检索结果-南通市图书馆

Analysis of coastal land use/land cover changes in the Indian Sunderbans using remotely sensed data

Geo-Spatial Information Science 2012年第4期15卷 241-250页

作者： Debajit Datta Shovik DEB Department of Agricultural and Food Engineering Indian Institute of TechnologyKharagpurWest Bengal 721302India Department of Geography Taki Government CollegeTakiWest Bengal 743429India

The world’s largest mangrove ecosystem,the Sunderbans is experiencing multidimensional threats of degradation.The present study was aimed to understand these problems and search for proper remedies by applying suitable remote sensing technologies.South-western parts of Indian Sunderbans Biosphere Reserve had been chosen for assessment of land use/land cover changes in between 1975 and 2006 by using multitemporal Landsat data.Results indicated considerable reduction of open mangrove stands and associated biodiversity mainly in the forest-habitation interference zones of Sunderbans.On the contrary,increase in the coverage of dense mangroves in the reserved forests had been observed indicating the existence of proper centralized management regimes.Overall,a cumulative loss of approximately 0.42%of its original mangrove cover in between 1975 and 2006 had been estimated for this part of the Sunderbans which was at parity with the findings of other studies in the Sunderbans or similar mangrove ecosystems of the tropics.Expansion of non agricultural lands in the last two decades was found to be related with the growth of new settlements,tourism infrastructure,and facilities.This transformation was attributed to the shifting of local peoples’interest from traditional forestry and subsistence farming towards alternative occupations like shrimp culture,coastal tourism,and commercial fishing although environmentally hazardous livelihood activities like collection of prawn seeds along the riverbanks were still persistent.

关键词： sustainable mangrove management landsat data land use/land cover changes

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Spatially explicit estimation of soil organic carbon stock of an estuarine mangrove wetland of eastern India using elemental analysis and very-fine resolution satellite data

引用

Ecological Processes 2022年第1期11卷 411-426页

作者： Debajit Datta Madhumita Bairagi Mansa Dey Argha Pratim Pal Jibananda Gayen Department of Geography Jadavpur UniversityKolkata 700032India Department of Geography Sree Chaitanya CollegeHabra 743268India

Background:This study estimated the total soil organic C(SOC)stock of the wetland influence zone of Bichitrapur mangroves in eastern India in a spatially explicit manner.Both spatial and vertical distribution of SOC densities with respect to land use/land cover(LULC)pattern were assessed.Subsequently,some site-specific management strate-gies were forwarded towards enhancement of C sequestration potential.Methods:The changing patterns of LULC within the wetland influence zone of the site were analyzed using Landsat TM(30 m)and Pleiades-1A(2 m)imageries from 1988 to 2018.Point-specific SOC measurement was done using samples taken from four core-depth intervals(viz.D1:0–20 cm,D2:20–40 cm,D3:40–70 cm,D4:70–100 cm)at 89 locations belonging to different LULC categories.Spatial interpolation was applied on this point-based data to produce SOC density and stock models as a whole and at all core-depths.Relationships between SOC density,core-depth and present LULC were evaluated through multivariate statistical analyses.Results:The LULC transformations during last three decades suggested the gradual growth of mangrove plantations as well as agricultural and aquacultural activities.Most amount of SOC was concentrated in D1(37.17%)followed by D3(26.51%),while D4 had the lowest(10.87%).The highest mean SOC density was observed in the dense mangrove patches(248.92 Mg ha^(−1))and the lowest mean was in the Casuarina plantations(2.78 Mg ha^(−1)).Here,Spline method emerged as the best-fit interpolation technique to model SOC data(R^(2)=0.74)and estimated total SOC stock of the entire wetland influence zone as 169,569.40 Mg and the grand mean as 125.56 Mg ha^(−1).Overall,LULC was inferred as a major determinant of SOC dynamics with a statistically significant effect(p<0.001),whereas no such inference could be drawn for soil core-depth.Conclusions:The C sequestration potential of sites such as the present one could be increased with appropriate zone-wise plantation strategies,restriction on the land conversion to aquaculture and pr

