检索结果-南通市图书馆

Generating Time-Series Data Using Generative Adversarial Networks for Mobility Demand Prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第3期74卷 5507-5525页

作者： Subhajit Chatterjee yung-cheol byun Department of Computer Engineering Jeju National UniversityJeju-si63243Korea Department of Computer Engineering Major of Electronic EngineeringJeju National UniversityInstitute of Information Science&TechnologyJeju63243Korea

The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist and education-centric localities.In the upcoming arrival of electric kickboard vehicles,deploying a customer rental service is essential.Due to its freefloating nature,the shared electric kickboard is a common and practical means of transportation.Relocation plans for shared electric kickboards are required to increase the quality of service,and forecasting demand for their use in a specific region is crucial.Predicting demand accurately with small data is troublesome.Extensive data is necessary for training machine learning algorithms for effective prediction.Data generation is a method for expanding the amount of data that will be further accessible for training.In this work,we proposed a model that takes time-series customers’electric kickboard demand data as input,pre-processes it,and generates synthetic data according to the original data distribution using generative adversarial networks(GAN).The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data.We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results.We modified The Wasserstein GAN-gradient penalty(GP)with the RMSprop optimizer and then employed Spectral Normalization(SN)to improve training stability and faster convergence.Finally,we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction.We used various evaluation criteria and visual representations to compare our proposed model’s performance.Synthetic data generated by our suggested GAN model is also evaluated.The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem,and it also converges faster than previous GAN models for synthetic data creation.The presented model’s performance is compared to

关键词： Machine learning generative adversarial networks electric vehicle time-series TGAN WGAN-GP blend model demand prediction regression

Generating Synthetic Data to Reduce Prediction Error of Energy Consumption

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第2期70卷 3151-3167页

作者： Debapriya Hazra Wafa Shafqat yung-cheol byun Department of Computer Engineering Jeju National UniversityJeju-siKorea

Renewable and nonrenewable energy sources are widely incorporated for solar and wind energy that produces electricity without increasing carbon dioxide emissions.Energy industries worldwide are trying hard to predict future energy consumption that could eliminate over or under contracting energy resources and unnecessary financing.Machine learning techniques for predicting energy are the trending solution to overcome the challenges faced by energy companies.The basic need for machine learning algorithms to be trained for accurate prediction requires a considerable amount of data.Another critical factor is balancing the data for enhanced prediction.Data Augmentation is a technique used for increasing the data available for training.Synthetic data are the generation of new data which can be trained to improve the accuracy of prediction models.In this paper,we propose a model that takes time series energy consumption data as input,pre-processes the data,and then uses multiple augmentation techniques and generative adversarial networks to generate synthetic data which when combined with the original data,reduces energy consumption prediction error.We propose TGAN-skip-Improved-WGAN-GP to generate synthetic energy consumption time series tabular data.We modify TGANwith skip connections,then improveWGANGPby defining a consistency term,and finally use the architecture of improved WGAN-GP for training TGAN-skip.We used various evaluation metrics and visual representation to compare the performance of our proposed model.We also measured prediction accuracy along with mean and maximum error generated while predicting with different variations of augmented and synthetic data with original data.The mode collapse problemcould be handled by TGAN-skip-Improved-WGAN-GP model and it also converged faster than existing GAN models for synthetic data generation.The experiment result shows that our proposed technique of combining synthetic data with original data could significantly reduce the prediction error rate and increase the p

关键词： Energy consumption generative adversarial networks synthetic data time series data TGAN WGAN-GP TGAN-skip prediction error augmentation

Lung Cancer Segmentation with Three-Parameter Logistic Type Distribution Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第4期75卷 1447-1465页

作者： Debnath Bhattacharyya EaliStephen Neal Joshua N.Thirupathi Rao yung-cheol byun Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaramGuntur522302Andhra PradeshIndia Department of Computer Science&Engineering Vignan’s Institute of Information Technology(A)Visakhapatnam530049Andhra PradeshIndia Department of Computer Engineering Jeju National University102 Jejudaehak-roJeju-siJeju-do690-756Korea

Lung cancer is the leading cause of mortality in the world affectingboth men and women equally.When a radiologist just focuses on the patient’sbody, it increases the amount of strain on the radiologist and the likelihoodof missing pathological information such as abnormalities are increased.One of the primary objectives of this research work is to develop computerassisteddiagnosis and detection of lung cancer. It also intends to make iteasier for radiologists to identify and diagnose lung cancer accurately. Theproposed strategy which was based on a unique image feature, took intoconsideration the spatial interaction of voxels that were next to one another.Using the U-NET+Three parameter logistic distribution-based technique, wewere able to replicate the situation. The proposed technique had an averageDice co-efficient (DSC) of 97.3%, a sensitivity of 96.5% and a specificity of94.1% when tested on the Luna-16 dataset. This research investigates howdiverse lung segmentation, juxta pleural nodule inclusion, and pulmonarynodule segmentation approaches may be applied to create Computer AidedDiagnosis (CAD) systems. When we compared our approach to four otherlung segmentation methods, we discovered that ours was the most successful.We employed 40 patients from Luna-16 datasets to evaluate this. In termsof DSC performance, the findings demonstrate that the suggested techniqueoutperforms the other strategies by a significant margin.

关键词： Magnetic resonance imaging(MRI) lung cancer Luna-16 logistic distribution segmentation deep learning juxta plural pulmonary nodules

High-Movement Human Segmentation in Video Using Adaptive N-Frames Ensemble

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第12期73卷 4743-4762页

作者： Yong-Woon Kim yung-cheol byun Dong Seog Han Dalia Dominic Sibu Cyriac Centre for Digital Innovation CHRIST(Deemed to be University)Bangalore560029India Department of Computer Engineering Jeju National UniversityJeju63243Korea School of Electronics Engineering Kyungpook National UniversityDaegu41566Korea

Awide range of camera apps and online video conferencing services support the feature of changing the background in real-time for aesthetic,privacy,and security reasons.Numerous studies show that theDeep-Learning(DL)is a suitable option for human segmentation,and the ensemble of multiple DL-based segmentation models can improve the segmentation result.However,these approaches are not as effective when directly applied to the image segmentation in a video.This paper proposes an Adaptive N-Frames Ensemble(AFE)approach for high-movement human segmentation in a video using an ensemble of multiple DL models.In contrast to an ensemble,which executes multiple DL models simultaneously for every single video frame,the proposed AFE approach executes only a single DL model upon a current video frame.It combines the segmentation outputs of previous frames for the final segmentation output when the frame difference is less than a particular threshold.Our method employs the idea of the N-Frames Ensemble(NFE)method,which uses the ensemble of the image segmentation of a current video frame and previous video frames.However,NFE is not suitable for the segmentation of fast-moving objects in a video nor a video with low frame rates.The proposed AFE approach addresses the limitations of the NFE method.Our experiment uses three human segmentation models,namely Fully Convolutional Network(FCN),DeepLabv3,and Mediapipe.We evaluated our approach using 1711 videos of the TikTok50f dataset with a single-person view.The TikTok50f dataset is a reconstructed version of the publicly available TikTok dataset by cropping,resizing and dividing it into videos having 50 frames each.This paper compares the proposed AFE with single models and the Two-Models Ensemble,as well as the NFE models.The experiment results show that the proposed AFE is suitable for low-movement as well as high-movement human segmentation in a video.

关键词： High movement human segmentation artificial intelligence deep learning ensemble video instance segmentation

Adaptive Error Curve Learning Ensemble Model for Improving Energy Consumption Forecasting

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第11期69卷 1893-1913页

作者： Prince Waqas Khan yung-cheol byun Department of Computer Engineering Jeju National UniversityJeju-siKorea

Despite the advancement within the last decades in the field of smart grids,energy consumption forecasting utilizing the metrological features is still challenging.This paper proposes a genetic algorithm-based adaptive error curve learning ensemble(GA-ECLE)model.The proposed technique copes with the stochastic variations of improving energy consumption forecasting using a machine learning-based ensembled approach.A modified ensemble model based on a utilizing error of model as a feature is used to improve the forecast accuracy.This approach combines three models,namely CatBoost(CB),Gradient Boost(GB),and Multilayer Perceptron(MLP).The ensembled CB-GB-MLP model’s inner mechanism consists of generating a meta-data from Gradient Boosting and CatBoost models to compute the final predictions using the Multilayer Perceptron network.A genetic algorithm is used to obtain the optimal features to be used for the model.To prove the proposed model’s effectiveness,we have used a four-phase technique using Jeju island’s real energy consumption data.In the first phase,we have obtained the results by applying the CB-GB-MLP model.In the second phase,we have utilized a GA-ensembled model with optimal features.The third phase is for the comparison of the energy forecasting result with the proposed ECL-based model.The fourth stage is the final stage,where we have applied the GA-ECLE model.We obtained a mean absolute error of 3.05,and a root mean square error of 5.05.Extensive experimental results are provided,demonstrating the superiority of the proposed GA-ECLE model over traditional ensemble models.

关键词： Energy consumption meteorological features error curve learning ensemble model energy forecasting gradient boost catboost multilayer perceptron genetic algorithm

“If I Do not Go to Work, They Will Die!” Dual Roles of Older-Adult Personal Support Workers' Contributions During the COVID-19 Pandemic

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Disaster Risk Science 2024年第2期15卷 226-238页

作者： Haorui Wu Mandy yung School of Social Work Faculty of Health Dalhousie University

When COVID-19 devastated older-adult organizations(long-term care homes and retirement homes), most public attention was directed toward the older-adult residents rather than their service providers. This was especially true in the case of personal support workers, some of whom are over the age of 55, putting them in two separate categories in the COVID-19 settings:(1) a vulnerable and marginalized group who are disproportionately impacted by COVID-19; and(2) essential healthcare workers. Since the current disaster-driven research, practice, and policy have primarily focused on generalized assumptions that older-adults are a vulnerable, passive, and dependent group rather than recognizing their diversity, expertise, assets, and experiences, this study aimed to identify their contributions from the perspective of older-adult personal support worker(OAPSW). This qualitative study conducted in-depth interviews, inviting 15 OAPSWs from the Greater Toronto Area, Canada. This study uncovered the OAPSWs' contribution at three levels: individual(enhancing physical health, mental health, and overall well-being), work(improving working environment and service and supporting co-workers), and family(protecting their nuclear and extended families). The outcomes inform the older-adult research, practice, policy, public discourse, and education by enhancing the appreciation of older-adults' diverse strengths and promoting their engagement and contributions in disaster settings.

关键词： Canada COVID-19 Individual-work-family triangulation Older-adult personal support workers

Chronic venous insufficiency, could it be one of the missing pieces in the puzzle of treating pain?

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

World Journal of Clinical Cases 2024年第1期12卷 232-235页

作者： Min cheol Chang Department of Physical Medicine and Rehabilitation Yeungnam University HospitalDaegu 705-717South Korea

Pain is a common complaint among patients seeking medical care.If left un-treated,pain can become chronic,significantly affecting patients’quality of life.An accurate diagnosis of the underlying cause of pain is crucial for effective treatment.Chronic venous insufficiency(CVI)is frequently overlooked by pain physicians.Moreover,many pain physicians lack sufficient knowledge about CVI.CVI is a common condition resulting from malfunctioning or damaged valves in lower limb veins.Symptoms of CVI,ranging from mild to severe,include pain,heaviness,fatigue,itching,swelling,skin color changes,and ulcers in the lower limbs.Recently,it has become more widely known that these symptoms can be attributed to CVI.Even slight or mild CVI can cause related symptoms.Pain physicians primarily consider neuromusculoskeletal disorders when assessing patients with leg pain,and often neglect the possibility of CVI.In clinical practice,when pain physicians encounter patients with unresolved leg pain,they must assess whether the patients exhibit symptoms of CVI and conduct tests to differ-entiate CVI from other potential causes.

关键词： Pain Chronic venous insufficiency Diagnosis Treatment Vein

Use of artificial intelligence in the field of pain medicine

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Clinical Cases 2024年第2期12卷 236-239页

作者： Min cheol Chang Department of Physical Medicine and Rehabilitation College of MedicineYeungnam UniversityDaegu 705-717South Korea

In this editorial we comment on the article“Potential and limitations of ChatGPT and generative artificial intelligence in medial safety education”published in the recent issue of the World Journal of Clinical Cases.This article described the usefulness of artificial intelligence(AI)in medial safety education.Herein,we focus specifically on the use of AI in the field of pain medicine.AI technology has emerged as a powerful tool,and is expected to play an important role in the healthcare sector and significantly contribute to pain medicine as further developments are made.AI may have several applications in pain medicine.First,AI can assist in selecting testing methods to identify causes of pain and improve diagnostic accuracy.Entry of a patient’s symptoms into the algorithm can prompt it to suggest necessary tests and possible diagnoses.Based on the latest medical information and recent research results,AI can support doctors in making accurate diagnoses and setting up an effective treatment plan.Second,AI assists in interpreting medical images.For neural and musculoskeletal disorders,imaging tests are of vital importance.AI can analyze a variety of imaging data,including that from radiography,computed tomography,and magnetic resonance imaging,to identify specific patterns,allowing quick and accurate image interpretation.Third,AI can predict the outcomes of pain treatments,contributing to setting up the optimal treatment plan.By predicting individual patient responses to treatment,AI algorithms can assist doctors in establishing a treatment plan tailored to each patient,further enhancing treatment effectiveness.For efficient utilization of AI in the pain medicine field,it is crucial to enhance the accuracy of AI decision-making by using more medical data,while issues related to the protection of patient personal information and responsibility for AI decisions will have to be addressed.In the future,AI technology is expected to be innovatively applied in the field of pain medicine.The advancement of AI is anticipa

关键词： Artificial intelligence Pain medicine Diagnosis Prediction Image

Ungraded Matrix Factorizations as Mirrors of Non-orientable Lagrangians

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2024年第1期40卷 26-42页

作者： Lino AMORIM cheol-Hyun CHO Department of Mathematics Kansas State University138 Cardwell Hall1228 N.17th StreetManhattanKS 66506USA Department of Mathematical Sciences Research Institute of MathematicsSeoul National UniversitySan 56-1ShinrimdongGwanakguSeoul 47907South Korea

We introduce the notion of ungraded matrix factorization as a mirror of non-orientable Lagrangian submanifolds.An ungraded matrix factorization of a polynomial W,with coefficients in a field of characteristic 2,is a square matrix Q of polynomial entries satisfying Q^(2)=W·Id.We then show that non-orientable Lagrangians correspond to ungraded matrix factorizations under the localized mirror functor and illustrate this construction in a few instances.Our main example is the Lagrangian submanifold RP^(2)⊂CP^(2)and its mirror ungraded matrix factorization,which we construct and study.In particular,we prove a version of Homological Mirror Symmetry in this setting.

关键词： Mirror symmetry non-orientable Lagrangian submanifold matrix factorization