检索结果-内蒙古大学图书馆

Option pricing for Barndorff-Nielsen and Shephard model by supervised deep learning

INTERNATIONAL JOURNAL OF FINANCIAL ENGINEERING 2025年第1期12卷

作者： Arai, Takuji Imai, Yuto Keio Univ Dept Econ 2-15-45 MitaMinato ku Tokyo 1088345 Japan Nishogakusha Univ Fac Int Polit & Econ 6-16 SanbanchoChiyoda ku Tokyo 1028336 Japan

This paper aims to develop a supervised deep learning scheme to compute call option prices for the Barndorff-Nielsen and Shephard model with a non-martingale asset price process having infinite active jumps. In our deep learning scheme, teaching data are generated through the Monte Carlo method developed by Arai and Imai [(2024). Monte Carlo simulation for Barndorff-Nielsen and Shephard model under change of measure, Mathematics and Computers in Simulation, 218, 223-234]. Moreover, the BNS model includes many parameters, which makes the deep learning accuracy worse. Therefore, we will create another input parameter using the Black-Scholes formula. As a result, the accuracy is improved dramatically.

关键词： Barndorff-Nielsen and Shephard model stochastic volatility model supervised deep learning Monte Carlo simulation Black-Scholes formula

来源：评论

学校读者我要写书评

暂无评论

supervised deep learning Algorithms for Delaminations Detection on Composites Panels by Wave Propagation Signals Analysis 10th

Supervised Deep Learning Algorithms for Delaminations Detect...

引用

10th European Workshop on Structural Health Monitoring (EWSHM)

作者： Monaco, Ernesto Boffa, Natalino D. Ricci, Fabrizio Univ Napoli Federico II Dept Ind Engn Aerosp Sect Naples Italy

ISBN: (纸本)9783031073229;9783031073212

Structural Health Monitoring deals mainly with sensorised structures providing signals related to their "health status" aiming at lower maintenance costs and weights of aircrafts. Much effort has been spent during last years on analysis techniques for evaluating metrics correlated to damages' existence, location and extensions from signals provided by the sensors networks. deep learning techniques can be a very powerful instrument for signals patterns reconstruction and selection but require the availability of consistent amount of both healthy and damaged structural configuration experimental data sets, with high materials and testing costs, or data reproduced by validated numerical simulations. Within this work explicit finite element simulation of impact damages on composite plates have been used to populate the data sets necessary for deep learning algorithm. The final scope is the detection of delaminations into composites plates for aerospace employ. Numerical time history signals have been collected for both the healthy and unhealthy state of the structure and transformed into RGB images. A convolutional algorithm trained on healthy and damaged signals has been used to identify anomalies in the form of delamination in the structure. This paper will present the preliminary results achieved by the authors.

关键词： Composite structures Structural health monitoring deep neural networks supervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Ride Comfort Improvement with Preview Control Semi-active Suspension System Based on supervised deep learning

引用

SAE INTERNATIONAL JOURNAL OF VEHICLE DYNAMICS STABILITY AND NVH 2021年第1期5卷 31-44页

作者： Zhu, Yugang Bian, Xueliang Su, Lili Gu, Cansong Wang, Zhenfeng Shi, Chenlu Hebei Univ Technol Tianjin Peoples R China CATARC Tianjin Automot Engn Res Inst Co Ltd Tianjin Peoples R China

As known to all, it is a challenging task to solve the delay of a controllable suspension system under the transient road. Thus, how to effectively and low-costly acquire road information and choose the reasonable control algorithm remains a hot topic in both academia and industry. With the rapid development and extensive application of the advanced intelligent driving system, a large number of sensors, such as cameras, have been installed on the vehicle, and deep learning technology has also been widely used to identify lane recognition, traffic direction signal, and pedestrian detection, but rarely used in semi-active suspension control. To address the above issues, a novel skyhook preview control (SPC) approach, which combines supervised deep learning, is proposed in the article. Firstly, a full vehicle dynamics model for semi-active suspension is established. Secondly, supervised deep learning (YOLOv3) is adopted to identify the transient road to preview the semi-active suspension. Finally, by comparing the vehicle road test results of the SPC with that of the skyhook wheelbase preview controller (SWPC), the skyhook controller (SC), and the passive suspension (PS), it is concluded that the designed algorithm can effectively improve the ride comfort of the vehicle.

关键词： Advanced intelligent driving system Semi-active suspension Transient road Skyhook preview control approach supervised deep learning YOLOv3

来源：评论

学校读者我要写书评

暂无评论

USING supervised deep learning FOR HUMAN AGE ESTIMATION PROBLEM 2

USING SUPERVISED DEEP LEARNING FOR HUMAN AGE ESTIMATION PROB...

引用

International Workshop on Photogrammetric and Computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine

作者： Drobnyh, K. A. Polovinkin, A. N. Lobachevsky State Univ Nizhny Novgorod Nizhnii Novgorod Russia

Automatic facial age estimation is a challenging task upcoming in recent years. In this paper, we propose using the supervised deep learning features to improve an accuracy of the existing age estimation algorithms. There are many approaches solving the problem, an active appearance model and the bio-inspired features are two of them which showed the best accuracy. For experiments we chose popular publicly available FG-NET database, which contains 1002 images with a broad variety of light, pose, and expression. LOPO (leave-one-person-out) method was used to estimate the accuracy. Experiments demonstrated that adding supervised deep learning features has improved accuracy for some basic models. For example, adding the features to an active appearance model gave the 4% gain (the error decreased from 4.59 to 4.41).

关键词： Machine learning Age Estimation supervised deep learning Active Appearance Model Bio-Inspired Feature Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

The Potential of the Intel® Xeon Phi™ for supervised deep learning 17

The Potential of the Intel® Xeon Phi™ for Supervised Deep ...

引用

2015 IEEE 17th International Conference on High Performance Computing and Communications (HPCC)

作者： Viebke, Andre Pllana, Sabri Linnaeus Univ Dept Comp Sci S-35195 Vaxjo Sweden

ISBN: (纸本)9781479989379

supervised learning of Convolutional Neural Networks (CNNs), also known as supervised deep learning, is a computationally demanding process. To find the most suitable parameters of a network for a given application, numerous training sessions are required. Therefore, reducing the training time per session is essential to fully utilize CNNs in practice. While numerous research groups have addressed the training of CNNs using GPUs, so far not much attention has been paid to the Intel Xeon Phi coprocessor. In this paper we investigate empirically and theoretically the potential of the Intel Xeon Phi for supervised learning of CNNs. We design and implement a parallelization scheme named CHAOS that exploits both the thread-and SIMD-parallelism of the coprocessor. Our approach is evaluated on the Intel Xeon Phi 7120P using the MNIST dataset of handwritten digits for various thread counts and CNN architectures. Results show a 103.5x speed up when training our large network for 15 epochs using 244 threads, compared to one thread on the coprocessor. Moreover, we develop a performance model and use it to assess our implementation and answer what-if questions.

关键词： graphics processing units learning (artificial intelligence) neural nets parallel processing CHAOS CNN GPU Intel Xeon Phi 7120P Intel Xeon Phi coprocessor SIMD-parallelism convolutional neural network parallelization scheme supervised deep learning thread-parallelism Biological neural networks Chaos Coprocessors Instruction sets Machine learning Neurons Training Convolutional Neural Networks Intel Xeon Phi Many-core Parallel Computing supervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Connectivity-maintenance Control of a Team of Unmanned Aerial Vehicles using supervised deep learning 10

Distributed Connectivity-maintenance Control of a Team of Un...

引用

10th International Conference on Control, Automation and Robotic (ICCAR)

作者： Nazeer, Muhammad Sunny Aggravi, Marco Giordano, Paolo Robuffo Univ Rennes Inria IRISA CNRS Rennes France Natl Univ Singapore Dept Mech Engn Singapore Singapore

ISBN: (纸本)9798350373172;9798350373189

This paper presents the design of a decentralized connectivity-maintenance technique for the teleoperation of a team of multiple Unmanned Aerial Vehicles (UAV). Different from current, typical connectivity-maintenance approaches, the proposed technique uses machine learning to attain significantly more scalability in terms of number of UAVs that can be part of the robotic team. It uses supervised deep learning (SDL) with Artificial Neural Networks (ANN), so that each robot can extrapolate the necessary actions for keeping the team connected in one computation step, regardless the size of the team. We compared the performance of our proposed approach vs. a state-of-the-art model-based connectivity-maintenance algorithm when managing a team composed of two, four, six, and ten aerial mobile robots. Results show that our approach can keep the computational cost almost constant as the number of drones increases, reducing it significantly with respect to model-based techniques. For example, our SDL approach needs 83% less time than a state-of-the-art model-based connectivity-maintenance algorithm when managing a team of ten drones.

关键词： Multi-robot systems supervised deep learning Machine learning Robot Control Control Imitation learning (IL) Real-time Control

来源：评论

学校读者我要写书评

暂无评论

Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using supervised deep learning

引用

IEEE ACCESS 2020年 8卷 224044-224058页

作者： Jin, Chengnan Shin, Seungmin Yu, Jiyoung Rhee, Sehun Hanyang Univ Sch Mech Convergence Engn Seoul 04763 South Korea Korea Inst Ind Technol Joining R&D Grp Incheon 21999 South Korea

Creating and consistently maintaining the weld shape during gas metal arc welding (GMAW) is vital for ensuring and maintaining the specified weld quality. However, the back-bead is often not uniformly generated owing to the change that occurs in the narrow gap between the base metals during butt joint GMAW, which substantially influences weldability. Automating the GMAW process requires the capability of real-time weld quality monitoring and diagnosis. In this study, we developed a convolutional neural network-based back-bead prediction model. Specifically, scalogram feature image data were acquired by performing Morlet wavelet transform on the welding current measured in the short-circuit transform mode of the GMAW process. The acquired scalogram feature image data were then analyzed and used to develop labeled weld quality training data for the convolutional neural network model. The model predictions were compared with welding data acquired through additional experiments to validate the proposed prediction model. The prediction accuracy was approximately 93.5%, indicating that the findings of this study could serve as a foundation for the future development of automated welding systems.

关键词： Welding Feature extraction Metals Monitoring Shape Wavelet transforms Transforms Gas metal arc welding back-bead monitoring automated weld quality control supervised deep learning time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Seismic volumetric dip estimation via a supervised deep learning model by integrating realistic synthetic data sets

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2022年第0期218卷

作者： Lou, Yihuai Li, Shizhen Liu, Naihao Liu, Rongchang Zhejiang Univ Ctr Hypergrav Expt & Interdisciplinary Res Hangzhou 310058 Zhejiang Peoples R China Zhejiang Univ Coll Civil Engn & Architecture MOE Key Lab Soft Soils & Geoenvironm Engn Hangzhou Zhejiang Peoples R China Xi An Jiao Tong Univ Coll Artificial Intelligence Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Informat & Commun Engn Xian 710049 Shaanxi Peoples R China CNPC PetroChina Res Inst Petr Explorat & Dev RIPED Beijing 100083 Peoples R China

Accurately estimating seismic volumetric dip is a crucial task for subsequent seismic processing and interpre-tation. The traditional window based dip estimation methods, such as gradient structure tensor (GST) and semblance based multiple window scanning strategy, usually struggle with complicated geological structures containing multiple reflections with different dips in the analysis window. Recently, deep learning has been utilized to estimate seismic volumetric dips. However, dip labels used for current convolutional neural network (CNN) based methods are usually created using traditional dip estimation methods, which are not the ground truth, or from specific geological structure models, which only cover a part of typical geological structures. We propose a supervised deep learning model to improve the accuracy of seismic dip estimation by integrating realistic synthetic data sets. Firstly, we propose a synthetic seismic data generation workflow for seismic volumetric dip estimation, which aims to simulate geological features from real seismic data. We then create numerous unique synthetic seismic images with realistic and diverse structural features by using the proposed workflow. To ensure that generated dip labels are exactly accurate and can be regarded as the ground truth, we create synthetic seismic images by deforming horizontal reflection images according to corresponding dip labels. We finally train an end-to-end supervised deep learning model, which focuses on the parallel processing and the extraction of various feature maps simultaneously, utilizing the created realistic synthetic data. The applications on synthetic and 3D real seismic data (Netherlands F3 block) effectually demonstrate the validity and effectiveness of our proposed model.

