Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00026
Mingxi Zhang, Guanying Su, Wei Wang
Tag generation aims to find relevant tags for a given entity, which has numerous applications, such as classification, information retrieval and recommender system. Practically, the data of real applications is sparse and lacks sufficient description for entities, which might lead to incomprehensive results. Random walk with restart (RWR) can find the hidden relationship between nodes by utilizing indirect connections. However, the traditional RWR computation is based on the whole structure of the given network, which maintains a matrix for storing all relevances between nodes. And the efficiency problem would be run into as network grows large. In this paper, we propose a top-k tag generation algorithm, namely DRWR, for efficiently generating the tags from entity-term network. The terms are treated as candidate tags, and the most relevant terms are treated as the tags for a given entity. The relevance computation between entity and terms is divided into two stages: off-line stage and on-line stage. In off-line stage, the relevances between terms are computed over the term-term network that is built based on the whole structure of entity-term network. In on-line stage, the relevances between entity and each term are computed based on the relevances between terms. For supporting fast on-line query processing, we develop a pruning algorithm, which skips the operations on relevances between terms smaller than a threshold. Extensive experiments on real datasets demonstrate the efficiency and effectiveness of the proposed approach.
标签生成的目的是为给定的实体找到相关的标签，在分类、信息检索和推荐系统等方面有着广泛的应用。实际应用中的数据是稀疏的，缺乏对实体的充分描述，可能导致结果不全面。RWR (Random walk with restart)可以利用间接连接来发现节点之间隐藏的关系。然而，传统的RWR计算是基于给定网络的整体结构，它维护一个矩阵来存储节点之间的所有相关性。随着网络规模的扩大，效率问题也会出现。为了有效地从实体术语网络中生成标签，我们提出了一种top-k标签生成算法，即DRWR。这些术语被视为候选标记，最相关的术语被视为给定实体的标记。实体与术语之间的关联计算分为离线和在线两个阶段。在离线阶段，基于实体-术语网络的整体结构构建术语-术语网络，计算术语之间的相关性。在在线阶段，根据词之间的关联度计算实体与各词之间的关联度。为了支持快速在线查询处理，我们开发了一种剪枝算法，该算法跳过了小于阈值的项之间的相关性操作。在实际数据集上的大量实验证明了该方法的效率和有效性。
{"title":"Random Walk-Based Top-k Tag Generation in Bipartite Networks of Entity-Term Type","authors":"Mingxi Zhang, Guanying Su, Wei Wang","doi":"10.1109/ICTAI.2019.00026","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00026","url":null,"abstract":"Tag generation aims to find relevant tags for a given entity, which has numerous applications, such as classification, information retrieval and recommender system. Practically, the data of real applications is sparse and lacks sufficient description for entities, which might lead to incomprehensive results. Random walk with restart (RWR) can find the hidden relationship between nodes by utilizing indirect connections. However, the traditional RWR computation is based on the whole structure of the given network, which maintains a matrix for storing all relevances between nodes. And the efficiency problem would be run into as network grows large. In this paper, we propose a top-k tag generation algorithm, namely DRWR, for efficiently generating the tags from entity-term network. The terms are treated as candidate tags, and the most relevant terms are treated as the tags for a given entity. The relevance computation between entity and terms is divided into two stages: off-line stage and on-line stage. In off-line stage, the relevances between terms are computed over the term-term network that is built based on the whole structure of entity-term network. In on-line stage, the relevances between entity and each term are computed based on the relevances between terms. For supporting fast on-line query processing, we develop a pruning algorithm, which skips the operations on relevances between terms smaller than a threshold. Extensive experiments on real datasets demonstrate the efficiency and effectiveness of the proposed approach.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130774932","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}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00273
Dheeraj Bhaskaruni, Hui Hu, Chao Lan
Fair machine learning is a topical problem. It studies how to mitigate unethical bias against minority people in model prediction. A promising solution is ensemble learning - Nina et al [1] first argue that one can obtain a fair model by bagging a set of standard models. However, they do not present any empirical evidence or discuss effective ensemble strategy for fair learning. In this paper, we propose a new ensemble strategy for fair learning. It adopts the AdaBoost framework, but unlike AdaBoost that upweights mispredicted instances, it upweights unfairly predicted instances which we identify using a variant of Luong's k-NN based situation testing method [2]. Through experiments on two real-world data sets, we show our proposed strategy achieves higher fairness than the bagging strategy discussed by Nina et al and several baseline methods. Our results also suggest standard ensemble strategies may not be sufficient for improving fairness.
