检索结果-南通市图书馆

A Novel Framework for Learning and Classifying the Imbalanced Multi-Label Data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer systems science & Engineering 2024年第5期48卷 1367-1385页

作者： P.K.A.chitra s.Appavu alias Balamurugan s.Geetha seifedine Kadry Jungeun Kim Keejun Han Department of Computer science and Engineering SRM Institute of Science and TechnologyTiruchirappalliTamil Nadu603203India Department of Computer science and Engineering Periyar Maniammai Institute of Science&Technology(Deemed to be University)ThanjavurTamil Nadu613403India school of Computer science and Engineering ChennaiTamil Nadu600048India Department of Applied Data science Noroff University CollegeKristiansand4612Norway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityP.O.Box 346AjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblos10150Lebanon Department of software Kongju National UniversityCheonan31080Republic of Korea Division of Computer Engineering Hansung UniversitySeoul02876Republic of Korea

A generalization of supervised single-label learning based on the assumption that each sample in a dataset may belong to more than one class simultaneously is called multi-label *** main objective of this work is to create a novel framework for learning and classifying imbalancedmulti-label *** work proposes a framework of two *** imbalanced distribution of themulti-label dataset is addressed through the proposed Borderline MLsMOTE resampling method in phase ***,an adaptive weighted l21 norm regularized(Elastic-net)multilabel logistic regression is used to predict unseen samples in phase *** proposed Borderline MLsMOTE resampling method focuses on samples with concurrent high labels in contrast to conventional *** minority labels in these samples are called difficult minority labels and are more prone to penalize classification *** concurrentmeasure is considered borderline,and labels associated with samples are regarded as borderline labels in the decision *** phase II,a novel adaptive l21 norm regularized weighted multi-label logistic regression is used to handle balanced data with different weighted synthetic *** on various benchmark datasets shows the outperformance of the proposed method and its powerful predictive performances over existing conventional state-of-the-art multi-label methods.

关键词： Multi-label imbalanced data multi-label learning Borderline MLsMOTE concurrent multi-label adaptive weighted multi-label elastic net difficult minority label

Investigating species boundaries in Colletotrichum

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fungal Diversity 2021年第2期107卷 107-127页

作者： chitra.hanu s.bhunjun Chayanard Phukhamsakda Ruvishika s.Jayawardena Rajesh Jeewon Itthayakorn Promputtha Kevin D.Hyde Center of Excellence in Fungal Research Mae Fah Luang UniversityChiang Rai 57100Thailand school of science Mae Fah Luang UniversityChiang Rai 57100Thailand Institute of Plant Protection College of AgricultureJilin Agricultural UniversityChangchun 130118JilinPeople’s Republic of China Engineering Research Center of Chinese Ministry of Education for Edible and Medicinal Fungi Jilin Agricultural UniversityChangchun 130118JilinPeople’s Republic of China Department of Health sciences Faculty of Medicine and Health SciencesUniversity of MauritiusReduitMauritius Department of Biology Faculty of ScienceChiang Mai UniversityChiang Mai 50200Thailand

Colletotrichum is one of the most important plant pathogenic genera that is responsible for numerous diseases which can have a profound impact on the agricultural *** delineation is difficult due to a lack of distinctive phenotypic ***,in this study three different genomic approaches based on phylogenetic,evolutionary and coalescent-based methods are applied to establish robust species *** reliability of five different DNA barcodes was also assessed to provide further insights into species *** ITs region can resolve the placement of taxa up to the species complex *** GAPDH and TUB2 markers are determined to be the most informative for most ***,no single marker could discriminate between species in all complexes,therefore different molecular approaches based on multi-locus datasets are *** is the first study to provide an estimated divergence time for all species complexes in *** estimated divergence time for species complexes ranged between 4.8 to 32.2 *** on the high level of congruent results obtained from the different molecular approaches,a new species complex,the Colletotrichum agaves complex is *** complex consists of five taxa which are characterised by the presence of straight or slightly curved conidia with obtuse *** study shows that coalescent approaches and multi-locus phylogeny are crucial to establish species boundaries in *** taxonomic placement of three singleton taxa Colletotrichum axonopodi,*** and *** is *** accept 248 species and provide recommendations regarding species boundaries in the graminicola-caudatum complex.

关键词： BEAsT General mixed yule coalescent method Glomerellaceae Multi-rate poisson tree process sordariomycetes Taxonomy

A polyphasic approach to delineate species in Bipolaris

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fungal Diversity 2020年第3期102卷 225-256页

作者： chitra.hanu s.bhunjun Yang Dong Ruvishika s.Jayawardena Rajesh Jeewon Chayanard Phukhamsakda Digvijayini Bundhun Kevin D.Hyde Jun sheng state Key Laboratory for Conservation and Utilization of Bio‑Resources in Yunnan Yunnan Agricultural UniversityKunming 650201People’s Republic of China Center of Excellence in Fungal Research Mae Fah Luang UniversityChiang Rai 57100Thailand school of science Mae Fah Luang UniversityChiang Rai 57100Thailand Yunnan Research Institute for Local Plateau Agriculture and Industry Kunming 650201People’s Republic of China Department of Health sciences Faculty of ScienceUniversity of MauritiusReduitMauritius Department of Entomology and Plant Pathology Faculty of AgricultureChiang Mai UniversityChiang Mai 50002Thailand Institute of Plant Health Zhongkai University of Agriculture and EngineeringHaizhu DistrictGuangzhou 510225People’s Republic of China Centre for Mountain Futures Kunming Institute of BotanyKunming 650201YunnanPeople’s Republic of China

Bipolaris species are important plant pathogens with a worldwide distribution in tropical and temperate *** recognition in Bipolaris has been problematic due to a lack of molecular data from ex-type cultures,the use of few gene regions for species resolution and overlapping morphological *** this study,we evaluate the efficiency of different DNA barcodes in species delimitation in Bipolaris by phylogenetic analyses,Automatic Barcode Gap Discovery and Objective *** is determined to be the best single marker for the *** approaches are used to clarify the taxonomic placement of all sequences currently named as Bipolaris in GenBank based on ITs and GAPDH gene sequence *** checking various publications,we found that the majority of new host records of fungal species published in the Plant Disease journal from 2010 to 2019 were based on BLAsT searches of the ITs sequences and up to 82%of those records could be ***,relying on BLAsT searches from GenBank to name species is not *** boards of journals and reviewers of new record papers should be aware of this *** naming Bipolaris species,whether new or known,it is recommended to perform phylogenetic analyses based on GAPDH using the correct taxon sampling for accurate results and the species relationship should have reliable statistical *** least two new species are represented by molecular data in GenBank and we provide an updated taxonomic revision of *** accept 45 species in Bipolaris and notes are provided for all the species including hosts and geographic distribution.

关键词： Classification DNA barcoding Dothideomycetes Integrative taxonomy Pairwise differences Pleosporales

What are fungal species and how to delineate them?

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fungal Diversity 2021年第4期109卷 1-25页

作者： K.W.Thilini Chethana Ishara s.Manawasinghe V.G.Hurdeal chitra.hanu s.bhunjun M.A.Appadoo Eleni Gentekaki Olivier Raspé Itthayakorn Promputtha Kevin D.Hyde Innovative institute for plant health zhongkai university of agriculture and engineeringguangzhou 510225people’s republic of china center of excellence in fungal research mae fah luang universitychiang rai 57100thailand school of science mae fah luang universitychiang rai 57100thailand department of biology faculty of sciencechiang mai universitychiang mai 50200thailand

This is the opening paper in the special issue of Fungal Diversity,which collates the data on defining *** and recognizing species has long been a controversial *** Darwin’s proposed origin of species,over 30 species criteria have been brought forth and used to define species *** recent times,phylogenetic analyses based on multiple loci have been extensively used as a method to define species ***,only a few mycologists are aware that phylogenetic species criteria can mask discordances among fungal groups,leading to inaccurately defined species *** the current review,we discuss species recognition criteria,how and where these criteria can be applied along with their limitations and derived *** order to delimit fungal species,authors need to take into account not only the phylogenetic and phenotypic coherence,but also the timing of events that lead to fungal speciation and subsequent *** in the rate of phenotypic diversifications and convergent fungal evolution make it difficult to establish a universal species recognition *** best practice can only be defined in the context of each fungal *** this review,we provide a set of guidelines,encouraging an integrative taxonomic approach for species delimitation that can be used to define fungal species boundaries in the *** other papers in this special issue deal with fungal speciation in Ascomycota,Dothideomycetes,Basidiomycota,basal fungi,lichen-forming fungi,plant pathogenic fungi,and yeasts.

关键词： Allopatry speciation species concepts species criteria species recognition sympatry

A modified neural learning algorithm for online resistance estimation in vector controlled induction drives rotor motor

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 in Energy 2015年第1期9卷 22-30页

作者： A. chitra s. HIMAVATHI school of Electrical Engineering Vellore Institute of TechnologyUniversity Katpadi Vellore 632014 India Department of Electrical and Electronics Engineering PondicherryEngineering College Pudhucherry 605014 India

Online estimation of rotor resistance is essen- tial for high performance vector controlled drives. In this paper, a novel modified neural algorithm has been identified for the online estimation of rotor resistance. Neural based estimators are now receiving active con- sideration as they have a number of advantages over conventional techniques. The training algorithm of the neural network determines its learning speed, stability, weight convergence, accuracy of estimation, speed of tracking and ease of implementation. In this paper, the neural estimator has been studied with conventional and proposed learning algorithms. The sensitivity of the rotor resistance change has been tested for a wide range of variation from -50% to ＋50% on the stability of the drive system with and without estimator. It is quiet appealing to settle with optimal estimation time and error for the viable realization. The study is conducted extensively for estimation and tracking. The proposed learning algorithm is found to exhibit good estimation and tracking capabilities. Besides, it reduces computational complexity and, hence, more feasible for practical digital implementa- tion.

关键词： neural networks back propagation (BP) rotorresistance estimators vector control induction motor

Hybrid Cloud security by Revocable KUNodes-storage with Identity-Based Encryption

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

Computer systems science & Engineering 2022年第12期43卷 985-996页

作者： s.saravanakumar s.chitra Department of Information Technology Paavai Engineering CollegeNamakkal637018India Department of Computer science and Engineering Er.Perumal Manimekalai College of EngineeringHosur63117India

Cloud storage is a service involving cloud service providers providingstorage space to customers. Cloud storage services have numerous advantages,including convenience, high computation, and capacity, thereby attracting usersto outsource data in the cloud. However, users outsource data directly via cloudstage services that are unsafe when outsourcing data is sensitive for users. Therefore, cipher text-policy attribute-based encryption is a promising cryptographicsolution in a cloud environment, and can be drawn up for access control by dataowners (DO) to define access policy. Unfortunately, an outsourced architectureapplied with attribute-based encryption introduces numerous challenges, including revocation. This issue is a threat to the data security of DO. Furthermore,highly secure and flexible cipher text-based attribute access control with role hierarchy user grouping in cloud storage is implemented by extending the KUNodes(revocation) storage identity-based encryption. Result is evaluated using Cloudsim, and our algorithm outperforms in terms of computational cost by consuming32 MB for 150-MB files.

关键词： Cloud computing storage identification based revocation attribute based access control encryption decryption

Energy Efficient Networks Using Ant Colony Optimization with Game Theory Clustering

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & soft Computing 2023年第3期35卷 3557-3571页

作者： Harish Gunigari s.chitra Department of Computer science and Engineering Hosur635117India Er.Perumal Manimekalai College of Engineering Hosur635117India

Real-time applications based on Wireless sensor Network(WsN)tech-nologies quickly lead to the growth of an intelligent *** nodes play an essential role in distributing information from networking and its transfer to the *** ability of dynamical technologies and related techniques to be aided by data collection and analysis across the Internet of Things(IoT)network is widely *** nodes are low-power devices with low power devices,storage,and quantitative processing *** existing system uses the Artiﬁcial Immune system-Particle swarm Optimization method to mini-mize the energy and improve the network’s *** the proposed system,a hybrid Energy Efﬁcient and Reliable Ant Colony Optimization(ACO)based on the Routing protocol(E-RARP)and game theory-based energy-efﬁcient clus-tering algorithm(GEC)were used.E-RARP is a new Energy Efﬁcient,and Reli-able ACO-based Routing Protocol for Wireless sensor *** suggested protocol provides communications dependability and high-quality channels of communication to improve *** wireless sensor networks,a game theo-ry-based energy-efﬁcient clustering technique(GEC)is used,in which each sen-sor node is treated as a player on the *** sensor node can choose beneﬁcial methods for itself,determined by the length of idle playback time in the active phase,and then decide whether or not to *** proposed E-RARP-GEC improves the network’s lifetime and data transmission;it also takes a minimum amount of energy compared with the existing algorithms.

