2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)最新文献

{"title":"State of Charge Estimation of the Lithium-ion Battery based on Neural Network in Electric Vehicles","authors":"C. C. Lee, Panpan Hu, C. Y. Li, S. Wang","doi":"10.1109/ISPCE-ASIA57917.2022.9971063","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9971063","url":null,"abstract":"In recent years, Lithium-ion batteries have been widely applied in electric vehicles (EVs). The accurate estimation of state of charge (SOC) of EV battery is important for prolonging the battery life. Surely, it is also important for the EV drivers to handle the range anxiety. In this paper, we focus on reviewing applications of neural network algorithms in SOC estimation of EVs' batteries.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123475054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"End-to-End Task-oriented Dialogue System Using Knowledge Filter and Attention Memory Pointer","authors":"Mengjuan Liu, Jiang Liu, Chenyang Liu, Luyao Chen, Kuo-Hui Yeh","doi":"10.1109/ISPCE-ASIA57917.2022.9970837","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9970837","url":null,"abstract":"The end-to-end neural model provides a more robust solution to generate responses than the traditional pipe-line method in the task-oriented dialogue system. However, it is challenging to incorporate the proper knowledge into the gen-erated response, especially when there are substantially related knowledge tuples. This paper proposes a knowledge filter and an attention memory pointer to improve the task-oriented dia-logue model. Specifically, the model uses the knowledge filter to obtain the knowledge tuples most relevant to the keywords of dialog context and builds the knowledge vector. Besides, the task-oriented dialogue model usually needs to copy objects from the correct knowledge tuples to form the question's an-swer. We define an attention memory pointer to help the model choose the correct knowledge tuples. Finally, we conduct ex-periments on the In-Car Assistant dataset. The experimental results show that our model can generate more accurate re-sponses than baseline models in automatic and human evaluations.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126276106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fuzzy Neural Network Based Tracking Control of Dissolved Oxgen in WWTP","authors":"Dingyuan Chen, Cuili Yang, Jun-Li Qiao","doi":"10.1109/ISPCE-ASIA57917.2022.9970818","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9970818","url":null,"abstract":"Wastewater treatment process (WWTP) is a complex industrial process with strong nonlinear and time-varying dynamic characteristics. Dissolved oxygen (DO) concentration is a main factor limiting the effluent quality. Due to the complex biochemical reactions, designing an effective controller for this kind of process is a huge challenge. To achieve efficacious control under actuator saturation, a self-organizing fuzzy neural network adaptive tracking control method is proposed. Firstly, a structured model of actuator saturation is employed to ensure the prescribed steady-state and transient tracking performance. Secondly, the self-organizing fuzzy neural network is used to identify the unknown dynamics in WWTP. Then, the structure learning algorithm with correlation entropy is used to adjust the structure online. Thirdly, the stability of the control strategy is analyzed and the corresponding stability conditions are given. Finally, the simulation results on benchmark simulation model 1 (BSM 1) verify the effectiveness of the control method.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"412 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132342669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ALGANs: Enhancing membership inference attacks in federated learning with GANs and active learning","authors":"Yuanyuan Xie, Bing Chen, Jiale Zhang, Wenjuan Li","doi":"10.1109/ISPCE-ASIA57917.2022.9971068","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9971068","url":null,"abstract":"Federated learning has received a lot of attention in recent years due to its privacy protection features. However, federated learning is susceptible to various inference attacks. Membership inference attack aims to determine whether the target data is a member or non-member of the target federated learning model, which poses a serious threat to the privacy of the training data set. Membership inference method in federated learning is dissatisfied due to a lack of attack data. Recent work shows that generative adversarial networks(GANs) can effectively enrich attack data. However, data generated by GANs lacks labels. Previous work labels data by inputting it to the target classifier model, which may be imprecise when the target model outputs ambiguous results. In this paper, to overcome the lack of attack data and the lack of labels for GANs, we propose ALGANs. ALGANs increases data diversity using GANs while applies active learning to label data generated by GANs. Membership inference attack enhanced by ALGANs has a high attack accuracy due to applying active learning to label data and extensive experimental results prove our point. We performed experiments to show that ALGAN makes membership inference attacks more threatening in federated learning.