Big Data Research最新文献

{"title":"Distributed Heterogeneous Transfer Learning","authors":"Paolo Mignone ,&nbsp;Gianvito Pio ,&nbsp;Michelangelo Ceci","doi":"10.1016/j.bdr.2024.100456","DOIUrl":"10.1016/j.bdr.2024.100456","url":null,"abstract":"<div><p>Transfer learning has proved to be effective for building predictive models even in complex conditions with a low amount of available labeled data, by constructing a predictive model for a target domain also using the knowledge coming from a separate domain, called source domain. However, several existing transfer learning methods assume identical feature spaces between the source and the target domains. This assumption limits the possible real-world applications of such methods, since two separate, although related, domains could be described by totally different feature spaces. Heterogeneous transfer learning methods aim to overcome this limitation, but they usually <em>i)</em> make other assumptions on the features, such as requiring the same number of features, <em>ii)</em> are not generally able to distribute the workload over multiple computational nodes, <em>iii)</em> cannot work in the Positive-Unlabeled (PU) learning setting, which we also considered in this study, or <em>iv)</em> their applicability is limited to specific application domains, i.e., they are not general-purpose methods.</p><p>In this manuscript, we present a novel distributed heterogeneous transfer learning method, implemented in Apache Spark, that overcomes all the above-mentioned limitations. Specifically, it is able to work also in the PU learning setting by resorting to a clustering-based approach, and can align totally heterogeneous feature spaces, without exploiting peculiarities of specific application domains. Moreover, our distributed approach allows us to process large source and target datasets.</p><p>Our experimental evaluation was performed in three different application domains that can benefit from transfer learning approaches, namely the reconstruction of the human gene regulatory network, the prediction of cerebral stroke in hospital patients, and the prediction of customer energy consumption in power grids. The results show that the proposed approach is able to outperform 4 state-of-the-art heterogeneous transfer learning approaches and 3 baselines, and exhibits ideal performances in terms of scalability.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"37 ","pages":"Article 100456"},"PeriodicalIF":3.3,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2214579624000327/pdfft?md5=33cf99e10874514291bfc635b26d260f&pid=1-s2.0-S2214579624000327-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141025163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SD-SLAM: A semantic SLAM approach for dynamic scenes based on LiDAR point clouds","authors":"Feiya Li ,&nbsp;Chunyun Fu ,&nbsp;Dongye Sun ,&nbsp;Jian Li ,&nbsp;Jianwen Wang","doi":"10.1016/j.bdr.2024.100463","DOIUrl":"https://doi.org/10.1016/j.bdr.2024.100463","url":null,"abstract":"<div><p>Point cloud maps generated via LiDAR sensors using extensive remotely sensed data are commonly used by autonomous vehicles and robots for localization and navigation. However, dynamic objects contained in point cloud maps not only downgrade localization accuracy and navigation performance but also jeopardize the map quality. In response to this challenge, we propose in this paper a novel semantic SLAM approach for dynamic scenes based on LiDAR point clouds, referred to as SD-SLAM hereafter. The main contributions of this work are in three aspects: 1) introducing a semantic SLAM framework dedicatedly for dynamic scenes based on LiDAR point clouds, 2) employing semantics and Kalman filtering to effectively differentiate between dynamic and semi-static landmarks, and 3) making full use of semi-static and pure static landmarks with semantic information in the SD-SLAM process to improve localization and mapping performance. To evaluate the proposed SD-SLAM, tests were conducted using the widely adopted KITTI odometry dataset. Results demonstrate that the proposed SD-SLAM effectively mitigates the adverse effects of dynamic objects on SLAM, improving vehicle localization and mapping performance in dynamic scenes, and simultaneously constructing a static semantic map with multiple semantic classes for enhanced environment understanding.