检索结果-内蒙古大学图书馆

DuFCALF: Enabling computers to Feel Songs

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Mukherjee, Himadri Marciano, Matteo Dhar, Ankita Roy, Kaushik Department of Computer Science West Bengal State University India Gazelien Records Lab Department of Arts and Humanities Music Program New York University Abu Dhabi United Arab Emirates Department of Computational Science Brainware University India

Music recommendation systems have evolved significantly in the past couple of years and have become extremely popular with the advancement of Artificial Intelligence (AI). Such systems categorize songs based on disparate perspectives, like genre, artist, tempo, etc. However, there have been lesser development in the purview of song categorization based on feelings. Songs amplify the mood of a person and often, listeners choose the type of song they want to listen to based on their mood. Hence, modeling the emotional content of songs is crucial. However, this is a challenging affair because songs embody multiple instruments and vocals in a single instance. Each of them is often modulated differently for a better experience for the listeners as well. In this paper, a system is presented to distinguish song clips based on their emotion. The clips were parameterized using two features which were fed to disparate deep networks. Thereafter, a dual feature cross architecture late fusion (DuFCALF) strategy was used to distinguish the moods. Experiments were performed with multitudinous sections of songs and the sadness of songs was captured with over 80% accuracy. © 2022, The Authors. All rights reserved.

关键词： Deep learning

THE BLESSINGS OF MULTIPLE TREATMENTS AND OUTCOMES IN TREATMENT EFFECT ESTIMATION

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Yong Liu, Mingzhou Yan, Jing Fu, Yanwei Wang, Shouyan Wang, Yizhou Sun, Xinwei Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China Computer Science Department Peking University China School of Data Science Fudan University China Key Laboratory of Computational Neuroscience Brain-Inspired Intelligence China MOE Frontiers Center for Brain Science Fudan University China Zhangjiang Fudan International Innovation Center China Engineering Research Center of AI & Robotics Ministry of Education Fudan University China

Assessing causal effects in the presence of unobserved confounding is a challenging problem. Existing studies leveraged proxy variables or multiple treatments to adjust for the confounding bias. In particular, the latter approach attributes the impact on a single outcome to multiple treatments, allowing estimating latent variables for confounding control. Nevertheless, these methods primarily focus on a single outcome, whereas in many real-world scenarios, there is greater interest in studying the effects on multiple outcomes. Besides, these outcomes are often coupled with multiple treatments. Examples include the intensive care unit (ICU), where health providers evaluate the effectiveness of therapies on multiple health indicators. To accommodate these scenarios, we consider a new setting dubbed as multiple treatments and multiple outcomes. We then show that parallel studies of multiple outcomes involved in this setting can assist each other in causal identification, in the sense that we can exploit other treatments and outcomes as proxies for each treatment effect under study. We proceed with a causal discovery method that can effectively identify such proxies for causal estimation. The utility of our method is demonstrated in synthetic data and sepsis disease. Copyright © 2023, The Authors. All rights reserved.

关键词： Intensive care units

Robot self-recognition via facial expression sensorimotor learning

学校读者我要写书评

暂无评论

Robot self-recognition via facial expression sensorimotor le...

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Zhegong Shangguan Mengyuan Ding Chuang Yu Chaona Chen Adriana Tapus Autonomous Systems and Robotics Lab/U2IS ENSTA Paris Institut Polytechnique de Paris 828 Boulevard des Maréchaux Palaiseau France National Engineering Laboratory for Visual Information Applications college of Artificial Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Cognitive Robotics Lab Department of Computer Science University of Manchester Kilburn Building Oxford Rd Manchester UK School of Psychology and Neuroscience University of Glasgow Glasgow UK

To develop robots that can show cognitive functions, we must learn from the knowledge of human cognition. Existing biological and psychological evidence suggests that self-face perception and sensorimotor learning mechanisms play a crucial role in self-recognition. However, one of the most important self-identity cues – facial information – has not been extensively studied in the robot self-recognition task. Current research on robot self-recognition primarily relies on the recognition of high-precision targets and tracking of manipulator motions, where the self-perception of facial information is not well studied. In this work, we propose a novel approach to achieve self-recognition via self-perception of facial expressions. Specifically, we developed a Conditional Generative Adversarial Network (CGAN) model using the knowledge on human cognitive and sensorimotor functions. It allows the robot to be aware of self-face (i.e., off-line model). Passing the observed visual variations in a mirror and comparing them to self-perceptive information, the robot can recognize the self through an online Bayesian learning regression. The results of our first experiment show that the robot can recognize itself in a mirror. The results from the second experiment show that our algorithm could be tricked by a similar robot with the same facial expressions, which is similar to the rubber hand illusion (RHI).

关键词：

Tracking Everything in Robotic-Assisted Surgery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhan, Bohan Zhao, Wang Fang, Yi Du, Bo Vasconcelos, Francisco Stoyanov, Danail Elson, Daniel S. Huang, Baoru The Hamlyn Centre for Robotic Surgery Imperial College London SW7 2AZ United Kingdom Department of Computer Science Tsinghua University Beijing China Embodied AI and Robotics Lab NYU Abu Dhabi Abu Dhabi United Arab Emirates School of Computer Science Wuhan University Wuhan China Hawkes Institute University College London WC1E 6BT United Kingdom Department of Computer Science University of Liverpool L69 7ZX United Kingdom

Accurate tracking of tissues and instruments in videos is crucial for Robotic-Assisted Minimally Invasive Surgery (RAMIS), as it enables the robot to comprehend the surgical scene with precise locations and interactions of tissues and tools. Traditional keypoint-based sparse tracking is limited by featured points, while flow-based dense two-view matching suffers from long-term drifts. Recently, the Tracking Any Point (TAP) algorithm was proposed to overcome these limitations and achieve dense accurate long-term tracking. However, its efficacy in surgical scenarios remains untested, largely due to the lack of a comprehensive surgical tracking dataset for evaluation. To address this gap, we introduce a new annotated surgical tracking dataset for benchmarking tracking methods for surgical scenarios, comprising real-world surgical videos with complex tissue and instrument motions. We extensively evaluate state-of-the-art (SOTA) TAP-based algorithms on this dataset and reveal their limitations in challenging surgical scenarios, including fast instrument motion, severe occlusions, and motion blur, etc. Furthermore, we propose a new tracking method, namely SurgMotion, to solve the challenges and further improve the tracking performance. Our proposed method outperforms most TAP-based algorithms in surgical instruments tracking, and especially demonstrates significant improvements over baselines in challenging medical videos. Our code and dataset are available at https://***/zhanbh1019/SurgicalMotion. © 2024, CC BY-NC-ND.

关键词： Robotic surgery

Link Prediction Accuracy on Real-World Networks Under Non-Uniform Missing Edge Patterns

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Xie Ghasemian, Amir Lee, Eun Schwarze, Alice C. Clauset, Aaron Mucha, Peter J. The Department of Mathematics Dartmouth College HanoverNH03755 United States The Human Nature Lab Yale University CT06520 United States The Computational Social Science Lab The University of Pennsylvania PA19104 United States The Department of Scientific Computing Pukyong National University Busan Korea Republic of The Department of Computer Science The BioFrontiers Institute The University of Colorado BoulderCO80309 United States The Santa Fe Institute Santa FeNM87501 United States

Real-world network datasets are typically obtained in ways that fail to capture all edges. The patterns of missing data are often non-uniform as they reflect biases and other shortcomings of different data collection methods. Nevertheless, uniform missing data is a common assumption made when no additional information is available about the underlying missing-edge pattern, and link prediction methods are frequently tested against uniformly missing edges. To investigate the impact of different missing-edge patterns on link prediction accuracy, we employ 9 link prediction algorithms from 4 different families to analyze 20 different missing-edge patterns that we categorize into 5 groups. Our comparative simulation study, spanning 250 real-world network datasets from 6 different domains, provides a detailed picture of the significant variations in the performance of different link prediction algorithms in these different settings. With this study, we aim to provide a guide for future researchers to help them select a link prediction algorithm that is well suited to their sampled network data, considering the data collection process and application domain. © 2024, CC BY.

关键词： Data acquisition

IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Jing Chen, Yuehai Du, Shaoyi Chen, Badong Principe, Jose C. School of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong Xi'An710049 China Institute of Articial Intelligence and Robotics College of Articial Intelligence Xi'an Jiaotong University Shanxi Xi'An710049 China The Computational NeuroEngineering Laboratory Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States

Predicting the trajectory of pedestrians in crowd scenarios is indispensable in self-driving or autonomous mobile robot field because estimating the future locations of pedestrians around is beneficial for policy decision to avoid collision. It is a challenging issue because humans have different walking motions, and the interactions between humans and objects in the current environment, especially between humans themselves, are complex. Previous researchers focused on how to model human-human interactions but neglected the relative importance of interactions. To address this issue, a novel mechanism based on correntropy is introduced. The proposed mechanism not only can measure the relative importance of human-human interactions but also can build personal space for each pedestrian. An interaction module including this data-driven mechanism is further proposed. In the proposed module, the data-driven mechanism can effectively extract the feature representations of dynamic human-human interactions in the scene and calculate the corresponding weights to represent the importance of different interactions. To share such social messages among pedestrians, an interaction-aware architecture based on long short-term memory network for trajectory prediction is designed. Experiments are conducted on two public datasets. Experimental results demonstrate that our model can achieve better performance than several latest methods with good performance. © 2023, CC BY-NC-ND.

关键词： Long short-term memory

Maize EfficientNet Fusion: Advancing Maize Disease Detection with MF-NET

学校读者我要写书评

暂无评论

Maize EfficientNet Fusion: Advancing Maize Disease Detection...

