Top Read Articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Automatic generation of Web front-end code based on UI images
    Jin GE, Xuesong LU
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 100-109.   DOI: 10.3969/j.issn.1000-5641.2023.05.009
    Abstract432)   HTML16)    PDF (1748KB)(180)      

    User interfaces (UIs) play a vital role in the interactions between an application and its users. The current popularity of mobile Internet has led to the large-scale migration of web-based applications from desktop to mobile. Web front-end development has become more extensive and in-depth in application development. Traditional web front-end development relies on designers to give initial design drafts and then programmers to write the corresponding UI code. This method has high industry barriers and slow development, which are not conducive to rapid product iteration. The development of deep learning makes it possible to automatically generate web front-end code based on UI images. Existing methods poorly capture the features of UI images, and the accuracy of the generated code is low. To mitigate these problems, we propose an encoder–decoder model, called image2code, based on the Swin Transformer, which is used to generate web front-end code from UI images. Image2code regards the process of generating web front-end code from UI images as an image captioning task and uses Swin Transformer with a sliding window design as the backbone network of the encoder and decoder. The sliding window operation limits the attention calculation to one window, which reduces the amount of calculation by the attention mechanism while simultaneously ensuring that feature connections remain across windows. In addition, image2code generates Emmet code, which is much simpler and can be directly converted to HTML code, improving the efficiency of model training. Experimental results show that image2code performs better than existing representative models, such as pix2code and image2emmet, in the task of web front-end code generation on existing and newly constructed datasets.

    Table and Figures | Reference | Related Articles | Metrics
    Species and life cycles report on Tettigoniidea and Gryllidea in Minhang District, Shanghai
    Zhuqing HE, Xinyi LIAO
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 119-124.   DOI: 10.3969/j.issn.1000-5641.2023.06.011
    Abstract301)   HTML8)    PDF (1055KB)(128)      

    This research study focuses on Tettigoniidea and Gryllidea insects distributed across Shanghai Pujiang Country Park, with data collected twice a month from April to December of Year 2020 and 2021. The results show that 8 species of Tettigonioidea, 16 species of Grylloidea, and 1 species of Gryllotalpidae live in Shanghai Pujiang Country Park. The adult phase and voltinism in their life cycles, moreover, were found to be stable. Most Tettigoniidea and Gryllidea tend to overwinter in soil as diapause eggs, and a proportion of them overwinter as nymphs. The research suggests, furthermore, that using the calling songs of Tettigoniidea and Gryllidea can be a simple and effective way to carry out studies about phenology and ecology of singing insect.

    Table and Figures | Reference | Related Articles | Metrics
    Research on Autoformer-based electricity load forecasting and analysis
    Litao TANG, Zhiyong ZHANG, Jun CHEN, Linna XU, Jiachen ZHONG, Peisen YUAN
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 135-146.   DOI: 10.3969/j.issn.1000-5641.2023.05.012
    Abstract258)   HTML10)    PDF (1298KB)(125)      

    Next-generation power grids is the main direction of future smart grid development, and the accurate prediction of power loads is an important basic task of smart grids. To improve the accuracy of load prediction in smart power systems, this work characterized the load dataset based on an Autoformer, a prediction model with an autocorrelation mechanism; adds a feature extraction layer to the original model; optimized the model parameters in terms of the number of coding layers, decoding layers, learning rate, and batch size; and achieved cycle-flexible load prediction. The experimental results show that the model performs better in prediction, with an MAE, MSE, and coefficient of determination of 0.2512, 0.1915, and 0.9832, respectively. Compared with other methods, this method has better load prediction results.

    Table and Figures | Reference | Related Articles | Metrics
    Persistent memory- and shared cache architecture-based high-performance database
    Congcong WANG, Huiqi HU
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 1-10.   DOI: 10.3969/j.issn.1000-5641.2023.05.001
    Abstract212)   HTML23)    PDF (1228KB)(122)      

    The upsurge in cloud-native databases has been drawing attention to shared architectures. Although a shared cache architecture can effectively address cache consistency issues among multiple read-write nodes, problems still exist, such as slow persistence speed, high latency in maintaining cache directories, and timestamp bottlenecks. To address these issues, this study proposes a shared cache architecture-based solution that is combined with novel persistent memory hardware, to realize a three-layer shared architecture database—TampoDB, which includes memory, persistent memory, and storage layers. The transaction execution process was redesigned based on this architecture with optimized timestamps and directories, thereby resolving the aforementioned problems. Experimental results show that TampoDB effectively enhances the persistence speed of transactions.

