检索结果-内蒙古大学图书馆

Deep Learning Models for intelligent Healthcare: Implementation and Challenges 7th

学校读者我要写书评

暂无评论

Deep Learning Models for Intelligent Healthcare: Implementat...

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Rehman, Sadaqat ur Tu, Shanshan Shah, Zubair Ahmad, Jawad Waqas, Muhammad Rehman, Obaid ur Kouba, Anis Abbasi, Qammer H. Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information Technology Beijing University of Technology Beijing100124 China Department of Computer Science Namal Institute Mianwali42250 Pakistan Department of Computer Science and Engineering Hammad Bin Khalifa University Doha Qatar School of Computing Edinburgh Napier University Edinburgh United Kingdom Department of Electrical Engineering Sarhad University of Science and IT Peshawar25000 Pakistan Department of Computer Science Prince Sultan University Riyadh Saudi Arabia James Watt School of Engineering University of Glasgow GlasgowG12 8QQ United Kingdom

ISBN: (纸本)9783030786083

The rapid developments of artificial intelligent (AI) is being transformed for its extensive use-cases, people-centered intelligent systems focusing on care delivery, research encounter complex problems related to improve the overall infrastructure and management of intelligent delivery service;for instance, bringing transformation in healthcare sector for monitoring patients with chronic disease. Most of these systems are driven by state-of-the-art learning algorithms i.e., Convolution Neural Network. The CNN algorithm is considered to be one of the most prominent architectures of DL. Recently, due to enormous growth in the amount of annotated data and the development of CNN hardware accelerator, further, boost the research on CNN and accomplished benchmark enactment on different applications. This paper presents cutting-edge applications of CNN for an intelligent healthcare system. We provide useful findings of different CNN features such as optimization, fast computation, design, activation function, and loss function. To our knowledge, this is the first comprehensive work to address the recent trends in the architecture of CNN, which offers insight to the underlying problems and provides the potential solutions for any given intelligent healthcare applications. © 2021, Springer Nature Switzerland AG.

关键词： Deep learning

Social Presence in Evaluations for a Humanoid Robot and Its Effect on Children-Robot Relationship 23rd

学校读者我要写书评

暂无评论

Social Presence in Evaluations for a Humanoid Robot and Its ...

23rd International Conference on Human-computer Interaction, HCII 2021

作者： Chen, Yi-Chen Gamborino, Edwinn Fu, Li-Chen Yueh, Hsiu-Ping Yeh, Su-Ling Department of Psychology National Taiwan University Taipei Taiwan Department of Electrical Engineering and Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare Taipei Taiwan Center for Artificial Intelligence and Advanced Robotics National Taiwan University Taipei Taiwan Department of Bio-Industry Communication and Development National Taiwan University Taipei Taiwan Graduate Institute of Brain and Mind Sciences National Taiwan University Taipei Taiwan

ISBN: (纸本)9783030786342

As children are at a critical stage in their lives in developing and practicing social skills, they tend to imagine objects as interactive agents. For example, even a toy dinosaur can be perceived as affable and more as a social entity, namely, with a strong social presence (SP). This study investigated whether perceived SP changes (measured using the SP questionnaire) as children interacted with a robot. Furthermore, we investigated how SP modulated children-robot relationships and children’s overall attitudes towards robots. Children aged 6–12 interacted with a companion robot, RoBoHoN, for short intervals. Attitude evaluations were completed at three-time points: prior-, mid-, and post-interaction. SP and rapport with RoBoHoN were measured and compared mid-and post-interaction, while attitudes towards the robot were tested prior- and post-interaction. The results showed a stronger intention to use robots before interaction correlated with higher SP scores with RoBoHoN. As SP level was stable across mid- and post-interaction, we analyzed SP as a between-groups factor to compare attitude evaluations among children who rated RoBoHoN with higher versus lower SP scores. The high SP group found RoBoHoN to be more likable and playing with it as more enjoyable, but the effect on rapport level was marginal. The Implicit Association Task revealed no bias towards robots among children in both groups. This study shows SP’s positive effect on children-robot interaction and highlights the importance of SP in designing social companion robots for children. © 2021, Springer Nature Switzerland AG.

关键词： Association reactions

Creating Own AI Datasets from Different Language Sources Efficiently: Advantages, Disadvantages and Best Pracitces to Make Own Datasets

学校读者我要写书评

暂无评论

Creating Own AI Datasets from Different Language Sources Eff...

International IEEE Conference and Workshop: Óbuda on electrical and Power engineering (CANDO-EPE)

作者： György Molnár József Cserkó Enikő Nagy Zoltán Balogh Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary János Csere Apáczai Faculty Széchenyi University Győr Hungary GAMF Faculty of Engineering and Computer Science John Von Neumann University Kecskemét Hungary Széchenyi University Doctoral School of Multidisciplinary Engineering Sciences (MMTDI) Győr Hungary Antal Bejczy Center for Intelligent Robotics John von Neumann Faculty Institute of Cyberphysical Systems Óbuda University Budapest Hungary Department of Informatics Faculty of Natural Sciences and Informatics Constantine the Philosopher University in Nitra Nitra Slovakia

Artificial Intelligence (AI) has become a ubiquitous technology that has the potential to revolutionize many industries. However, AI requires access to vast amounts of data to achieve its full potential. By understanding these data sources and the best practices for working with them, we can unlock the full potential of AI and create groundbreaking solutions that benefit society as a whole. Data sources can be utilized to train AI algorithms, including structured and unstructured data, but finding relevant datasets is challenging. The main problem is the international sources. Most of the datasets are available only in English or other common languages. However these are good sources, but translating them is expensive and time-consuming. This paper shows how to generate own datasets from open-source data with translation.

关键词：

Heterogeneous Oblique Double Random Forest

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ganaie, M.A. Tanveer, M. Beheshti, I. Ahmad, N. Suganthan, P.N. Department of Robotics University of Michigan Ann ArborMI United States Department of Mathematics Indian Institute of Technology Indore Simrol Indore453552 India Department of Human Anatomy and Cell Science Rady Faculty of Health Sciences Max Rady College of Medicine University of Manitoba WinnipegMB Canada Department of International Program of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan KINDI Center for Computing Research College of Engineering Qatar University Doha Qatar

The decision tree ensembles use a single data feature at each node for splitting the data. However, splitting in this manner may fail to capture the geometric properties of the data. Thus, oblique decision trees generate the oblique hyperplane for splitting the data at each non-leaf node. Oblique decision trees capture the geometric properties of the data and hence, show better generalization. The performance of the oblique decision trees depends on the way oblique hyperplanes are generate and the data used for the generation of those hyperplanes. Recently, multiple classifiers have been used in a heterogeneous random forest (RaF) classifier, however, it fails to generate the trees of proper depth. Moreover, double RaF studies highlighted that larger trees can be generated via bootstrapping the data at each non-leaf node and splitting the original data instead of the bootstrapped data recently. The study of heterogeneous RaF lacks the generation of larger trees while as the double RaF based model fails to take over the geometric characteristics of the data. To address these shortcomings, we propose heterogeneous oblique double RaF. The proposed model employs several linear classifiers at each non-leaf node on the bootstrapped data and splits the original data based on the optimal linear classifier. The optimal hyperplane corresponds to the models based on the optimized impurity criterion. The experimental analysis indicates that the performance of the introduced heterogeneous double random forest is comparatively better than the baseline models. To demonstrate the effectiveness of the proposed heterogeneous double random forest, we used it for the diagnosis of Schizophrenia disease. The proposed model predicted the disease more accurately compared to the baseline models. © 2023, CC BY-NC-ND.

