检索结果-南通市图书馆

Reinforcement learning models for scheduling in wireless networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2013年第5期7卷 754-766页

作者： Kok-lim Alvin yau Kae Hsiang KWONG Chong SHEN Faculty of Science and Technology Sunway University Selangor 46150 Malaysia R&D Department Recovision Selangor 47650 Malaysia College of Information Science and Technology Hainan University Haikou 570228 China

The dynamicity of available resources and net- work conditions, such as channel capacity and traffic charac- teristics, have posed major challenges to scheduling in wire- less networks. Reinforcement learning （RL） enables wire- less nodes to observe their respective operating environment, learn, and make optimal or near-optimal scheduling deci- sions. Learning, which is the main intrinsic characteristic of RL, enables wireless nodes to adapt to most forms of dynamicity in the operating environment as time goes by. This paper presents an extensive review on the application of the traditional and enhanced RL approaches to various types of scheduling schemes, namely packet, sleep-wake and task schedulers, in wireless networks, as well as the advantages and performance enhancements brought about by RL. Addi- tionally, it presents how various challenges associated with scheduling schemes have been approached using RL. Finally, we discuss various open issues related to RL-based schedul- ing schemes in wireless networks in order to explore new re- search directions in this area. Discussions in this paper are presented in a tutorial manner in order to establish a founda- tion for further research in this field.

关键词： reinforcement learning scheduling wireless networks

Deep Reinforcement Learning for Addressing Disruptions in Traffic Light Control

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第5期71卷 2225-2247页

作者： Faizan Rasheed Kok-lim Alvin yau Rafidah Md Noor Yung-Wey Chong School of Engineering and Computer Science University of HertfordshireHatfieldAL109ABUK Department of Computing and Information Systems Sunway UniversitySubang Jaya47500Malaysia Faculty of Computer Science and Information Technology University of MalayaKuala Lumpur50603Malaysia National Advanced IPv6 Centre Universiti Sains MalaysiaUSMPenang11800Malaysia

This paper investigates the use of multi-agent deep Q-network(MADQN)to address the curse of dimensionality issue occurred in the traditional multi-agent reinforcement learning(MARL)*** proposed MADQN is applied to traffic light controllers at multiple intersections with busy traffic and traffic disruptions,particularly *** is based on deep Q-network(DQN),which is an integration of the traditional reinforcement learning(RL)and the newly emerging deep learning(DL)*** enables traffic light controllers to learn,exchange knowledge with neighboring agents,and select optimal joint actions in a collaborative manner.A case study based on a real traffic network is conducted as part of a sustainable urban city project in the Sunway City of Kuala Lumpur in *** is also performed using a grid traffic network(GTN)to understand that the proposed scheme is effective in a traditional traffic *** proposed scheme is evaluated using two simulation tools,namely Matlab and Simulation of Urban Mobility(SUMO).Our proposed scheme has shown that the cumulative delay of vehicles can be reduced by up to 30%in the simulations.

关键词： Artificial intelligence traffic light control traffic disruptions multi-agent deep Q-network deep reinforcement learning

Edge Computing-Based Joint Client Selection and Networking Scheme for Federated Learning in Vehicular IoT

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2021年第6期18卷 39-52页

作者： Wugedele Bao Celimuge Wu Siri Guleng Jiefang Zhang Kok-lim Alvin yau Yusheng Ji School of computer science and information engineering Hohhot Minzu CollegeHohhot 010051China Graduate School of Informatics and Engineering The University of Electro-Communications1-5-1ChofugaokaChofu-shiTokyo182-8585 Japan Institute of Intelligent Media Technology Communication University of ZhejiangZhejiang 310018China School of Science and Technology Sunway University5Jalan UniversitiBandar Sunway47500 Petaling JayaSelangorMalaysia Information Systems Architecture Research Division National Institute of Informatics2-1-2HitotsubashiChiyoda-kuTokyo 101-8430 Japan

In order to support advanced vehicular Internet-of-Things(IoT)applications,information exchanges among different vehicles are required to find efficient solutions for catering to different application requirements in complex and dynamic vehicular *** learning(FL),which is a type of distributed learning technology,has been attracting great interest in recent years as it performs knowledge exchange among different network entities without a violation of user ***,client selection and networking scheme for enabling FL in dynamic vehicular environments,which determines the communication delay between FL clients and the central server that aggregates the models received from the clients,is still *** this paper,we propose an edge computing-based joint client selection and networking scheme for vehicular *** proposed scheme assigns some vehicles as edge vehicles by employing a distributed approach,and uses the edge vehicles as FL clients to conduct the training of local models,which learns optimal behaviors based on the interaction with *** clients also work as forwarder nodes in information sharing among network *** client selection takes into account the vehicle velocity,vehicle distribution,and the wireless link connectivity between vehicles using a fuzzy logic algorithm,resulting in an efficient learning and networking *** use computer simulations to evaluate the proposed scheme in terms of the communication overhead and the information covered in learning.

关键词： vehicular IoT federated learning client selection networking scheme

COLLABORATIVE INTELLIGENCE FOR VEHICULAR INTERNET OF THINGS

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

China Communications 2021年第7期18卷 I0003-I0006页

作者： Celimuge Wu Kok-lim Alvin yau Carlos Tavares Calafate Lei Zhong University of Electro-Communications since IEEE TCGCC Special Interest Group on Green Internet IEEE TCBD Special Interest Group on Big Data with Computational Intelligence Department of Computing and Information Systems Sunway University Department of Computer Engineering at the Technical University of Valencia(UPV)in Spain Connected Advanced Development Division at Toyota Motor Corporation

Future vehicular Internet-of-Things(IoT)systems feature a large number of devices and multi-access environments where different types of communication,computing,and storage resources must be efficiently *** the same time,novel services such as cooperative autonomous driving and intelligent transportation systems(ITS),that demand unprecedented high accuracy,ultra-low latency,and large bandwidth,are emerging.

关键词： INTERNET services utilized

The Role of Deep Learning in Parking Space Identification and Prediction Systems

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

计算机、材料和连续体（英文） 2023年第4期75卷 761-784页

作者： Faizan Rasheed Yasir Saleem Kok-lim Alvin yau Yung-Wey Chong Sye Loong Keoh School of Physics Engineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computer Science Aberystwyth UniversityAberystwyth SY233FLUK Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul RahmanKajang43200SelangorMalaysia National Advanced IPv6 Centre(NAv6) Universiti Sains MalaysiaPenang11800Malaysia School of Computing Science University of Glasgow Singapore737729Singapore

In today’s smart city transportation,traffic congestion is a vexing issue,and vehicles seeking parking spaces have been identified as one of the causes leading to approximately 40%of traffic *** parking spaces alone is insufficient because an identified available parking space may have been taken by another vehicle when it arrives,resulting in the driver’s frustration and aggravating traffic jams while searching for another parking *** explains the need to predict the availability of parking ***,deep learning(DL)has been shown to facilitate drivers to find parking spaces efficiently,leading to a promising performance enhancement in parking identification and prediction ***,no work reviews DL approaches applied to solve parking identification and prediction *** by this gap,the purpose of this work is to investigate,highlight,and report on recent advances inDLapproaches applied to predict and identify the availability of parking *** of DL-based parking identification and prediction systems is established as a methodology by classifying and categorizing existing literature,and by doing so,the salient and supportive features of different DL techniques for providing parking solutions are ***,several open research challenges are *** work identifies that there are various DL architectures,datasets,and performance measures used to address parking identification and prediction ***,there are some open-source implementations available that can be used directly either to extend existing works or explore a new *** is the first short survey article that focuses on the use of DL-based techniques in parking identification and prediction systems for smart *** study concludes that although the deployment of DL in parking identification and prediction systems provides various benefits,the convergence of these two types of systems and DL brings about new i

关键词： Convolutional neural network deep learning neural networks parking identification parking prediction smart city

Relevant Visual Semantic Context-Aware Attention-Based Dialog

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8期76卷 2337-2354页

作者： Eugene Tan Boon Hong Yung-Wey Chong Tat-Chee Wan Kok-lim Alvin yau National Advanced IPv6 Centre Universiti Sains MalaysiaPenangMalaysia Lee Kong Chian Faculty of Engineering and Science(LKCFES) Universiti Tunku Abdul RahmanSungai LongSelangorMalaysia

