Pub Date : 2024-08-05DOI: 10.1109/TAI.2024.3438094
Lokesh Kumar;Arup Kumar Sadhu;Ranjan Dasgupta
This article proposes an approach for local path planning. Unlike traditional approaches, the proposed local path planner simultaneously learns and plans within the sensing range (SLPA-SR) during local path planning. SLPA-SR is the synergy between the local path planner, the dynamic window approach (DWA), the obstacle avoidance by velocity obstacle (VO) approach, and the proposed next-best reward learning (NBR) algorithms. In the proposed SLPA-SR, the DWA acts as an actuator and helps to balance exploration and exploitation in the proposed NBR. In the proposed NBR, dimensions of state and action do not need to be defined a priori ; rather, dimensions of state and action change dynamically. The proposed SLPA-SR is simulated and experimentally validated on the TurtleBot3 Waffle Pi. The performance of the proposed SLPA-SR is tested in several typical environments, both in simulation and hardware experiments. The proposed SLPA-SR outperforms the contender algorithms (i.e., DWA, DWA-RL, improved time elastic band, predictive artificial potential field, and artificial potential field) by a significant margin in terms of run-time, linear velocity, angular velocity, success rate, average trajectory length, and average velocity. The efficacy of the proposed NBR is established by analyzing the percentage of exploitation, average reward, and state-action pair count.
{"title":"Simultaneous Learning and Planning Within Sensing Range: An Approach for Local Path Planning","authors":"Lokesh Kumar;Arup Kumar Sadhu;Ranjan Dasgupta","doi":"10.1109/TAI.2024.3438094","DOIUrl":"https://doi.org/10.1109/TAI.2024.3438094","url":null,"abstract":"This article proposes an approach for local path planning. Unlike traditional approaches, the proposed local path planner simultaneously learns and plans within the sensing range (SLPA-SR) during local path planning. SLPA-SR is the synergy between the local path planner, the dynamic window approach (DWA), the obstacle avoidance by velocity obstacle (VO) approach, and the proposed next-best reward learning (NBR) algorithms. In the proposed SLPA-SR, the DWA acts as an actuator and helps to balance exploration and exploitation in the proposed NBR. In the proposed NBR, dimensions of state and action do not need to be defined a \u0000<italic>priori</i>\u0000; rather, dimensions of state and action change dynamically. The proposed SLPA-SR is simulated and experimentally validated on the TurtleBot3 Waffle Pi. The performance of the proposed SLPA-SR is tested in several typical environments, both in simulation and hardware experiments. The proposed SLPA-SR outperforms the contender algorithms (i.e., DWA, DWA-RL, improved time elastic band, predictive artificial potential field, and artificial potential field) by a significant margin in terms of run-time, linear velocity, angular velocity, success rate, average trajectory length, and average velocity. The efficacy of the proposed NBR is established by analyzing the percentage of exploitation, average reward, and state-action pair count.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6399-6411"},"PeriodicalIF":0.0,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810194","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}
The rapid deployment and low-cost inference of controller area network (CAN) bus anomaly detection models on intelligent vehicles can drive the development of the Green Internet of Vehicles. Anomaly detection on intelligent vehicles often utilizes recurrent neural network models, but computational resources for these models are limited on small platforms. Model compression is essential to ensure CAN bus security with restricted computing resources while improving model computation efficiency. However, the existence of shared cyclic units significantly constrains the compression of recurrent neural networks. In this study, we propose a structured pruning method for long short-term memory (LSTM) based on the contribution values of shared vectors. By analyzing the contribution value of each dimension of shared vectors, the weight matrix of the model is structurally pruned, and the output value of the LSTM layer is supplemented to maintain the information integrity between adjacent network layers. We further propose an approximate matrix multiplication calculation module that runs in the whole process of model calculation and is deployed in parallel with the pruning module. Evaluated on a realistic public CAN bus dataset, our method effectively achieves highly structured pruning, improves model computing efficiency, and maintains performance stability compared to other compression methods.
