检索结果-内蒙古大学图书馆

International Conference on Advances in Information Technology (ICAIT)

作者： R. Shanthi Balasubramaniam D R. Venkatesh C. Sankari V. Manimaran Shaik Hedayath Basha Department of computer applications Faculty of science and humanities SRM Institute of science and Technology Chengalpattu Tamilnadu Department of Biomedical Engineering VelTech Rangarajan Dr Sagunthala R & D Institute of Science and Technology Chennai Computer Science and Engineering Ramco Institute of Technology Rajapalayam Electrical and Electronics Engineering Chennai Institute of Technology Department of Computer Science and Engineering Kongu Engineering College Erode Tamilnadu Department of ECE R.M.K. College of Engineering and Technology

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

The classification of Remote sensing image (RSI)is a vital task in field of geospatial analysis where aerial or satellite images are classified into predefined classes or land cover sorts. It plays a main part in diverse fields namely agriculture, disaster management, environmental surveillance, urban planning, and natural resource management. With the machine learning (ML) and deep learning (DL) models, these images examined and categorized depending on their spatial, spectral and temporal features. The exact detection of remote sensing images simplifies decision-making procedures, aiding governments, environmental agencies, and companies to make knowledgeable decisions and policies. It authorizes experts to observe variations in lands, discover land use trends, and evaluate environmental effects and making it a vital device in addressing present difficult challenges connected to weather change, urban development, and natural resource protection. This study presents an enhanced remote sensing image classification utilizing arithmetic optimization algorithm with DL (ERSC-AODL) Approach. The ERSC-AODL technique concentrates on the accurate recognition of the RSI into dissimilar classes. It begins with the use of an EfficientNet feature extractor, which derives complex spectral and spatial data, and acts as a base of proper representation of the images. Moreover, the recognition process takes place by a bidirectional long short-term memory (BiLSTM). Finally, the hyperparameter optimization procedure is performed by the ERSC-AODL technique. To portray the proficient classification outputs of the ERSC-AODL technique, a range of experiments were utilized. The investigational outputs stated that the ERSC-AODL technique attains improved accomplishment over other models.

关键词： Natural resources Recurrent neural networks Feature extraction Spatial databases Classification algorithms Data mining Remote sensing Optimization Long short term memory Image classification

来源：评论

学校读者我要写书评

暂无评论

The Effect of Mismatch between SPECT and CT Images on Deep Learning-based Attenuation Correction for Myocardial Perfusion SPECT

The Effect of Mismatch between SPECT and CT Images on Deep L...

引用

2022 IEEE Nuclear Science Symposium, Medical Imaging Conference, and Room Temperature Semiconductor Detector Conference, IEEE NSS MIC RTSD 2022

作者： Du, Yu Shang, Jingjie Sun, Jingzhang Wang, Lu Xu, Hao Mok, Greta S. P. University of Macau Faculty of Science and Technology Department of Electrical and Computer Engineering China The First Affiliated Hospital of Jinan University Department of Nuclear Medicine PET/CT-MRI Centre Guangdong Guangzhou China

ISBN: (纸本)9781665488723

Attenuation correction (AC) using deep learning (DL)-based methods improves image quality and quantitative accuracy in myocardial perfusion (MP) SPECT when CT-based AC (CT-AC) is not feasible. However, potential misalignments between SPECT and CT may affect the DL-based AC performance. This study aims to evaluate this effect based on real patient data. Fifity-eight stress/rest99mTc-sestamibi scans from 34 patients were retrospectively analyzed. Thirty-six projections, acquired from RAO to LPO in 11 min, were reconstructed by OS-EM algorithm, with and without CT-AC. A 3D conditional generative adversarial network was implemented and optimized for the DL-ACµ and DL-AC, while 43, 5 and 10 datasets were used for training, validation and testing with a 6-fold cross-validation. SPECT and CT mismatch was modeled by randomly shifting the CT images in 3 dimensions (8.6±3.8 mm) with respective to their corresponding SPECT images based on a clinical reference. Mismatched SPECT and CT images were also used to train the network separately, i.e., mDL-AC and mDL-ACµ. NMSE, SSIM, joint correlation histogram and linear regression on a 3D cardiac VOI were compared for all cases, with matched CT-AC as the reference. NMSE and SSIM show significantly degraded performance on mDL-ACµ and mDL-AC as compared to DL-ACµ and DL-AC, respectively. mDL-ACµ is consistently better than mDL-AC. The joint correlation histogram and linear regression result is consistent. We conclude that though SPECT and CT mismatch significantly degrades DL-based AC performance, mDL-ACµ is more robust to mDL-AC for MP SPECT and shows improved results as compared to NAC. © 2022 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Depth and Pitch Control of Autonomous Underwater Glider Using Model Predictive Control with ARX Model

Depth and Pitch Control of Autonomous Underwater Glider Usin...

引用

International Conference on electrical engineering and Informatics, ICEEI

作者： Jason Jeremy Egi Muhammad Idris Hidayat Simon Siregar Bambang Riyanto Trilaksono Natsir Habibullah School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Department Computer Engineering Faculty of Applied Science Telkom University Bandung Indonesia

Autonomous Underwater Gliders (AUGs) are extensively developed vehicles capable of prolonged exploration and observation in complex marine environments. Control of the AUG is challenging due to its slow response system and its constraints. In this research, a linear model representation of AutoRegressive eXogenous input (ARX) will be constructed using input and output data from the AUG system, built Model Predictive Control (MPC), analyzed the performance, comparing with traditional Proportional-Integral-Derivative (PID). The objective is to enhance setpoint tracking accuracy and minimize energy to extend exploration time while faced with constraints. Simulation results reveal MPC exhibits potential setpoint tracking, low overshoot as low as 0.6% up to 0.3m/s maximum depth rate, has relatively low input changes indicating good efficiency compared to PID. MPC approach effectively addresses slow response systems, managing momentum, and handling actuator constraints commonly encountered in AUG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Can Copyright be Reduced to Privacy?

arXiv

引用

arXiv 2023年

作者： Elkin-Koren, Niva Hacohen, Uri Livni, Roi Moran, Shay Faculty of Law Tel Aviv University Department of Electrical Engineering Tel Aviv University Department of Mathematics and Computer Science Technion

There is a growing concern that generative AI models will generate outputs closely resembling the copyrighted materials for which they are trained. This worry has intensified as the quality and complexity of generative models have immensely improved, and the availability of extensive datasets containing copyrighted material has expanded. Researchers are actively exploring strategies to mitigate the risk of generating infringing samples, with a recent line of work suggesting to employ techniques such as differential privacy and other forms of algorithmic stability to provide guarantees on the lack of infringing copying. In this work, we examine whether such algorithmic stability techniques are suitable to ensure the responsible use of generative models without inadvertently violating copyright laws. We argue that while these techniques aim to verify the presence of identifiable information in datasets, thus being privacy-oriented, copyright law aims to promote the use of original works for the benefit of society as a whole, provided that no unlicensed use of protected expression occurred. These fundamental differences between privacy and copyright must not be overlooked. In particular, we demonstrate that while algorithmic stability may be perceived as a practical tool to detect copying, such copying does not necessarily constitute copyright infringement. Therefore, if adopted as a standard for detecting an establishing copyright infringement, algorithmic stability may undermine the intended objectives of copyright law. © 2023, CC BY-SA.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

A Novel Terahertz Metamaterial Absorber Based on Split-Relief Design for the Application of Refractive Index Sensing

SSRN

引用

SSRN 2023年

作者： Abdulkarim, Yadgar I. Muhammadsharif, Fahmi F. Appasani, Bhargav Bakır, Mehmet Karaaslan, Muharrem Rezaei, Pejman Khatami, Seyed Amin Daraei, Omid Mohsen Zamzam, Pouria Dong, Jian School of Computer Science and Engineering Central South University Changsha410075 China Physics Department College of Science Charmo University Chamchamal Sulaimania46023 Iraq Department of Physics Faculty of Science and Health Koya University KOY45 Koya Iraq School of Electronics Engineering KIIT University Odisha Bhubaneswar India Department of Computer Engineering Bozok University Yozgat66200 Turkey Department of Electrical-Electronics Engineering Iskenderun Technical University Hatay 31200 Turkey Electrical and Computer Engineering Faculty Semnan University Semnan Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran

THz metamaterial absorbers are a subclass of metamaterial-based structures that can absorb THz electromagnetic radiations in the THz range. In this paper, four different designs of THz metamaterial absorbers are proposed which are based on split-relief (SR) design. They consist of sun-shaped, SR sun-shaped, star-shaped and SR star-shaped resonators coated on top of a dielectric substrate. The resonance frequencies of the designs were found to be at 0.70, 1.04, 0.41 and 0.60 THz, respectively. Results showed that the resonance frequency was independent on the incident and polarization angles. The proposed absorbers were used to detect the thickness and refractive index of the analyte. The thickness of the analyte can be detected with a sensitivity of 73 GHz/µm for the Sun design, 238 GHz/µm for the SRSun design, 45.2 GHz/µm for the Star design, and 133.4 GHz/µm for the SRStar design. Similarly, the refractive index of the analyte can be measured with a sensitivity of 1.581 THz/RIU for the Sun design, 4.053 THz/RIU for the SRSun design, 1.077 THz/RIU for the Star design, and 2.067 THz/RIU for the SRStar design when the analyte thickness was fixed at 3 μm. The resonance mechanism was explained considering electric and magnetic field distributions. © 2023, The Authors. All rights reserved.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

