We present two simple, intuitive and general algorithmic frameworks that can be used to design a wide variety of permutation generation algorithms. The frameworks can be used to produce 19 existing permutation algorithms, including the well-known algorithms of Heap, Wells, Langdon, Zaks, Tompkins and Lipski. We use the frameworks to design two new sorting-based permutation generation algorithms, one of which is optimal.
{"title":"A Unified Framework to Discover Permutation Generation Algorithms","authors":"Pramod Ganapathi;Rezaul Chowdhury","doi":"10.1093/comjnl/bxab181","DOIUrl":"https://doi.org/10.1093/comjnl/bxab181","url":null,"abstract":"We present two simple, intuitive and general algorithmic frameworks that can be used to design a wide variety of permutation generation algorithms. The frameworks can be used to produce 19 existing permutation algorithms, including the well-known algorithms of Heap, Wells, Langdon, Zaks, Tompkins and Lipski. We use the frameworks to design two new sorting-based permutation generation algorithms, one of which is optimal.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"603-614"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49977703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid growth of the number of web services on the Internet, various service providers provide many similar services with the same function but different quality of service (QoS) attributes. It is a key problem to be solved urgently to select the service composition quickly, meeting the users’ QoS requirements from many candidate services. Optimization of web service composition is an NP-hard issue and intelligent optimization algorithms have become the mainstream method to solve this complex problem. This paper proposed a hybrid strategy improved whale optimization algorithm, which is based on the concepts of chaos initialization, nonlinear convergence factor and mutation. By maintaining a balance between exploration and exploitation, the problem of slow or early convergence is overcome to a certain extent. To evaluate its performance more accurately, the proposed algorithm was first tested on a set of standard benchmarks. After, simulations were performed using the real quality of web service dataset. Experimental results show that the proposed algorithm is better than the original version and other meta-heuristic algorithms on average, as well as verifies the feasibility and stability of web service composition optimization.
{"title":"A Hybrid Strategy Improved Whale Optimization Algorithm for Web Service Composition","authors":"Chuanxiang Ju;Hangqi Ding;Benjia Hu","doi":"10.1093/comjnl/bxab187","DOIUrl":"https://doi.org/10.1093/comjnl/bxab187","url":null,"abstract":"With the rapid growth of the number of web services on the Internet, various service providers provide many similar services with the same function but different quality of service (QoS) attributes. It is a key problem to be solved urgently to select the service composition quickly, meeting the users’ QoS requirements from many candidate services. Optimization of web service composition is an NP-hard issue and intelligent optimization algorithms have become the mainstream method to solve this complex problem. This paper proposed a hybrid strategy improved whale optimization algorithm, which is based on the concepts of chaos initialization, nonlinear convergence factor and mutation. By maintaining a balance between exploration and exploitation, the problem of slow or early convergence is overcome to a certain extent. To evaluate its performance more accurately, the proposed algorithm was first tested on a set of standard benchmarks. After, simulations were performed using the real quality of web service dataset. Experimental results show that the proposed algorithm is better than the original version and other meta-heuristic algorithms on average, as well as verifies the feasibility and stability of web service composition optimization.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"662-677"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49977704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K Durga Devi;P Uma Maheswari;Phani Kumar Polasi;R Preetha;M Vidhyalakshmi
As there are countless significant works done for handwritten character recognition, very meager effort has been reported for inscription characters especially for Tamil stone inscriptions. The real challenge faced in handling stone inscription is dataset collection and foreground and background discrimination. Till present days, the archeological department follows traditional way of capturing, preserving and deciphering stone inscriptions which is manual, more time consuming and need expert assistance. Hence digitized recognition is essential and efficient pattern matching algorithm is needed to be developed to deal with variations in shape and size of complex structured characters present in Tamil stone inscriptions. In this paper, an automated character recognition by pattern matching approach is developed, where character features were extracted by using pattern matching algorithm that helps achieving good recognition rate. Recognition of ancient Tamil stone inscriptions characters and finding their corresponding contemporary Tamil character is done by Image-based Character Pattern Identification (ICPI) system. Modified Speeded Up Robust Feature with Bag of Grapheme (MSURF-BoG) algorithm is implemented to detect the strongest key points from the input character with different orientations. These key point features were created for training the image as a model called Bag of Grapheme (BoG) with code word creation. Hence unsupervised key point features were extracted and pattern matching is performed. 11 th century Tamil stone inscriptions were taken as samples which has 7 vowels and 17 consonants, totally 24 characters were used. Here samples with different orientation from each 24 character were used for training the system. The proposed system is evaluated by recognition accuracy which is reported for character wise at the maximum of 96%.