{"title":"LSTM-Based Model Compression for CAN Security in Intelligent Vehicles","authors":"Yuan Feng;Yingxu Lai;Ye Chen;Zhaoyi Zhang;Jingwen Wei","doi":"10.1109/TAI.2024.3438110","DOIUrl":"https://doi.org/10.1109/TAI.2024.3438110","url":null,"abstract":"The rapid deployment and low-cost inference of controller area network (CAN) bus anomaly detection models on intelligent vehicles can drive the development of the Green Internet of Vehicles. Anomaly detection on intelligent vehicles often utilizes recurrent neural network models, but computational resources for these models are limited on small platforms. Model compression is essential to ensure CAN bus security with restricted computing resources while improving model computation efficiency. However, the existence of shared cyclic units significantly constrains the compression of recurrent neural networks. In this study, we propose a structured pruning method for long short-term memory (LSTM) based on the contribution values of shared vectors. By analyzing the contribution value of each dimension of shared vectors, the weight matrix of the model is structurally pruned, and the output value of the LSTM layer is supplemented to maintain the information integrity between adjacent network layers. We further propose an approximate matrix multiplication calculation module that runs in the whole process of model calculation and is deployed in parallel with the pruning module. Evaluated on a realistic public CAN bus dataset, our method effectively achieves highly structured pruning, improves model computing efficiency, and maintains performance stability compared to other compression methods.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6457-6471"},"PeriodicalIF":0.0,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810725","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 : 2024-08-01DOI: 10.1109/TAI.2024.3436538
Renato Sortino;Thomas Cecconello;Andrea De Marco;Giuseppe Fiameni;Andrea Pilzer;Daniel Magro;Andrew M. Hopkins;Simone Riggi;Eva Sciacca;Adriano Ingallinera;Cristobal Bordiu;Filomena Bufano;Concetto Spampinato
Along with the nearing completion of the square kilometer array (SKA), comes an increasing demand for accurate and reliable automated solutions to extract valuable information from the vast amount of data it will allow acquiring. Automated source finding is a particularly important task in this context, as it enables the detection and classification of astronomical objects. Deep-learning-based object detection and semantic segmentation models have proven to be suitable for this purpose. However, training such deep networks requires a high volume of labeled data, which is not trivial to obtain in the context of radio astronomy. Since data needs to be manually labeled by experts, this process is not scalable to large dataset sizes, limiting the possibilities of leveraging deep networks to address several tasks. In this work, we propose RADiff, a generative approach based on conditional diffusion models trained over an annotated radio dataset to generate synthetic images, containing radio sources of different morphologies, to augment existing datasets and reduce the problems caused by class imbalances. We also show that it is possible to generate fully synthetic image-annotation pairs to automatically augment any annotated dataset. We evaluate the effectiveness of this approach by training a semantic segmentation model on a real dataset augmented in two ways: 1) using synthetic images obtained from real masks; and 2) generating images from synthetic semantic masks. Finally, we also show how the model can be applied to populate background noise maps for simulating radio maps for data challenges.