Optimizing energy payment, user satisfaction, and self-sufficiency in flexibility-constrained smart home energy management: A multi-objective optimization approach

引用

e-Prime - Advances in electrical engineering, Electronics and Energy 2023年 6卷

作者： Dorahaki, Sobhan MollahassaniPour, Mojgan Rashidinejad, Masoud Department of Electrical Engineering Shahid Bahonar University of Kerman Kerman Iran Faculty of Electrical and Computer Engineering University of Sistan and Baluchestan Zahedan Iran

Smart homes have assumed a pivotal role within energy communities, offering sophisticated home energy management systems tailored to end-users preferences across technical, economic, social, and environmental facets. Amid the proliferation of smart appliances and advanced communication infrastructure, these domiciles play a crucial part in optimizing energy utilization and fostering sustainable practices. Notably, they create an enabling environment for the integration of renewable energy resources, but their widespread adoption may potentially challenge the flexibility of the overarching energy system. In this paper, a novel flexibility-constrained smart home energy management framework is proposed aiming at optimizing energy payment, end-user satisfaction, and end-user self-sufficiency preferences. Diverse technologies including Combined Heat and power (CHP) units, PhotoVoltaic (PV) generation units, electrical energy storage systems, and electric vehicles are considered in the smart home where the PV unit uncertainty is modeled by a scenario-based approach. The lexicographic technique as a Multi-Criteria Decision Making (MCDM) approach is utilized to find an appropriate compromise among different targets. The proposed model is structured as a Mixed-Integer Linear Programming (MILP) problem that is solved by the CPLEX solver in the GAMS environment. The results reveal a significant disparity in energy payments when the flexibility limit falls below 40 % of the predefined amount. The results demonstrate that altering the priority order of the objective functions has led to significant changes in energy payment, end-user satisfaction, and end-user self-sufficiency, with variations of 27.4 %, 100 %, and 56.64 %, respectively. © 2023 The Author(s)

关键词： End-User Satisfaction Flexibility Home Energy Management Lexicographic Multi-Objective Optimization Self-sufficiency

来源：评论

学校读者我要写书评

暂无评论

Development of a digital twin environment for smart collision avoidance algorithms for mobile robots using reinforcement learning

Development of a digital twin environment for smart collisio...

引用

SICE Annual Conference

作者： Natsumi Matsumoto Kazuyuki Kobayashi Tomoyuki Ohkubo Kaiqiao Tian Nashwan J Sebi Ka C Cheok Cai Changqing Graduate School of Science and Engineering Hosei University Tokyo Japan Faculty of Advanced Engineering Nippon Institute of Technology Saitama Japan Electrical & Computer Engineering Department School of Engineering & Computer Science Oakland University Rochester USA School of Electrical Engineering and Information Technology Changchun Institute of Technology China

This paper describes a study on building a digital twin environment using point cloud data for mobile robots. A digital twin environment for mobile robots is a method to reproduce almost the same environment in a simulation space as if it were a twin, using data from an actual natural environment. In fact, in the development of mobile robots, experiments on public urban area are conducted, however, they are incredibly time-consuming and labor-intensive, so it would be helpful if a realistic simulation environment could be created. This study focuses on building a digital twin environment using point-cloud-data for mobile robots. In order to verify the effectiveness of this approach, we constructed the environment using data from a real mobile robot that has been driven. The navigation of the mobile robot was performed in the constructed simulation environment, and it was possible to realize a navigation run in the driving environment that was almost the same as the run of the real mobile robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter for tracking a noisy cosinusoidal signal with constant amplitude

Kalman Filter for tracking a noisy cosinusoidal signal with ...

引用

International Conference on computer and Communication engineering, ICCCE

作者： Prima Wijaya Kusuma Mohamed Hadi Habaebi Galang P. N. Hakim Rachmat Muwardi Md. Rafiqul Islam Department of Electrical Engineering Faculty of Engineering Universitas Mercu Buana Jakarta Indonesia Department of Electrical and Computer Engineering Kulliyyah of Engineering (KOE) International Islamic University Malaysia (IIUM) Selangor Malaysia School of Optics and Photonics Beijing Institute of Technology Beijing China

