检索结果-内蒙古大学图书馆

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Wei-Hsi Chen Shivangi Misra J. Diego Caporale Daniel E. Koditschek Shu Yang Cynthia R. Sung Department of Electrical and Systems Engineering University of Pennsylvania Department of Computer and Information Science University of Pennsylvania Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania Department of Materials Science and Engineering University of Pennsylvania

ISBN: (数字)9781728165707

ISBN: (纸本)9781728165714

We report on experiments with a laptop-sized (0.23m, 2.53kg), paper origami robot that exhibits highly dynamic and stable two degree-of-freedom (circular boom) hopping at speeds in excess of 1.5 bl/s (body-lengths per second) at a specific resistance O(1) while achieving aerial phase apex states 25% above the stance height over thousands of cycles. Three conventional brushless DC motors load energy into the folded paper springs through pulley-borne cables whose sudden loss of tension upon touchdown triggers the release of spring potential that accelerates the body back through liftoff to flight with a 20W powerstroke, whereupon the toe angle is adjusted to regulate fore-aft speed. We also demonstrate in the vertical hopping mode the transparency of this actuation scheme by using proprioceptive contact detection with only motor encoder sensing. The combination of actuation and sensing shows potential to lower system complexity for tendon-driven robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Industrial solid waste recycling using digital servitisation for decarbonisation to promote Net zero in the circular economy

引用

computers and Industrial Engineering 2025年 206卷

作者： Gao, Pengqun Zhou, Yang Sun, Lipeng Alahmari, Saad Innab, Nisreen Venkatachalam, K. Ferrara, Massimiliano Business School Jiangsu Open University Nanjing210036 China Jiangsu Innovation Ecology Research Institute Jiangsu Nanjing210036 China College of Innovation and Entrepreneurship Jiangsu Maritime Institute Nanjing211170 China School of Management Wenzhou Business College Wenzhou325035 China Department of Computer Science Applied College Northern Border University Arar Saudi Arabia Department of Computer Science and Information Systems College of Applied Sciences AlMaarefa University Riyadh Diriyah13713 Saudi Arabia Faculty of Science University of Hradec Králové Hradec Králové50003 Czech Republic ICRIOS University Bocconi Via Röntgen no 1 Milan 20136 Italy

The smart circular economy framework proposed in this study encourages a net-zero economy by improving industrial solid waste recycling for decarbonization through the digital service economy. A blockchain-based cloud platform uses advanced technologies like artificial intelligence, blockchain, and data analytics to encourage smooth communication between all parties. These suggested framework developments include requirement elicitation and quality grading, smart life cycle option selection, and returned products clustering. The FuzClu algorithm clusters returned products to improve their allocation to collection centers based on specific features like product type, return time and location. Subsequently, requirement elicitation through Latent Dirichlet Analysis identifies consumer needs and return patterns to produce innovation and predict future return volumes. Finally, the Smart Life Cycle Option Selection applies the Modified Convolutional Neural Network Algorithm to recommend optimal life cycle options based on product quality and lifetime. This approach increases the value of end-of-life products, encourages sustainability and reduces environmental pollution. Overall, this research contributes to addressing industrial solid waste challenges by aligning digital servitisation with circular economy principles, notably supporting decarbonisation with a focus on a net-zero economy. © 2025 Elsevier Ltd

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

(KAUH-BCUSD): computer-aided breast cancer diagnosis using transformer and CNN using ultrasound dataset

引用

Intelligence-Based Medicine 2025年 12卷

作者： Eman Hussein Alshdaifat Mohammad Amin Hamad Yahia Abu Mhanna Majd Malkawi Asma'a Mohammad Al-Mnayyis Hasan Gharaibeh Hanan Fawaz Akhdar Rola Madain Salem Alhatamleh Tamara Amjad Al-Qablan Neda'a Alsalmanc Alaa Alomar Qutaiba Mohammad Amer Mahmoud Sindiani Department of Obstetrics and Gynecology Faculty of Medicine Yarmouk University Irbid 211633 Jordan Computer Science Department Faculty of Information Technology and Computer Sciences Yarmouk University Irbid 21163 Jordan Department of Medical Imaging Faculty of Allied Medical Sciences Isra University Amman 11622 Jordan Department of Medicine Faculty of Medicine Jordan University of Science and Technology Irbid 22110 Jordan Department of Internal Medicine College of Medicine Yarmouk University Irbid 211633 Jordan Artificial Intelligence and Data Innovation Office King Hussein Cancer Center Jordan Amman 11622 Jordan Physics Department Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh 13318 Saudi Arabia Department of Obstetrics and Gynecology Faculty of Medicine Jordan University of Science and Technology Irbid 22110 Jordan Department of Information Technology Al-Huson University College Al-Balqa Applied University Irbid 50 Jordan Department of Computer Science Faculty of Information Technology Jordan University of Science and Technology Irbid 22110 Jordan Department of Medicine Faculty of Medicine Yarmouk University Irbid 211633 Jordan Professor of Obstetrics and Gynecology Department of Obstetrics and Gynecology Faculty of Medicine Jordan University of Science and Technology Irbid 22110 Jordan