由于有无数重要的工作，手写的字符识别，非常微薄的努力已被报道的铭文字符，特别是泰米尔石刻铭文。石刻处理面临的真正挑战是数据集的收集和前景背景的区分。迄今为止，考古部门仍采用传统的采集、保存和破译石刻的方法，这种方法既费时又费力，还需要专家的协助。因此，数字化识别是必要的，需要开发有效的模式匹配算法来处理泰米尔石刻中存在的形状和大小变化的复杂结构字符。本文提出了一种基于模式匹配的字符自动识别方法，利用模式匹配算法提取字符特征，从而达到较好的识别率。采用基于图像的字符模式识别(ICPI)系统对古代泰米尔石刻文字进行识别，并找到与之对应的当代泰米尔文字。采用改进的加速稳健特征与Grapheme Bag (MSURF-BoG)算法，从不同方向的输入字符中检测出最强的关键点。创建这些关键点特征是为了将图像训练为一个称为Grapheme Bag (BoG)的模型，并使用码字创建。在此基础上提取无监督的关键点特征并进行模式匹配。以11世纪泰米尔石刻碑文为例，有7个元音和17个辅音，共使用了24个字。在这里，使用来自每24个字符的不同方向的样本来训练系统。该系统的识别准确率最高可达96%。
{"title":"Pattern Matching Model for Recognition of Stone Inscription Characters","authors":"K Durga Devi;P Uma Maheswari;Phani Kumar Polasi;R Preetha;M Vidhyalakshmi","doi":"10.1093/comjnl/bxab177","DOIUrl":"https://doi.org/10.1093/comjnl/bxab177","url":null,"abstract":"As there are countless significant works done for handwritten character recognition, very meager effort has been reported for inscription characters especially for Tamil stone inscriptions. The real challenge faced in handling stone inscription is dataset collection and foreground and background discrimination. Till present days, the archeological department follows traditional way of capturing, preserving and deciphering stone inscriptions which is manual, more time consuming and need expert assistance. Hence digitized recognition is essential and efficient pattern matching algorithm is needed to be developed to deal with variations in shape and size of complex structured characters present in Tamil stone inscriptions. In this paper, an automated character recognition by pattern matching approach is developed, where character features were extracted by using pattern matching algorithm that helps achieving good recognition rate. Recognition of ancient Tamil stone inscriptions characters and finding their corresponding contemporary Tamil character is done by Image-based Character Pattern Identification (ICPI) system. Modified Speeded Up Robust Feature with Bag of Grapheme (MSURF-BoG) algorithm is implemented to detect the strongest key points from the input character with different orientations. These key point features were created for training the image as a model called Bag of Grapheme (BoG) with code word creation. Hence unsupervised key point features were extracted and pattern matching is performed. 11\u0000<sup>th</sup>\u0000 century Tamil stone inscriptions were taken as samples which has 7 vowels and 17 consonants, totally 24 characters were used. Here samples with different orientation from each 24 character were used for training the system. The proposed system is evaluated by recognition accuracy which is reported for character wise at the maximum of 96%.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"554-564"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49946834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Weina Niu;Yuheng Luo;Kangyi Ding;Xiaosong Zhang;Yanping Wang;Beibei Li
In recent years, deep neural networks have been extensively applied in various fields, and face recognition is one of the most important applications. Artificial intelligence has reached or even surpassed human capabilities in many fields. However, while artificial intelligence application provides convenience to the human lives, it also leads to the risk of privacy leaking. At present, the privacy protection technology for human faces has received extensive attention. Research goals of face privacy protection technology mainly include providing face anonymization and data availability protection. Existing methods usually have insufficient anonymity and they are not easy to control the degree of image distortion, which makes it difficult to achieve the purpose of privacy protection. Moreover, they do not explicitly perform diversity preservation of attributes such as emotions, expressions and ethnicities, so they cannot perform data analysis tasks on non-identity attributes. This paper proposes a diverse privacy face image generation algorithm based on machine learning, called DIVFGEN. This algorithm comprehensively considers image distortion, identity mapping distance loss and emotion classification loss; transforms the privacy protection target into the problem of generating adversarial examples based on the recognition model; and uses an adaptive optimization algorithm to generate anonymity and diversity of privacy images. The experimental results show that on the Cohn-Kanade+ dataset, our algorithm can reduce the probability of facial recognition by the neural network when it accurately classifies sentiment, from 98.6% to 4.8%.
