeldin M. Hafez

Electronics 2022, 11(19), 3172; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics11193172 - 02 Oct 2022

Cited by 3 | Viewed by 1866

Abstract

Companies aim to offer customized treatments, intelligent care, and a seamless experience to their customers. Interactions between a company and its customers largely depend on the company’s ability to learn, understand, and predict customer behaviors. Customer behavior prediction is a pivotal factor in [...] Read more.

Companies aim to offer customized treatments, intelligent care, and a seamless experience to their customers. Interactions between a company and its customers largely depend on the company’s ability to learn, understand, and predict customer behaviors. Customer behavior prediction is a pivotal factor in improving a company’s quality of services and thus its growth. Different machine learning techniques have been applied to gather customer data to predict behavioral patterns. Traditional methods are unable to discover hidden patterns in ideal situations and need to be improved to produce more accurate predictions. This work proposes a novel hybrid model comprised of two modules: a novel clustering module on the basis of an optimized fuzzy deep belief network and a customer behavior prediction module on the basis of a deep recurrent neural network. Customers’ previous purchasing characteristics and portfolio details were analyzed by applying learning parameters. In this paper, the deep learning techniques were optimized by applying the butterfly optimization method, which minimizes the maximum error classification problem. The performance of the system was evaluated using experimental analysis. The proposed approach was compared to other single and hybrid-model-based approaches and attained the highest performance in the respective metrics. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

16 pages, 4529 KiB

Open AccessArticle

Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting

by Zhi Liu, Jixin Bian, Deju Zhang, Yang Chen, Guojiang Shen and Xiangjie Kong

Electronics 2022, 11(16), 2620; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics11162620 - 21 Aug 2022

Cited by 3 | Viewed by 1589

Abstract

Accurate urban travel demand forecasting can help organize traffic flow, improve traffic utilization, reduce passenger waiting time, etc. It plays an important role in intelligent transportation systems. Most of the existing research methods construct static graphs from a single perspective or two perspectives, [...] Read more.

Accurate urban travel demand forecasting can help organize traffic flow, improve traffic utilization, reduce passenger waiting time, etc. It plays an important role in intelligent transportation systems. Most of the existing research methods construct static graphs from a single perspective or two perspectives, without considering the dynamic impact of time changes and various factors on traffic demand. Moreover, travel demand is also affected by regional functions such as weather, etc. To address these issues, we propose an urban travel demand prediction framework based on dynamic multi-view coupled graph convolution (DMV-GCN). Specifically, we dynamically construct demand similarity graphs based on node features to model the dynamic correlation of demand. Then we combine it with the predefined geographic similarity graph, functional similarity graph, and road similarity graph. We use coupled graph convolution network and gated recurrent units (GRU), to model the spatio-temporal correlation in traffic. We conduct extensive experiments over two large real-world datasets. The results verify the superior performance of our proposed approach for the urban travel demand forecasting task. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

14 pages, 4841 KiB

Open AccessArticle

Gravity-Law Based Critical Bots Identification in Large-Scale Heterogeneous Bot Infection Network

by Qinglin He, Lihong Wang, Lin Cui, Libin Yang and Bing Luo

Electronics 2022, 11(11), 1771; https://0-doi-org.brum.beds.ac.uk/10.3390/electronics11111771 - 02 Jun 2022

Viewed by 1384

Abstract

The explosive growth of botnets has posed an unprecedented potent threat to the internet. It calls for more efficient ways to screen influential bots, and thus precisely bring the whole botnet down beforehand. In this paper, we propose a gravity-based critical bots identification [...] Read more.

The explosive growth of botnets has posed an unprecedented potent threat to the internet. It calls for more efficient ways to screen influential bots, and thus precisely bring the whole botnet down beforehand. In this paper, we propose a gravity-based critical bots identification scheme to assess the influence of bots in a large-scale botnet infection. Specifically, we first model the propagation of the botnet as a Heterogeneous Bot Infection Network (HBIN). An improved SEIR model is embedded into HBIN to extract both heterogeneous spatial and temporal dependencies. Within built-up HBIN, we elaborate a gravity-based influential bots identification algorithm where intrinsic influence and infection diffusion influence are specifically designed to disclose significant bots traits. Experimental results based on large-scale sample collections from the implemented prototype system demonstrate the promising performance of our scheme, comparing it with other state-of-the-art baselines. Full article

(This article belongs to the Special Issue Big Data Analysis Based Network)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Big Data Analysis Based Network

Share This Special Issue

Special Issue Editors

Special Issue Information

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI