检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Yike Noble, Jack H. Dept. of Computer Science Vanderbilt University United States Dept. of Electrical and Computer Engineering Vanderbilt University United States

Cochlear Implant (CI) procedures involve performing an invasive mastoidectomy to insert an electrode array into the cochlea. In this paper, we introduce a novel pipeline that is capable of generating synthetic multi-view videos from a single CI microscope image. In our approach, we use a patient’s pre-operative CT scan to predict the post-mastoidectomy surface using a method designed for this purpose. We manually align the surface with a selected microscope frame to obtain an accurate initial pose of the reconstructed CT mesh relative to the microscope. We then perform UV projection to transfer the colors from the frame to surface textures. Novel views of the textured surface can be used to generate a large dataset of synthetic frames with ground truth poses. We evaluated the quality of synthetic views rendered using Pytorch3D and PyVista. We found both rendering engines lead to similarly high-quality synthetic novel-view frames compared to ground truth with a structural similarity index for both methods averaging ∼0.86. A large dataset of novel views with known poses is critical for ongoing training of a method to automatically estimate microscope pose for 2D to 3D registration with the pre-operative CT to facilitate augmented reality surgery. This dataset will empower various downstream tasks, such as integrating Augmented Reality (AR) in the OR, tracking surgical tools, and supporting other video analysis studies. Copyright © 2024, The Authors. All rights reserved.

关键词： Cochlear implants

来源：评论

学校读者我要写书评

暂无评论

Motion Sickness Alleviation Based on a Mindfulness Brain-computer Interface 16

Motion Sickness Alleviation Based on a Mindfulness Brain-Com...

引用

16th International Conference on Advanced Computational Intelligence, ICACI 2024

作者： Zhu, Jiawei Bao, Xiaoyu Huang, Qiyun Wang, Tao Huang, Li Han, Yupeng Li, Kendi Chen, Di Xu, Kailin Wang, Zijian Jiang, Ya Li, Yuanqing Pazhou Laboratory Dept. Research Center for Brain-Computer Interface Guangzhou China Huizhou Desay SV Automotive Co. Ltd. Huizhou China South China University of Technology Dept. School of Automation Science and Engineering China Pazhou Laboratory Dept. Research Center for Brain-Computer Interface China South China Brain-Computer Interface Technology Co. Ltd. Guangzhou China

ISBN: (纸本)9798350308501

Motion sickness is a common affliction that affects nearly half of the global population and poses challenges to comfortable travel experiences, necessitating diverse intervention strategies. Pharmacological interventions have shown promise but present limitations due to side effects. To date, there is no non- pharmacological alleviation method for motion sickness that has been proven effective in a large population. In this study, we developed a novel mindfulness brain-computer interface (mindfulness BCI) for alleviation of motion sickness. Thirty-one subjects who were susceptible to motion sickness participated in our experiments in a real-world car motion environment. The experimental results demonstrated that the proposed mindfulness BCI can effectively alleviate motion sickness symptoms, where more than 90% of subjects reported the effectiveness of the mindfulness BCI system and a significant reduction of Motion Sickness Susceptibility Questionnaire (MISC) scores was obtained when comparing the BCI-based meditation state with the resting state for the subjects (t30=4.968, P © 2024 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Accessing Visual Information for Divyangjan

Accessing Visual Information for Divyangjan

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： M S Divya Rani Hrishikesh Vivekanand Ghodke M Manikandan R Manaswini Shivani K Sri Sai Venkata Gayathri Dhara Shreya Dept. of Electronics and Communication Engineering Presidency University Bengaluru Dept. of Computer Science Engineering Presidency University Bengaluru

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

Approximately 1.3 billion people worldwide suffer from a visual impairment. Typically, they must use Braille to read printed materials. However, when the content is not printed in Braille, these individuals have difficulties. Even though there are a lot of electronic reading aids available, the costs remain prohibitive. Therefore, our work suggests a low-cost document reader that uses a webcam to take pictures of printed materials. The Optical Character Recognition (OCR) framework's image-to-text conversion is then used to turn the acquired image into text. Finally, the Text to Speech (TTS) framework's text-to-speech conversion will be used to read the text aloud in speech format. Consequently, a person with a visual impairment can use hearing rather than touch to comprehend printed materials that are not written in Braille. Users may view documents printed in five different languages. The choice of different document sizes is this work's greatest novelty. The system is equipped with a Raspberry Pi, Arduino Uno, NEMA 17 stepper motors, a web camera and speaker. The Raspberry Pi, Arduino Uno, NEMA 17 stepper motors, webcam, and speaker are all part of the system.

关键词： Braille Visualization Costs Webcams Optical character recognition Visual impairment Government Motors Text to speech NEMA

来源：评论

学校读者我要写书评

暂无评论

Monocular Microscope to CT Registration using Pose Estimation of the Incus for Augmented Reality Cochlear Implant Surgery

arXiv

引用

arXiv 2024年

作者： Zhang, Yike Davalos, Eduardo Su, Dingjie Lou, Ange Noble, Jack H. Dept. of Computer Science Vanderbilt University United States Dept. of Electrical and Computer Engineering Vanderbilt University United States

For those experiencing severe-to-profound sensorineural hearing loss, the cochlear implant (CI) is the preferred treatment. Augmented reality (AR) aided surgery can potentially improve CI procedures and hearing outcomes. Typically, AR solutions for image-guided surgery rely on optical tracking systems to register pre-operative planning information to the display so that hidden anatomy or other important information can be overlayed and co-registered with the view of the surgical scene. In this paper, our goal is to develop a method that permits direct 2D-to-3D registration of the microscope video to the pre-operative Computed Tomography (CT) scan without the need for external tracking equipment. Our proposed solution involves using surface mapping of a portion of the incus in surgical recordings and determining the pose of this structure relative to the surgical microscope by performing pose estimation via the perspective-n-point (PnP) algorithm. This registration can then be applied to pre-operative segmentations of other anatomy-of-interest, as well as the planned electrode insertion trajectory to co-register this information for the AR display. Our results demonstrate the accuracy with an average rotation error of less than 25 degrees and a translation error of less than 2 mm, 3 mm, and 0.55% for the x, y, and z axes, respectively. Our proposed method has the potential to be applicable and generalized to other surgical procedures while only needing a monocular microscope during intra-operation. Copyright © 2024, The Authors. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

ML-Based Wildfire Prediction and Detection

ML-Based Wildfire Prediction and Detection

引用

Computing and Machine Intelligence (ICMI), International Conference on

作者： Chiragee C. Joshi Jaya S. S. K. Payyavula Soham Patel Yasser M. Alginahi Electrical and Computer Engineering Dept. University of Windsor Windsor Canada Computer Science Dept. Adrian College Michigan USA

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

This paper provides a comprehensive study on prediction and detection of wildfire using Machine Learning and Deep Learning algorithms. Due to the current environmental trends, wildfire possess a great threat to the ecosystem and human lives at a great cost. Multiple factors are the root cause for wildfires which include environmental factors like temperature, humidity, air pressure index, forest terranean, vegetation. Taking these factors into consideration, a Machine Learning model was built considering diverse algorithms to learn the previous trends and predict future wildfires instances. Based on the satellite imagery of previous wildfires, using CNN and AlexNet algorithms to detect wildfires that are currently taking place for early detection so to contain and control the fire without it causing any damage. Amalgamating these two algorithms, in a single graphical user interface, enhances user accessibility and convenience, providing an invaluable tool in wildfire management. The algorithm achieved an accuracy of average 96.33 % to predict wildfires and was able to detect them based on images at the rate of 93.66%.

关键词： Temperature sensors Wildfires Machine learning algorithms Accuracy Prediction algorithms Market research Data models

来源：评论

学校读者我要写书评

暂无评论

Optimal Channel Selection for EEG-Based Enhanced Brain Robot Interface for Autonomous Wheelchair

Optimal Channel Selection for EEG-Based Enhanced Brain Robot...

引用

International Conference on Awareness science and Technology (iCAST)

作者： Sabbir Ahmed Sibli Raihan Kabir Nuray Jannat Yutaka Watanobe Md Rashedul Islam Dept. of Computer Science and Engineering Fareast International University Dhaka Bangladesh Dept. of Computer Science and Engineering University of Aizu Aizuwakamatsu Fukushima Japan Dept. of Computer Science and Engineering BRAC University Dhaka Bangladesh Dept. of Computer Science and Engineering University of Asia Pacific Dhaka Bangladesh

Creating an autonomous wheelchair system based on EEG (electroencephalogram) signals is a fascinating and challenging concept. In non-invasive Brain robot Interface (BRI), scalp EEG signals acquired from the multiple channels come with different artifact types, majorly as an electrooculogram (EoG). Also, all the channels don't carry equally important information regarding the particular motor activities. The primary contribution of this paper is to denoise the EEG signal and then find the optimal channels to achieve the most informative EEG signals for the motor activity recognition. Thus, this research proposes a model where firstly the EoG artifacts have been removed from EEG signals with the regression method and other noises with Discrete Wavelet Transform (DWT). Secondly, It proposes a model of selecting optimal channels using a hybrid feature selection process, which includes a filter and wrapper method using sequential floating forward search (SFFS). Maximum Class Separability (MCS) and Support Vector Machine (SVM), both have been used for evaluating the channels. Then again SVM has been applied for classifying the motor activities by the signals recorded from the optimal channels. A dataset with four classes of human motor activities has been used for evaluating the whole proposed model. This proposed model shows the highest accuracy of 84.15% for the optimal channel set with Standard Deviation (STD) feature among other optimal channel sets of features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The ORIS tool: App, library, and toolkit for quantitative evaluation of non-Markovian systems

The ORIS tool: App, library, and toolkit for quantitative ev...

引用

作者： Carnevali, Laura Paolieri, Marco Vicario, Enrico Information Engineering Dept. Univ. Of Florence Italy Computer Science Dept. Univ. Of Southern California United States

ORIS is a tool for quantitative modeling and evaluation of concurrent systems with non-Markovian durations. It provides a Graphical User Interface (GUI) for model specification as Stochastic Time Petri Nets (STPNs), validation by interactive simulation, and evaluation by several techniques, computing instantaneous and cumulative rewards. It also provides an open-source Java Application Programming Interface (API) to automate the workflow, and it can be used as a toolkit for derivation and evaluation of STPNs in model driven engineering. As distinguishing features, ORIS implements transient and steady-state analysis of STPNs with underlying Markov Regenerative Process (MRP), and transient analysis of STPNs with underlying Generalized Semi-Markov Process (GSMP). It also implements nondeterministic analysis of Time Petri Nets (TPNs), simulation of STPNs, and solution methods for Continuous-Time Markov Chains (CTMCs) and MRPs with at most one non-exponential timer in each state. The well-engineered software architecture of ORIS supports agile implementation of new STPN features, new modeling formalisms, and new analysis methods. © 2022 is held by the owner/author(s).

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

An Ensemble ML Model to Predict the Wastage of Food: Towards Achieving the Food Sustainability

An Ensemble ML Model to Predict the Wastage of Food: Towards...

引用

Next-Generation Computing, IoT and Machine Learning (NCIM), International Conference on

作者： Md Masrur Masuk Shopnil Asmaul Husna Shaheena Sultana Muhammad Nazrul Islam Dept. of Computer Science and Engineering Military Institute of Science and Technology Dhaka Dept. of Computer Science and Engineering NotreDame University Bangladesh Dhaka

Food waste is a major issue in students' hostel or dormitories, where uneaten food often ends up in the garbage, resulting in economic losses as well as reducing the food sus-tainability. Although Machine Leaning (ML) has emerged as a promising tool for predicting future events in several files, but a very few has been focused to generate accurate predictions and reducing food waste by analyzing read data for a particular context or a country. Therefore, the objective of this research is to explore the factors of affecting food waste in students' hostel or dormitories and to develop an ensemble ML-based food waste prediction system for the student hostel or dormitories. In order to attain these objectives, this study firstly find out the 18 key features that ensure a comprehensive understanding of food waste patterns; then collected the data against these features over the last six months from various mess records of a students' hostel of an engineering university situated in Dhaka, Bangladesh. Secondly, six classification models were developed and analyzed their results and found that Random Forest and Decision Tree performed best accurate prediction (75.41%). Thirdly, the all possible combinations of the studies ML models were explored to find out the best possible ensemble combination; as such, the proposed ensemble ML model showed the highest F1-score of 86.88% that considers the Random Forest and AdaBoost; while all other possible combinations showed around 80–82% F1-score. This research thus contributes to the broader goal of reducing food waste and promoting sustainability in students' mess and other food service settings; as well as may assist the management team in making data-driven decisions about food production, purchasing, and resource allocation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full-duplex OFDM modulation based FSO-Fiber system for 5G scenario 6

Full-duplex OFDM modulation based FSO-Fiber system for 5G sc...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Arya, Vivek Kumari, Meet Chauhan, Rahul Sharma, Neha Dept. of ECE Haridwar India Chandigarh University Dept. of ECE Mohali India Graphic Era Hill University Computer Science and Engineering Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9798350304480

A full-duplex 40/40Gbps orthogonal frequency division multiplexing (OFDM) basics free space optics (FSO)-fiber system is presented. The performance is measured under different turbulences effects with fiber impairments. The simulation results indicate that faithful fiber and FSO transmission ranges of 40km and 350m under turbulences effects is obtained. It is also observed that fiber-FSO link indicates best performance compared to fiber and FSO links with signal to noise ratio of 25dB in upstream and 10dB downstream direction. Also, the designed system shows that best performance than other existing ones for fifth generation (5G) applications. © 2023 IEEE.

关键词： free space optics (FSO) orthogonal frequency division multiplexing (OFDM) quadrature amplitude modulation (QAM) turbulence

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Analysis of Reinforcement Learning for Massive-MultiAgent Systems 2

Sensitivity Analysis of Reinforcement Learning for Massive-M...

引用

2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2022

作者： Liu, Zhiyuan Shen, Tianqi Li, Yupei Dept. of Computer Science University of Toronto TorontoON Canada Department of Aero Space Information Engineering Beihang University Beijing China Dept. of Computer Science University of Oxford Oxford United Kingdom

ISBN: (纸本)9781510657717

Over the past few years, reinforcement learning has become one of the most popular topics in the field of Machine Leaning. Its nature of unsupervised learning has made it rather powerful and convenient for solving specific tasks. Unlike decision trees, reinforcement learning models do not need a pre-configured policy tree to conduct actions, which makes it possible for machinery to solve extreme complex tasks such as playing GO or other games. One of the most powerful networks is the Deep-Q network. DQN picks the optimal action under current situation to achieve the largest reward. However, even though DQN has been tested to work well on single agent environments, there lack experiments of its performance on large massive multi-agent environment trainings. This paper conducts several experiments in Petting Zoo to test the performance and other factors that affect the performance of the DQN in a massive-multi-agent system. Results demonstrates that lager number of agents and experience replay size improve the performance of DQN in a "Battle" environment. © 2022 SPIE. All rights reserved.

关键词： Multi agent systems

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：