{"title":"A Novel Generation Method for Diverse Privacy Image Based on Machine Learning","authors":"Weina Niu;Yuheng Luo;Kangyi Ding;Xiaosong Zhang;Yanping Wang;Beibei Li","doi":"10.1093/comjnl/bxab176","DOIUrl":"https://doi.org/10.1093/comjnl/bxab176","url":null,"abstract":"In recent years, deep neural networks have been extensively applied in various fields, and face recognition is one of the most important applications. Artificial intelligence has reached or even surpassed human capabilities in many fields. However, while artificial intelligence application provides convenience to the human lives, it also leads to the risk of privacy leaking. At present, the privacy protection technology for human faces has received extensive attention. Research goals of face privacy protection technology mainly include providing face anonymization and data availability protection. Existing methods usually have insufficient anonymity and they are not easy to control the degree of image distortion, which makes it difficult to achieve the purpose of privacy protection. Moreover, they do not explicitly perform diversity preservation of attributes such as emotions, expressions and ethnicities, so they cannot perform data analysis tasks on non-identity attributes. This paper proposes a diverse privacy face image generation algorithm based on machine learning, called DIVFGEN. This algorithm comprehensively considers image distortion, identity mapping distance loss and emotion classification loss; transforms the privacy protection target into the problem of generating adversarial examples based on the recognition model; and uses an adaptive optimization algorithm to generate anonymity and diversity of privacy images. The experimental results show that on the Cohn-Kanade+ dataset, our algorithm can reduce the probability of facial recognition by the neural network when it accurately classifies sentiment, from 98.6% to 4.8%.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"540-553"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49946835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a multi-document summarization model using an optimization algorithm named CAVIAR Sun Flower Optimization (CAV-SFO). In this method, two classifiers, namely: Generative Adversarial Network (GAN) classifier and Deep Recurrent Neural Network (Deep RNN), are utilized to generate a score for summarizing multi-documents. Initially, the simHash method is applied for removing the duplicate/real duplicate contents from sentences. Then, the result is given to the proposed CAV-SFO based GAN classifier to determine the score for individual sentences. The CAV-SFO is newly designed by incorporating CAVIAR with Sun Flower Optimization Algorithm (SFO). On the other hand, the pre-processing step is done for duplicate-removed sentences from input multi-document based on stop word removal and stemming. Afterward, text-based features are extracted from pre-processed documents, and then CAV-SFO based Deep RNN is introduced for generating a score; thereby, the internal model parameters are optimally tuned. Finally, the score generated by CAV-SFO based GAN and CAV-SFO based Deep RNN is hybridized, and the final score is obtained using a multi-document compression ratio. The proposed TaylorALO-based GAN showed improved results with maximal precision of 0.989, maximal recall of 0.986, maximal F-Measure of 0.823, maximal Rouge-Precision of 0.930, and maximal Rouge-recall of 0.870.
{"title":"Caviar-Sunflower Optimization Algorithm-Based Deep Learning Classifier for Multi-Document Summarization","authors":"Sheela J;Janet B","doi":"10.1093/comjnl/bxab193","DOIUrl":"https://doi.org/10.1093/comjnl/bxab193","url":null,"abstract":"This paper proposes a multi-document summarization model using an optimization algorithm named CAVIAR Sun Flower Optimization (CAV-SFO). In this method, two classifiers, namely: Generative Adversarial Network (GAN) classifier and Deep Recurrent Neural Network (Deep RNN), are utilized to generate a score for summarizing multi-documents. Initially, the simHash method is applied for removing the duplicate/real duplicate contents from sentences. Then, the result is given to the proposed CAV-SFO based GAN classifier to determine the score for individual sentences. The CAV-SFO is newly designed by incorporating CAVIAR with Sun Flower Optimization Algorithm (SFO). On the other hand, the pre-processing step is done for duplicate-removed sentences from input multi-document based on stop word removal and stemming. Afterward, text-based features are extracted from pre-processed documents, and then CAV-SFO based Deep RNN is introduced for generating a score; thereby, the internal model parameters are optimally tuned. Finally, the score generated by CAV-SFO based GAN and CAV-SFO based Deep RNN is hybridized, and the final score is obtained using a multi-document compression ratio. The proposed TaylorALO-based GAN showed improved results with maximal precision of 0.989, maximal recall of 0.986, maximal F-Measure of 0.823, maximal Rouge-Precision of 0.930, and maximal Rouge-recall of 0.870.