{"title":"Improving Prediction Fairness via Model Ensemble","authors":"Dheeraj Bhaskaruni, Hui Hu, Chao Lan","doi":"10.1109/ICTAI.2019.00273","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00273","url":null,"abstract":"Fair machine learning is a topical problem. It studies how to mitigate unethical bias against minority people in model prediction. A promising solution is ensemble learning - Nina et al [1] first argue that one can obtain a fair model by bagging a set of standard models. However, they do not present any empirical evidence or discuss effective ensemble strategy for fair learning. In this paper, we propose a new ensemble strategy for fair learning. It adopts the AdaBoost framework, but unlike AdaBoost that upweights mispredicted instances, it upweights unfairly predicted instances which we identify using a variant of Luong's k-NN based situation testing method [2]. Through experiments on two real-world data sets, we show our proposed strategy achieves higher fairness than the bagging strategy discussed by Nina et al and several baseline methods. Our results also suggest standard ensemble strategies may not be sufficient for improving fairness.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133149770","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}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00041
Aaron N. Richter, T. Khoshgoftaar
Labeling data for supervised learning can be an expensive task, especially when large amounts of data are required to build an adequate classifier. For most problems, there exists a point of diminishing returns on a learning curve where adding more data only marginally increases model performance. It would be beneficial to approximate this point for scenarios where there is a large amount of data available but only a small amount of labeled data. Then, time and resources can be spent wisely to label the sample that is required for acceptable model performance. In this study, we explore learning curve approximation methods on a big imbalanced dataset from the bioinformatics domain. We evaluate a curve fitting method developed on small data using an inverse power law model, and propose a new semi-supervised method to take advantage of the large amount of unlabeled data. We find that the traditional curve fitting method is not effective for large sample sizes, while the semi-supervised method more accurately identifies the point of diminishing returns.
{"title":"Approximating Learning Curves for Imbalanced Big Data with Limited Labels","authors":"Aaron N. Richter, T. Khoshgoftaar","doi":"10.1109/ICTAI.2019.00041","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00041","url":null,"abstract":"Labeling data for supervised learning can be an expensive task, especially when large amounts of data are required to build an adequate classifier. For most problems, there exists a point of diminishing returns on a learning curve where adding more data only marginally increases model performance. It would be beneficial to approximate this point for scenarios where there is a large amount of data available but only a small amount of labeled data. Then, time and resources can be spent wisely to label the sample that is required for acceptable model performance. In this study, we explore learning curve approximation methods on a big imbalanced dataset from the bioinformatics domain. We evaluate a curve fitting method developed on small data using an inverse power law model, and propose a new semi-supervised method to take advantage of the large amount of unlabeled data. We find that the traditional curve fitting method is not effective for large sample sizes, while the semi-supervised method more accurately identifies the point of diminishing returns.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116149756","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}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00194
Zeshan Lu, Tao Xu, Kun Liu, Z. Liu, Feipeng Zhou, Qingjie Liu
Building detection in remote sensing images plays an important role in applications such as urban management and urban planning. Recently, convolutional neural network (CNN) based methods which benefits from the popularity of large-scale datasets have achieved good performance for object detection. To our best knowledge, there is no large-scale remote sensing image dataset specially build for building detection. Existing building datasets are in small size and lack of diversity, which hinder the development of building detection. In this paper, we present a large-scale high-resolution building dataset named 5M-Building after the number of samples in the dataset. The dataset consists of more than 10 thousand images all collected from GaoFen-2 with a spatial resolution of 0.8 meter. We also present a baseline for the dataset by evaluating three state of the art CNN based detectors. The experiments demonstrate that it is great challenge to accurately detect various buildings from remote sensing images. We hope the 5M-Building dataset will facilitate the research on building detection.
{"title":"5M-Building: A Large-Scale High-Resolution Building Dataset with CNN Based Detection Analysis","authors":"Zeshan Lu, Tao Xu, Kun Liu, Z. Liu, Feipeng Zhou, Qingjie Liu","doi":"10.1109/ICTAI.2019.00194","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00194","url":null,"abstract":"Building detection in remote sensing images plays an important role in applications such as urban management and urban planning. Recently, convolutional neural network (CNN) based methods which benefits from the popularity of large-scale datasets have achieved good performance for object detection. To our best knowledge, there is no large-scale remote sensing image dataset specially build for building detection. Existing building datasets are in small size and lack of diversity, which hinder the development of building detection. In this paper, we present a large-scale high-resolution building dataset named 5M-Building after the number of samples in the dataset. The dataset consists of more than 10 thousand images all collected from GaoFen-2 with a spatial resolution of 0.8 meter. We also present a baseline for the dataset by evaluating three state of the art CNN based detectors. The experiments demonstrate that it is great challenge to accurately detect various buildings from remote sensing images. We hope the 5M-Building dataset will facilitate the research on building detection.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116271827","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}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00190
G. B. Paulus, J. Assunção, L. A. L. Silva
This work investigates the combination of cases and clusters in the reuse of game actions (e.g., cards played, bets made) recorded in the cases retrieved for a given query in Case-based Reasoning (CBR) card-playing agents. With the support of the K-MEANS clustering algorithm, clustering results detailing problem states/situations and game outcomes relationships recorded in cases from the case base guide the execution of augmented reuse policies. These policies consider the game actions recorded in the retrieved cases in the selection of the clusters to be used. Then, the cases that belong to the selected clusters are used in the determination of which game action is reused as a solution to the current game problem situation. With this two-step reuse process, the proposed policies rely on the majority with clusters, the probability with clusters, the number of points won with clusters and the chance of victory with clusters. To evaluate these proposals, card-playing agents implemented with different reuse policies competed against each other in duplicated game matches where all of them played using the same set of cards.
{"title":"Cases and Clusters in Reuse Policies for Decision-Making in Card Games","authors":"G. B. Paulus, J. Assunção, L. A. L. Silva","doi":"10.1109/ICTAI.2019.00190","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00190","url":null,"abstract":"This work investigates the combination of cases and clusters in the reuse of game actions (e.g., cards played, bets made) recorded in the cases retrieved for a given query in Case-based Reasoning (CBR) card-playing agents. With the support of the K-MEANS clustering algorithm, clustering results detailing problem states/situations and game outcomes relationships recorded in cases from the case base guide the execution of augmented reuse policies. These policies consider the game actions recorded in the retrieved cases in the selection of the clusters to be used. Then, the cases that belong to the selected clusters are used in the determination of which game action is reused as a solution to the current game problem situation. With this two-step reuse process, the proposed policies rely on the majority with clusters, the probability with clusters, the number of points won with clusters and the chance of victory with clusters. To evaluate these proposals, card-playing agents implemented with different reuse policies competed against each other in duplicated game matches where all of them played using the same set of cards.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132765733","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}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00226
Arpita Roy, Youngja Park, Shimei Pan
Word embedding is a Natural Language Processing (NLP) technique that automatically maps words from a vocabulary to vectors of real numbers in an embedding space. It has been widely used in recent years to boost the performance of a variety of NLP tasks such as named entity recognition, syntactic parsing and sentiment analysis. Classic word embedding methods such as Word2Vec and GloVe work well when they are given a large text corpus. When the input texts are sparse as in many specialized domains (e.g., cybersecurity), these methods often fail to produce high-quality vectors. In this paper, we describe a novel method, called Annotation Word Embedding (AWE), to train domain-specific word embeddings from sparse texts. Our method is generic and can leverage diverse types of domain knowledge such as domain vocabulary, semantic relations and attribute specifications. Specifically, our method encodes diverse types of domain knowledge as text annotations and incorporates the annotations in word embedding. We have evaluated AWE in two cybersecurity applications: identifying malware aliases and identifying relevant Common Vulnerabilities and Exposures (CVEs). Our evaluation results have demonstrated the effectiveness of our method over state-of-the-art baselines.