关键词： Decision trees

Nonsingular Adaptive Barrier Function-Based Finite Time Control for Uncertain Nonlinear systems

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Mobayen, Saleh Zhang, Jianhua Zhu, Quanmin Fekih, Afef Future Technology Research Center Taiwan Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliu Taiwan School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China Department of Engineering Design and Mathematics University of the West of England Frenchy Campus Coldharbour Lane BristolBS16 1QY United Kingdom Department of Electrical and Computer Engineering University of Louisiana at Lafayette LafayetteLA70504 United States

This study presents a novel approach for using sliding mode control (SMC) for uncertain nonlinear systems with external unknown disturbances. A nonsingular adaptive barrier function-based finite time control is developed to deal with such systems. In technical implementation, first a novel sliding surface is designed based on the Hurwitz condition, then, using the finite-time stability method, a novel nonsingular terminal sliding manifold is established and the barrier function is obtained, which can guarantee the sliding surface convergence to the origin in finite time. For functional and numerical validation, two examples of uncertain nonlinear systems are selected to illustrate the effectiveness of the proposed method in comparison with the other representative approaches. © 2023, The Authors. All rights reserved.

关键词： Sliding mode control

Chance Constrained Economic Dispatch Considering the Capability of Network Flexibility Against Renewable Uncertainties

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Song, Yue Liu, Tao Hill, David J. The Department of Control Science and Engineering Tongji University Shanghai201804 China The National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai201210 China The Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai200120 China Hong Kong The HKU Shenzhen Institute of Research and Innovation Shenzhen China The Department of Electrical and Computer Systems Engineering Monash University MelbourneVIC3000 Australia The Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

This paper incorporates a continuous-type network flexibility into chance constrained economic dispatch (CCED). In the proposed model, both power generations and line susceptances are continuous variables to minimize the expected generation cost and guarantee a low probability of constraint violation in terms of generations and line flows under renewable uncertainties. From the analytical form of CCED, we figure out the mechanism of network flexibility against uncertainties-while renewable uncertainties shrink the usable line capacities and aggravate transmission congestion, network flexibility mitigates congestion by re-routing the base-case line flows and reducing the line capacity shrinkage caused by uncertainties. Further, we propose an alternate iteration solver for this problem. By duality theory, we set up a master problem in the form of second-order cone programming to optimize generation dispatch scheme and a subproblem in the form of linear programming to optimize line susceptances. A satisfactory solution can be obtained efficiently by alternately solving these two problems. The proposed method applies to both Gaussian uncertainty and non-Gaussian uncertainty by means of Gaussian mixture model. The case studies on the IEEE 14-bus system and IEEE 118-bus system suggest that network flexibility can significantly improve operational economy while ensuring security under uncertainties. © 2021, CC BY.

关键词： Second-order cone programming

High Quality Factor AlScN Lamb Wave Resonators Using NbN/Al Top Electrodes at Cryogenic Temperature

学校读者我要写书评

暂无评论

High Quality Factor AlScN Lamb Wave Resonators Using NbN/Al ...

International Conference on Solid State Sensors and Actuators (TRANSDUCERS)

作者： Zhifang Luo Shuai Shao Peng Dong Haowen Guo Xinbo Zou Jun Li Chengkuo Lee Tao Wu School of Information Science and Technology ShanghaiTech University China Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Department of Electrical & Computer Engineering National University of Singapore Singapore Center for Intelligent Sensors and MEMS National University of Singapore Singapore School of Physical Science and Technology ShanghaiTech University China Shanghai Engineering Research Center of Energy Efficient and Custom AI IC China

Coupling between phonons and qubits provides a solid quantum platform for information transmission and processing. We report the high quality factor (Q a ) aluminum scandium nitride (AlScN) Lamb wave resonators (LWRs) at cryogenic temperature for quantum applications. Superconducting 60 nm NbN/30nm Al serves as top electrodes for ultra-low energy dissipation at around 11 K. Al 0.84 Sc 0.16 N provides a high piezoelectric constant for high electro-mechanical coupling $\left( {{{\text{k}}_{\text{t}}}^{\text{2}}} \right)$ of resonators. Additionally, LWRs allow lithography-defined resonant frequency for flexible multi-frequency phonon sources. The fabricated LWR shows Q a over 6000, and resulting in a record figure-of-merit $\left( {{\text{FoM }} = {\text{ }}{{\text{k}}_{\text{t}}}^{\text{2}}{\text{*}}{{\text{Q}}_{\text{a}}}} \right)$ of 211 for AlScN resonators.