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"727-742"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49977710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, a novel record linkage system for E-commerce products is presented. Our system aims to cluster the same products that are crawled from different E-commerce websites into the same cluster. The proposed system achieves a very high success rate by combining both semi-supervised and unsupervised approaches. Unlike the previously proposed systems in the literature, neither a training set nor structured corpora are necessary. The core of the system is based on Hierarchical Agglomerative Clustering (HAC); however, the HAC algorithm is modified to be dynamic such that it can efficiently cluster a stream of incoming new data. Since the proposed system does not depend on any prior data, it can cluster new products. The system uses bag-of-words representation of the product titles, employs a single distance metric, exploits multiple domain-based attributes and does not depend on the characteristics of the natural language used in the product records. To our knowledge, there is no commonly used tool or technique to measure the quality of a clustering task. Therefore in this study, we use ELKI (Environment for Developing KDD-Applications Supported by Index-Structures), an open-source data mining software, for performance measurement of the clustering methods; and show how to use ELKI for this purpose. To evaluate our system, we collect our own dataset and make it publicly available to researchers who study E-commerce product clustering. Our proposed system achieves 96.25% F-Measure according to our experimental analysis. The other state-of-the-art clustering systems obtain the best 89.12% F-Measure.
本文提出了一种新的电子商务产品备案联动系统。我们的系统旨在将从不同电子商务网站抓取的相同产品聚集到同一个集群中。该系统结合了半监督和无监督两种方法，取得了很高的成功率。与文献中先前提出的系统不同，既不需要训练集，也不需要结构化的语料库。该系统的核心是基于层次聚类(HAC);然而，HAC算法被修改为动态的，这样它可以有效地对传入的新数据流进行聚类。由于所提出的系统不依赖于任何先前的数据，它可以聚类新产品。该系统使用词袋表示产品标题，采用单一距离度量，利用多个基于域的属性，并且不依赖于产品记录中使用的自然语言的特征。据我们所知，没有常用的工具或技术来衡量聚类任务的质量。因此，在本研究中，我们使用开源数据挖掘软件ELKI (Environment for Developing KDD-Applications Supported by Index-Structures)对聚类方法进行性能度量;并展示如何使用ELKI实现此目的。为了评估我们的系统，我们收集了自己的数据集，并将其公开提供给研究电子商务产品聚类的研究人员。通过实验分析，我们提出的系统达到了96.25%的F-Measure。其他最先进的集群系统获得了89.12%的最佳F-Measure。
{"title":"An Incremental Hierarchical Clustering Based System For Record Linkage In E-Commerce Domain","authors":"Furkan Gözükara;Selma Ayşe Özel","doi":"10.1093/comjnl/bxab179","DOIUrl":"https://doi.org/10.1093/comjnl/bxab179","url":null,"abstract":"In this study, a novel record linkage system for E-commerce products is presented. Our system aims to cluster the same products that are crawled from different E-commerce websites into the same cluster. The proposed system achieves a very high success rate by combining both semi-supervised and unsupervised approaches. Unlike the previously proposed systems in the literature, neither a training set nor structured corpora are necessary. The core of the system is based on Hierarchical Agglomerative Clustering (HAC); however, the HAC algorithm is modified to be dynamic such that it can efficiently cluster a stream of incoming new data. Since the proposed system does not depend on any prior data, it can cluster new products. The system uses bag-of-words representation of the product titles, employs a single distance metric, exploits multiple domain-based attributes and does not depend on the characteristics of the natural language used in the product records. To our knowledge, there is no commonly used tool or technique to measure the quality of a clustering task. Therefore in this study, we use ELKI (Environment for Developing KDD-Applications Supported by Index-Structures), an open-source data mining software, for performance measurement of the clustering methods; and show how to use ELKI for this purpose. To evaluate our system, we collect our own dataset and make it publicly available to researchers who study E-commerce product clustering. Our proposed system achieves 96.25% F-Measure according to our experimental analysis. The other state-of-the-art clustering systems obtain the best 89.12% F-Measure.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"581-602"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49946837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yalan Wu;Jiaquan Yan;Long Chen;Jigang Wu;Yidong Li
Parameter servers (PSs) placement is one of the most important factors for global model training on distributed deep learning. This paper formulates a novel problem for placement strategy of PSs in the dynamic available storage capacity, with the objective of minimizing the training time of the distributed deep learning under the constraints of storage capacity and the number of local PSs. Then, we provide the proof for the NP-hardness of the proposed problem. The whole training epochs are divided into two parts, i.e. the first epoch and the other epochs. For the first epoch, an approximation algorithm and a rounding algorithm are proposed in this paper, to solve the proposed problem. For the other epochs, an adjustment algorithm is proposed, by continuously adjusting the decisions for placement strategy of PSs to decrease the training time of the global model. Simulation results show that the proposed approximation algorithm and rounding algorithm perform better than existing works for all cases, in terms of the training time of global model. Meanwhile, the training time of global model for the proposed approximation algorithm is very close to that for optimal solution generated by the brute-force approach for all cases. Besides, the integrated algorithm outperforms the existing works when the available storage capacity varies during the training.