关键词： Blue C density Core-depth Coastal wetland Dry combustion Land use conversion Wetland influence zone

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Performance Comparison of Deep CNN Models for Detecting Driver’s Distraction

引用

Computers, Materials & Continua 2021年第9期68卷 4109-4124页

作者： Kathiravan Srinivasan Lalit Garg Debajit Datta Abdulellah A.Alaboudi N.Z.Jhanjhi Rishav Agarwal Anmol George Thomas School of Information Technology and Engineering Vellore Institute of TechnologyVellore632014India Faculty of Information and Communication Technology University of MaltaMsida2080MSDMalta School of Computer Science and Engineering Vellore Institute of TechnologyVellore632014India College of Computer Science Shaqra UniversityKingdom of Saudi Arabia School of Computer Science and Engineering SCETaylor’s UniversitySubang Jaya47500Malaysia

According to various worldwide statistics,most car accidents occur solely due to human error.The person driving a car needs to be alert,especially when travelling through high traffic volumes that permit high-speed transit since a slight distraction can cause a fatal accident.Even though semiautomated checks,such as speed detecting cameras and speed barriers,are deployed,controlling human errors is an arduous task.The key causes of driver’s distraction include drunken driving,conversing with co-passengers,fatigue,and operating gadgets while driving.If these distractions are accurately predicted,the drivers can be alerted through an alarm system.Further,this research develops a deep convolutional neural network(deep CNN)models for predicting the reason behind the driver’s distraction.The deep CNN models are trained using numerous images of distracted drivers.The performance of deep CNN models,namely the VGG16,ResNet,and Xception network,is assessed based on the evaluation metrics,such as the precision score,the recall/sensitivity score,the F1 score,and the specificity score.The ResNet model outperformed all other models as the best detection model for predicting and accurately determining the drivers’activities.

关键词： Deep-CNN ResNet Xception VGG16 data classification

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Eye Gaze Detection Based on Computational Visual Perception and Facial Landmarks

引用

Computers, Materials & Continua 2021年第8期68卷 2545-2561页

作者： Debajit Datta Pramod Kumar Maurya Kathiravan Srinivasan Chuan-Yu Chang Rishav Agarwal Ishita Tuteja V.Bhavyashri Vedula School of Computer Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India School of Information Technology and Engineering Vellore Institute of Technology(VIT)Vellore632014India Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan

The pandemic situation in 2020 brought about a‘digitized new normal’and created various issues within the current education systems.One of the issues is the monitoring of students during online examination situations.A system to determine the student’s eye gazes during an examination can help to eradicate malpractices.In this work,we track the users’eye gazes by incorporating twelve facial landmarks around both eyes in conjunction with computer vision and the HAAR classifier.We aim to implement eye gaze detection by considering facial landmarks with two different Convolutional Neural Network(CNN)models,namely the AlexNet model and the VGG16 model.The proposed system outperforms the traditional eye gaze detection system which only uses computer vision and the HAAR classifier in several evaluation metric scores.The proposed system is accurate without the need for complex hardware.Therefore,it can be implemented in educational institutes for the fair conduct of examinations,as well as in other instances where eye gaze detection is required.

关键词： Computer vision convolutional neural network data integrity digital examination eye gaze detection extraction information entropy

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An Efficient Sound and Data Steganography Based Secure Authentication System

引用

Computers, Materials & Continua 2021年第4期67卷 723-751页

作者： Debajit Datta Lalit Garg Kathiravan Srinivasan Atsushi Inoue G.Thippa Reddy M.Praveen Kumar Reddy K.Ramesh Nidal Nasser School of Computer Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India Faculty of Information and Communication Technology University of MaltaMsidaMSD2080Malta School of Information Technology and Engineering Vellore Institute of Technology(VIT)Vellore632014India Department of Information Systems&Business Analytics Eastern Washington UniversitySpokaneWA99202USA Department of Computer Science Karnataka State Akkamahadevi Women’s UniversityVijayapuraIndia College of Engineering Alfaisal UniversityRiyadh1153Saudi Arabia