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100463"},"PeriodicalIF":3.3,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141083349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Utilizing convolutional neural networks (CNN) and U-Net architecture for precise crop and weed segmentation in agricultural imagery: A deep learning approach","authors":"Mughair Aslam Bhatti ,&nbsp;M.S. Syam ,&nbsp;Huafeng Chen ,&nbsp;Yurong Hu ,&nbsp;Li Wai Keung ,&nbsp;Zeeshan Zeeshan ,&nbsp;Yasser A. Ali ,&nbsp;Nadia Sarhan","doi":"10.1016/j.bdr.2024.100465","DOIUrl":"10.1016/j.bdr.2024.100465","url":null,"abstract":"<div><p>This study presents the implementation and evaluation of a convolutional neural network (CNN) based image segmentation model using the U-Net architecture for forest image segmentation. The proposed algorithm starts by preprocessing the datasets of satellite images and corresponding masks from a repository source. Data preprocessing involves resizing, normalizing, and splitting the images and masks into training and testing datasets. The U-Net model architecture, comprising encoder and decoder parts with skip connections, is defined and compiled with binary cross-entropy loss and Adam optimizer. Training includes early stopping and checkpoint saving mechanisms to prevent overfitting and retain the best model weights. Evaluation metrics such as Intersection over Union (IoU), Dice coefficient, pixel accuracy, precision, recall, specificity, and F1-score are computed to assess the model's performance. Visualization of results includes comparing predicted segmentation masks with ground truth masks for qualitative analysis. The study emphasizes the importance of training data size in achieving accurate segmentation models and highlights the potential of U-Net architecture for forest image segmentation tasks.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100465"},"PeriodicalIF":3.3,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141026200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non pilot data-aided carrier and sampling frequency offsets estimation in fast time-varying channel","authors":"Yanan Wu,&nbsp;Rong Mei,&nbsp;Jie Xu","doi":"10.1016/j.bdr.2024.100461","DOIUrl":"https://doi.org/10.1016/j.bdr.2024.100461","url":null,"abstract":"<div><p>This paper considers the non pilot data-aided estimation of the carrier frequency offset (CFO) and sample frequency offset (SFO) of orthogonal frequency division multiplexing (OFDM) signals in fast time-varying channel. The main obstacle is the time-variant channel response, which deteriorates the estimation validity. A practical approach to mitigate this impact is to reduce the time consumption of one-shot estimation. In this way, we propose a method to reduce the time consumption to within one OFDM symbol duration. The maximum likelihood (ML) estimator is derived based on the observations of frequency domain constellations output of two FFTs on one symbol; its closed-form approximation is then derived to reduce the calculation burden. Remarkably, our method does not require any training symbol or pilot tone embedded in the signal spectrum, therefore achieves the highest spectral efficiency. Theoretical analysis and simulation results are employed to assess the performance of proposed method in comparison with existing alternatives.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100461"},"PeriodicalIF":3.3,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140901432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Similarity Measurement for Graph Data: An Improved Centrality and Geometric Perspective-Based Approach","authors":"Li Deng ,&nbsp;Shihu Liu ,&nbsp;Weihua Xu ,&nbsp;Xianghong Lin","doi":"10.1016/j.bdr.2024.100462","DOIUrl":"https://doi.org/10.1016/j.bdr.2024.100462","url":null,"abstract":"<div><p>How to make a precise similarity measurement for graph data is considered as highly recommended research in many fields. Hereinto, the so-named graph data is the coalition of patterns and edges that connect patterns. By taking both of pattern information and edge information into consideration, this paper introduces an improved centrality and geometric perspective-based approach to measure the similarity between any two graph data. Once these two graph data are projected into a plane, the pattern distance can be calculated by Euclid metric. With the help of the area composed by length of each edge and angle that constructed by the positive X-axis and the edge, the area-based edge distance is computed. To get better measurement, position-based edge distance is used to modify the edge distance. Up to now, the global distance between any two graph data can be determined by combining the above mentioned two distance results. Finally, the <span>letter dataset</span> is applied for experiment to examine the proposed similarity approach. The experimental results show that the proposed approach captures the similarity of graph data commendably and gets a tradeoff between time and precision.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100462"},"PeriodicalIF":3.3,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140824127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the Sea Surface Temperature Forecasting Problem with Deep Dilation-Erosion-Linear Models","authors":"Ricardo de A. Araújo ,&nbsp;Paulo S.G. de Mattos Neto ,&nbsp;Nadia Nedjah ,&nbsp;Sergio C.B. Soares","doi":"10.1016/j.bdr.2024.100455","DOIUrl":"https://doi.org/10.1016/j.bdr.2024.100455","url":null,"abstract":"<div><p>The sea surface temperature (SST) is considered an important measure for detecting changes in climate and marine ecosystems. So, its forecasting is essential for supporting governmental strategies to avoid side effects on the global population. In this paper, we analyze the SST time series and suggest that a combination between a linear component and a nonlinear component with long-term dependency can better represent it. Based on this assumption, we propose a deep neural network architecture with dilation-erosion-linear (DEL) processing units to deal with this particular kind of time series. An empirical analysis is performed in this work using three SST time series, where we explore three statistical measures. The experimental results demonstrate that the proposed model outperformed recent and classical literature forecasting techniques according to well-known performance metrics.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100455"},"PeriodicalIF":3.3,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140813373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Cross-Chain Mechanism for Agricultural Engineering Document Management Blockchain in the Context of Big Data","authors":"Lei Shi ,&nbsp;Yimin Zhou ,&nbsp;Wei Wang ,&nbsp;Juan Wang ,&nbsp;Yang Bai ,&nbsp;Chengzong Peng ,&nbsp;Ding Chen ,&nbsp;Zuli Wang","doi":"10.1016/j.bdr.2024.100459","DOIUrl":"10.1016/j.bdr.2024.100459","url":null,"abstract":"<div><p>Cross-chain mechanism functions as typical approaches for information interaction between diverse blockchains tackling the problem of information silos in the big data era. Most of the existing cross-chain mechanisms are targeted at virtual currency blockchains in the financial sector. With more and more engineering documents manufactured by the development of modern smart farming, the need for engineering document management and cross-chaining between various blockchains has become increasingly urgent. This paper proposes a novel attainable cross-chain mechanism for agricultural engineering document management blockchains concerning the unique structure and operation principals of the specific domain. The methodology sufficiently integrated the characteristics of the agricultural engineering document management with the notary scheme, constructed by government supervision nodes with high credibility. Meanwhile, the authentication technology and cryptographic algorithms are internally fused, solving the authentication problem of the document cross-chain and protecting the cross-chain information respectively, which ensures the integrity and security of the file attribute information, alongside file ontology data in the cross-chain process. Adequate security proof and experiments illustrate that the developed mechanism can guarantee the feasibility of the mechanism, authenticity of the cross-chain parties, and the integrality and reliability of the document information, thus catering to the requirements of the cross-chain performance of blockchain in the field of agricultural engineering document management.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100459"},"PeriodicalIF":3.3,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140782467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tree parameter extraction method based on new remote sensing technology and terrestrial laser scanning technology","authors":"Aiguo Wang ,&nbsp;Jun Wang ,&nbsp;Haiming Li ,&nbsp;Jian Hu ,&nbsp;Haiyuan Zhou ,&nbsp;Xinyu Zhang ,&nbsp;Xuan Liu ,&nbsp;Wanying Wang ,&nbsp;Wenjin Zhang ,&nbsp;Siting Wu ,&nbsp;Ningyang Jiao ,&nbsp;Yihao Wang","doi":"10.1016/j.bdr.2024.100460","DOIUrl":"10.1016/j.bdr.2024.100460","url":null,"abstract":"<div><p>Ground LiDAR is a terrestrial LiDAR system that is often used for terrain and geomorphic mapping. Ground-based LiDAR can be used to collect more local and short-range data, making it ideal for mapping smaller areas with high precision. In order to solve the rapid extraction of tree parameters in the national public welfare forest survey, the ground-based LIDAR was used to obtain the point cloud of trees, and the point cloud data was registered, denoised, normalized, sliced, parameter extracted, etc., and the parameters of individual trees in the forest were obtained. The Bland-Altman consistency test is used to test whether the method of extracting tree parameters from point clouds is consistent with the traditional measurement method. The experimental results show that the point cloud data obtained by the ground-based LIDAR can quickly, conveniently and accurately extract the tree parameters, which is consistent with the traditional tree parameter extraction method, and has the advantages than the traditional tree parameter measurement, such as point cloud, image and traceability. It has a unique advantage in establishing a tree database. It is suggested that LIDAR should be used for forest survey in the future.