Breast cancer is the leading cause of death among women worldwide. Early detection of breast cancer helps reduce global mortality rates. The current era is characterized by the rapid spread of computer-aided diagnosis (CAD) technologies in the medical field. This research analyzes ultrasound-derived medical images of breast cancer. The researchers suggest that breast cancer risk factors are associated with cultural and societal influences. Therefore, there is a need for a local dataset that accurately reflects breast cancer in our region to facilitate the development and evaluation of automated CAD systems for breast cancer. This study presents a novel dataset for breast cancer ultrasound diagnosis from King Abdullah University Hospital (KAUH). The KAUH-BCUSD dataset is the first dataset in the Hashemite Kingdom of Jordan to include multiple breast cancer ultrasound examinations. It consists of 6159 images collected from 5000 cases. Physicians from KAUH annotated, evaluated, and classified the dataset into benign and malignant images. Breast ultrasound images achieve exceptional results in breast cancer classification and diagnosis when combined with machine learning. The CNN_ViT model, which combines a convolutional neural network (CNN) and a vision transformer (ViT), was developed and evaluated on the KAUH-BCUSD dataset. Eight pre-trained neural network models, namely Vgg16, Vgg19, MobileNetV2, ResNet50, InceptionV3, Xception, DenseNet121, and ConvNeXt, were also evaluated on the KAUH-BCUSD dataset. The proposed CNN_ViT model outperformed the pre-trained models, achieving an accuracy of 0.9512. It also performed better in recall and F1 score, reaching 0.9754 and 0.9524, respectively. In conclusion, these results demonstrate the potential of the proposed model in improving breast cancer classification, indicating its reliability in real-world clinical applications. Future work will focus on further improving the model's performance and exploring its integration wit

关键词： Breast cancer Ultrasound dataset Vision Transformer (ViT) Convolutional neural networks (CNNs) Medical image

来源：评论

学校读者我要写书评

暂无评论

J-PET detection modules based on plastic scintillators for performing studies with positron and positronium beams

arXiv

引用

arXiv 2023年

作者： Sharma, S. Baran, J. Brusa, R.S. Caravita, R. Chug, N. Coussat, A. Curceanu, C. Czerwiński, E. Dadgar, M. Dulski, K. Eliyan, K. Gajos, A. Hiesmayr, B.C. Kacprzak, K. Kaplon, L. Klimaszewski, K. Konieczka, P. Korcyl, G. Kozik, T. Krzemień, W. Kumar, D. Mariazzi, S. Niedźwiecki, S. Panasa, L. Parzych, S. Povolo, L. del Rio, E. Perez Raczyński, L. Shivani Shopa, R.Y. Skurzok, M. Stępień, E.L. Tayefi, F. Tayefi, K. Wiślicki, W. Moskal, P. Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Krakow Poland Total-Body Jagiellonian-PET Laboratory Jagiellonian University Kraków Poland Center for Theranostics Jagiellonian University Cracow Poland Department of Physics University of Trento via Sommarive 14 Povo Trento38123 Italy TIFPA INFN via Sommarive 14 Povo Trento38123 Italy INFN Laboratori Nazionali di Frascati Frascati Italy Faculty of Physics University of Vienna Vienna Austria Department of Complex Systems National Centre for Nuclear Research Otwock-Świerk Poland High Energy Physics Division National Centre for Nuclear Research Otwock-Świerk Poland

The J-PET detector, which consists of inexpensive plastic scintillators, has demonstrated its potential in the study of fundamental physics. In recent years, a prototype with 192 plastic scintillators arranged in 3 layers has been optimized for the study of positronium decays. This allows performing precision tests of discrete symmetries (C, P, T) in the decays of positronium atoms. Moreover, thanks to the possibility of measuring the polarization direction of the photon based on Compton scattering, the predicted entanglement between the linear polarization of annihilation photons in positronium decays can also be studied. Recently, a new J-PET prototype was commissioned, based on a modular design of detection units. Each module consists of 13 plastic scintillators and can be used as a stand-alone, compact and portable detection unit. In this paper, the main features of the J-PET detector, the modular prototype and their applications for possible studies with positron and positronium beams are discussed. Preliminary results of the first test experiment performed on two detection units in the continuous positron beam recently developed at the Antimatter Laboratory (AML) of Trento are also reported. Copyright © 2023, The Authors. All rights reserved.