The prodigious advancements in contemporary technologies have also brought in the situation of unprecedented cyber-attacks.Further,the pin-based security system is an inadequate mechanism for handling such a scenario.The reason is that hackers use multiple strategies for evading security systems and thereby gaining access to private data.This research proposes to deploy diverse approaches for authenticating and securing a connection amongst two devices/gadgets via sound,thereby disregarding the pins’manual verification.Further,the results demonstrate that the proposed approaches outperform conventional pin-based authentication or QR authentication approaches.Firstly,a random signal is encrypted,and then it is transformed into a wave file,after which it gets transmitted in a short burst via the device’s speakers.Subsequently,the other device/gadget captures these audio bursts through its microphone and decrypts the audio signal for getting the essential data for pairing.Besides,this model requires two devices/gadgets with speakers and a microphone,and no extra hardware such as a camera,for reading the QR code is required.The first module is tested with realtime data and generates high scores for the widely accepted accuracy metrics,including precision,Recall,F1 score,entropy,and mutual information(MI).Additionally,this work also proposes a module helps in a secured transmission of sensitive data by encrypting it over images and other files.This steganographic module includes two-stage encryption with two different encryption algorithms to transmit data by embedding inside a file.Several encryption algorithms and their combinations are taken for this system to compare the resultant file size.Both these systems engender high accuracies and provide secure connectivity,leading to a sustainable communication ecosystem.

关键词： Cyber-attacks signals privacy security organization encryption decryption authentication effective communication steganography

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Rainfall Forecasting Using Machine Learning Algorithms for Localized Events

引用

Computers, Materials & Continua 2022年第6期71卷 6333-6350页

作者： Ganapathy Pattukandan Ganapathy Kathiravan Srinivasan Debajit Datta Chuan-Yu Chang Om Purohit Vladislav Zaalishvili Olga Burdzieva Centre for Disaster Mitigation and Management Vellore Institute of TechnologyVellore632014India School of Computer Science and Engineering Vellore Institute of TechnologyVellore632014India Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin64002Taiwan Service Systems Technology Center Industrial Technology Research InstituteHsinchuTaiwan School of Information Technology and Engineering Vellore Institute of TechnologyVellore632014India Geophysical Institute of Vladikavkaz Scientific Centre Russian Academy of Sciences(RAS)VladikavkazRussian Federation

A substantial amount of the Indian economy depends solely on agriculture.Rainfall,on the other hand,plays a significant role in agriculture–while an adequate amount of rainfall can be considered as a blessing,if the amount is inordinate or scant,it can ruin the entire hard work of the farmers.In this work,the rainfall dataset of the Vellore region,of Tamil Nadu,India,in the years 2021 and 2022 is forecasted using several machine learning algorithms.Feature engineering has been performed in this work in order to generate new features that remove all sorts of autocorrelation present in the data.On removal of autocorrelation,the data could be used for performing operations on the time-series data,which otherwise could only be performed on any other regular regression data.The work uses forecasting techniques like the AutoRegessive Integrated Moving Average(ARIMA)and exponential smoothening,and then the time-series data is further worked on using Long Short Term Memory(LSTM).Later,regression techniques are used by manipulating the dataset.The work is benchmarked with several evaluation metrics on a test dataset,where XGBoost Regression technique outperformed the test.The uniqueness of this work is that it forecasts the daily rainfall for the year 2021 and 2022 in Vellore region.This work can be extended in the future to predict rainfall over a bigger region based on previously recorded time-series data,which can help the farmers and common people to plan accordingly and take precautionary measures.

关键词： Time-series ARIMA LSTM regression rainfall

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：