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100460"},"PeriodicalIF":3.3,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140795530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multiscale electricity theft detection model based on feature engineering","authors":"Wei Zhang,&nbsp;Yu Dai","doi":"10.1016/j.bdr.2024.100457","DOIUrl":"10.1016/j.bdr.2024.100457","url":null,"abstract":"<div><p>With the widespread adoption of smart meters and the growing availability of data mining and machine learning algorithms, there is a pressing demand for methods that are both accurate and explicable in identifying electricity theft patterns among end-users. To address this need, this study proposes a multi-scale anomaly detection model based on feature engineering.Specifically, tsfresh is utilized in feature engineering to extract electricity consumption features from the raw data, and XGBoost is employed to select features that are highly correlated with anomalous behavior, which have clear physical interpretations. Multi-scale convolutional neural networks are then used to analyze and process the data at different temporal and frequency scales. Attention mechanisms are applied to assign weights to different feature channels, and all of the extracted information is fused for anomaly detection. The combination of feature engineering and multi-scale convolutional neural networks not only enhances the interpretability of the model but also improves its performance, as demonstrated by the experimental results, which show that the proposed method outperforms traditional anomaly detection approaches across multiple evaluation metrics.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100457"},"PeriodicalIF":3.3,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140762245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative analysis of big data for land resource classification and zoning at the township level in Northern Shaanxi","authors":"Hongkun Xie ,&nbsp;Minghua Huang ,&nbsp;Wentao Lei ,&nbsp;Yang Wang ,&nbsp;Lu Ou","doi":"10.1016/j.bdr.2024.100458","DOIUrl":"10.1016/j.bdr.2024.100458","url":null,"abstract":"<div><p>To analyze and evaluate the conditions and distribution characteristics of rural land resources in northern Shaanxi. The experiment extracts two terrain feature values, namely slope and undulation, which are highly correlated with land resources. Then, the extraction results of all 302-township level administrative regions in northern Shaanxi are processed, and the scoring results of all township level units are sorted. Based on this, optimization and adjustment are made to form a classification result. The experimental results show that land resources in primary townships are most scarce, mainly distributed in the central and western regions of northern Shaanxi, with 53 in Yan'an and 7 in Yulin; Land resources in secondary townships are relatively scarce, mainly distributed along the Yellow River in the central and southern parts of northern Shaanxi, with 40 in Yan'an and 53 in Yulin; The land resources of third level townships are relatively abundant, generally distributed along the Great Wall, and belong to the transitional zone between windblown sand and grassland areas and hilly and gully areas. Except for one third level township located in Yan'an, all 22 other townships are located in Yulin; The fourth level townships have abundant land resources and are located in the loess plateau landform area in the southern part of northern Shaanxi. They belong to Yan'an Luochuan and three surrounding counties, totaling 17 townships; The terrain of the fifth and sixth level townships is flat, and the land resources are the most abundant. They belong to the sandy and grassy terrain north of the Great Wall in northern Shaanxi. A total of 56 townships are located in 7 county-level administrative regions of Yulin City. The experimental results lay the foundation for the research on optimizing the spatial pattern of rural life in northern Shaanxi, and can also provide support for classified guidance and precise policy implementation for rural revitalization, agricultural industry policy formulation, human settlement environment construction, and ecological environment protection.</p></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"36 ","pages":"Article 100458"},"PeriodicalIF":3.3,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140788495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}