关键词： Positrons

来源：评论

学校读者我要写书评

暂无评论

Verifiable Arithmetic Computations Using Additively Homomorphic Tags

Verifiable Arithmetic Computations Using Additively Homomorp...

引用

2019 IEEE International Conference on Advanced Trends in information Theory, ATIT 2019

作者： Anisimov, Anatoly V. Novokshonov, Andrey Taras Shevchenko National University of Kyiv Faculty of Computer Science and Cybernetics Kyiv Ukraine International Research and Training Center for Information Technologies and Systems Kyiv Ukraine

ISBN: (纸本)9781728161440

It is possible to represent significant amount of arithmetic functions using only addition and subtraction operations, looping and conditional branching constructions. Combining this representation with an additively homomorphic cryptosystem allows building a simple yet efficient non-interactive scheme for verifying integrity of delegated arithmetic computations within a stateless model. © 2019 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Hybrid AI- and Blockchain-Powered Secure Internet Hospital Communication and Anomaly Detection in Smart Cities

引用

Processes 2025年第5期13卷 1466-1466页

作者： Wang, Xiaofeng Yue, Xiaoguang Tariq, Noshina Sajid, Ahthasham College of Management Shenzhen University Shenzhen518060 China Department of Artificial Intelligence and Data Science National University of Computer and Emerging Sciences Islamabad44000 Pakistan Faculty of Computing and Informatics Multimedia University Cyberjaya63100 Malaysia Department of Information Security and Data Science Riphah Institute of Systems Engineering Riphah International University Islamabad46000 Pakistan

Internet of Things (IoT) devices have revolutionized real-time monitoring and distant patient care in smart cities’ healthcare systems. However, this advancement has come with several issues, such as data security, scalability, operational efficiency, and fault tolerance. Previous approaches are not well suited to the real-time processing of IoT data in healthcare, given the low latency, high throughput, and effective anomaly detection needed for such a task. Given these challenges, this paper proposes a hybrid Artificial Intelligence (AI)- and blockchain-based IoT governance framework for Internet hospitals using Proof-of-Authority (PoA) in smart cities. It encompasses application of the enhanced RSA for secure data transmission, real-time anomaly detection through the Isolation Forest algorithm, and a private blockchain architecture designed for high scalability. It effectively detects tampering and replay attacks to minimize illegitimate and unauthorized access or manipulation of patients’ data. The proposed framework achieves relatively significant improvements over a state-of-the-art baseline model. It has cut the transaction response time by 50%, doubled the Throughput Per Second (TPS), and attained a 100% detection performance in anomalies. Comparative analysis reveals its linear scalability with increasing workload, ensuring consistent performance under varying transaction volumes. This study’s findings highlight the proposed framework’s potential to mitigate key issues in IoT-enabled Internet hospitals in smart cities. © 2025 by the authors.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

vieCap4H-VLSP 2021: Vietnamese Image Captioning for Healthcare Domain using Swin Transformer and Attention-based LSTM

arXiv

引用

arXiv 2022年

作者： Nguyen, Thanh Tin Nguyen, Long H. Pham, Nhat Truong Nguyen, Liu Tai Do, Van Huong Nguyen, Hai Nguyen, Ngoc Duy Human Computer Interaction Lab Sejong University Seoul Korea Republic of Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam ASICLAND Suwon Korea Republic of Khoury College of Computer Sciences Northeastern University Boston United States Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia

This study presents our approach on the automatic Vietnamese image captioning for healthcare domain in text processing tasks of Vietnamese Language and Speech Processing (VLSP) Challenge 2021, as shown in Figure 1. In recent years, image captioning often employs a convolutional neural network-based architecture as an encoder and a long short-term memory (LSTM) as a decoder to generate sentences. These models perform remarkably well in different datasets. Our proposed model also has an encoder and a decoder, but we instead use a Swin Transformer in the encoder, and a LSTM combined with an attention module in the decoder. The study presents our training experiments and techniques used during the competition. Our model achieves a BLEU4 score of 0.293 on the vietCap4H dataset, and the score is ranked the 3rd place on the private leaderboard. Our code can be found at https://***/JDdJm. © 2022, CC BY.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