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115610053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-models with averaging in feature domain for non-invasive blood glucose estimation","authors":"Yiting Wei, B. Ling, Qinzg Liu, Jiaxin Liu","doi":"10.1109/ISPCE-ASIA57917.2022.9971019","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9971019","url":null,"abstract":"Diabetes is a serious chronic metabolic disease. In the recent years, more and more studies focus on the use of the non-invasive methods to achieve the blood glucose estimation. More and more consumer technology enterprises focusing on human health are committed to implementing accurate and non-invasive blood glucose algorithm in their products. The near infrared spectroscopy built in the wearable devices is one of the common approaches to achieve the non-invasive blood glucose estimation. However, due to the interference from the external environment, these wearable non-invasive methods yield the low estimation accuracy. Even if it is not medical equipment, as a consumer product, the detection accuracy will also be an important indicator for consumers. To address this issue, this paper employs different models based on different ranges of the blood glucose values for performing the blood glucose estimation. First the photoplethysmograms (PPGs) are acquired and they are denoised via the bit plane singular spectrum analysis (SSA) method. Second, the features are extracted. For the data in the training set, first the features are averaged across the measurements in the feature domain via the optimization approach. Second, the random forest is employed to sort the importance of each feature. Third, the training set is divided into three subsets according to the reference blood glucose values. Fourth, the feature vectors and the corresponding blood glucose values in the same group are employed to build an individual model. Fifth, for each feature, the average of the feature values for all the measurements in the same subset is computed. For the data in the test set, first, the sum of the weighted distances between the test feature values and the average values obtained in the above is computed for each model. Here, the weights are defined based on the importance sorted by the random forest obtained in the above. The model corresponding to the smallest sum is assigned. Finally, the blood glucose value is estimated based on the corresponding model. Compared to the state of arts methods, our proposed method can effectively improve the estimation accuracy. In particular, the mean absolute relative difference (MARD) and the percentage of the data fall in the zone A of the Clarke error grid yielded by our proposed method reaches 12.19%, and 87.0588%, respectively.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133248217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lyapunov-based Dynamic Computation Offloading Optimization in Heterogeneous Vehicular Networks","authors":"Yuchen Yue, Junhua Wang","doi":"10.1109/ISPCE-ASIA57917.2022.9971076","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9971076","url":null,"abstract":"As a flying Mobile Edge Computing (MEC) server, the Unmanned aerial vehicle (UAV) has been employed to strength the computation capability of vehicular networks. However, the intermittent connection between moving vehicles and UAVs, and unknown distribution of computation requests bring great challenges to the online computation offloading optimization. In this work, we propose a dynamic vehicular computation offloading problem with hybrid Vehicle-to-Vehicle (V2V), Vehicle-to-Roadside unit (V2R) and Vehicle-to-UAV (V2U) communications. In order to minimize the long-term computation offloading delay in dynamic environment, we present a Lyapunov-based dynamic computation offloading (LDCO) algorithm, which transforms the original problem into a series of subproblems by minimizing the derived upper bound of the Lyapunov drift-plus-penalty function. Each subproblem is then formulated as a two-dimensional multiple knapsack problem (TDMKP), which only involves the information of current vehicles' positions and computation requests at each time slot. Comprehensive studies show significant performances of the proposed computation offloading architecture together with the dynamic offloading algorithms.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133727811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"C-Mobile: A Lightweight Composite MobileNetV2 Model for Intrusive Object Detection under Power Grid Surveillance","authors":"Chao Ouyang, Haijun Zhang, Jie Hou, Qun Li, Biao Yang, F. Gao","doi":"10.1109/ISPCE-ASIA57917.2022.9970963","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9970963","url":null,"abstract":"Intrusive object detection is a key task in real-time power grid surveillance, as the national smart grid is developing rapidly. It turns out to be time-consuming and inaccurate if the surveillance is manually performed by workers. Thus, with the booming of deep learning, we proposed an intrusive object detection algorithm, named C-Mobile, based on lightweight backbone MobileNetV2. To promote the interaction among features and ensure the real-time detection, we designed the composite MobileNetV2 backbone with an SE layer, where one of the MobileNetV2 can enhance the features of the other with a small increase in model complexity. To further utilize the extracted features, we proposed a top-down-bottom-up feature pyramid network (FPN) in which the bottom-up fusion with downsampling is applied after the traditional FPN and a cascaded region proposal network. Our dataset was collected through surveillance camera with 8,177 images and 17,883 object instances in five categories including trucks, cranes, lifts, excavators and pile drivers. Our C-Mobile reaches the highest mAP and the lowest model complexity on our dataset among state-of-the-art object detection algorithms, proving the efficacy of C-Mobile in real-time power grid surveillance.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122393767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Hybrid Model for Predicting Missing Records in Data Using XGBoost","authors":"Pascal Ndayishimiyepas, Cheruiyot Wilson, Micheal W. Kimwele","doi":"10.1109/ISPCE-ASIA57917.2022.9971092","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9971092","url":null,"abstract":"Many of the datasets in real-world applications contain incompleteness. The volume of the historical data is usually large. Moreover, there are many missing values for many features of the data. Therefore, this paper implemented an enhanced model for predicting missing records in data using supervised machine learning XGBoost regression. The paper explores different approaches that have been implemented for predicting missing records in data and then implement an enhanced approach. XGBoost stands for extreme Gradient Boosting. The main goal of XGBoost's development was improvement in model performance and speed of computation. It is an implementation of Gradient Boosting Machine which enhances the computing power for boosted trees algorithms. From the results of accuracy, precision, and recall score, it can be concluded that the implemented XGBoost algorithm model is capable of predicting missing records in a dataset.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130011713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Verifiable and Multi-Keyword Searchable Encryption Scheme Based on LSSS","authors":"Su Li, Cheng Qin, Zi-Han Xu, Xinzhe Zhang, Zhien Liu, Lei Wu","doi":"10.1109/ISPCE-ASIA57917.2022.9970993","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9970993","url":null,"abstract":"Attribute-based Searchable Encryption (ABSE) schemes allow keyword encryption to be outsourced to cloud servers, and users can securely search for keyword ciphertext documents of interest. However, most existing searchable encryption schemes do not encourage the fine-grained search of users, and attributes are exposed to third parties easily. Moreover, ABSE schemes have high computational costs for resource-constrained clients on the user's client side. To solve the above problems, a verifiable and multi-keyword searchable encryption scheme based on linear secret sharing schemes (LSSS) is presented by us, which enables users to achieve a more efficient and secure fine-grained search of multi-keyword documents. In this scheme, access control is achieved using LSSS technology, and user attribute hiding is accomplished by hash. Furthermore, user authentication and pre-decryption are outsourced to cloud servers without leaking any information, which lessens the client's computational burden. It is demonstrated that the scheme can resist selective plaintext and selective keyword attacks in security models. In addition, the performance evaluation shows that our scheme performs well in real application scenarios.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124116713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D Objective Detection for Autonomous Driving based on Two-stage Approach","authors":"Yuhui Lu, Zhong Chen, Mingde Zhao","doi":"10.1109/ISPCE-ASIA57917.2022.9971105","DOIUrl":"https://doi.org/10.1109/ISPCE-ASIA57917.2022.9971105","url":null,"abstract":"As one of the hottest areas in the current technology industry, the field of autonomous driving has attracted the attention of many technology workers. How to use point cloud data for accurate multi-objective prediction is a key issue, which includes 3D object detection and multi-object tracking. CenterPoint proposes a novel anchor-free, two-stage 3D object detection method. The first stage uses a CenterNet approach, that is, using the center point to represent the object, using the feature map after feature extraction as input, and outputting a heatmap of the probability of the location of the center of the object for each category to predict the location of the target object, and obtaining other properties from the feature regression of the point location. The second stage is to extract features from the center point of the bounding box of the prediction target to refine the prediction results. However, the 3D backbone network of the CenterPoint has the disadvantages of low feature extraction accuracy and low second stage refinement accuracy. In order to solve these problems, this paper proposes to use VoxelResBackBone8x based on deep residual network Resnet as the 3D backbone network, simplify the 2D backbone network to improve feature extraction accuracy, and use the Set Abstraction Module to make the model use both the processed advanced features and the original point cloud features to further improve the accuracy.","PeriodicalId":197173,"journal":{"name":"2022 IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130762490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}