The existing dataset for visual dialog comprises multiple rounds of questions and a diverse range of image ***,it faces challenges in overcoming visual semantic limitations,particularly in obtaining sufficient context from visual and textual aspects of *** paper proposes a new visual dialog dataset called Diverse History-Dialog(DS-Dialog)to address the visual semantic limitations faced by the existing ***-Dialog groups relevant histories based on their respective Microsoft Common Objects in Context(MSCOCO)image categories and consolidates them for each ***,each MSCOCO image category consists of top relevant histories extracted based on their semantic relationships between the original image caption and historical *** relevant histories are consolidated for each image,and DS-Dialog enhances the current dataset by adding new context-aware relevant history to provide more visual semantic context for each *** new dataset is generated through several stages,including image semantic feature extraction,keyphrase extraction,relevant question extraction,and relevant history dialog *** DS-Dialog dataset contains about 2.6 million question-answer pairs,where 1.3 million pairs correspond to existing VisDial’s question-answer pairs,and the remaining 1.3 million pairs include a maximum of 5 image features for each VisDial image,with each image comprising 10-round relevant question-answer ***,a novel adaptive relevant history selection is proposed to resolve missing visual semantic information for each ***-Dialog is used to benchmark the performance of previous visual dialog models and achieves better performance than previous ***,the proposed DSDialog model achieves an 8% higher mean reciprocal rank(MRR),11% higher R@1%,6% higher R@5%,5% higher R@10%,and 8% higher normalized discounted cumulative gain(NDCG)compared to ***-Dialog also achieves approximately 1 point improvement o

关键词： Visual dialog context-aware relevant history computer vision natural language processing

Cetuximab plus irinotecan in pretreated metastatic colorectal cancer patients:The ELSIE study

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 Gastroenterology 2011年第14期17卷 1879-1888页

作者： Robert lim Yan Sun Seock-Ah Im Ruey-Kuen Hsieh Tsz Kok yau Anthony Bonaventura Arkom Cheirsilpa Regina Esser Matthias Mueser Suresh Advani Department of Hematology-Oncology National University Hospital 119074 Singapore Singapore Department of Medical Oncology Cancer Hospital and Institute Chinese Academy of Medical Science Beijing 100021 China Division of Hematology-Oncology Department of Internal Medicine Seoul National University Hospital Seoul 110-744 South Korea Department of Oncology-Hematology Mackay Memorial Hospital Taipei 104 Taiwan China Department of Clinical Oncology Pamela Youde Nethersole Eastern Hospital Hong Kong China Department of Medical Oncology Calvary Mater Newcastle Hospital Waratah New South Wales 2298. Australia National Cancer Institute Bangkok 10400 Thailand Global Clinical Development Unit Oncology Merck KGaA Darmstadt 64293 Germany Medical Affairs Oncology Asia Pacific Merck Serono 609927 Singapore Singapore Jaslok Hospital and Research Centre Mumbai 400026 India

AIM:To evaluate the efficacy and safety of cetuxim-ab plus irinotecan in irinotecan-refractory metastatic colorectal cancer (mCRC) patients from South-East Asia and Australia. METHODS:In this open-label,phase Ⅱ study,the main eligibility criteria were epidermal growth factor receptor-positive mCRC with progressive disease within 3 mo of an irinotecan-based regimen as the most recent chemotherapy. Patients received cetuximab 400 mg/m2 initially,then 250 mg/m2 every week,with the same regimen of irinotecan on which the patients had progressed (4 pre-defined regim-ens allowed). The prim-ary objective was evaluation of progression-free survival (PFS) at 12 wk. Secondary objectives included a further investigation of PFS,and an assessment of the overall response rate (ORR),duration of response,time to treatment failure (TTF),overall survival and the safety profile. RESULTS:One hundred and twenty nine patients were enrolled from-25 centers in the Asia-Pacific region and of these 123 received cetuximab plus irinotecan. The most common recent irinotecan regimen used was 180 mg/m2 every 2 wk which had been used in 93 patients (75.6%). The PFS rate at 12 wk was 50% (95% confidence interval (CI,41-59) and m-edian PFS tim-e was 12.1 wk (95% CI:9.7-17.7). The ORR was 13.8% (95% CI:8.3-21.2) and disease control rate was 49.6% (95% CI:40.5-58.8). Median duration of response was 31.1 wk (95% CI:18.0-42.6) and median overall survival was 9.5 mo (95% CI,7.5-11.7). The median TTF was 11.7 wk (95% CI:9.1-17.4). Treatment was generally well tolerated. The most common grade 3/4 adverse events were diarrhea (13.8%),neutropenia (8.9%),rash (5.7%) and vomiting (5.7%).CONCLUSION:In patients from Asia and Australia,this study confirm-s the activity and safety of cetuxim-ab plus irinotecan observed in previous studies in Europe and South America.