DNA encoding schemes herald a new age in cybersecurity for safeguarding digital assets

引用

Scientific reports 2024年第1期14卷 13839页

作者： Sehrish Aqeel Sajid Ullah Khan Adnan Shahid Khan Meshal Alharbi Sajid Shah Mohammed El Affendi Naveed Ahmad Faculty of Computer Science and Information Technology Universiti Malaysia Sarawak 94300 Kota Samarahan Malaysia. Department of Information Systems College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University AlKharj Kingdom of Saudi Arabia. sk.khan@psau.edu.sa. Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia. sk.khan@psau.edu.sa. Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia. EIAS Lab CCIS Prince Sultan University Riyadh Saudi Arabia. College of Computer Information Sciences CCIS Prince Sultan University Riyadh Saudi Arabia.

With the urge to secure and protect digital assets, there is a need to emphasize the immediacy of taking measures to ensure robust security due to the enhancement of cyber security. Different advanced methods, like encryption schemes, are vulnerable to putting constraints on attacks. To encode the digital data and utilize the unique properties of DNA, like stability and durability, synthetic DNA sequences are offered as a promising alternative by DNA encoding schemes. This study enlightens the exploration of DNA's potential for encoding in evolving cyber security. Based on the systematic literature review, this paper provides a discussion on the challenges, pros, and directions for future work. We analyzed the current trends and new innovations in methodology, security attacks, the implementation of tools, and different metrics to measure. Various tools, such as Mathematica, MATLAB, NIST test suite, and Coludsim, were employed to evaluate the performance of the proposed method and obtain results. By identifying the strengths and limitations of proposed methods, the study highlights research challenges and offers future scope for investigation.

关键词： Analytical survey computer network Cyber security Cyber threats DNA encoding Digital data protection Encryption scheme Enhanced security Evaluation metrics Evaluation tools Network attacks

来源：评论

学校读者我要写书评

暂无评论

Traffic sign detection for panoramic images using convolution neural network technique 19

Traffic sign detection for panoramic images using convolutio...

引用

3rd High Performance Computing and Cluster Technologies Conference, HPCCT 2019 and the 2nd International Conference on Big Data and Artificial Intelligence, BDAI 2019

作者： Prasomphan, Sathit Tathong, Thanthip Charoenprateepkit, Primpisa Department of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok 1518 Pracharat 1 Rd. Wongsawang Bangsue Bangkok10800 Thailand

ISBN: (纸本)9781450371858

This research presents a method for panoramic traffic sign images detection for regulatory signs and guide signs especially blue and green sign. A new approach for detecting the signs inside a large panoramic image was considered. A convolution neural network technique was used as tools for detecting. In addition, the steps required are the technique used in conjunction with the convolution neural network technique by using Tensorflow training to improve the accuracy of traffic sign detection. Moreover, to improve the accuracy of image detection, some image processing technique was added. For example, adding brightness to an image. From the experimental results, detection of traffic signs from panoramic images (360°) by using trained convolution neural network model to improve a traffic sign detection, the accuracy from panoramic images (360°) is better than the traditional model. © 2019 Association for Computing Machinery.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Synthesis of SQL queries from south african local language narrations

arXiv

引用

arXiv 2020年

作者： Obaido, George Ade-Ibijola, Abejide Vadapalli, Hima School of Computer Science and Applied Mathematics University of the Witwatersrand Johannesburg2001 South Africa School of Consumer Intelligence and Information Systems University of Johannesburg Johannesburg2001 South Africa

English remains the language of choice for database courses and widely used for instruction in nearly all South African universities, and also in many other countries. Novice programmers of native origins are mostly taught Structured Query Language (SQL) through English as the medium of instruction. Consequently, this creates a myriad of problems in understanding the syntax of SQL as most native learners are not too proficient in English. This could affect a learner’s ability in comprehending SQL syntaxes. To resolve this problem, this work proposes a tool called local language narrations to SQL (Local-Nar-SQL) that uses a type of Finite Machine, such as a Jumping Finite Automaton to translate local language narratives into SQL queries. Further, the generated query extracts information from a sample database and presents an output to the learner. This paper is an extension of work originally presented in a previous study in this field. A survey involving 145 participants concluded that the majority found Local-Nar-SQL to be helpful in understanding SQL queries from local languages. If the proposed tool is used as a learning aid, native learners will find it easier to work with SQL, which will eliminate many of the barriers faced with English proficiencies in programming pedagogies. © 2020, CC BY.

关键词： Query languages

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：