检索结果-内蒙古大学图书馆

Modeling and Correcting Bias in Sequential Evaluation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jingyan Pananjady, Ashwin Schools of Industrial and Systems Engineering United States Electrical and Computer Engineering Georgia Institute of Technology

We consider the problem of sequential evaluation, in which an evaluator observes candidates in a sequence and assigns scores to these candidates in an online, irrevocable fashion. Motivated by the psychology literature that has studied sequential bias in such settings—namely, dependencies between the evaluation outcome and the order in which the candidates appear—we propose a natural model for the evaluator’s rating process that captures the lack of calibration inherent to such a task. We conduct crowdsourcing experiments to demonstrate various facets of our model. We then proceed to study how to correct sequential bias under our model by posing this as a statistical inference problem. We propose a near-linear time, online algorithm for this task and prove guarantees in terms of two canonical ranking metrics. We also prove that our algorithm is information theoretically optimal, by establishing matching lower bounds in both metrics. Finally, we perform a host of numerical experiments to show that our algorithm often outperforms the de facto method of using the rankings induced by the reported scores, both in simulation and on the crowdsourcing data that we collected. Copyright © 2022, The Authors. All rights reserved.

关键词： Crowdsourcing

Deep Learning Assisted End-to-End Synthesis of mm-Wave Passive Networks with 3D EM Structures: A Study on A Transformer-Based Matching Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Er, Siawpeng Liu, Edward Chen, Minshuo Li, Yan Liu, Yuqi Zhao, Tuo Wang, Hua School of Electrical and Computer Engineering Georgia Tech School of Industrial and Systems Engineering Georgia Tech

This paper presents a deep learning assisted synthesis approach for direct end-to-end generation of RF/mm-wave passive matching network with 3D EM structures. Different from prior approaches that synthesize EM structures from target circuit component values and target topologies, our proposed approach achieves the direct synthesis of the passive network given the network topology from desired performance values as input. We showcase the proposed synthesis Neural Network (NN) model on an on-chip 1:1 transformer-based impedance matching network. By leveraging parameter sharing, the synthesis NN model successfully extracts relevant features from the input impedance and load capacitors, and predict the transformer 3D EM geometry in a 45nm SOI process that will match the standard 50Ω load to the target input impedance while absorbing the two loading capacitors. As a proof-of-concept, several example transformer geometries were synthesized, and verified in Ansys HFSS to provide the desired input impedance. © 2022, CC BY.

关键词： Impedance matching (electric)

Special Issue on Robotics and Mechatronics Technology for Aerial Robots

学校读者我要写书评

暂无评论

Journal of Robotics and Mechatronics 2024年第5期36卷 999-1000页

作者： Ohtake, Hiroshi Suzuki, Satoshi Takesue, Naoyuki Miwa, Masafumi Fujikawa, Taro Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka Fukuoka820-8502 Japan Faculty of Engineering Chiba University 1-33 Yayoi-cho Inage-ku Chiba Chiba263-8522 Japan Graduate School of Systems Design Tokyo Metropolitan University 6-6 Asahigaoka Hino Tokyo191-0065 Japan Graduate School of Technology Industrial and Social Sciences Tokushima University 2-1 Minamijosanjima-cho Tokushima Tokushima770-8506 Japan Graduate School of Science and Technology for Future Life Tokyo Denki University 5 Senju Asahi-cho Adachi-ku Tokyo120-8551 Japan

A Novel Krill Herd Based Random Forest Algorithm for Monitoring Patient Health

学校读者我要写书评

暂无评论

computers, Materials & Continua 2023年第5期75卷 4553-4571页

作者： Md.Moddassir Alam Md Mottahir Alam Muhammad Moinuddin Mohammad Tauheed Ahmad Jabir Hakami Anis Ahmad Chaudhary Asif Irshad Khan Tauheed Khan Mohd Department of Health Information Management and Technology University of Hafr Al-BatinSaudi Arabia Department of Electrical and Computer Engineering Faculty of EngineeringKing AbdulazizJeddah21589Saudi Arabia Center of Excellence in Intelligent Engineering Systems King Abdul Aziz UniversityJeddahSaudi Arabia College of Medicine King Khalid UniversityAbhaSaudi Arabia Department of Physics College of ScienceJazan UniversityP.O.Box.114Jazan45142Saudi Arabia Department of Biology College of ScienceImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11623Saudi Arabia Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Math and Computer Science Augustana CollegeIL61201United States