{"title":"RADiff: Controllable Diffusion Models for Radio Astronomical Maps Generation","authors":"Renato Sortino;Thomas Cecconello;Andrea De Marco;Giuseppe Fiameni;Andrea Pilzer;Daniel Magro;Andrew M. Hopkins;Simone Riggi;Eva Sciacca;Adriano Ingallinera;Cristobal Bordiu;Filomena Bufano;Concetto Spampinato","doi":"10.1109/TAI.2024.3436538","DOIUrl":"https://doi.org/10.1109/TAI.2024.3436538","url":null,"abstract":"Along with the nearing completion of the square kilometer array (SKA), comes an increasing demand for accurate and reliable automated solutions to extract valuable information from the vast amount of data it will allow acquiring. Automated source finding is a particularly important task in this context, as it enables the detection and classification of astronomical objects. Deep-learning-based object detection and semantic segmentation models have proven to be suitable for this purpose. However, training such deep networks requires a high volume of labeled data, which is not trivial to obtain in the context of radio astronomy. Since data needs to be manually labeled by experts, this process is not scalable to large dataset sizes, limiting the possibilities of leveraging deep networks to address several tasks. In this work, we propose RADiff, a generative approach based on conditional diffusion models trained over an annotated radio dataset to generate synthetic images, containing radio sources of different morphologies, to augment existing datasets and reduce the problems caused by class imbalances. We also show that it is possible to generate fully synthetic image-annotation pairs to automatically augment any annotated dataset. We evaluate the effectiveness of this approach by training a semantic segmentation model on a real dataset augmented in two ways: 1) using synthetic images obtained from real masks; and 2) generating images from synthetic semantic masks. Finally, we also show how the model can be applied to populate background noise maps for simulating radio maps for data challenges.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6524-6535"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825894","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 : 2024-08-01DOI: 10.1109/TAI.2024.3436659
Jing Xiao;Jing Cao;Xiao-Ke Xu
Higher-order community detection in real-life networks has recently gained significant attention, because motif-based communities reflect not only higher-order mesoscale structures but also functional characteristics. However, motif-based communities detected by existing methods for directed networks often disregard edge directionality (nonreciprocal directional arcs), so they typically fail to comprehensively reveal intrinsic characteristics of higher-order topology and information flow. To address this issue, first, we model higher-order directed community detection as a biobjective optimization problem, aiming to provide high-quality and diverse compromise partitions that capture both characteristics. Second, we introduce a multiobjective genetic algorithm based on motif density and information flow (MOGA-MI) to approximate the Pareto optimal higher-order directed community partitions. On the one hand, an arc-and-motif neighbor-based genetic generator (AMN-GA) is developed to generate high-quality and diverse offspring individuals; on the other hand, a higher-order directed neighbor community modification (HD-NCM) operation is designed to further improve generated partitions by modifying easily confused nodes into more appropriate motif-neighbor communities. Finally, experimental results demonstrate that the proposed MOGA-MI outperforms state-of-the-art algorithms in terms of higher-order topology and information flow indicators while providing more diverse community information.
{"title":"Higher-Order Directed Community Detection by A Multiobjective Evolutionary Framework","authors":"Jing Xiao;Jing Cao;Xiao-Ke Xu","doi":"10.1109/TAI.2024.3436659","DOIUrl":"https://doi.org/10.1109/TAI.2024.3436659","url":null,"abstract":"Higher-order community detection in real-life networks has recently gained significant attention, because motif-based communities reflect not only higher-order mesoscale structures but also functional characteristics. However, motif-based communities detected by existing methods for directed networks often disregard edge directionality (nonreciprocal directional arcs), so they typically fail to comprehensively reveal intrinsic characteristics of higher-order topology and information flow. To address this issue, first, we model higher-order directed community detection as a biobjective optimization problem, aiming to provide high-quality and diverse compromise partitions that capture both characteristics. Second, we introduce a multiobjective genetic algorithm based on motif density and information flow (MOGA-MI) to approximate the Pareto optimal higher-order directed community partitions. On the one hand, an arc-and-motif neighbor-based genetic generator (AMN-GA) is developed to generate high-quality and diverse offspring individuals; on the other hand, a higher-order directed neighbor community modification (HD-NCM) operation is designed to further improve generated partitions by modifying easily confused nodes into more appropriate motif-neighbor communities. Finally, experimental results demonstrate that the proposed MOGA-MI outperforms state-of-the-art algorithms in terms of higher-order topology and information flow indicators while providing more diverse community information.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6536-6550"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825895","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}
Horizontal federated learning (HFL) exhibits substantial similarities in feature space across distinct clients. However, not all features contribute significantly to the training of the global model. Moreover, the curse of dimensionality delays the training. Therefore, reducing irrelevant and redundant features from the feature space makes training faster and inexpensive. This work aims to identify the common feature subset from the clients in federated settings. We introduce a hybrid approach called Fed-MOFS, 1
This manuscript is an extension of Banerjee et al. [1].
utilizing mutual information (MI) and clustering for local FS at each client. Unlike the Fed-FiS, which uses a scoring function for global feature ranking, Fed-MOFS employs multiobjective optimization to prioritize features based on their higher relevance and lower redundancy. This article compares the performance of Fed-MOFS 2
We share our code, data, and supplementary copy through https://github.com/DevBhuyan/Horz-FL/blob/main/README.md.
with conventional and federated FS methods. Moreover, we tested the scalability, stability, and efficacy of both Fed-FiS and Fed-MOFS across diverse datasets. We also assessed how FS influenced model convergence and explored its impact in scenarios with data heterogeneity. Our results show that Fed-MOFS enhances global model performance with a 50% reduction in feature space and is at least twice as fast as the FSHFL method. The computational complexity for both approaches is O( $d^{2}$ ), which is lower than the state of the art.
{"title":"Cost-Efficient Feature Selection for Horizontal Federated Learning","authors":"Sourasekhar Banerjee;Devvjiit Bhuyan;Erik Elmroth;Monowar Bhuyan","doi":"10.1109/TAI.2024.3436664","DOIUrl":"https://doi.org/10.1109/TAI.2024.3436664","url":null,"abstract":"Horizontal federated learning (HFL) exhibits substantial similarities in feature space across distinct clients. However, not all features contribute significantly to the training of the global model. Moreover, the curse of dimensionality delays the training. Therefore, reducing irrelevant and redundant features from the feature space makes training faster and inexpensive. This work aims to identify the common feature subset from the clients in federated settings. We introduce a hybrid approach called Fed-MOFS,\u0000<xref><sup>1</sup></xref>\u0000<fn><label><sup>1</sup></label><p>This manuscript is an extension of Banerjee et al. <xref>[1]</xref>.</p></fn>\u0000 utilizing mutual information (MI) and clustering for local FS at each client. Unlike the Fed-FiS, which uses a scoring function for global feature ranking, Fed-MOFS employs multiobjective optimization to prioritize features based on their higher relevance and lower redundancy. This article compares the performance of Fed-MOFS\u0000<xref><sup>2</sup></xref>\u0000<fn><label><sup>2</sup></label><p>We share our code, data, and supplementary copy through <uri>https://github.com/DevBhuyan/Horz-FL/blob/main/README.md</uri>.</p></fn>\u0000 with conventional and federated FS methods. Moreover, we tested the scalability, stability, and efficacy of both Fed-FiS and Fed-MOFS across diverse datasets. We also assessed how FS influenced model convergence and explored its impact in scenarios with data heterogeneity. Our results show that Fed-MOFS enhances global model performance with a 50% reduction in feature space and is at least twice as fast as the FSHFL method. The computational complexity for both approaches is O(\u0000<inline-formula><tex-math>$d^{2}$</tex-math></inline-formula>\u0000), which is lower than the state of the art.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6551-6565"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825816","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 : 2024-07-31DOI: 10.1109/TAI.2024.3435608
Chan Young Koh;Mohamed Ali;Abdeltawab Hendawi
Automatic sidewalk crack detection is necessary for urban infrastructure maintenance to ensure pedestrian safety. Such a task becomes complex on overgrown sidewalks, where crack detection usually misjudges vegetation as cracks. A lack of automated crack detection targets overgrown sidewalk problems; most crack detection focuses on vehicular roadway cracks that are recognizable even at the aerial photography level. Hence, this article introduces CrackLens, an automated sidewalk crack detection framework capable of detecting cracks even on overgrown sidewalks. We include several contributions as follows. First, we designed an automatic data parser using a red, green, and blue (RGB)-depth fusion sidewalk dataset we collected. The RGB and depth information are combined to create depth-embedded matrices, which are used to prelabel and separate the collected dataset into two categories (with and without crack). Second, we created an automatic annotation process using image processing methods and tailored the tool only to annotate cracks on overgrown sidewalks. This process is followed by a binary classification for verification, allowing the tool to target overgrown problems on sidewalks. Lastly, we explored the robustness of our framework by experimenting with it using 8,000 real sidewalk images with some overgrown problems. The evaluation leveraged several transformer-based neural network models. Our framework achieves substantial crack detection and segmentation in overgrown sidewalks by addressing the challenges of limited data and subjective manual annotations.