{"title":"Efficient Parameter Server Placement for Distributed Deep Learning in Edge Computing","authors":"Yalan Wu;Jiaquan Yan;Long Chen;Jigang Wu;Yidong Li","doi":"10.1093/comjnl/bxab188","DOIUrl":"https://doi.org/10.1093/comjnl/bxab188","url":null,"abstract":"Parameter servers (PSs) placement is one of the most important factors for global model training on distributed deep learning. This paper formulates a novel problem for placement strategy of PSs in the dynamic available storage capacity, with the objective of minimizing the training time of the distributed deep learning under the constraints of storage capacity and the number of local PSs. Then, we provide the proof for the NP-hardness of the proposed problem. The whole training epochs are divided into two parts, i.e. the first epoch and the other epochs. For the first epoch, an approximation algorithm and a rounding algorithm are proposed in this paper, to solve the proposed problem. For the other epochs, an adjustment algorithm is proposed, by continuously adjusting the decisions for placement strategy of PSs to decrease the training time of the global model. Simulation results show that the proposed approximation algorithm and rounding algorithm perform better than existing works for all cases, in terms of the training time of global model. Meanwhile, the training time of global model for the proposed approximation algorithm is very close to that for optimal solution generated by the brute-force approach for all cases. Besides, the integrated algorithm outperforms the existing works when the available storage capacity varies during the training.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"678-691"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49977708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Taxi flow forecast is significant for planning transportation and allocating basic transportation resources. The flow forecast in the urban adjacent area is different from the fixed-point flow forecast. Their data are more complex and diverse, which make them more challenging to forecast. This paper introduces a deep spatial–temporal forecast (DeepSTF) model for the flow forecasting of urban adjacent area, which divides the urban into grids and makes it have a graph structure. The model builds a spatial–temporal calculation block, which uses graph convolutional network to extract spatial correlation feature and uses two-layer temporal convolutional networks to extract time-dependent feature. Based on the theory of dilation convolution and causal convolution, the model overcomes the under-fitting phenomenon of other models when calculating with rapidly changing data. In order to improve the accuracy of prediction, we take weather as an implicit factor and let it participate in the feature calculation process. A comparison experiment is set between our model and the seven existing traffic flow forecast models. The experimental results prove that the model has better the capabilities of long-term traffic prediction and performs well in various evaluation indicators.
{"title":"DeepSTF: A Deep Spatial–Temporal Forecast Model of Taxi Flow","authors":"Zhiqiang Lv;Jianbo Li;Chuanhao Dong;Zhihao Xu","doi":"10.1093/comjnl/bxab178","DOIUrl":"https://doi.org/10.1093/comjnl/bxab178","url":null,"abstract":"Taxi flow forecast is significant for planning transportation and allocating basic transportation resources. The flow forecast in the urban adjacent area is different from the fixed-point flow forecast. Their data are more complex and diverse, which make them more challenging to forecast. This paper introduces a deep spatial–temporal forecast (DeepSTF) model for the flow forecasting of urban adjacent area, which divides the urban into grids and makes it have a graph structure. The model builds a spatial–temporal calculation block, which uses graph convolutional network to extract spatial correlation feature and uses two-layer temporal convolutional networks to extract time-dependent feature. Based on the theory of dilation convolution and causal convolution, the model overcomes the under-fitting phenomenon of other models when calculating with rapidly changing data. In order to improve the accuracy of prediction, we take weather as an implicit factor and let it participate in the feature calculation process. A comparison experiment is set between our model and the seven existing traffic flow forecast models. The experimental results prove that the model has better the capabilities of long-term traffic prediction and performs well in various evaluation indicators.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"565-580"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49946836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intensional sets are sets given by a property rather than by enumerating their elements. In a previous work, we have proposed a decision procedure for a first-order logic language which provides restricted intensional sets (RISs), i.e. a sub-class of intensional sets that are guaranteed to denote finite—though unbounded—sets. In this paper, we show how RIS can be exploited as a convenient programming tool also in a conventional setting, namely the imperative O-O language Java. We do this by considering a Java library, called JSetL, that integrates the notions of logical variable, (set) unification and constraints that are typical of constraint logic programming languages into the Java language. We show how JSetL is naturally extended to accommodate for RIS and RIS constraints and how this extension can be exploited; on the one hand, to support a more declarative style of programming and, on the other hand, to effectively enhance the expressive power of the constraint language provided by the library.