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Fatima Khalid Muhammad Hanif Qurat Ul Ain Faculty of Computer Science and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Engineering Topi KPK Pakistan Aerial Robotics and Vision Lab Ghulam Ishaq Khan Institute of Engineering Sciences and Engineering Topi KPK Pakistan Department of Computing Shifa Tameer-E-Millat University Islamabad Pakistan

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Maize is a vital global crop, essential for food security but highly susceptible to diseases that threaten yield and quality. Traditional methods for detecting these diseases are computationally intensive and rely on high-quality images, limiting their practical use in diverse field conditions. This research addresses these challenges by proposing MF-Net, a novel model that leverages two EfficientNet-b0 architectures with ReLU and Swish activation functions. Our approach involves partially training Model R with frozen early layers using ReLU, and fully training Model S with Swish activation for enhanced optimization and robustness. We employ model concatenation and feature fusion techniques to create a lightweight yet powerful model, complemented by additional layers for improved feature extraction and regularization. Experimental results on the Corn Disease and Severity (CD&S) dataset are compelling: MF-Net achieves a remarkable 95.7% accuracy and 96% precision in disease classification, and 88.3% accuracy and 88.46% precision in severity level detection. These results highlight the model's effectiveness under challenging conditions such as cluttered backgrounds and variable lighting, significantly reducing computation time without compromising accuracy. Hence, MF-Net presents an innovative and efficient solution for maize disease detection and severity assessment, offering significant advancements for agricultural practices and crop management.

关键词： Training Adaptation models Accuracy computational modeling Crops Lighting computer architecture Feature extraction Robustness Diseases

Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Mingyang Bing, Zhenshan Yao, Xiangtong Wang, Shuai Su, Hang Yang, Chenguang Huang, Kai Knoll, Alois Department of Informatics Technical University Munich Germany Tencent Robotics X Lab Singapore Dipartimento di Elettronica Politecnico di Milano Italy Bristol Robotics Laboratory University of the West of England United Kingdom School of Computer Science and Engineering Sun Yat-Sen University China Shenzhen Institute Sun Yat-Sen University China

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that are parametric and stationary, and does not consider out-of-distribution tasks during the evaluation, thus, restricting its application. In this paper, we propose MoSS, a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning to address this *** extend meta-RL to broad non-parametric task distributions which have never been explored before, and also achieve state-of-the-art results in non-stationary and out-of-distribution tasks. Specifically, MoSS consists of a task inference module and a policy module. We utilize the Gaussian mixture model for task representation to imitate the parametric and non-parametric task variations. Additionally, our online adaptation strategy enables the agent to react at the first sight of a task change, thus being applicable in non-stationary tasks. MoSS also exhibits strong generalization robustness in out-of-distributions tasks which benefits from the reliable and robust task representation. The policy is built on top of an off-policy RL algorithm and the entire network is trained completely off-policy to ensure high sample efficiency. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

A Full wCDM Analysis of KiDS-1000 Weak Lensing Maps using Deep Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fluri, Janis Kacprzak, Tomasz Lucchi, Aurelien Schneider, Aurel Refregier, Alexandre Hofmann, Thomas Institute of Particle Physics and Astrophysics Department of Physics ETH Zurich Switzerland Data Analytics Lab Department of Computer Science ETH Zurich Switzerland Swiss Data Science Center Paul Scherrer Institute Switzerland Department of Mathematics and Computer Science University of Basel Switzerland Center for Theoretical Astrophysics and Cosmology Institute for Computational Science University of Zurich Switzerland

We present a full forward-modeled wCDM analysis of the KiDS-1000 weak lensing maps using graph-convolutional neural networks (GCNN). Utilizing the CosmoGrid, a novel massive simulation suite spanning six different cosmological parameters, we generate almost one million tomographic mock surveys on the sphere. Due to the large data set size and survey area, we perform a spherical analysis while limiting our map resolution to HEALPix nside = 512. We marginalize over systematics such as photometric redshift errors, multiplicative calibration and additive shear bias. Furthermore, we use a map-level implementation of the non-linear intrinsic alignment model along with a novel treatment of baryonic feedback to incorporate additional astrophysical nuisance parameters. We also perform a spherical power spectrum analysis for comparison. The constraints of the cosmological parameters are generated using a likelihood-free inference method called Gaussian Process Approximate Bayesian Computation (GPABC). Finally, we check that our pipeline is robust against choices of the simulation parameters. We find constraints on the degeneracy parameter of S8 ≡ σ8pΩM/0.3 = 0.78+0−00606 for our power spectrum analysis and S8 = 0.79+0−00505 for our GCNN analysis, improving the former by 16%. This is consistent with earlier analyses of the 2-point function, albeit slightly higher. Baryonic corrections generally broaden the constraints on the degeneracy parameter by about 10%. These results offer great prospects for full machine learning based analyses of on-going and future weak lensing surveys. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys