检索结果-内蒙古大学图书馆

Isolation of Microcrystalline Cellulose from Wood and Fabrication of Polylactic Acid(PLA)Based Green Biocomposites

Journal of Renewable Materials 2024年第8期12卷 1455-1474页

作者： Selwin Maria Sekar Rajini Nagarajan Ponsuriyaprakash Selvakumar Ismail Sikiru Oluwarotimi Kumar Krishnan Faruq Mohammad Mohammed Rafi Shaik Nadir Ayrilmis Department of Mechanical Engineering Kalasalingam Academy of Research and EducationKrishnankoil626126India Department of Mechanical Engineering SSM Institute of Engineering and TechnologyDindigul624002India Department of Engineering Centre for Engineering ResearchSchool of PhysicsEngineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK INTI International University Persiaran Perdana BBNNilai71800Malaysia Department of Chemistry College of ScienceKing Saud UniversityP.O.Box 2455Riyadh11451Kingdom of Saudi Arabia Department of Wood Mechanics and Technology Faculty of ForestryIstanbul University–CerrahpasaBahcekoySariyerIstanbul34473Turkey

An innovative microcrystalline cellulose(MCC)natural fibre powder-reinforced PLA biocomposite was investigated using the hand lay-up *** polymer matrix composite(PMC)samples were prepared by varying the weight percentages(wt.%)of both PLA matrix and MCC reinforcement:pure PLA/100:0,90:10,80:20,70:30,60:40 and 50:50 wt.%,*** the results obtained,MCC powder,with its impressive aspect ratio,proved to be an ideal reinforcement for the PLA,exhibiting exceptional mechanical *** was evident that the 80:20 wt.%biocomposite sample exhibited the maximum improvement in the tensile,flexural,notched impact,compressive strength and hardness by 28.85%,20.00%,91.66%,21.53%and 35.82%,respectively compared to the pure PLA ***,during the thermogravimetric analysis(TGA),the same 80:20 wt.%biocomposite sample showed a minimum weight loss of 20%at 400℃,among *** morphological study using Field Emission Scanning Electron Microscopy(FE-SEM)revealed that the uniform distribution of cellulose reinforcement in the PLA matrix actively improved the mechanical properties of the biocomposites,especially the optimal 80:20 wt.%***,it was evident that the optimal PLA/cellulose biocomposite sample could be a suitable and alternative sustainable,environmentally friendly and biodegradable material for semi/structural applications,replacing synthetic and traditional components.

关键词： Polylactic acid micro crystalline cellulose biocomposite characterizations FESEM environmental pollution

来源：评论

学校读者我要写书评

暂无评论

Chat Failures and Troubles: Reasons and Solutions

arXiv

引用

arXiv 2023年

作者： Helal, Manal Holthaus, Patrick Lakatos, Gabriella Amirabdollahian, Farshid University of Hertfordshire School of Physics Engineering and Computer Science Hatfield United Kingdom

This paper examines some common problems in Human-Robot Interaction (HRI) causing failures and troubles in Chat. A given use case’s design decisions start with the suitable robot, the suitable chatting model, identifying common problems that cause failures, identifying potential solutions, and planning continuous improvement. In conclusion, it is recommended to use a closed-loop control algorithm that guides the use of trained Artificial Intelligence (AI) pre-trained models and provides vocabulary filtering, re-train batched models on new datasets, learn online from data streams, and/or use reinforcement learning models to self-update the trained models and reduce errors. © 2023, CC BY.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Electrically tunable planar liquid-crystal singlets for simultaneous spectrometry and imaging

引用

Light(science & Applications) 2024年第11期13卷 2589-2598页

作者： Zhou Zhou Yiheng Zhang Yingxin Xie Tian Huang Zile Li Peng Chen Yan-qing Lu Shaohua Yu Shuang Zhang Guoxing Zheng Electronic Information School and School of MicroelectronicsWuhan UniversityWuhan 430072China NUS Graduate School National University of SingaporeSingapore 119077Singapore Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore National Laboratory of Solid State Microstructures Key Laboratory of Intelligent Optical Sensing and Manipulationand College of Engineering and Applied SciencesNanjing UniversityNanjing 210093China Peng Cheng Laboratory Shenzhen 518055China New Cornerstone Science Laboratory Department of PhysicsUniversity of Hong KongHong KongChina Department of Electrical and Electronic Engineering University of Hong KongHong KongChina Wuhan Institute of Quantum Technology Wuhan 430206China

Conventional hyperspectral cameras cascade lenses and spectrometers to acquire the spectral datacube,which forms the fundamental framework for hyperspectral ***,this cascading framework involves tradeoffs among spectral and imaging performances when the system is driven toward ***,we propose a spectral singlet lens that unifies optical imaging and computational spectrometry functions,enabling the creation of minimalist,miniaturized and high-performance hyperspectral *** a paradigm,we capitalize on planar liquid crystal optics to implement the proposed framework,with each liquid-crystal unit cell acting as both phase modulator and electrically tunable spectral *** with various targets show that the resulting millimeter-scale hyperspectral camera exhibits both high spectral fidelity(>95%)and high spatial resolutions(~1.7 times the diffraction limit).The proposed“two-in-one”framework can resolve the conflicts between spectral and imaging resolutions,which paves a practical pathway for advancing hyperspectral imaging systems toward miniaturization and portable applications.

关键词： crystal planar singlet

来源：评论

学校读者我要写书评

暂无评论

The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition

引用

computers, Materials & Continua 2023年第1期74卷 1709-1722页

作者： Mohammad Amaz Uddin Mohammad Salah Uddin Chowdury Mayeen Uddin Khandaker Nissren Tamam Abdelmoneim Sulieman Department of Computer Science and Engineering BGC Trust University BangladeshChittagong4381Bangladesh Centre for Applied Physics and Radiation Technologies School of Engineering and TechnologySunway UniversityBandar SunwaySelangor47500Malaysia Department of Physics College of SciencesPrincess Nourah bint Abdulrahman UniversityP.O Box 84428Riyadh11671Saudi Arabia Department of Radiology and Medical Imaging Prince Sattam bin Abdulaziz UniversityAlkharjSaudi Arabia

Human speech indirectly represents the mental state or emotion of *** use of Artificial Intelligence(AI)-based techniques may bring revolution in this modern era by recognizing emotion from *** this study,we introduced a robust method for emotion recognition from human speech using a well-performed preprocessing technique together with the deep learning-based mixed model consisting of Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN).About 2800 audio files were extracted from the Toronto emotional speech set(TESS)database for this study.A high pass and Savitzky Golay Filter have been used to obtain noise-free as well as smooth audio data.A total of seven types of emotions;Angry,Disgust,Fear,Happy,Neutral,Pleasant-surprise,and Sad were used in this ***,Fundamental frequency,and Mel Frequency Cepstral Coefficient(MFCC)have been used to extract the emotion features,and these features resulted in 97.5%accuracy in the mixed LSTM+CNN *** mixed model is found to be performed better than the usual state-of-the-art models in emotion recognition from *** also indicates that this mixed model could be effectively utilized in advanced research dealing with sound processing.

关键词： Emotion recognition Savitzky Golay fundamental frequency MFCC neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework

arXiv

引用

arXiv 2023年

作者： Helal, Manal University of Hertfordshire School of Physics Engineering and Computer Science Hatfield United Kingdom

The burgeoning growth of public domain data and the increasing complexity of deep learning model architectures have underscored the need for more efficient data representation and analysis techniques. This paper is motivated by the work of (Helal, 2023) and aims to present a comprehensive overview of tensorization. This transformative approach bridges the gap between the inherently multidimensional nature of data and the simplified 2-dimensional matrices commonly used in linear algebra-based machine learning algorithms. This paper explores the steps involved in tensorization, multidimensional data sources, various multiway analysis methods employed, and the benefits of these approaches. A small example of Blind Source Separation (BSS) is presented comparing 2-dimensional algorithms and a multiway algorithm in Python. Results indicate that multiway analysis is more expressive. Contrary to the intuition of the dimensionality curse, utilising multidimensional datasets in their native form and applying multiway analysis methods grounded in multilinear algebra reveal a profound capacity to capture intricate interrelationships among various dimensions while, surprisingly, reducing the number of model parameters and accelerating processing. A survey of the multi-away analysis methods and integration with various Deep Neural Networks models is presented using case studies in different application domains. © 2023, CC BY.

关键词： Bridge approaches

来源：评论

学校读者我要写书评

暂无评论

Towards Net Zero — A Hybrid Energy Harvesting System for Sustainable Wireless Sensor Networks in Industrial Applications (Part 1 Review)

Towards Net Zero — A Hybrid Energy Harvesting System for Su...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Azunka N. Ukala Martin Thomas Eugene A. Ogbodo Tiffany Cao Uchenna Kesieme School of Physics Engineering and Computer Science University of Hertfordshire Hertfordshire United Kingdom

This paper investigates the effectiveness of utilizing a 2.4 GHz patch antenna for energy harvesting in a hybrid system that incorporates photovoltaic (PV) technology as an additional energy source. The proposed system is designed to extract energy from both the RF and light sources, which can provide a sustainable energy supply for equipment within a manufacturing environment. The 2.4 GHz patch antenna is utilized to capture RF energy from the surrounding environment, while the PV system generates energy from a light source (including sunlight). The performance of the proposed hybrid system is assessed in terms of energy efficiency and power output. Previous studies have highlighted the potential of using hybrid energy systems for power generation in wireless sensor networks [1], [2]. Energy harvesting from multiple sources can provide a reliable energy supply that is less dependent on a single source of energy. The use of PV systems in combination with RF energy harvesting has been previously explored [3], [4]. However, the potential of using a 2.4 GHz patch antenna in a hybrid system that incorporates PV technology has not been thoroughly investigated. Simulation results show that the hybrid system proposed in this study can achieve a marginally higher energy harvesting efficiency compared to using only the patch antenna or the PV system alone. This indicates that a combination of RF and light energy sources can be an effective approach for energy harvesting in wireless sensor networks. However, it is important to note that more work is required to generate energy significant enough to power other devices within a manufacturing environment. The proposed hybrid system has the potential to provide a sustainable energy supply for wireless sensor networks in manufacturing environments. The results of this study suggest that a combination of PV and RF energy harvesting can enhance the energy harvesting efficiency of wireless sensor networks. This finding is consistent

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Tree Classifiers to Mitigate Fraud in Electronic Loan Application 2

Comparative Analysis of Tree Classifiers to Mitigate Fraud i...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Yeboah, Foster Yeboah, Jones Yeboah, George Bampoh, Kofi Nyarko-Boateng, Owusu University of Cincinnati College of Engineering and Applied Science Cincinnati United States University of Cincinnati Maths Physics and Computer Science Department Cincinnati United States EProcess International S.A Information Technology Department Accra Ghana Ipmc School of It Accra Ghana University of Cincinnati School of Information Tevhnology Cincinnati United States

ISBN: (纸本)9798331529529

Loan disbursement is crucial and remains the core to every bank. With the advancement of technology and the proliferation of mobile devices financial institutions are working to bring the banking hall to the doorsteps of their clients. There are systems that allow applicants to apply for loans online. This inadvertently has enormous benefits and risks, but applicants may not be honest providing such data. To minimize risks and maximize benefits, a system for predicting fraud is necessary. This research, through experiments and comparative analysis, confirmed that data mining can effectively assess applicants' creditworthiness. The findings revealed that the Random Forest classifier produced the most robust model, offering the highest classification accuracy among the selected classifiers, with an accuracy rate of 0.7773. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Interactive robots as inclusive tools to increase diversity in higher education

arXiv

引用

arXiv 2023年

作者： Holthaus, Patrick University of Hertfordshire School of Physics Engineering and Computer Science Hatfield United Kingdom

There is a major lack of diversity in engineering, technology, and computing subjects in higher education. The resulting underrepresentation of some population groups contributes largely to gender and ethnicity pay gaps and social disadvantages. We aim to increase the diversity among students in such subjects by investigating the use of interactive robots as a tool that can get prospective students from different backgrounds interested in robotics as their field of study. For that, we will survey existing solutions that have proven to be successful in engaging underrepresented groups with technical subjects in educational settings. Moreover, we examine two recent outreach events at the University of Hertfordshire against inclusivity criteria. Based on that, we suggest specific activities for higher education institutions that follow an inclusive approach using interactive robots to attract prospective students at open days and other outreach events. Our suggestions provide tangible actions that can be easily implemented by higher education institutions to make technical subjects more appealing to everyone and thereby tackle inequalities in student uptake. © 2023, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enabled Predictive Vehicle Health Monitoring and Maintenance with LSTM Networks for Time-Series Analysis 1