{"title":"CrackLens: Automated Sidewalk Crack Detection and Segmentation","authors":"Chan Young Koh;Mohamed Ali;Abdeltawab Hendawi","doi":"10.1109/TAI.2024.3435608","DOIUrl":"https://doi.org/10.1109/TAI.2024.3435608","url":null,"abstract":"Automatic sidewalk crack detection is necessary for urban infrastructure maintenance to ensure pedestrian safety. Such a task becomes complex on overgrown sidewalks, where crack detection usually misjudges vegetation as cracks. A lack of automated crack detection targets overgrown sidewalk problems; most crack detection focuses on vehicular roadway cracks that are recognizable even at the aerial photography level. Hence, this article introduces CrackLens, an automated sidewalk crack detection framework capable of detecting cracks even on overgrown sidewalks. We include several contributions as follows. First, we designed an automatic data parser using a red, green, and blue (RGB)-depth fusion sidewalk dataset we collected. The RGB and depth information are combined to create depth-embedded matrices, which are used to prelabel and separate the collected dataset into two categories (with and without crack). Second, we created an automatic annotation process using image processing methods and tailored the tool only to annotate cracks on overgrown sidewalks. This process is followed by a binary classification for verification, allowing the tool to target overgrown problems on sidewalks. Lastly, we explored the robustness of our framework by experimenting with it using 8,000 real sidewalk images with some overgrown problems. The evaluation leveraged several transformer-based neural network models. Our framework achieves substantial crack detection and segmentation in overgrown sidewalks by addressing the challenges of limited data and subjective manual annotations.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5418-5430"},"PeriodicalIF":0.0,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600362","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}
Industrial volatile organic compounds (VOCs) emissions and leakage have caused serious problems to the environment and public safety. Traditional VOCs monitoring systems require professionals to carry gas sensors into the emission area to collect VOCs, which might cause secondary hazards. VOCs infrared (IR) imaging visual inspection technology is a convenient and low-cost method. However, current visual detection methods with VOCs IR imaging are limited due to blurred imaging and indeterminate gas shapes. Moreover, major works pay attention to only IR modality for VOCs emissions detection, which would neglect semantic expressions of VOCs. To this end, we propose a dual-stream fusion detection framework to deal with visible and IR features of VOCs. Additionally, a multimodal fusion induced attention (MFIA) module is designed to realize feature fusion across modalities. Specifically, MFIA uses the spatial attention fusion module (SAFM) to mine association among modalities in terms of spatial location and generates fused features by spatial location weighting. Then, the modality adapter (MA) and induced attention module (IAM) are proposed to weight latent VOCs regions in IR features, which alleviates the problem of noise interference and degradation of VOCs characterization caused by fusion. Finally, comprehensive experiments are carried out on the challenging VOCs dataset, and the mAP@0.5 and F1-score of the proposed model are 0.527 and 0.601, which outperforms the state-of-the-art methods by 3.3% and 3.4%, respectively.