{"title":"Incorporating Domain Knowledge in Learning Word Embedding","authors":"Arpita Roy, Youngja Park, Shimei Pan","doi":"10.1109/ICTAI.2019.00226","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00226","url":null,"abstract":"Word embedding is a Natural Language Processing (NLP) technique that automatically maps words from a vocabulary to vectors of real numbers in an embedding space. It has been widely used in recent years to boost the performance of a variety of NLP tasks such as named entity recognition, syntactic parsing and sentiment analysis. Classic word embedding methods such as Word2Vec and GloVe work well when they are given a large text corpus. When the input texts are sparse as in many specialized domains (e.g., cybersecurity), these methods often fail to produce high-quality vectors. In this paper, we describe a novel method, called Annotation Word Embedding (AWE), to train domain-specific word embeddings from sparse texts. Our method is generic and can leverage diverse types of domain knowledge such as domain vocabulary, semantic relations and attribute specifications. Specifically, our method encodes diverse types of domain knowledge as text annotations and incorporates the annotations in word embedding. We have evaluated AWE in two cybersecurity applications: identifying malware aliases and identifying relevant Common Vulnerabilities and Exposures (CVEs). Our evaluation results have demonstrated the effectiveness of our method over state-of-the-art baselines.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134499530","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}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00217
A. Tato, R. Nkambou
Deep Knowledge Tracing (DKT), along with other machine learning approaches, are biased toward data used during the training step. Thus, for problems where we have few amounts of data for training, the generalization power will be low, the models will tend to give good results on classes containing many examples and poor results on those with few examples. Theses problems are frequent in educational data where for example, there are skills that are very difficult (floor) or very easy to master (ceiling). There will be less data on students that correctly answered questions related to difficult knowledge and that incorrectly answered questions related to knowledge easy to master. In that case, the DKT is unable to correctly predict the student's answers to questions associated with those skills. To improve the DKT, we penalize the model using a 'cost-sensitive' technique. To overcome the problem of the few amounts of data, we propose a hybrid model combining the DKT and expert knowledge. Thus, the DKT is combined with a Bayesian Network (built from domain experts) by using the attention mechanism. The resulting model can accurately track knowledge of students in Logic-Muse Intelligent Tutoring System (ITS), compared to the BKT and the original DKT.
{"title":"Some Improvements of Deep Knowledge Tracing","authors":"A. Tato, R. Nkambou","doi":"10.1109/ICTAI.2019.00217","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00217","url":null,"abstract":"Deep Knowledge Tracing (DKT), along with other machine learning approaches, are biased toward data used during the training step. Thus, for problems where we have few amounts of data for training, the generalization power will be low, the models will tend to give good results on classes containing many examples and poor results on those with few examples. Theses problems are frequent in educational data where for example, there are skills that are very difficult (floor) or very easy to master (ceiling). There will be less data on students that correctly answered questions related to difficult knowledge and that incorrectly answered questions related to knowledge easy to master. In that case, the DKT is unable to correctly predict the student's answers to questions associated with those skills. To improve the DKT, we penalize the model using a 'cost-sensitive' technique. To overcome the problem of the few amounts of data, we propose a hybrid model combining the DKT and expert knowledge. Thus, the DKT is combined with a Bayesian Network (built from domain experts) by using the attention mechanism. The resulting model can accurately track knowledge of students in Logic-Muse Intelligent Tutoring System (ITS), compared to the BKT and the original DKT.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122172600","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}
Recent computer-aided polyp detection systems showed its effectiveness to decrease the polyp miss rate in colonoscopy operations, which is helpful to reduce colorectal cancer mortality. However, traditional polyp detection approaches suffer from the following drawbacks: low precision and sensitivity caused by the variance of polyp's appearance, and the system may not be able to detect polyps in real time due to the high computation complexity of the detection algorithms. To alleviate those problems, we introduce a real-time detection framework that incorporates spatial and temporal information extracted from colonoscopy videos. Our framework consists of the following three components: 1) we adopt Single Shot MultiBox Detector (SSD) to generate the proposal bounding boxes in each video frame. 2) Simultaneously, we compute optical flow from neighboring frames to extract temporal information and generate another group of polyp proposals with the temporal detection network. 3) At last, the final result is generated by a fusion module that connects the end of both streams. Experimental results on ETIS-LARIB dataset demonstrate that our proposed approach reaches the state-of-the-art performance on polyp localization with real-time performance.
{"title":"An Efficient Spatial-Temporal Polyp Detection Framework for Colonoscopy Video","authors":"Pengfei Zhang, Xinzi Sun, Dechun Wang, Xizhe Wang, Yu Cao, Benyuan Liu","doi":"10.1109/ICTAI.2019.00-93","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00-93","url":null,"abstract":"Recent computer-aided polyp detection systems showed its effectiveness to decrease the polyp miss rate in colonoscopy operations, which is helpful to reduce colorectal cancer mortality. However, traditional polyp detection approaches suffer from the following drawbacks: low precision and sensitivity caused by the variance of polyp's appearance, and the system may not be able to detect polyps in real time due to the high computation complexity of the detection algorithms. To alleviate those problems, we introduce a real-time detection framework that incorporates spatial and temporal information extracted from colonoscopy videos. Our framework consists of the following three components: 1) we adopt Single Shot MultiBox Detector (SSD) to generate the proposal bounding boxes in each video frame. 2) Simultaneously, we compute optical flow from neighboring frames to extract temporal information and generate another group of polyp proposals with the temporal detection network. 3) At last, the final result is generated by a fusion module that connects the end of both streams. Experimental results on ETIS-LARIB dataset demonstrate that our proposed approach reaches the state-of-the-art performance on polyp localization with real-time performance.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126004232","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}
In the logistics industry, the integration of the vehicle routing problem and the container loading problem which has been generalised as pickup and delivery problem with three-dimensional loading constraints (3L-PDP) is very challenging. It involves not only ensuring the shortest route of travel but also minimising the effort of reloading goods. Traditional optimisation methods such as exhaustive search and greedy search are hard to achieve an optimal solution for such kinds of complex problems. In this paper, a hybrid heuristic algorithm for the 3L-PDP problem is extended by two key improvements: the usage of a tabu strategy for enlarging the local search space of the large neighbourhood search (LNS) algorithm, which is proposed in the framework of the simulated annealing process, and the employment of complex block generation and depth-first heuristic for incrementally finding one proper box at a time in the packing phase. The experimental results show that the improved hybrid heuristic algorithm outperforms its origin regarding total travel distance on benchmark instances proposed by Li and Lim or Dirk and Andreas.
{"title":"An Improved Hybrid Heuristic Algorithm for Pickup and Delivery Problem with Three-Dimensional Loading Constraints","authors":"Jiangqing Wu, Ling Zheng, Can Huang, Sifan Cai, Shaorong Feng, Defu Zhang","doi":"10.1109/ICTAI.2019.00233","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00233","url":null,"abstract":"In the logistics industry, the integration of the vehicle routing problem and the container loading problem which has been generalised as pickup and delivery problem with three-dimensional loading constraints (3L-PDP) is very challenging. It involves not only ensuring the shortest route of travel but also minimising the effort of reloading goods. Traditional optimisation methods such as exhaustive search and greedy search are hard to achieve an optimal solution for such kinds of complex problems. In this paper, a hybrid heuristic algorithm for the 3L-PDP problem is extended by two key improvements: the usage of a tabu strategy for enlarging the local search space of the large neighbourhood search (LNS) algorithm, which is proposed in the framework of the simulated annealing process, and the employment of complex block generation and depth-first heuristic for incrementally finding one proper box at a time in the packing phase. The experimental results show that the improved hybrid heuristic algorithm outperforms its origin regarding total travel distance on benchmark instances proposed by Li and Lim or Dirk and Andreas.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130262455","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}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00258
D. Mansouri, Seif-Eddine Benkabou, Bachir Kaddar, K. Benabdeslem
In this paper, we aim to improve the performance, time complexity and energy efficiency of deep convolutional neural networks (CNNs) by combining hardware and specialization techniques. Since the pooling step represents a process that contributes significantly to CNNs performance improvement, we propose the Mode-Fisher (MF) pooling method. This form of pooling can potentially offer a very promising results in terms of improving feature extraction performance. The proposed method reduces significantly the data movement in the CNN and save up to 10% of total energy, without any performance penalty.
{"title":"A Novel Proposed Pooling for Convolutional Neural Network","authors":"D. Mansouri, Seif-Eddine Benkabou, Bachir Kaddar, K. Benabdeslem","doi":"10.1109/ICTAI.2019.00258","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00258","url":null,"abstract":"In this paper, we aim to improve the performance, time complexity and energy efficiency of deep convolutional neural networks (CNNs) by combining hardware and specialization techniques. Since the pooling step represents a process that contributes significantly to CNNs performance improvement, we propose the Mode-Fisher (MF) pooling method. This form of pooling can potentially offer a very promising results in terms of improving feature extraction performance. The proposed method reduces significantly the data movement in the CNN and save up to 10% of total energy, without any performance penalty.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128785006","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}
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：