the proceedings contain 89 papers. the special focus in this conference is on Neural Computing for Advanced Applications. the topics include: Online Car-Hailing Order Matching Method Based on Demand Clustering an...
ISBN:
(纸本)9789819770069
the proceedings contain 89 papers. the special focus in this conference is on Neural Computing for Advanced Applications. the topics include: Online Car-Hailing Order Matching Method Based on Demand Clustering and Reinforcement Learning;Multi-objective Optimization of Antenna Based on Improved WOA-BP Neural Network;A Multi-mechanism Collaborative Seagull Optimization Algorithm for Optimizing BP Neural Network Classification Model;an analysis on Balance Model of Exploration and Exploitation Under Decoupled-Learning pattern for Large-Scale Particle Swarm Optimizers;marine Ship Detection Under Fog Conditions Based on an Improved Deep-Learning Approach;skeleton-Based Point Cloud Sampling and Its Facilitation to Classification;multi-agent Reinforcement Learning for Taxi-Fleet Cruising Strategy in Ride-Hailing Services;a New Indoor Occupancy Detection Model by Integrating the Efficient Multi-scale Attention Mechanism into the EfficientDet Model;a Novel Automatic Generation Method for Neural Network by Using Iterative Function System;a Predictive Maintenance Platform for a Conveyor Motor Sensor System Using Recurrent Neural Networks;A Deep Learning-Based Method Facilitates scRNA-seq Cell Type Identification;adaptive Hierarchical Clustering Based Student Group Exercise Recommendation via Multi-objective Evolutionary Method;Quantile Regression and GCN Ensembled Hybrid Interval Forecasting Model for Wind Power Generation;efficient Path Planning for Large-Scale Vehicular Networks via Multi-agent Mean Field Reinforcement Learning;a Fast and Accurate Reconstruction Method for Boiler Temperature Field Based on Inverse Distance Weight and Long Short-Term Memory;RoBERTa-wwm-CBA: A Mental Disease Identification Model Based on RoBERTa-wwm and Hybrid Neural Networks;3D Pose Estimation of Markerless Fish on Deep Learning;safety Helmet-Wearing Detection Method Fusing Pose Estimation;Clothes Image Retrieval via Learnable FashionCLIP;mannequin2Real+: A Two-Stage Framework for Generating P
the proceedings contain 89 papers. the special focus in this conference is on Neural Computing for Advanced Applications. the topics include: Online Car-Hailing Order Matching Method Based on Demand Clustering an...
ISBN:
(纸本)9789819770007
the proceedings contain 89 papers. the special focus in this conference is on Neural Computing for Advanced Applications. the topics include: Online Car-Hailing Order Matching Method Based on Demand Clustering and Reinforcement Learning;Multi-objective Optimization of Antenna Based on Improved WOA-BP Neural Network;A Multi-mechanism Collaborative Seagull Optimization Algorithm for Optimizing BP Neural Network Classification Model;an analysis on Balance Model of Exploration and Exploitation Under Decoupled-Learning pattern for Large-Scale Particle Swarm Optimizers;marine Ship Detection Under Fog Conditions Based on an Improved Deep-Learning Approach;skeleton-Based Point Cloud Sampling and Its Facilitation to Classification;multi-agent Reinforcement Learning for Taxi-Fleet Cruising Strategy in Ride-Hailing Services;a New Indoor Occupancy Detection Model by Integrating the Efficient Multi-scale Attention Mechanism into the EfficientDet Model;a Novel Automatic Generation Method for Neural Network by Using Iterative Function System;a Predictive Maintenance Platform for a Conveyor Motor Sensor System Using Recurrent Neural Networks;A Deep Learning-Based Method Facilitates scRNA-seq Cell Type Identification;adaptive Hierarchical Clustering Based Student Group Exercise Recommendation via Multi-objective Evolutionary Method;Quantile Regression and GCN Ensembled Hybrid Interval Forecasting Model for Wind Power Generation;efficient Path Planning for Large-Scale Vehicular Networks via Multi-agent Mean Field Reinforcement Learning;a Fast and Accurate Reconstruction Method for Boiler Temperature Field Based on Inverse Distance Weight and Long Short-Term Memory;RoBERTa-wwm-CBA: A Mental Disease Identification Model Based on RoBERTa-wwm and Hybrid Neural Networks;3D Pose Estimation of Markerless Fish on Deep Learning;safety Helmet-Wearing Detection Method Fusing Pose Estimation;Clothes Image Retrieval via Learnable FashionCLIP;mannequin2Real+: A Two-Stage Framework for Generating P
Calcium imaging, as a means of high temporal and spatial resolution, has been widely used in neuroscience research to monitor the dynamic activity of neuronal networks. In this paper, a comprehensive analysis process ...