    Table and Figures | Reference | Related Articles | Metrics
    Privacy-preserving cloud-end collaborative training
    Xiangyun GAO, Dan MENG, Mingkai LUO, Jun WANG, Liping ZHANG, Chao KONG
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 77-89.   DOI: 10.3969/j.issn.1000-5641.2023.05.007
    Abstract195)   HTML6)    PDF (2331KB)(81)      

    China has the advantages of scale and diversity in data resources, and mobile internet data applications, which generate massive amounts of data in diverse application scenarios, recommendation systems have the capability to extract valuable information from this massive amounts of data, thereby mitigating the problem of information overload. Most existing research on recommendation systems focused on centralized recommender systems, training the data on the cloud centrally. However, with increasingly prominent data security and privacy protection issues, collecting user data has become increasingly difficult, making centralized recommendation methods infeasible. This study focuses on privacy-preserving cloud-end collaborative training in a decentralized manner for personalized recommender systems. To fully utilize the advantages of end devices and cloud servers while considering privacy and security issues, a cloud-end collaborative training method named FedMNN (federated machine learning and mobile neural network) is proposed for recommender systems based on federated machine learning (FedML) and a mobile neural network (MNN). The proposed method was divided into three parts: First, cloud-based models implemented in various deep learning frameworks were converted into general MNN models for end-device training using the ONNX (open neural network exchange) intermediate framework and a MNN model conversion tool. Second, the cloud server sends the model to the end-side devices, which initialized and obtain local data for training and loss calculation, followed by gradient back-propagation. Finally, the end-side models are fed back to the cloud server for model aggregation and updating. Depending on different requirements, the cloud model was deployed on end-side devices as required, achieving end-cloud collaboration. Experiments comparing power consumption of the proposed FedMNN and FLTFlite (flower and TensorFlow lite) frameworks on benchmark tasks identified that FedMNN is 32% to 51% lower than FLTFlite. Using DSSM (deep structured semantic model) and deep and wide recommendation models, the experimental results demonstrated the effectiveness of the proposed cloud-end collaborative training method.

    Table and Figures | Reference | Related Articles | Metrics
    An HTAP database prototype with an adaptive data synchronization
    Rong YU, Panfei YANG, Qingshuai WANG, Rong ZHANG
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 11-25.   DOI: 10.3969/j.issn.1000-5641.2023.05.002
    Abstract194)   HTML5)    PDF (2638KB)(64)      

    In HTAP (hybrid transactional and analytical processing) database, resource isolation and data sharing is a difficult problem. Although different vendors achieve resource isolation through different architectures, the freshness of user concerns, that is, the gap between online transactional processing (OLTP) write and online analytical processing (OLAP) read versions, is determined by the consistency model of data sharing. However, existing HTAP databases apply only one consistency synchronization model for an easy implementation, which is contradictory to the multiple consistency requirements of user applications, and the overall system performance is sacrificed for the highest consistency upward compatibility. In this paper, by constructing a cost model of freshness and performance tradeoff, proposing a consistency switching algorithm and a processing strategy for synchronized data before and after switching, and realizing an HTAP database prototype with adaptive switching between sequential consistency synchronization and linear consistency synchronization, which makes it possible to support query loads with different consistency (freshness) requirements and maximize the system performance without adjusting the HTAP architecture. The effectiveness of adaptive switching is also verified by extensive experiments.s of adaptive switching is also verified by extensive experiments.

    Table and Figures | Reference | Related Articles | Metrics
    Evaluation of eutrophication by satellite remote sensing based on machine learning: A case study of Huancheng River in Hefei
    Yong ZHANG, Hui WANG, Chuanhua ZHU, Hao ZHOU, Yu ZHAN, Can LI, Yifan XIAO, Lili YANG, Jiaqi LIU
    Journal of East China Normal University(Natural Science)    2024, 2024 (1): 1-8, 112.   DOI: 10.3969/j.issn.1000-5641.2024.01.001
    Abstract189)   HTML92)    PDF (1874KB)(137)      

    Taking Huancheng River in Hefei City as the study site, machine learning models such as linear regression, random forest, support vector regression, and lasso regression were utilized to establish the relationship between Landsat8 satellite data and water quality parameters, model the reflectance and water quality parameters of remote sensing image values, and compare the performance of four different models. Results showed that the random forest model performed best, and the accuracy of the inversion models for total nitrogen (TN), total phosphorus (TP), and ammonia nitrogen (NH3-N) was above 0.7. The concentration distribution map of water quality parameters showed that the pollution of TN and TP was the most significant in the northeast section of Huancheng River, while NH3-N was most present in the southwest section. The water eutrophication distribution map shows that the water body in the eastern section of the Huancheng River showed a moderate nutrition state.