Artificial Intelligence(AI)is finding increasing application in healthcare *** learning systems are utilized for monitoring patient health through the use of IoT sensor,which keep track of the physiological state by way of various health ***,early detection of any disease or derangement can aid doctors in saving patients’***,there are some challenges associated with predicting health status using the common algorithms,such as time requirements,chances of errors,and improper *** propose an Artificial Krill Herd based on the Random Forest(AKHRF)technique for monitoring patients’health and eliciting an optimal prescription based on their health *** begin with,various patient datasets were collected and trained into the system using IoT *** a result,the framework developed includes four processes:preprocessing,feature extraction,classification,and result ***,preprocessing removes errors,noise,and missing values from the dataset,whereas feature extraction extracts the relevant ***,in the classification layer,we updated the fitness function of the krill herd to classify the patient’s health status and also generate a *** found that the results fromthe proposed framework are comparable to the results from other state-of-the-art techniques in terms of sensitivity,specificity,Area under the Curve(AUC),accuracy,precision,recall,and F-measure.

关键词： Healthcare system health monitoring clinical decision support internet of things artificial intelligence machine learning diagnosis

Water Wave Optimization with Deep Learning Driven Smart Grid Stability Prediction

学校读者我要写书评

暂无评论

computers, Materials & Continua 2022年第12期73卷 6019-6035页

作者： Anwer Mustafa Hilal Aisha Hassan Abdalla Hashim Heba G.Mohamed Mohammad Alamgeer Mohamed K.Nour Anas Abdelrahman Abdelwahed Motwakel Department of Electrical and Computer Engineering International Islamic University MalaysiaKuala Lumpur53100Malaysia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam Bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Electrical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer Science and Bioinformatics Singhania UniversityPacheri BariJhnujhunuRajasthanIndia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Mechanical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11835Egypt

Smart Grid(SG)technologies enable the acquisition of huge volumes of high dimension and multi-class data related to electric power grid operations through the integration of advanced metering infrastructures,control systems,and communication *** SGs,user demand data is gathered and examined over the present supply criteria whereas the expenses are then informed to the clients so that they can decide about electricity *** the entire procedure is valued on the basis of time,it is essential to perform adaptive estimation of the SG’s *** advancements inMachine Learning(ML)andDeep Learning(DL)models enable the designing of effective stability prediction models in *** this background,the current study introduces a novel Water Wave Optimization with Optimal Deep Learning Driven Smart Grid Stability Prediction(WWOODL-SGSP)*** aim of the presented WWOODL-SGSP model is to predict the stability level of SGs in a proficient *** attain this,the proposed WWOODL-SGSP model initially applies normalization process to scale the data to a uniform ***,WWO algorithm is applied to choose an optimal subset of features from the pre-processed ***,Deep Belief Network(DBN)model is followed to predict the stability level of ***,Slime Mold Algorithm(SMA)is exploited to fine tune the hyperparameters involved in DBN *** order to validate the enhanced performance of the proposedWWOODL-SGSP model,a wide range of experimental analyses was *** simulation results confirmthe enhanced predictive results of WWOODL-SGSP model over other recent approaches.

关键词： Smart grid stability prediction deep learning energy systems machine learning metaheursitics

Hyperparameter tuning via trajectory predictions: Stochastic prox-linear methods in matrix sensing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lou, Mengqi Verchand, Kabir Aladin Pananjady, Ashwin School of Industrial and Systems Engineering Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Statistical Laboratory University of Cambridge United Kingdom

Motivated by the desire to understand stochastic algorithms for nonconvex optimization that are robust to their hyperparameter choices, we analyze a mini-batched prox-linear iterative algorithm for the problem of recovering an unknown rank-1 matrix from rank-1 Gaussian measurements corrupted by noise. We derive a deterministic recursion that predicts the error of this method and show, using a non-asymptotic framework, that this prediction is accurate for any batch-size and a large range of step-sizes. In particular, our analysis reveals that this method, though stochastic, converges linearly from a local initialization with a fixed step-size to a statistical error floor. Our analysis also exposes how the batch-size, step-size, and noise level affect the (linear) convergence rate and the eventual statistical estimation error, and we demonstrate how to use our deterministic predictions to perform hyperparameter tuning (e.g. step-size and batch-size selection) without ever running the method. On a technical level, our analysis is enabled in part by showing that the fluctuations of the empirical iterates around our deterministic predictions scale with the error of the previous iterate. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

Multi-Unit Floor Plan Recognition and Reconstruction Using Improved Semantic Segmentation of Raster-Wise Floor Plans

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kratochvila, Lukas de Jong, Gijs Arkesteijn, Monique Bilík, Šimon Zemčík, Tomáš Horak, Karel Rellermeyer, Jan S. Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic Department of Software Technology Faculty of Electrical Engineering Mathematics and Computer Science TU Delft Delft Netherlands Department of Management in the Built Environment Faculty of Architecture and the Built Environment TU Delft Delft Netherlands Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering Lappeenranta-Lahti University of Technology LUT Lappeenranta Finland Dependable and Scalable Software Systems Institute of Systems Engineering Faculty of Electrical Engineering and Computer Science Leibniz University Hannover Hannover Germany

Digital twins have a major potential to form a significant part of urban management in emergency planning, as they allow more efficient designing of the escape routes, better orientation in exceptional situations, and faster rescue intervention. Nevertheless, creating the twins still remains a largely manual effort, due to a lack of 3D-representations, which are available only in limited amounts for some new buildings. Thus, in this paper we aim to synthesize 3D information from commonly available 2D architectural floor plans. We propose two novel pixel-wise segmentation methods based on the MDA-Unet and MACU-Net architectures with improved skip connections, an attention mechanism, and a training objective together with a reconstruction part of the pipeline, which vectorizes the segmented plans to create a 3D model. The proposed methods are compared with two other state-of-the-art techniques and several benchmark datasets. On the commonly used CubiCasa benchmark dataset, our methods have achieved the mean F1 score of 0.86 over five examined classes, outperforming the other pixel-wise approaches tested. We have also made our code publicly available to support research in the field. © 2024, CC BY.

关键词： Semantic Segmentation

Confidential Computing as an Attempt to Secure Service Provider's Confidential Client Data in a Multi-Tenant Cloud Environment 44

学校读者我要写书评

暂无评论

Confidential Computing as an Attempt to Secure Service Provi...

44th International Convention on Information, Communication and Electronic Technology, MIPRO 2021

作者： Novkovic, Bojan Bozic, Anita Golub, Marin Gros, Stjepan Microelectronics Computer and Intelligent Systems Faculty of Electrical Engineering and Computing Zagreb Department of Electronics Croatia

ISBN: (纸本)9789532331011

Cloud-oriented infrastructure posed itself as a predominant deployment paradigm in the recent decade due to its ease of provisioning and relatively low cost. However, entrusting a third party with sensitive data in a multi-tenant environment brings about increased data breach risks. The aim of this paper is to give an insight into challenges and threats encountered in mitigating data breach and repudiation risks for service providers utilizing cloud-based environments. Through constructing and studying a possible cloud-based service, we form a corresponding threat model with a special focus on risks originating from internal actors. We explore confidential computing as a possible solution for data confidentiality and mitigation of internal data breach risks for Software as a Service (SaaS) providers. © 2021 Croatian Society MIPRO.

关键词： Costs

Sharp Analysis of Out-of-Distribution Error for “Importance-Weighted” Estimators in the Overparameterized Regime

学校读者我要写书评

暂无评论

Sharp Analysis of Out-of-Distribution Error for “Importance...

IEEE International Symposium on Information Theory

作者： Kuo-Wei Lai Vidya Muthukumar School of Electrical & Computer Engineering Georgia Institute of Technology Atlanta GA USA H. Milton Stewart School of Industrial & Systems Engineering Georgia Institute of Technology Atlanta GA USA

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

Overparameterized models that achieve zero training error are observed to generalize well on average, but degrade in performance when faced with data that is under-represented in the training sample. In this work, we study an overparameterized Gaussian mixture model imbued with a spurious feature, and sharply analyze the in-distribution and out-of-distribution test error of a cost-sensitive interpolating solution that incorporates “importance weights”. Compared to recent work [1], [2], our analysis is sharp with matching upper and lower bounds, and significantly weakens required assumptions on data dimensionality. Our error characterizations apply to any choice of importance weights and unveil a novel tradeoff between worst-case robustness to distribution shift and average accuracy as a function of the importance weight magnitude 1 1 An extended version of this paper is available at https://***/abs/2405.06546..

关键词： Training Support vector machines Interpolation Accuracy Data models Robustness Gaussian mixture model