|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Feature Selection with Deep Reinforcement Learning for Intrusion Detection System显示文摘An intrusion detection system(IDS)becomes an important tool for ensuring security in the network.In recent times,machine learning(ML)and deep learning(DL)models can be applied for the identification of intrusions over the network effectively.To resolve the security issues,this paper presents a new Binary Butterfly Optimization algorithm based on Feature Selection with DRL technique,called BBOFS-DRL for intrusion detection.The proposed BBOFSDRL model mainly accomplishes the recognition of intrusions in the network.To attain this,the BBOFS-DRL model initially designs the BBOFS algorithm based on the traditional butterfly optimization algorithm(BOA)to elect feature subsets.Besides,DRL model is employed for the proper identification and classification of intrusions that exist in the network.Furthermore,beetle antenna search(BAS)technique is applied to tune the DRL parameters for enhanced intrusion detection efficiency.For ensuring the superior intrusion detection outcomes of the BBOFS-DRL model,a wide-ranging experimental analysis is performed against benchmark dataset.The simulation results reported the supremacy of the BBOFS-DRL model over its recent state of art approaches. | S.Priya K.Pradeep Mohan Kumar | 2023 | Computer Systems Science & Engineering2023，46，9： | 1 |
| 2 | Bird Swarm Algorithm with Fuzzy Min-Max Neural Network for Financial Crisis Prediction显示文摘Financial crisis prediction(FCP)models are used for predicting or forecasting the financial status of a company or financial firm.It is considered a challenging issue in the financial sector.Statistical and machine learning(ML)models can be employed for the design of accurate FCP models.Though numerous works have existed in the literature,it is needed to design effective FCP models adaptable to different datasets.This study designs a new bird swarm algorithm(BSA)with fuzzy min-max neural network(FMM-NN)model,named BSA-FMMNN for FCP.The major intention of the BSA-FMMNN model is to determine the financial status of a firm or company.The presented BSA-FMMNN model primarily undergoes minmax normalization to transform the data into uniformity range.Besides,k-medoid clustering approach is employed for the outlier removal process.Finally,the classification process is carried out using the FMMNN model,and the parameters involved in it are tuned by the use of BSA.The utilization of proficient parameter selection process using BSA demonstrate the novelty of the study.The experimental result analysis of the BSA-FMMNN model is validated using benchmark dataset and the comparative outcomes highlighted the supremacy of the BSA-FMMNN model over the recent approaches. | K.Pradeep Mohan Kumar S.Dhanasekaran I.S.Hephzi Punithavathi P.Duraipandy Ashit Kumar Dutta Irina V.Pustokhina Denis A.Pustokhin | 2022 | Computers, Materials & Continua2022，，10： | 0 |
| 3 | MDCN:Modified Dense Convolution Network Based Disease Classification in Mango Leaves显示文摘The most widely farmed fruit in the world is mango.Both the production and quality of the mangoes are hampered by many diseases.These diseases need to be effectively controlled and mitigated.Therefore,a quick and accurate diagnosis of the disorders is essential.Deep convolutional neural networks,renowned for their independence in feature extraction,have established their value in numerous detection and classification tasks.However,it requires large training datasets and several parameters that need careful adjustment.The proposed Modified Dense Convolutional Network(MDCN)provides a successful classification scheme for plant diseases affecting mango leaves.This model employs the strength of pre-trained networks and modifies them for the particular context of mango leaf diseases by incorporating transfer learning techniques.The data loader also builds mini-batches for training the models to reduce training time.Finally,optimization approaches help increase the overall model’s efficiency and lower computing costs.MDCN employed on the MangoLeafBD Dataset consists of a total of 4,000 images.Following the experimental results,the proposed system is compared with existing techniques and it is clear that the proposed algorithm surpasses the existing algorithms by achieving high performance and overall throughput. | Chirag Chandrashekar K.P.Vijayakumar K.Pradeep A.Balasundaram | 2024 | Computers, Materials & Continua2024，78，2： | 0 |
| 4 | Determination of the major geochemical processes of groundwater along the Cretaceous-Tertiary boundary of Trichinopoly,Tamilnadu,India显示文摘The hydrogeochemical variations in groundwater are mainly influenced by lithology,residence time of water in the aquifer matrix,and anthropogenic activities.This study was focused on the geochemical variations of groundwater in different lithological units(Archaean,Cretaceous,Tertiary,and Quaternary)by understanding the major factors governing the geochemical variations in each lithology.The 71 groundwater samples were collected from these rock types,namely,Archaean(14),Cretaceous(37),Tertiary(11),Quaternary(9).The collected samples were measured for major ions and they were used for preparation of standard geochemical plots and ionic ratios.Factor analysis and factor score were used to identify the major factors controlling the hydrochemistry and their spatial distribution in the study area.In addition,geochemical model,WATEQ 4 F was used to determine the saturation condition of carbonate and sulphate minerals in the groundwater.Na–Cl and mixed Ca–Na–HCO3 were the dominant hydrochemical facies irrespective of lithological units.The overall interpretation of geochemical data revealed that leaching of secondary salts,weathering and ion exchange reaction along the groundwater flow path through various lithological units,and anthropogenic influence from domestic sewages and agricultural activities constitute the major geochemical processes in the study area.Hence,this study brings out the multiple hydrogeochemical process in the complex geological terrain along the Cretaceous-Tertiary boundary. | N.Devaraj S.Chidambaram U.Vasudevan K.Pradeep M.Nepolian M.V.Prasanna V.S.Adithya R.Thilagavathi C.Thivya Banajarani Panda | 2020 | Acta Geochimica2020，39，5： | 0 |
| 5 | Privacy Preserving Blockchain with Optimal Deep Learning Model for Smart Cities显示文摘Recently,smart cities have emerged as an effective approach to deliver high-quality services to the people through adaptive optimization of the available resources.Despite the advantages of smart cities,security remains a huge challenge to be overcome.Simultaneously,Intrusion Detection System(IDS)is the most proficient tool to accomplish security in this scenario.Besides,blockchain exhibits significance in promoting smart city designing,due to its effective characteristics like immutability,transparency,and decentralization.In order to address the security problems in smart cities,the current study designs a Privacy Preserving Secure Framework using Blockchain with Optimal Deep Learning(PPSF-BODL)model.The proposed PPSFBODL model includes the collection of primary data using sensing tools.Besides,z-score normalization is also utilized to transform the actual data into useful format.Besides,Chameleon Swarm Optimization(CSO)with Attention Based Bidirectional Long Short TermMemory(ABiLSTM)model is employed for detection and classification of intrusions.CSO is employed for optimal hyperparameter tuning of ABiLSTM model.At the same time,Blockchain(BC)is utilized for secure transmission of the data to cloud server.This cloud server is a decentralized,distributed,and open digital ledger that is employed to store the transactions in different methods.A detailed experimentation of the proposed PPSF-BODL model was conducted on benchmark dataset and the outcomes established the supremacy of the proposed PPSFBODL model over recent approaches with a maximum accuracy of 97.46%. | K.Pradeep Mohan Kumar Jenifer Mahilraj D.Swathi R.Rajavarman Subhi R.M.Zeebaree Rizgar RZebari Zryan Najat Rashid Ahmed Alkhayyat | 2022 | Computers, Materials & Continua2022，，12： | 0 |
| 6 | A hydrochemical approach to estimate mountain front recharge in an aquifer system in Tamilnadu, India显示文摘Mountain-front recharge(MFR) is a process of recharging an aquifer by infiltration of surface flow from streams and adjacent basins in a mountain block and along a mountain front(MF). This is the first attempt in India to estimate MFR along the foothills of Courtallam using hydrogeochemistry and geostatistical tools. The estimation of MFR has been carried out by collecting groundwater samples along the foothills of Courtallam. Collected water samples were analyzed for major cations and anions using standard procedures. Hydrogeochemical facies show the existence of four water types in this region. Calcium-rich water derived from gneissic rock terrain indicates significant recharge from higher elevation. Log p CO_2 and ionic strength of the samples were also calculated to identify the geochemical process. Majority of the collected samples have sodium-rich water and weak ionic strength, which indicate foothill recharge and low residence time. Silicate and carbonate weathering have an equal interplay along the foothills with a relatively large fraction of Mg from the MF. The spatial diagrams of three factors show that the southern part of the study area is dominated by both weathering and anthropogenic processes, whereas the northern part is dominated by both leaching and weathering processes. Thus, the dominant weathering process represented by the second factor indicates the large recharge process along the foothills. | Banaja Rani Panda S.Chidambaram N.Ganesh V.S.Adithya M.V.Prasanna K.Pradeep U.Vasudevan | 2018 | Acta Geochimica2018，37，3： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员