关键词： Ant colony optimization game theory wireless sensor network network lifetime routing protocol data transmission energy efﬁciency

Optimal Data Placement and Replication Approach for sIoT with Edge

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer systems science & Engineering 2022年第5期41卷 661-676页

作者： B.Prabhu shankar s.chitra Department of Information Technology Er Perumal Manimekalai College of EngineeringHosur635117TamilnaduIndia Department of Computer science and Engineering Er Perumal Manimekalai College of EngineeringHosur63117TamilnaduIndia

social networks(sNs)are sources with extreme number of users around the world who are all sharing data like images,audio,and video to their friends using IoT *** concept is the so-called social Internet of Things(sIot).The evolving nature of edge-cloud computing has enabled storage of a large volume of data from various sources,and this task demands an efficient storage *** this kind of large volume of data storage,the usage of data replication using edge with geo-distributed cloud service area is suited to fulfill the user’s expectations with low *** major issue is the way to store the data and replicate these large data items optimally and allocate the request from the data center *** efficient storage of these data,we use edge server,which is part of the cloud server,in this ***,the data are distributed and stored with quick access,which will reduce the latency with *** proposed data placement approach learns with machine learning(ML)algorithm called radial basis kernel function assisted with support vector machine(RBF-sVM)to classify the data center for storing the user and friend’s data from the sIoT *** learning algorithms will be used to predict the workload of the data stored in the data center as either edge or cloud depending on the existing time *** data placement with dynamic nature is also optimized using the proposed dynamic graph partitioning(GP)method to meet the individual user’s demand of low latency with minimum *** way will keep the sIoT data placement efficient and effective over ***,this proposed data placement and replication approach introduces three kinds of innovations compared with the existing data placement approach.(i)Rather than storing the user data in a single cloud,this study uses the edge server closest to the sIoT devices for faster access with reduced response time.(ii)The classification algorithm called RBF-sVM is used to find storage for

关键词： Data placement data replication social network social internet of things edge computing cloud computing graph partitioning support vector machine machine learning radial basis function latency storage cost

Mango Pest Detection Using Entropy-ELM with Whale Optimization Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & soft Computing 2023年第3期35卷 3447-3458页

作者： U.Muthaiah s.chitra Department of Computer science and Engineering Sri Shanmugha College of Engineering and TechnologySankari637304India Department of Computer science and Engineering Er.Perumal Manimekalai College of EngineeringHosur635117India

Image processing,agricultural production,andﬁeld monitoring are essential studies in the researchﬁ*** diseases have an impact on agricultural production and *** disease detection at a preliminary phase reduces economic losses and improves the quality of *** identifying the agricultural pests is usually evident in plants;also,it takes more time and is an expensive technique.A drone system has been developed to gather photographs over enormous regions such as farm areas and *** atmosphere generates vast amounts of data as it is monitored closely;the evaluation of this big data would increase the production of agricultural *** paper aims to identify pests in mango trees such as hoppers,mealybugs,inﬂorescence midges,fruitﬂies,and stem *** of the massive volumes of large-scale high-dimensional big data collected,it is necessary to reduce the dimensionality of the input for classify-ing *** community-based cumulative algorithm was used to classify the pests in the existing *** proposed method uses the Entropy-ELM method with Whale Optimization to improve the classiﬁcation in detecting pests in *** Entropy-ELM method with the Whale Optimization Algorithm(WOA)is used for feature selection,enhancing mango pests’classiﬁcation *** Vector Machines(sVMs)are especially effective for classifying while users get var-ious classes in which they are *** are created as suitable classiﬁers to categorize any dataset in Big Data *** proposed Entropy-ELM-WOA is more capable compared to the existing systems.

关键词： Whale optimization algorithm Entropy-ELM feature selection pests detection support vector machine mango trees classiﬁcation