检索结果-内蒙古大学图书馆

Coresets for near-convex functions 34

学校读者我要写书评

暂无评论

Coresets for near-convex functions

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Tukan, Murad Maalouf, Alaa Feldman, Dan The Robotics and Big Data Lab. Department of Computer Science University of Haifa Haifa Israel

Coreset is usually a small weighted subset of n input points in Rd, that provably approximates their loss function for a given set of queries (models, classifiers, etc.). Coresets become increasingly common in machine learning since existing heuristics or inefficient algorithms may be improved by running them possibly many times on the small coreset that can be maintained for streaming distributed data. Coresets can be obtained by sensitivity (importance) sampling, where its size is proportional to the total sum of sensitivities. Unfortunately, computing the sensitivity of each point is problem dependent and may be harder to compute than the original optimization problem at hand. We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. This is by suggesting the f-SVD factorization that generalizes the SVD factorization of matrices to functions. Example applications include coresets that are either new or significantly improves previous results, such as SVM, Logistic regression, M-estimators, and z-regression. Experimental results and open source are also provided. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： Factorization

ORBSLAM3-Enhanced Autonomous Toy Drones: Pioneering Indoor Exploration

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tukan, Murad Fares, Fares Grufinkle, Yotam Talmor, Ido Mualem, Loay Braverman, Vladimir Feldman, Dan DataHeroes Israel The Robotics and Big Data lab University of Haifa Haifa Israel The Computer Science Department University of Haifa Haifa Israel The Computer Science Department Rice University HoustonTX United States

Navigating toy drones through uncharted GPS-denied indoor spaces poses significant difficulties due to their reliance on GPS for location determination. In such circumstances, the necessity for achieving proper navigation is a primary concern. In response to this formidable challenge, we introduce a real-time autonomous indoor exploration system tailored for drones equipped with a monocular RGB camera. Our system utilizes ORB-SLAM3, a state-of-the-art vision feature-based SLAM, to handle both the localization of toy drones and the mapping of unmapped indoor terrains. Aside from the practicability of ORB-SLAM3, the generated maps are represented as sparse point clouds, making them prone to the presence of outlier data. To address this challenge, we propose an outlier removal algorithm with provable guarantees. Furthermore, our system incorporates a novel exit detection algorithm, ensuring continuous exploration by the toy drone throughout the unfamiliar indoor environment. We also transform the sparse point to ensure proper path planning using existing path planners. To validate the efficacy and efficiency of our proposed system, we conducted offline and real-time experiments on the autonomous exploration of indoor spaces. The results from these endeavors demonstrate the effectiveness of our methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Drones

Adaptive Context Selection for Polyp Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Ruifei Li, Guanbin Li, Zhen Cui, Shuguang Qian, Dahong Yu, Yizhou School of Data and Computer Science Sun Yat-sen University Guangzhou China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Deepwise Ai Lab Beijing China

Accurate polyp segmentation is of great significance for the diagnosis and treatment of colorectal cancer. However, it has always been very challenging due to the diverse shape and size of polyp. In recent years, state-of-the-art methods have achieved significant breakthroughs in this task with the help of deep convolutional neural networks. However, few algorithms explicitly consider the impact of the size and shape of the polyp and the complex spatial context on the segmentation performance, which results in the algorithms still being powerless for complex samples. In fact, segmentation of polyps of different sizes relies on different local and global contextual information for regional contrast reasoning. To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM). Specifically, LCA modules deliver local context features from encoder layers to decoder layers, enhancing the attention to the hard region which is determined by the prediction map of previous layer. GCM aims to further explore the global context features and send to the decoder layers. ASM is used for adaptive selection and aggregation of context features through channel-wise attention. Our proposed approach is evaluated on the EndoScene and Kvasir-SEG datasets, and shows outstanding performance compared with other state-of-the-art methods. The code is available at https://***/ReaFly/ACSNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

Human-Machine Co-Adaptation for Robot-Assisted Rehabilitation via Dual-Agent Multiple Model Reinforcement Learning (DAMMRL)

学校读者我要写书评

暂无评论

arXiv 2024年

作者： An, Yang Li, Yaqi Wang, Hongwei Duffield, Rob Su, Steven W. Jinan Key Lab of Intelligent Rehabilitation Robotics College of Artificial Intelligence and Big data for Medical Sciences Shandong First Medical University Shandong Academy of Medical Sciences China Faculty of Engineering and IT University of Technology SydneyNSW2007 Australia Faculty of Health University of Technology SydneyNSW2007 Australia

This study introduces a novel approach to robot-assisted ankle rehabilitation by proposing a Dual-Agent Multiple Model Reinforcement Learning (DAMMRL) framework, leveraging multiple model adaptive control (MMAC) and coadaptive control strategies. In robot-assisted rehabilitation, one of the key challenges is modelling human behaviour due to the complexity of human cognition and physiological systems. Traditional single-model approaches often fail to capture the dynamics of human-machine interactions. Our research employs a multiple model strategy, using simple sub-models to approximate complex human responses during rehabilitation tasks, tailored to varying levels of patient incapacity. The proposed system’s versatility is demonstrated in real experiments and simulated environments. Feasibility and potential were evaluated with 13 healthy young subjects, yielding promising results that affirm the anticipated benefits of the approach. This study not only introduces a new paradigm for robot-assisted ankle rehabilitation but also opens the way for future research in adaptive, patient-centred therapeutic interventions. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

Outcomes of Salvage Robotic-assisted Radical Prostatectomy: High-volume Multicentric data from the European Association of Urology Robotic Urology Section Scientific Working Group

学校读者我要写书评

暂无评论

European Urology 2025年第1期88卷 103-113页

作者： Covas Moschovas, Marcio Saikali, Shady Sandri, Marco Bravi, Carlo Falagario, Ugo Nathan, Arjun Collins, Justin Balestrazzi, Eleonora de Naeyer, Gert Groote, Ruben Chiara Sighinolfi, Maria Knipper, Sophie Graefen, Markus Pose, Randi Ploussard, Guillaume Idais, Hamza John, Hubert Mottaran, Angelo Schiavina, Riccardo Piazza, Pietro Brunocilla, Eugenio Breda, Alberto Rocco, Bernardo Harke, Nina N. Mottrie, Alexandre Nathan, Senthil Patel, Vipul Wiklund, Peter Adventhealth Global Robotics Institute Kissimmee FL United States Big and Open Data Innovation Laboratory (BODaI-Lab) and Data Methods and Systems Statistical Milan Italy The Royal Marsden NHS Foundation Trust London United Kingdom Karolinska Institute Stockholm Sweden University College London Hospital (UCLH) London United Kingdom Onze-Lieve-Vrouwziekenhuis (OLV) Aalst Belgium Orsi Academy Ghent Belgium ASST Santi Paolo e Carlo Milan Italy Martini Klinik Hamburg Germany Clinique La Croix du Sud Quint-Fonsegrives France Institut Universitaire du Cancer-Oncopole Toulouse France Hannover Medical School Hannover Germany Kantonsspital Winterthur (KSW) Winterthur Switzerland IRCCS Azienda Ospedaliero-Universitaria di Bologna Bologna Italy Fundacio Puigvert Barcelona Spain

Background and objective: Salvage robotic-assisted radical prostatectomy (S-RARP) is one option for treating patients with recurrent prostate cancer after prostate-preserving primary therapy. However, the tissue damage, anatomical distortion, and lack of surgical landmarks caused by the primary treatment still constitute a major challenge to surgeons. We aim to report the experience of our group on S-RARP. Methods and surgical procedure: A retrospective multicentric study including data from nine centers from the European Association of Urology Robotic Urology Section Scientific Working Group was conducted. Overall, 397 patients who underwent S-RARP from 2008 to 2023 were included and divided into three groups (primary radiation therapy [RT], whole gland [WG] ablation, and focal gland [FG] ablation). The primary endpoints were the safety and feasibility of S-RARP. The secondary endpoints were the comparison of functional and oncological outcomes among different primary therapies. Key findings and limitations: The median (interquartile range) follow-up periods for RT, FG ablation, and WG ablation were 38 (19–73), 20 (10–37), and 24 (16–38) mo, respectively (p < 0.001). Only four patients (1%) had intraoperative complications and <2% had Clavien grade ≥3 after surgery. The 5-yr cumulative incidence rates of biochemical recurrence were 35%, 45%, and 23% for RT, FG ablation, and WG ablation, respectively (p = 0.3). The 3-yr cumulative incidence rates of continence were 67%, 92%, and 71% for RT, FG ablation, and WG ablation, respectively (p < 0.001). The 5-yr cumulative incidence rates of potency were 16%, 11%, and 5.3% (p = 0.2), while the overall survival rates at 5 yr were 95%, 94%, and 100% for RT, FG ablation, and WG ablation, respectively (p = 0.7). Conclusions: S-RARP is safe and feasible with very low rates of perioperative complications. Functional outcomes in patients undergoing S-RARP are inferior to outcomes at primary surgery and demand highly skilled surgic

关键词： Prostate cancer Prostate cancer recurrence Salvage robotic-assisted radical prostatectomy

Adaptive Kalman-Based Hybrid Car Following Strategy Using Td3 and Cacc

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zheng, Yuqi Yan, Ruidong Jia, Bin Jiang, Rui Tapus, Adriana Chen, Xiaojing Zheng, Shiteng Ying, Shang Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport School of Systems Science Beijing Jiaotong University Beijing100044 China Autonomous Systems and Robotics Lab ENSTA Paris Institute Polytechnique de Paris Palaiseau91120 France School of Economics and Management Beihang University Beijing100044 China

In autonomous driving, the hybrid strategy of deep reinforcement learning and cooperative adaptive cruise control (CACC) can fully utilize the advantages of both algorithms and significantly improve the performance of car following. However, the conventional hybrid car following strategy (HCFS) based on fixed coefficient can hardly adapt to mixed traffic flow scenarios. As a result, HCFS may decrease car following performance and even increase collision risk. To address this problem, an adaptive Kalman-based HCFS (AK-HCFS) is proposed by fusing CACC and Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithms. Different from conventional HCFS based on fixed coefficient, the adaptive Kalman gain H, adjusting to complex traffic scenarios, is derived from multi-timestep predictions and Monte Carlo Tree Search algorithm. Finally, simulation results with 4157745 timesteps indicate that, compared with TD3 and HCFS, AK-HCFS can substantially enhance the safety of car following in mixed traffic flow without decreasing the comfort and efficiency. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Enhancing EEG Signal Generation through a Hybrid Approach Integrating Reinforcement Learning and Diffusion Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： An, Yang Tong, Yuhao Wang, Weikai Su, Steven W. Jinan Key Lab of Intelligent Rehabilitation Robotics College of Artificial Intelligence and Big data for Medical Sciences Shandong First Medical University Shandong Academy of Medical Sciences China Faculty of Engineering and IT University of Technology SydneyNSW2007 Australia The Sixth Mobile Detachment of the First Mobile Corps The Chinese People’s Armed Police Force China

The present study introduces an innovative approach to the synthesis of Electroencephalogram (EEG) signals by integrating diffusion models with reinforcement learning. This integration addresses key challenges associated with traditional EEG data acquisition, including participant burden, privacy concerns, and the financial costs of obtaining high-fidelity clinical data. Our methodology enhances the generation of EEG signals with detailed temporal and spectral features, enriching the authenticity and diversity of synthetic datasets. The uniqueness of our approach lies in its capacity to concurrently model time-domain characteristics, such as waveform morphology, and frequency-domain features, including rhythmic brainwave patterns, within a cohesive generative framework. This is executed through the reinforcement learning model’s autonomous selection of parameter update strategies, which steers the diffusion process to accurately reflect the complex dynamics inherent in EEG signals. We validate the efficacy of our approach using both the BCI Competition IV 2a dataset and a proprietary dataset, each collected under stringent experimental conditions. Our results indicate that the method preserves participant privacy by generating synthetic data that lacks biometric identifiers and concurrently improves the efficiency of model training by minimizing reliance on large annotated datasets. This research offers dual contributions: firstly, it advances EEG research by providing a novel tool for data augmentation and the advancement of machine learning algorithms;secondly, it enhances brain-computer interface technologies by offering a robust solution for training models on diverse and representative EEG datasets. Collectively, this study establishes a foundation for future investigations in neurological care and the development of tailored treatment protocols in neurorehabilitation. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis

Trusted data Forever: Is AI the Answer?

学校读者我要写书评

暂无评论

Trusted Data Forever: Is AI the Answer?

2022 Workshops of the EDBT/ICDT Joint Conference, EDBT/ICDT-WS 2022

作者： Frontoni, Emanuele Paolanti, Marina Lauriault, Tracey P. Stiber, Michael Duranti, Luciana Abdul-Mageed, Muhammad VRAI Vision Robotics and Artificial Intelligence Lab University of Macerata Italy Critical Media and Big Data Lab Carleton University OttawaONK1S 5B6 Canada Intelligent Networks Lab University of Washington BothellWA United States InterPARES Lab University of British Columbia VancouverBCV6T 1Z4 Canada NLP and ML Lab University of British Columbia VancouverBCV6T 1Z4 Canada

Archival institutions and programs worldwide work to ensure that the records of governments, organizations, communities, and individuals are preserved for future generations as cultural heritage, as sources of rights, and as vehicles for holding the past accountable and to inform the future. This commitment is guaranteed through the adoption of strategic and technical measures for the long-term preservation of digital assets in any medium and form — textual, visual, or aural. Public and private archives are the largest providers of data big and small in the world and collectively host yottabytes of trusted data, to be preserved forever. Several aspects of retention and preservation, arrangement and description, management and administrations, and access and use are still open to improvement. In particular, recent advances in Artificial Intelligence (AI) open the discussion as to whether AI can support the ongoing availability and accessibility of trustworthy public records. This paper presents preliminary results of the InterPARES Trust AI ("I Trust AI") international research partnership, which aims to (1) identify and develop specific AI technologies to address critical records and archives challenges;(2) determine the benefits and risks of employing AI technologies on records and archives;(3) ensure that archival concepts and principles inform the development of responsible AI;and (4) validate outcomes through a conglomerate of case studies and demonstrations. © 2022 Copyright for this paper by its authors.

关键词： Deep learning

Advancing Speaker Embedding Learning: Wespeaker Toolkit for Research and Production

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wang, Shuai Chen, Zhengyang Han, Bing Wang, Hongji Liang, Chengdong Zhang, Binbin Xiang, Xu Ding, Wen Rohdin, Johan Silnova, Anna Qian, Yanmin Li, Haizhou Shenzhen Institute of Big Data Guangdong Shenzhen China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China Horizon Robotics Beijing China NVIDIA Shanghai China Brno University of Technology Faculty of Information Technology IT4I Centre of Excellence Czech Republic School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen China

Speaker modeling plays a crucial role in various tasks, and fixed-dimensional vector representations, known as speaker embeddings, are the predominant modeling approach. These embeddings are typically evaluated within the framework of speaker verification, yet their utility extends to a broad scope of related tasks including speaker diarization, speech synthesis, voice conversion, and target speaker extraction. This paper presents Wespeaker, a user-friendly toolkit designed for both research and production purposes, dedicated to the learning of speaker embeddings. Wespeaker offers scalable data management, state-of-the-art speaker embedding models, and self-supervised learning training schemes with the potential to leverage large-scale unlabeled real-world data. The toolkit incorporates structured recipes that have been successfully adopted in winning systems across various speaker verification challenges, ensuring highly competitive results. For production-oriented development, Wespeaker integrates CPU- and GPUcompatible deployment and runtime codes, supporting mainstream platforms such as Windows, Linux, Mac and on-device chips such as horizon X3’PI. Wespeaker also provides off-the-shelf high-quality speaker embeddings by providing various pretrained models, which can be effortlessly applied to different tasks that require speaker modeling. The toolkit is publicly available at https://***/wenet-e2e/wespeaker. © 2024, The Authors. All rights reserved.

关键词： Speech recognition