{"title":"Declarative Programming with Intensional Sets in Java Using JSetL","authors":"Maximiliano Cristiá;Andrea Fois;Gianfranco Rossi","doi":"10.1093/comjnl/bxab195","DOIUrl":"https://doi.org/10.1093/comjnl/bxab195","url":null,"abstract":"Intensional sets are sets given by a property rather than by enumerating their elements. In a previous work, we have proposed a decision procedure for a first-order logic language which provides restricted intensional sets (RISs), i.e. a sub-class of intensional sets that are guaranteed to denote finite—though unbounded—sets. In this paper, we show how RIS can be exploited as a convenient programming tool also in a conventional setting, namely the imperative O-O language Java. We do this by considering a Java library, called JSetL, that integrates the notions of logical variable, (set) unification and constraints that are typical of constraint logic programming languages into the Java language. We show how JSetL is naturally extended to accommodate for RIS and RIS constraints and how this extension can be exploited; on the one hand, to support a more declarative style of programming and, on the other hand, to effectively enhance the expressive power of the constraint language provided by the library.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"763-784"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49946839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuchen Tian;Weizhe Zhang;Andrew Simpson;Yang Liu;Zoe Lin Jiang
Federated learning (FL), a variant of distributed learning (DL), supports the training of a shared model without accessing private data from different sources. Despite its benefits with regard to privacy preservation, FL's distributed nature and privacy constraints make it vulnerable to data poisoning attacks. Existing defenses, primarily designed for DL, are typically not well adapted to FL. In this paper, we study such attacks and defenses. In doing so, we start from the perspective of DL and then give consideration to a real-world FL scenario, with the aim being to explore the requisites of a desirable defense in FL. Our study shows that (i) the batch size used in each training round affects the effectiveness of defenses in DL, (ii) the defenses investigated are somewhat effective and moderately influenced by batch size in FL settings and (iii) the non-IID data makes it more difficult to defend against data poisoning attacks in FL. Based on the findings, we discuss the key challenges and possible directions in defending against such attacks in FL. In addition, we propose detect and suppress the potential outliers(DSPO), a defense against data poisoning attacks in FL scenarios. Our results show that DSPO outperforms other defenses in several cases.
{"title":"Defending Against Data Poisoning Attacks: From Distributed Learning to Federated Learning","authors":"Yuchen Tian;Weizhe Zhang;Andrew Simpson;Yang Liu;Zoe Lin Jiang","doi":"10.1093/comjnl/bxab192","DOIUrl":"https://doi.org/10.1093/comjnl/bxab192","url":null,"abstract":"Federated learning (FL), a variant of distributed learning (DL), supports the training of a shared model without accessing private data from different sources. Despite its benefits with regard to privacy preservation, FL's distributed nature and privacy constraints make it vulnerable to data poisoning attacks. Existing defenses, primarily designed for DL, are typically not well adapted to FL. In this paper, we study such attacks and defenses. In doing so, we start from the perspective of DL and then give consideration to a real-world FL scenario, with the aim being to explore the requisites of a desirable defense in FL. Our study shows that (i) the batch size used in each training round affects the effectiveness of defenses in DL, (ii) the defenses investigated are somewhat effective and moderately influenced by batch size in FL settings and (iii) the non-IID data makes it more difficult to defend against data poisoning attacks in FL. Based on the findings, we discuss the key challenges and possible directions in defending against such attacks in FL. In addition, we propose detect and suppress the potential outliers(DSPO), a defense against data poisoning attacks in FL scenarios. Our results show that DSPO outperforms other defenses in several cases.","PeriodicalId":50641,"journal":{"name":"Computer Journal","volume":"66 3","pages":"711-726"},"PeriodicalIF":1.4,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49977709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：