Cloud-Enabled Predictive Vehicle Health Monitoring and Maint...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Vinya, Viyyapu Lokeshwari Manivannan, K.K. Manivannan, S.K. Sathiyamoorthy, C. Jagadeeswaran, M. Meenakshi, B. SRM Institute of Science and Technology Department of Computing Technologies School of Computing Kattankulathur Tamil Nadu Chennai India Easwari Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Vit Bhopal University Department of Physics School of Advanced Sciences and Languages Madhya Pradesh Bhopal India J.J College of Engineering and Technology Department of Information Technology Tamil Nadu Tiruchirappalli India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Saveetha School of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376517

Maximizing operational efficiency and customer satisfaction in the automobile sector depends on maintaining vehicle health and avoiding maintenance downtime. Vehicle Internet of Things (IoT) devices capture massive volumes of sensor data, enabling predictive maintenance. This research offers cloud-based predictive vehicle health monitoring and maintenance systems using Long Short-Term Memory (LSTM) networks for time-series analysis. System architecture uses IoT sensors in automobiles to gather real-time data on engine temperature, oil pressure, and vibration. This data is stored, analyzed, and predicted on clouds. To assess time-series sensor data and forecast failures or maintenance requirements, LSTM networks, a form of recurrent neural network, are used. The proposed system uses data preprocessing to manage missing values and outliers, feature extraction to find significant sensor data patterns, and LSTM-based predictive modeling to predict vehicle health conditions. Technology may predict future faults by continually monitoring and evaluating the vehicle's state, allowing proactive maintenance to avoid expensive breakdowns and downtime. The cloud-based architecture is scalable and flexible, providing smooth connection with fleet management systems and remote vehicle health monitoring across scattered sites. The suggested method optimizes maintenance schedules and resource allocation using predictive insights from real-time sensor data to improve operational efficiency and save costs. It may improve predictive vehicle health monitoring and maintenance in the automobile sector, improving dependability, safety, and cost. © 2024 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Accelerated Robustness Certification for Diffusion Denoised Smoothing Based on Image Super-Resolution

Accelerated Robustness Certification for Diffusion Denoised ...

引用

International Congress on Image and Signal Processing, BioMedical engineering and Informatics (CISP-BMEI)

作者： Qian Zeng Anjie Peng Fei Deng Hui Zeng School of Computer Science and Technology Southwest University of Science and Technology Mianyang China China Academy of Engineering Physics Mianyang China

ISBN: (数字)9798331507398

ISBN: (纸本)9798331507404

While diffusion denoised smoothing (DDS) achieves excellent certified defense performance under $l_{2}$ norm bounded perturbations, we find that DDS is vulnerable to image up-sampling. The bicubic interpolation used in DDS reduces the classification accuracy of the base classifier, thereby weakening its certified robustness. As an alternative, we introduce image super-resolution technology to compensate for the loss of detail or unrealistic content generated by interpolated images, thereby improving the classification accuracy while adapting to the input size required by classifier, but with some additional time cost. Therefore, in this paper, we propose an accelerated certified defense for enhancing DDS based on image super-resolution. By adaptively reducing the certified sample size according to input features to achieve cost-effectiveness for robustness certification, and as the base classifier's predictions are more accurate on super-resolution images than on interpolated images, our proposed method can quickly and effectively enhance certified defense performance based on DDS. Experimental results show that we achieve a top-1 certified accuracy of 56.2% on ImageNet under $l_{2}$ bounded perturbation $\delta=1.0, \mathbf{which}$ is at least 4% higher than the previous diffusion denoised smoothing, and saves nearly 1/3 of the total certified time compared to before.

关键词： Interpolation Accuracy Smoothing methods Runtime Perturbation methods Superresolution Noise reduction Robustness Certification Signal resolution

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：