关键词： Seismic volumetric dip estimation supervised deep learning Multi-channel convolution block Seismic attribute

来源：评论

学校读者我要写书评

暂无评论

Method for directly and instantaneously predicting conductive heat transfer topologies by using supervised deep learning

引用

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER 2019年 109卷 104368-000页

作者： Lin, Qiyin Liu, Zheng Hong, Jun Xi An Jiao Tong Univ Key Lab Educ Minist Modern Design & Rotor Bearing Syst Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Mech Engn Inst Design Sci & Basic Components Xian 710049 Shaanxi Peoples R China

A supervised deep learning predictor was developed to directly, intelligently, and instantaneously infer conductive heat transfer topologies. The architecture of the proposed supervised predictor consists of an encoder to decrease the dimensionality of the input data and a decoder. The high accuracy of the predictor is enabled by three parallel linked supervised deep learning predictors. Once the predictor has been trained and the physical parameters of the heat conduction problem, such as the boundary and constraint conditions, have been provided as input, the predictor directly and instantly outputs the optimized topology.

关键词： Topology optimization supervised deep learning Intelligent prediction Non-iterative method Instantaneous prediction

来源：评论

学校读者我要写书评

暂无评论

Using supervised deep-learning to Model Edge-FBG Shape Sensors: a Feasibility Study

Using Supervised Deep-Learning to Model Edge-FBG Shape Senso...

引用

Optical Sensors Conference

作者： Manavi, Samaneh Renna, Tatiana Horvath, Antal Freund, Sara Zam, Azhar Rauter, Georg Schade, Wolfgang Cattin, Philippe C. Univ Basel Dept Biomed Engn Ctr Med Image Anal & Nav CIAN Gewerbestr 14 CH-4123 Allschwil Switzerland Univ Basel Dept Biomed Engn Biomed Laser & Opt Grp BLOG Gewerbestr 14 CH-4123 Allschwil Switzerland Univ Basel Dept Biomed Engn Bioinspired RObots MED Lab BIROMED Lab Gewerbestr 14 CH-4123 Allschwil Switzerland Heinrich Hertz Inst Nachrichtentech Berlin GmbH HHI Fraunhofer Inst Telecommun Dept Fiber Opt Sensor Syst Stollen 19H D-38640 Goslar Germany

ISBN: (数字)9781510643796

ISBN: (纸本)9781510643796

Continuum robots are snake-like elastic structures that can be bent anywhere along their length hence representing ideal tools for minimally invasive surgery. To accurately control these flexible manipulators, 3D shape sensors that are small, sterile, immune to electromagnetic noise, and easy to replace are required. Fiber Bragg Grating (FBG)-based shape sensing is a promising approach for this task. The recently proposed Edge-FBG based shape sensors are particularly promising due to their high flexibility and high spatial resolution. In Edge-FBGs, the amplitude change at the Bragg wavelengths contains the strain information at sensing nodes. However, such sensors are sensitive to changes in the spectrum profile caused by undesired bending-related phenomena. As the existing theories cannot accurately predict the spectrum profile in curved optical fibers, changes in the initial intensity that each Edge-FBG receives are not precisely known. These uncontrolled variations cause inaccuracies in shape predictions and make standard characterization techniques less suitable for Edge-FBG sensors. Therefore, developing a model that distinguishes the strain signal from the changes in the spectrum profile is needed. Machine learning techniques are great tools for studying complex problems, making it possible to explore the full spectrum of the Edge-FBG sensor for identifying patterns caused by bending. In this paper, we studied the feasibility of using a low-cost interrogation system for the Edge-FBGs, considering the minimum required signal-to-noise ratio. We trained a neural network with supervised deep learning to directly extract the shape information from the Edge-FBG spectrum. The designed model can predict the shape of a fiber sensor consisting of five Edge-FBG triplets with less than 6 mm tip error.

关键词： supervised deep learning shape sensing bending birefringence bending loss Edge-FBG fiber sensor

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：