{"title":"Multimodal Fusion Induced Attention Network for Industrial VOCs Detection","authors":"Yu Kang;Kehao Shi;Jifang Tan;Yang Cao;Lijun Zhao;Zhenyi Xu","doi":"10.1109/TAI.2024.3436037","DOIUrl":"https://doi.org/10.1109/TAI.2024.3436037","url":null,"abstract":"Industrial volatile organic compounds (VOCs) emissions and leakage have caused serious problems to the environment and public safety. Traditional VOCs monitoring systems require professionals to carry gas sensors into the emission area to collect VOCs, which might cause secondary hazards. VOCs infrared (IR) imaging visual inspection technology is a convenient and low-cost method. However, current visual detection methods with VOCs IR imaging are limited due to blurred imaging and indeterminate gas shapes. Moreover, major works pay attention to only IR modality for VOCs emissions detection, which would neglect semantic expressions of VOCs. To this end, we propose a dual-stream fusion detection framework to deal with visible and IR features of VOCs. Additionally, a multimodal fusion induced attention (MFIA) module is designed to realize feature fusion across modalities. Specifically, MFIA uses the spatial attention fusion module (SAFM) to mine association among modalities in terms of spatial location and generates fused features by spatial location weighting. Then, the modality adapter (MA) and induced attention module (IAM) are proposed to weight latent VOCs regions in IR features, which alleviates the problem of noise interference and degradation of VOCs characterization caused by fusion. Finally, comprehensive experiments are carried out on the challenging VOCs dataset, and the mAP@0.5 and F1-score of the proposed model are 0.527 and 0.601, which outperforms the state-of-the-art methods by 3.3% and 3.4%, respectively.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6385-6398"},"PeriodicalIF":0.0,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810192","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 : 2024-07-29DOI: 10.1109/TAI.2024.3432857
Suman Adhya;Avishek Lahiri;Debarshi Kumar Sanyal;Partha Pratim Das
Negative sampling has emerged as an effective technique that enables deep learning models to learn better representations by introducing the paradigm of “learn-to-compare.” The goal of this approach is to add robustness to deep learning models to learn better representation by comparing the positive samples against the negative ones. Despite its numerous demonstrations in various areas of computer vision and natural language processing, a comprehensive study of the effect of negative sampling in an unsupervised domain such as topic modeling has not been well explored. In this article, we present a comprehensive analysis of the impact of different negative sampling strategies on neural topic models. We compare the performance of several popular neural topic models by incorporating a negative sampling technique in the decoder of variational autoencoder-based neural topic models. Experiments on four publicly available datasets demonstrate that integrating negative sampling into topic models results in significant enhancements across multiple aspects, including improved topic coherence, richer topic diversity, and more accurate document classification. Manual evaluations also indicate that the inclusion of negative sampling into neural topic models enhances the quality of the generated topics. These findings highlight the potential of negative sampling as a valuable tool for advancing the effectiveness of neural topic models.
{"title":"Evaluating Negative Sampling Approaches for Neural Topic Models","authors":"Suman Adhya;Avishek Lahiri;Debarshi Kumar Sanyal;Partha Pratim Das","doi":"10.1109/TAI.2024.3432857","DOIUrl":"https://doi.org/10.1109/TAI.2024.3432857","url":null,"abstract":"Negative sampling has emerged as an effective technique that enables deep learning models to learn better representations by introducing the paradigm of “learn-to-compare.” The goal of this approach is to add robustness to deep learning models to learn better representation by comparing the positive samples against the negative ones. Despite its numerous demonstrations in various areas of computer vision and natural language processing, a comprehensive study of the effect of negative sampling in an unsupervised domain such as topic modeling has not been well explored. In this article, we present a comprehensive analysis of the impact of different negative sampling strategies on neural topic models. We compare the performance of several popular neural topic models by incorporating a negative sampling technique in the decoder of variational autoencoder-based neural topic models. Experiments on four publicly available datasets demonstrate that integrating negative sampling into topic models results in significant enhancements across multiple aspects, including improved topic coherence, richer topic diversity, and more accurate document classification. Manual evaluations also indicate that the inclusion of negative sampling into neural topic models enhances the quality of the generated topics. These findings highlight the potential of negative sampling as a valuable tool for advancing the effectiveness of neural topic models.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5630-5642"},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600390","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 : 2024-07-25DOI: 10.1109/TAI.2024.3433419
Shuo Zhao;Zikun Zhu;Xin Li;Ying-Chi Chen
The increasing concerns about data privacy and security have driven the emergence of federated learning, which preserves privacy by collaborative learning across multiple clients without sharing their raw data. In this article, we propose a communication-efficient federated learning algorithm for decision trees (DTs), referred to as FL-DT. The key idea is to exchange the statistics of a small number of features among the server and all clients, enabling identification of the optimal feature to split each DT node without compromising privacy. To efficiently find the splitting feature based on the partially available information at each DT node, a novel formulation is derived to estimate the lower and upper bounds of Gini indexes of all features by solving a sequence of mixed-integer convex programming problems. Our experimental results based on various public datasets demonstrate that FL-DT can reduce the communication overhead substantially without surrendering any classification accuracy, compared to other conventional methods.
{"title":"Communication-Efficient Federated Learning for Decision Trees","authors":"Shuo Zhao;Zikun Zhu;Xin Li;Ying-Chi Chen","doi":"10.1109/TAI.2024.3433419","DOIUrl":"https://doi.org/10.1109/TAI.2024.3433419","url":null,"abstract":"The increasing concerns about data privacy and security have driven the emergence of federated learning, which preserves privacy by collaborative learning across multiple clients without sharing their raw data. In this article, we propose a communication-efficient federated learning algorithm for decision trees (DTs), referred to as FL-DT. The key idea is to exchange the statistics of a small number of features among the server and all clients, enabling identification of the optimal feature to split each DT node without compromising privacy. To efficiently find the splitting feature based on the partially available information at each DT node, a novel formulation is derived to estimate the lower and upper bounds of Gini indexes of all features by solving a sequence of mixed-integer convex programming problems. Our experimental results based on various public datasets demonstrate that FL-DT can reduce the communication overhead substantially without surrendering any classification accuracy, compared to other conventional methods.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5478-5492"},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600173","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 : 2024-07-25DOI: 10.1109/TAI.2024.3433469
Pranjala G. Kolapwar;Uday V. Kulkarni;Jaishri M. Waghmare
A pair trading strategy (PTS) is a balanced approach that involves simultaneous trading of two highly correlated stocks. This article introduces the PTS-return-based pair selection (PTS-R) strategy which is the modification of the traditional PTS. The PTS-R follows a similar framework to the traditional PTS, differing only in the criteria it employs for selecting stock pairs. Moreover, this article proposes a novel trading strategy called sector-based pairs trading strategy (SBPTS) along with its two variants, namely SBPTS-correlation-based pair selection (SBPTS-C) and SBPTS-return-based pair selection (SBPTS-R). The SBPTS focuses on the pairs of stocks within the same sector. It consists of three innovative phases: the classification of input stocks into the respective sectors, the identification of the best-performing sector, and the selection of stock pairs based on their returns. The goal is to identify the pairs with a strong historical correlation and the highest returns within the best-performing sector. These chosen pairs are then used for trading. The strategies are designed to enhance the efficacy of the pairs trading and are validated through experimentation on real-world stock data over a ten-year historical period from 2013 to 2023. The results demonstrate their effectiveness compared to the existing techniques for pair selection and trading strategy.
{"title":"Sector-Based Pairs Trading Strategy With Novel Pair Selection Technique","authors":"Pranjala G. Kolapwar;Uday V. Kulkarni;Jaishri M. Waghmare","doi":"10.1109/TAI.2024.3433469","DOIUrl":"https://doi.org/10.1109/TAI.2024.3433469","url":null,"abstract":"A pair trading strategy (PTS) is a balanced approach that involves simultaneous trading of two highly correlated stocks. This article introduces the PTS-return-based pair selection (PTS-R) strategy which is the modification of the traditional PTS. The PTS-R follows a similar framework to the traditional PTS, differing only in the criteria it employs for selecting stock pairs. Moreover, this article proposes a novel trading strategy called sector-based pairs trading strategy (SBPTS) along with its two variants, namely SBPTS-correlation-based pair selection (SBPTS-C) and SBPTS-return-based pair selection (SBPTS-R). The SBPTS focuses on the pairs of stocks within the same sector. It consists of three innovative phases: the classification of input stocks into the respective sectors, the identification of the best-performing sector, and the selection of stock pairs based on their returns. The goal is to identify the pairs with a strong historical correlation and the highest returns within the best-performing sector. These chosen pairs are then used for trading. The strategies are designed to enhance the efficacy of the pairs trading and are validated through experimentation on real-world stock data over a ten-year historical period from 2013 to 2023. The results demonstrate their effectiveness compared to the existing techniques for pair selection and trading strategy.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"6 1","pages":"3-13"},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142976032","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：