This paper presents a Kalman filter based approach in order to solve the problem of tracking a noisy cosinusoidal signal with constant amplitude in the presence of noise. The objective is to estimate the state of the signal accurately, considering the inherent challenges posed by noise corruption. The Kalman filter is utilized as the core algorithm for state estimation, leveraging its ability to combine noisy measurements and a dynamic model to provide optimal estimates. The filter is initialized with zero states and covariance, and the state and covariance estimates are iteratively updated using time updates and measurement update equations. Through extensive simulations, the performance of the proposed Kalman filter-based algorithm is evaluated. The results demonstrate its effectiveness in accurately tracking cosinusoidal signals and mitigating the impact of noise. the Kalman Filter algorithm in this system produces low MSE at about 0.021 and MAE at about 0.111. The metrics results signify the algorithm’s ability to filter noise and estimate the actual state of the system, reflecting its robust tracking performance. The simulation results validate the effectiveness of the proposed approach and highlight its potential to enhance signal tracking accuracy in the presence of noise. Further research can explore the algorithm’s performance in various scenarios and investigate additional modifications to increase its robustness in challenging environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Overview of Recent Developments in ‘Big’ Boolean Equations

arXiv

引用

arXiv 2023年

作者： Ali Rushdi, Ali Muhammad Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University P. O. Box 80200 Jeddah21589 Saudi Arabia

A task frequently encountered in digital circuit design is the solution of a two-valued Boolean equation of the form ℎ(X, Y, Z) = 1, where ℎ: B2κ+m+n → B2 and X, Y, and Z are binary vectors of lengths κ, m, and n, representing inputs, intermediary values, and outputs, respectively. The resultant of the suppression of the variables Y from this equation could be written in the form g(X, Z) = 1 where g: B2κ+n → B2. Typically, one needs to solve for Z in terms of X, and hence it is unavoidable to resort to ‘big’ Boolean algebras which are finite (atomic) Boolean algebras larger than the two-valued Boolean algebra. Other situations which necessitate ‘big’ Boolean-equation-solving are the so-called ‘elementary problems of digital circuit design,’ which entail five vector-Boolean quantities X, Y, Z, s and t that belong to B2κ, B2m, B2n, B2l , and B2l , respectively. Consider a ‘parent’ combinational network C of two (vectorial) inputs X and Y and a vectorial output t(X, Y), and assume that network C consists of two subnetworks A and B, where subnetwork A has the single (vectorial) input X and the (vectorial) output Z(X), while network B has the two vectorial inputs Z(X) and Y and the (vectorial) output s(Z, Y), which is exactly the same as the (vectorial) output t(X, Y) of network C. The above arrangement involves three vectorial Boolean functions, namely Z(X), s(Z, Y) and t(X, Y). Three problems arise when one utilizes the information that s(Z(X), Y) and t(X, Y) are equal, together with knowledge of two of the three functions X(X), s(Z, Y) and t(X, Y) in order to deduce the third function. Two of these problems are natural examples why ‘big’ Boolean-equation-solving is warranted. Methods of solving ‘big’ Boolean equations can be broadly classified as algebraic, tabular, numerical and map methods. The most prominent among these classes are the algebraic and map methods. This paper surveys and compares these two types of methods as regards simplicity, efficiency, and usabil

关键词： Integrated circuit manufacture

来源：评论

学校读者我要写书评

暂无评论

High temperature and low voltage AC poling for 0.24Pb(In_(1/2)Nb_(1/2))O_(3)- 0.46Pb(Mg_(1/3)Nb_(2/3))O_(3)-0.30PbTiO_(3) piezoelectric single crystals manufactured by continuous-feeding Bridgman method

引用

Journal of Materiomics 2021年第3期7卷 621-628页

作者： Cong Luo Tomoaki Karaki Yohachi(John)Yamashita Jiayue Xu School of Materials Science and Engineering Shanghai Institute of TechnologyShanghai201418China Department of Electrical and Computer Engineering Faculty of EngineeringToyama Prefectural University5180 KurokawaImizuToyama939-0398Japan Department of Mechanical&Aerospace Engineering North Carolina State UniversityRaleighNC27695-7910USA

Alternating current poling(ACP)in air by changing poling temperature(70e130℃)and voltages(2e6 kVrms/cm)on pseudo-ternary 0.24 Pb(In_(1/2)Nb_(1/2))O_(3)-0.46 Pb(Mg1/3Nb_(2/3))O3-0.30PbTiO_(3)(PIMN-0.30PT)single crystals(SCs)manufactured by continuous-feeding Bridgman(CF BM)method was *** dielectric permittivity(εT 33/ε0)and piezoelectric constant(d33)were improved to be 7000 and 2340 pC/N,which were 29%higher than those of direct current poling(DCP)at 90℃ with 4 kV/cm(εT 33/ε0=5440,d_(33)=1810 pC/N).However,phase change temperature(Tpc)decreased from 94℃ to 78℃ as opposite results reported by other *** demonstrated that the high temperature(HT)ACP improved piezoelectric performance of CF BM SCs,however,the Tpc were different from other crystal growth *** well-designed ACP process was a promising method for mass production not only to enhance the electrical properties for the pseudo-ternary SCs but also reduce the risk of breakdown and realizes organic solvent-free poling process.

关键词： High temperature alternating current poling Low voltages PIMN-0.30PT Continuous-feeding bridgman

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：