    Table and Figures | Reference | Related Articles | Metrics
    Treatment of industrial park wastewater using a combination of hydrolysis acidification, anaerobic-anoxic-oxic-anoxic-oxic, and Fenton oxidation technology
    Yanjie HUANG, Guoyi ZHENG, Huayong YU, Hanbin ZHU, Fudong YU, Jing WANG, Xuchao SUN, Jiguang YIN, Lei AN, Yuanyuan LIN
    Journal of East China Normal University(Natural Science)    2024, 2024 (1): 29-35.   DOI: 10.3969/j.issn.1000-5641.2024.01.004
    Abstract180)   HTML13)    PDF (880KB)(130)      

    Industrial park wastewater is characterized by various components, changeable water quality, complex pollutant factors, poor biodegradability, and high emission standards. A full-scale industrial park wastewater treatment plant in Deqing was used as an example to investigate the technical-economic feasibility of a process combining hydrolysis acidification, anaerobic-anoxic-oxic-anoxic-oxic (A2/O+AO), and Fenton oxidation in treating wastewater from various enterprises, primarily printing and dyeing, food manufacturing, and metal processing factories. The effluent chemical oxygen demand, ammoniacal nitrogen, total nitrogen, and total phosphorus stably met the required discharge limits for Urban Sewage Treatment Plants (DB33/2169—2018), while other indicators reached Grade A standard for Urban Sewage Treatment Plants (GB18918—2002). The engineering investment and actual operation costs of the wastewater treatment plant were 8200 and 2.39 yuan/m3, respectively.

    Table and Figures | Reference | Related Articles | Metrics
    A survey on the cell theory of weighted Coxeter groups
    Jianyi SHI, Qian HUANG
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 1-13.   DOI: 10.3969/j.issn.1000-5641.2023.06.001
    Abstract178)   HTML20)    PDF (1429KB)(169)      

    We give a survey on the contribution of our research group to the cell theory of weighted Coxeter groups. We present some detailed account for the description of cells of the affine Weyl group $ \widetilde{C}_n $ in the quasi-split case and a brief account for that of the affine Weyl group $ \widetilde{B}_n $ in the quasi-split case and of the weighted universal Coxeter group in general case.

    Table and Figures | Reference | Related Articles | Metrics
    Integrating multi-granularity semantic features into the Chinese sentiment analysis method
    Juxiang REN, Zhongbao LIU
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 95-107.   DOI: 10.3969/j.issn.1000-5641.2023.06.009
    Abstract177)   HTML7)    PDF (898KB)(123)      

    Chinese sentiment analysis is one of important researches in natural language processing, which aims to discover the sentimental tendencies in the Chinese text. In recent years, research on Chinese text sentiment analysis has made great progress in efficiencies, but few studies have explored the characteristics of the language and downstream task requirements. Therefore, in view of the particularity of Chinese text and the requirements of sentiment analysis, using the Chinese text sentiment analysis method that integrates multi-granularity semantic features, such as characters, words, radicals, and part-of-speech is proposed. This introduces radical features and emotional part-of-speech features based on character and word features. Additionally, this integration uses bidirectional the long short-term memory network (BLSTM), attention mechanism and recurrent convolutional neural network (RCNN). The softmax function is used to predict the sentimental tendencies by integrating multi-granularity semantic features. The comparative experiment results on the NLPECC (natural language processing and Chinese computing) dataset showed that the F1 score of the proposed method was 84.80%, which improved the performance of the existing methods to some extent and completed the Chinese text sentiment analysis task.

    Table and Figures | Reference | Related Articles | Metrics
    A review on the application of slow-release oxygen materials in the remediation of polluted rivers and lakes
    Yang CAO, Dungang GU, Guanghui LI, Minsheng HUANG, Wenhui HE
    Journal of East China Normal University(Natural Science)    2024, 2024 (1): 9-16.   DOI: 10.3969/j.issn.1000-5641.2024.01.002
    Abstract176)   HTML18)    PDF (623KB)(172)      

    Oxygen-releasing materials are often used in the treatment and restoration of urban waters as an important method to enhance dissolved oxygen. The development of materials with slow-release property can improve the durability and stability of oxygen release in practical engineering. This paper reviews the preparation methods and oxygen release performance of the slow-release oxygen materials reported in recent years. Moreover, the effects and mechanisms of slow-release oxygen materials on the occurrence, migration, and transformation of pollutants such as nutrients in sediments and overlying water of rivers and lakes are reviewed. Finally, prospects and suggestions for the application of slow-release oxygen materials in the remediation of rivers and lakes are proposed.

    Table and Figures | Reference | Related Articles | Metrics
    Comparative evaluations of testing methods for the biodegradation rates of degradable materials
    Wei ZHAO, Yu LI, Wei ZHANG, Kehua ZHU, Ke ZHOU, Qing LYU, Shixian LIU, Zhenming GE
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 158-167.   DOI: 10.3969/j.issn.1000-5641.2023.06.015
    Abstract170)   HTML7)    PDF (1022KB)(141)      

    Herein, based on existing standards for the measurements of material degradation rates and the degradation abilities of microorganisms, four methods were designed to determine material degradation rates. These four methods included two standard methods (inoculums: composting, vermiculite+composting leachate) and two experimental methods (inoculums: vermiculite+Bacillus, vermiculite+thermophilic bacteria). For this, the raw paper and plastic film (polylactic acid, PLA) components of environmentally friendly tape, as well as the finished tapes, were used as test materials to compare the material degradation rates using the above methods. Throughout the 60-day test cycle, both the PLA films and raw paper presented high degradation rates according to the four methods. The degradation rate of finished tape products increased gradually under the composting and vermiculite+composting leachate treatment and marginally rapidly under the vermiculite+Bacillus treatment. Additionally, under the vermiculite + thermophilic bacteria treatment method, the finished tape materials displayed a markedly higher degradation rate than that produced by other methods (roughly 1.7 ~ 7.5 times). Thus, the addition of microorganisms, particularly thermophilic bacteria, enhances the testing efficiency of material biodegradation rates. Therefore, we suggest that the optimization of degradation cultures can improve the testing efficiency of material degradation parameters, allowing manufacturing enterprises to shorten the research and development cycles of biodegradable products.

    Table and Figures | Reference | Related Articles | Metrics
    Hybrid granular buffer management scheme for storage and computing separation architecture
    Wenjuan MEI, Peng CAI
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 26-39.   DOI: 10.3969/j.issn.1000-5641.2023.05.003
    Abstract160)   HTML7)    PDF (1669KB)(95)      

    The architecture of storage-compute separation has emerged as a solution for improving the performance and efficiency of large-scale data processing. However, there are notable performance bottlenecks in this approach, primarily due to the low access efficiency of object storage and the significant network overhead. Additionally, object storage exhibits low storage efficiency for small-sized files. For instance, ClickHouse, a MergeTree-based database, generates a plethora of small-sized files when storing data. To address these challenges, HG-Buffer (hybrid granularity buffer) is introduced as an SSD (solid state driver)-based caching management solution for optimizing the storage-compute separation in ClickHouse and S3, while also tackling the small-file issue in object storage. The primary objective of HG-Buffer is to minimize network transmission overhead and enhance system access efficiency. This is achieved by introducing SSD as a caching layer between the compute and storage layers and organizing the SSD buffer into two granularities: object buffer and block buffer. The object buffer granularity corresponds to the data granularity in object storage, while the block buffer granularity represents the data granularity accessed by the system, with the block buffer granularity being a subset of the object buffer granularity. By statistically analyzing data hotness information, HG-Buffer adaptively selects the storage location for data, improving SSD space utilization and system performance. Experimental evaluations conducted on ClickHouse and S3 demonstrate the effectiveness and robustness of HG-Buffer.

    Table and Figures | Reference | Related Articles | Metrics
    Towards an identity inter-relationship-consistent face de-identification method
    Yifan BU, Xiaoling WANG, Keke HE, Xingjian LU, Wenxuan WANG
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 49-60.   DOI: 10.3969/j.issn.1000-5641.2023.06.005
    Abstract159)   HTML8)    PDF (1499KB)(92)      

    The popularity of intelligent devices such as smartphones and surveillance cameras has led to serious face privacy problems. Face de-identification is considered an effective tool for protecting face privacy by concealing identity information. However, most de-identification methods lack explicit control and controllable changes in identifying de-identified face images, resulting in de-identified images that are inapplicable to face authentication and retrieval and other identity-related tasks. Therefore, this study proposes an identity inter-relationship-consistent face de-identification task in which the identity inter-relationship between two arbitrary de-identified faces maintained the same as before de-identification. To this end, a task-driven identity inter-relationship consistent generative adversarial network is introduced to generate de-identified faces with a consistent identity inter-relationship. A rotation-based de-identifier was designed to modify the original identity features to be de-identified with identity inter-relationship consistency. In addition, identity control loss is introduced to guarantee a precise identity generation using a de-identified generator. Qualitative and quantitative results show that our method achieves improvements compared with exiting methods for de-identifying de-identified faces as well as for maintaining their identity inter-relationship consistent.

    Table and Figures | Reference | Related Articles | Metrics
    Method for improving the quality of trajectory data for riding-map inference
    Jie CHEN, Wenyi SHEN, Wenyu WU, Jiali MAO
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 14-27.   DOI: 10.3969/j.issn.1000-5641.2023.06.002
    Abstract156)   HTML14)    PDF (5823KB)(145)      

    The trajectory optimization of cycling is hindered by the errors of positioning equipment, riding habits of non-motor vehicles, and other factors. It leads to quality problems, such as abnormal data and missing positioning information in the riding trajectory, impacting the application of trajectory-based riding-map inference and riding-path planning. To solve these problems, this paper creates a framework for improving the quality of cycling-trajectory data, based on the construction of a grid index, screening of abnormal trajectory points, elimination of wandering trajectory segments, elimination of illegal trajectory segments, calibration of drift trajectory segments, and recovery of missing trajectory. Comparative and ablation experiments are conducted by using a real non-motor-vehicle cycling-trajectory dataset. The experimental results verify that the proposed method improves the accuracy of cycling-map inference.

    Table and Figures | Reference | Related Articles | Metrics
    Comparative study of the vertical distribution characteristics of microplastics and sampling methods for microplastics in the water column: A case study in the Jiulong River estuary
    Chunhua JIANG, Jinxu YI, Lixin ZHU, Kai LIU, Changxing ZONG, Daoji LI
    Journal of East China Normal University(Natural Science)    2024, 2024 (1): 79-89.   DOI: 10.3969/j.issn.1000-5641.2024.01.009
    Abstract155)   HTML6)    PDF (1342KB)(122)      

    Due to the influence of tidal processes, sampling and study of microplastics in estuarine areas have been hampered by inconsistent research methods and large data errors. In this study, whole-water depth sampling was conducted in the Jiulong River estuary using the pumping method in August of 2019. The abundances and distribution patterns of microplastics among different water layers and stations were analyzed and compared with research studies performed using different sampling methods. The results showed that the microplastic abundances in the surface, middle, and bottom waters of the Jiulong River estuary were markedly different and influenced by tidal effects. The abundances of microplastics obtained by different sampling methods were also significantly different. The abundance of microplastics in the surface water was significantly higher than the abundances in the middle and bottom waters near the source of pollution, and the abundances of microplastics in the middle and bottom waters were higher than the abundance in the surface water within the main estuary, which is subject to strong tidal action and has obvious stratification. The pumping method was more effective than the trawling method at retaining plastic fibers. The volume of water sample filtered by the pumping method and the size of the filtering mesh had significant effects on the abundances and sizes of the obtained microplastics. Different sampling methods lead to considerable differences in microplastic abundance results, and it is necessary to take tidal effects into account during microplastic monitoring in tidal estuaries. Therefore, it is recommended that operational monitoring and flux observations of microplastics in tidal estuaries be established and that sampling methods for observation of full tidal periods of flood and dry seasons and high and low tides should be used.

    Table and Figures | Reference | Related Articles | Metrics
    FeaDB: In-memory based multi-version online feature store
    Ge GAO, Huiqi HU
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 65-76.   DOI: 10.3969/j.issn.1000-5641.2023.05.006
    Abstract144)   HTML6)    PDF (1103KB)(96)      

    Feature management plays an important role in the AI(artificial intelligence) pipeline. Feature stores are designed to offer effective versioning of features during the model training and inference stages. Feature stores must ensure real-time feature updates and version management to collaborate with the upstream data ingestion tasks and power the model serving system. In AI-powered online decision augmentation applications, the model serving system responds to requests in real time to provide better user experience, and feature stores face the challenge of low-latency online feature retrieval. Focusing on this challenge, we developed FeaDB, an in-memory based multi-version online feature store, which adopts a time series model and provides feature versioning semantics to automatically manage features from ingestion to serving. Moreover, an append-write operation was applied to ensure ingestion performance, and version indexing was optimized to improve read operations. A snapshot mechanism is proposed, and it was experimentally proven that snapshot read operations improve performance of lookup and range lookup.