关键词：

Towards Cross-device and Training-free Robotic Grasping in 3D Open World

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Weiguang Jiang, Chenru Zhang, Chengrui Sun, Jie Yan, Yuyao Zhang, Rui Huang, Kaizhu Department of Computer Science University of Liverpool LiverpoolL69 7ZX United Kingdom Data Science Research Center Duke Kunshan University Suzhou215316 China Department of Electrical Engineering University of Liverpool LiverpoolL69 7ZX United Kingdom Department of Mechatronics and Robotics Xi’an-Jiaotong Liverpool University Suzhou215123 China School of Robotic Xi’an Jiaotong-Liverpool University Suzhou215123 China Department of Foundational Mathematics Xi’an Jiaotong-Liverpool University Suzhou215123 China

— Robotic grasping in the open world is a critical component of manufacturing and automation processes. While numerous existing approaches depend on 2D segmentation output to facilitate the grasping procedure, accurately determining depth from 2D imagery remains a challenge, often leading to limited performance in complex stacking scenarios. In contrast, techniques utilizing 3D point cloud data inherently capture depth information, thus enabling adeptly navigating and manipulating a diverse range of complex stacking scenes. However, such efforts are considerably hindered by the variance in data capture devices and the unstructured nature of the data, which limits their generalizability. Consequently, much research is narrowly concentrated on managing designated objects within specific settings, which confines their real-world applicability. This paper presents a novel pipeline capable of executing object grasping tasks in open-world scenarios even on previously unseen objects without the necessity for training. Additionally, our pipeline supports the flexible use of different 3D point cloud segmentation models across a variety of scenes. Leveraging the segmentation results, we propose to engage a training-free binary clustering algorithm that not only improves segmentation precision but also possesses the capability to cluster and localize unseen objects for executing grasping operations. In our experiments, we investigate a range of open-world scenarios, and the outcomes underscore the remarkable robustness and generalizability of our pipeline, consistent across various environments, robots, cameras, and objects. The code will be made available upon acceptance of the paper. © 2024, CC BY-NC-ND.

关键词： Image segmentation

A Chaotic Image Encryption Scheme Using Novel Geometric Block Permutation and Dynamic Substitution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ali, Muhammad Ahmad, Jawad Khan, Muhammad Abdullah Hussain Ullah, Safee Rehman, Mujeeb Ur Shah, Syed Aziz Khan, Muhammad Shahbaz Department of Electrical Engineering HITEC University Taxila47080 Pakistan Cyber Security Center Prince Mohammad Bin Fahd University Al Khobar31952 Saudi Arabia School of Computer Science and Informatics De Montfort University LeicesterLEl 9BH United Kingdom Research Centre for Intelligent Healthcare Coventry University CoventryCVl 5FB United Kingdom School of Computing Engineering and the Built Environment Edinburgh Napier University EdinburghEHlO 5DT United Kingdom

In this digital era, ensuring the security of digital data during transmission and storage is crucial. Digital data, particularly image data, needs to be protected against unauthorized access. To address this, this paper presents a novel image encryption scheme based on a confusion diffusion architecture. The diffusion module introduces a novel geometric block permutation technique, which effectively scrambles the pixels based on geometric shape extraction of pixels. The image is converted into four blocks, and pixels are extracted from these blocks using L-shape, U-shape, square-shape, and inverted U-shape patterns for each block, respectively. This robust extraction and permutation effectively disrupts the correlation within the image. Furthermore, the confusion module utilises bit-XOR and dynamic substitution techniques. For the bit-XOR operation, 2D Henon map has been utilised to generate a chaotic seed matrix, which is bit-XORed with the scrambled image. The resultant image then undergoes the dynamic substitution process to complete confusion phase. A statistical security analysis demonstrates the superior security of the proposed scheme with high uncertainty and unpredictability, achieving an entropy of 7.9974 and a correlation coefficient of 0.0014. These results validate the proposed scheme's effectiveness in securing digital images. © 2025, CC BY-NC-ND.

关键词： Digital image storage