关键词： Epidermal growth factor receptor Cetuximab Irinotecan Metastatic colorectal cancer Asia

Agreement of angle closure assessments between gonioscopy, anterior segment optical coherence tomography and spectral domain optical coherence tomography

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 Ophthalmology(English edition) 2015年第2期8卷 342-346页

作者： Elton Lik Tong Tay Vernon Khet yau Yong Boon Ang lim Stelson Sia Elizabeth Poh Ying Wong Leonard Wei Leon Yip Department of Ophthalmology Tan Tock Seng Hospital Republic of Singapore Air Force Aeromedical Centre Cardinal Santos Medical Center

AIM: To determine angle closure agreements between gonioscopy and anterior segment optical coherence tomography(AS-OCT), as well as gonioscopy and spectral domain OCT(SD-OCT). A secondary objective was to quantify inter-observer agreements of AS-OCT and SD-OCT ***: Seventeen consecutive subjects(33 eyes)were recruited from the study hospital’s Glaucoma *** was performed by a glaucomatologist masked to OCT results. OCT images were read independently by 2 other glaucomatologists masked to gonioscopy findings as well as each other’s analyses of OCT ***: Totally 84.8% and 45.5% of scleral spurs were visualized in AS-OCT and SD-OCT images respectively(P <0.01). The agreement for angle closure between AS-OCT and gonioscopy was fair at k =0.31(95% confidence interval, CI: 0.03-0.59) and k =0.35(95%CI: 0.07-0.63) for reader 1 and 2 respectively. The agreement for angle closure between SD-OCT and gonioscopy was fair at k =0.21(95% CI: 0.07-0.49) and slight at k =0.17(95% CI: 0.08-0.42) for reader 1 and 2 respectively. The inter-reader agreement for angle closure in AS-OCT images was moderate at 0.51(95% CI: 0.13-0.88). The inter-reader agreement for angle closure in SD-OCT images was slight at 0.18(95% CI: 0.08-0.45).CONCLUSION: Significant proportion of scleral spurs were not visualised with SD-OCT imaging resulting in weaker inter-reader agreements. Identifying other angle landmarks in SD-OCT images will allow more consistent angle closure assessments. Gonioscopy and OCT imaging do not always agree in angle closure assessments but have their own advantages, and should be used together and not exclusively.

关键词： anterior segment imaging spectral domain imaging angle closure assessment

Role of staging laparoscopy in gastric malignancies - our institutional experience

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 Gastrointestinal Surgery 2012年第9期4卷 214-219页

作者： Vishal G Shelat juin Fong Thong Melanie Seah Khong Hee lim Department of Surgery Tan Tock Seng Hospital Singapore 308433 Singapore

AIM: To investigate the value of staging laparoscopy with laparoscopic ultrasound (LUS) and peritoneal lavage cytology in patients with newly-diagnosed gastric tumours in our ***: Retrospective review of prospectively-collected data was conducted in all patients with newly-diagnosed gastric tumours on oesophagogastroduode-noscopy between December 2003 and July 2008. All the patients had a pretreatment histological diagnosis and were discussed at the hospital multidisciplinary tumour board meeting for their definitive management. Computed tomography scan was performed in all patients as a part of standard preoperative staging work up. Staging laparoscopy was subsequently performed in selected patients and staging by both modalities was ***: Twenty seven patients were included. Majority of patients had cardio-oesophageal junction adenocarcinoma. Thirteen patients (48%) were up-staged following staging laparoscopy and one patient was downstaged (3.7%). None of the patients had procedure-related complications. None of the patients with metastasis detected at laparoscopy underwent laparotomy. Gastrectomy after staging laparoscopy was performed in 13 patients (9R0 resections, 3 R1 resections and 1 R2 resection). Only one patient did not have gastrectomy at laparotomy because of extensive local invasion. Three patients were subjected to neoadjuvant therapy following laparoscopy but only one patient subsequently underwent gastrectomy. CONCLUSION: In this small series reflecting our institutional experience, staging laparoscopy appears to be safe and more accurate in detecting peritoneal and omental metastases as compared to conventional imaging. Peritoneal cytology provided additional prognostic information although there appeared to be a high false negative rate.

关键词： Gastric carcinoma Staging Laparoscopy Peritoneal lavage cytology Laparoscopic ultrasound