    Table and Figures | Reference | Related Articles | Metrics
    Diabetic retinopathy grading based on dual-view image feature fusion
    Lulu JIANG, Siqi SUN, Haidong ZOU, Lina LU, Rui FENG
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 39-48.   DOI: 10.3969/j.issn.1000-5641.2023.06.004
    Abstract143)   HTML5)    PDF (1286KB)(67)      

    The diagnostic method based on dual-view fundus imaging is widely used in diabetic retinopathy (DR) screening. This method effectively solves the problems of image occlusion and limited field of view under single-view. This paper proposes a learning method of feature fusion between dual-view images based on the attention mechanism to improve the accuracy of DR classification by effectively integrating different view information. Due to the small proportion of lesions in fundus images, the self-attention mechanism was introduced to enhance the learning of local lesion features. Moreover, a cross-attention mechanism is proposed to effectively utilize information between dual-view images to improve the classification of dual-view fundus images. Experiments were performed on the internal DFiD dataset and public DeepDRiD dataset. The proposed method can effectively improve the accuracy of DR classification and can be used for large-scale DR screening to assist doctors in achieving an efficient diagnosis.

    Table and Figures | Reference | Related Articles | Metrics
    Hierarchical description-aware personalized recommendation system
    Daojia CHEN, Zhiyun CHEN
    Journal of East China Normal University(Natural Science)    2023, 2023 (6): 73-84.   DOI: 10.3969/j.issn.1000-5641.2023.06.007
    Abstract138)   HTML5)    PDF (786KB)(103)      

    Review text contains comprehensive user and item information and it has a great influence on users’ purchase decision. When users interact with different target items, they may show complex interests. Therefore, accurately extracting review semantic features and modeling the contextual interaction between items and users is critical for learning user preferences and item attributes. Focusing on enhancing the personalization capture and dynamic interest modeling abilities of recommender systems, and considering the usefulness of different features, we propose a hierarchical description-aware personalized recommendation (DAPR) algorithm. At the word level of review text, we design a personalized information selection network to extract important word semantic features. At the review level, we design a neural network based on a cross-attention mechanism to dynamically learn the usefulness of reviews, concatenate review summaries as descriptions, and devise a co-attention network to capture rich context-aware features. The analysis of five Amazon datasets reveal that the proposed method can achieve comparable recommendation performance to the baseline models.

    Table and Figures | Reference | Related Articles | Metrics
    Identifying electricity theft based on residual network and depthwise separable convolution enhanced self attention
    Zhishang DUAN, Yi RAN, Duliang LYU, Jie QI, Jiachen ZHONG, Peisen YUAN
    Journal of East China Normal University(Natural Science)    2023, 2023 (5): 193-204.   DOI: 10.3969/j.issn.1000-5641.2023.05.016
    Abstract136)   HTML6)    PDF (1288KB)(88)      

    Power theft seriously endangers power equipment and personal safety, and causes significant economic losses for energy suppliers. Hence, it is important for these suppliers to accurately identify instances of power theft to reduce losses and increase efficiency. In this paper, based on the residual network (ResNet) structure, a 2D convolutional neural network is combined with a depthwise separable convolution enhanced self-attentive (DSCAttention) mechanism to improve the number of correctly-classified electricity theft users. In addition, electricity theft data often contains missing values, outliers, and positive and negative sample imbalance. Each of the above problems are treated separately using the zero-completion method, quantile transformation, and hierarchical splitting method, respectively. The proposed model has been extensively tested using real power theft data sets. The results show that the area under curve (AUC) index of the proposed model reaches a value of 91.92%, while mean average precision values MAP@100 and MAP@200 are measured reaching 98.58% and 96.77%, respectively. Compared with other electricity theft classification models, the proposed model performs the electricity theft classification task better. The method in this paper can be extended to electricity theft intelligent identification.

    Table and Figures | Reference | Related Articles | Metrics