详细信息
ISBN:
(纸本)9798400712203
Calcium imaging, as a means of high temporal and spatial resolution, has been widely used in neuroscience research to monitor the dynamic activity of neuronal networks. In this paper, a comprehensive analysis process for calcium imaging data is proposed to improve the accuracy and effectiveness of data processing, and the analysis is performed using OASIS. First, Z-score standardization is applied to normalize the signal of each neuron to eliminate the difference in signal amplitude between different neurons. then, we design and implement a high-pass filtering method based on the frequency domain to extract high-frequency components and remove low-frequency noise and background signals by fast Fourier transform (FFT), thus enhancing the signal features of neuronal activity. the method was verified on two sets of calcium imaging data, and the results show that the signal after filtering is clearer and can capture the instantaneous activity and synchronization pattern of neurons more effectively. Finally, the result displays that the highly connected neurons in the primary visual cortex mainly interact with a specific population of neurons, indicating the existence of a specific local network structure. this study provides an effective tool for calcium imaging data analysis in the field of neuroscience and is expected to be widely used in the dynamic study of complex neural networks.
A driver’s gaze has often been used to estimate driver attentiveness or focus during driving. these works often rely on simple definitions of what it means to "see", namely, a driver’s gaze falling on an o...
详细信息
Accurate segmentation of Multiple Sclerosis (MS) lesions in longitudinal MRI scans is crucial for monitoring disease progression and treatment efficacy. Although changes across time are taken into account when assessi...
详细信息
the increasing use of Artificial Intelligence (AI) in software development underscores the need to select suitable Large Language Models (LLMs) for automating software unit test generation. No prior work has been cond...
详细信息
ISBN:
(数字)9798331530983
ISBN:
(纸本)9798331530990
the increasing use of Artificial Intelligence (AI) in software development underscores the need to select suitable Large Language Models (LLMs) for automating software unit test generation. No prior work has been conducted to evaluate the performance of LLM in this domain. To address this gap, this study evaluates the effectiveness of four prominent LLMs—GPT-4, Claude 3.5, Command-R-08-2024 and Llama 3.1—in generating unit test cases. this study particularly aims to evaluate the performance of these models in real-world testing scenarios. Hence, 106 test cases from 23 test suites based on interviews with software experts and QA engineers are used to ensure relevance and comprehensiveness. these test cases are analyzed using JavaScript Engines Specification Tester (JEST) for code coverage and Stryker for mutation testing while adopting both quantitative and qualitative analysis. the findings reveal that Claude 3.5 consistently outperforms the other models against test success rate, statement coverage, and mutation score withthe achieved accuracy of 93.33%, 98.01%, and 89.23% respectively. the results also provide insights into the capabilities of LLMs for automated unit test generation and their integration into the continuous software integration pipeline. Further, the findings authenticated the importance of systematically comparing LLMs for test case generation.
wavelet methods were applied to semiparametric regression models. Weak dependence and moment restrictions on the errors were assumed. the estimators of parameter and nonparameter were presented. the strong consistency...
详细信息
ISBN:
(纸本)9781424410651
wavelet methods were applied to semiparametric regression models. Weak dependence and moment restrictions on the errors were assumed. the estimators of parameter and nonparameter were presented. the strong consistency of the wavelet estimators in the models was established.
In this paper the notion of univariate orthogonal wavelet packets is generalized. First, the definition nonseparable biorthogonal bivariate wavelet packets is given and a procedure for constructing them is presented N...
详细信息
ISBN:
(纸本)9781424410651
In this paper the notion of univariate orthogonal wavelet packets is generalized. First, the definition nonseparable biorthogonal bivariate wavelet packets is given and a procedure for constructing them is presented Next, the biorthogonality properties of biorthogonal bivariate wavelet packets is investigated.
In this paper, the author gives a new concept about waveletanalysis {omega(j), g}, j is an element of z and a concrete method of construction. this method avoids multi-scale analysis but directly define wavelet analy...
详细信息
ISBN:
(纸本)9781424410651
In this paper, the author gives a new concept about waveletanalysis {omega(j), g}, j is an element of z and a concrete method of construction. this method avoids multi-scale analysis but directly define waveletanalysis which satisfies general properties of wavelets.
In this paper, we show that there exist wavelet frame generated by two functions which have good dual wavelet frames, but for which the canonical dual wavelet frame does not consist of wavelets. that is to say, the ca...
详细信息
ISBN:
(纸本)9781424410651
In this paper, we show that there exist wavelet frame generated by two functions which have good dual wavelet frames, but for which the canonical dual wavelet frame does not consist of wavelets. that is to say, the canonical dual wavelet frame cannot be generated by the translations and dilations of a single function.
暂无评论