检索结果-南通市图书馆

CARVING-DETC: A network scaling and NMS ensemble for Balinese carving motif detection method

Visual Informatics 2023年第3期7卷 1-10页

作者： Wayan Agus Surya Darma nanik suciati Daniel Siahaan Department of Informatics Faculty of Technology and InformaticsInstitut Bisnis dan Teknologi IndonesiaDenpasar80225Indonesia Department of Informatics Faculty of Intelligent Electrical and Informatics TechnologyInstitut Teknologi Sepuluh NopemberSurabaya60111Indonesia

Balinese carvings are cultural objects that adorn sacred buildings. The carvings consist of several motifs,each representing the values adopted by the Balinese people. Detection of Balinese carving motifs ischallenging due to the unavailability of a Balinese carving dataset for detection tasks, high variance,and tiny-size carving motifs. This research aims to improve carving motif detection performance onchallenging Balinese carving motifs detection task through a modification of YOLOv5 to support adigital carving conservation system. We proposed CARVING-DETC, a deep learning-based Balinesecarving detection method consisting of three steps. First, the data generation step performs dataaugmentation and annotation on Balinese carving images. Second, we proposed a network scalingstrategy on the YOLOv5 model and performed non-maximum suppression (NMS) on the modelensemble to generate the most optimal predictions. The ensemble model utilizes NMS to producehigher performance by optimizing the detection results based on the highest confidence score andsuppressing other overlap predictions with a lower confidence score. Third, performance evaluation onscaled-YOLOv5 versions and NMS ensemble models. The research findings are beneficial in conservingthe cultural heritage and as a reference for other researchers. In addition, this study proposed a novelBalinese carving dataset through data collection, augmentation, and annotation. To our knowledge,it is the first Balinese carving dataset for the object detection task. Based on experimental results,CARVING-DETC achieved a detection performance of 98%, which outperforms the baseline model.

关键词： Balinese carving Object detection Network scaling Non-maximum suppression Ensemble model

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

Combining MobileNetV1 and Depthwise Separable convolution bottleneck with Expansion for classifying the freshness of fish eyes

引用

Information Processing in Agriculture 2022年第4期9卷 485-496页

作者： Eko Prasetyo Rani Purbaningtyas Raden Dimas Adityo nanik suciati Chastine Fatichah Department of Informatics Engineering FacultyUniversitas Bhayangkara SurabayaJl.Ahmad Yani 114Surabaya 60234Indonesia Department of Informatics Faculty of Intelligent Electrical and Informatics TechnologyInstitut Teknologi Sepuluh NopemberJl.Raya ITSSurabaya 60111Indonesia

Image classification using Convolutional Neural Network(CNN)achieves optimal perfor-mance with a particular *** reduces the parameter number for learning features by switching from the standard convolution paradigm to the depthwise separable convolution(DSC)***,there are not enough features to learn for identify-ing the freshness of fish ***,minor variances in features should not require complicated CNN *** this paper,our first contribution proposed DSC Bottle-neck with Expansion for learning features of the freshness of fish eyes with a Bottleneck *** second contribution proposed Residual Transition to bridge current feature maps and skip connection feature maps to the next convolution *** third contribu-tion proposed MobileNetV1 Bottleneck with Expansion(MB-BE)for classifying the freshness of fish *** result obtained from the Freshness of the Fish Eyes dataset shows that MB-BE outperformed other models such as original MobileNet,VGG16,Densenet,Nasnet Mobile with 63.21%accuracy.

关键词： Depthwise separable convolution Bottleneck Classification Freshness Fish eye Residual transition

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

Contamination of microplastics in Brantas River, East Java, Indonesia and its distribution in gills and digestive tracts of fish Gambusia affinis

引用

Emerging Contaminants 2021年第1期7卷 172-178页

作者： nanik Retno Buwono Yenny Risjani Agoes Soegianto Doctoral Study Program of Mathematics and Natural Sciences Faculty of Science and TechnologyUniversitas AirlanggaSurabayaIndonesia Departement of Aquatic Resources Management Faculty of Fisheries and Marine SciencesBrawijaya UniversityJl.Veteran Malang65145Indonesia AquaRES Research Group Faculty of Fisheries and Marine Sciences Brawijaya UniversityJl.Veteran Malang65145Indonesia Department of Biology Faculty of Science and TechnologyUniversitas AirlanggaJl.Mulyorejo Surabaya60115Indonesia Research Group of Environmental Technology and Innovation Faculty of Science and TechnologyUniversitas AirlanggaJl.Mulyorejo Surabaya60115Indonesia

The Brantas River is currently vulnerable to microplastics *** not only pollute the aquatic environment but also enter the body of fish and other aquatic *** research is aimed at deciding if microplastics were present in the waters and the gills and digestive tract of the Gambusia affinis fish of the *** also looked at differences in the abundance of several types of microplastics found in the various organ samples and *** research was conducted from January 2020 to March *** microplastics were identified by type,size,color,and the abundance of each type was *** types of microplastics identified were fragments,fibres,films,and *** of 0.1 mm size are predominant and formed about 76%-100%of the microplastics that were *** microplastics were more common in water samples(24%),gills(43%),and digestive tract(46%).The greatest abundance of microplastic fragments was found in water samples of 4066.67 particles/m^(3),1352.78 particles/gram in gill samples,and 2138.89 particles/gram in the digestive *** tests for variants of microplastic types found in the organs at different sampling locations gave a p-value<*** results indicate a difference in the abundance values of microplastic species in different organ samples and sites.

关键词： Gill Digestive tract Fragments Fish Freshwater Water pollution

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

Life Cycle Assessment of Household Water Tanks—A Study of LLDPE, Mild Steel and RCC Tanks

引用

Journal of Environmental Protection 2016年第5期7卷 760-769页

作者： Kunal N. Shah nanik S. Varandani Monika Panchani Environment & Energy Efficiency Research Wing (E&EERW) Gujarat Energy Research and Management Institute (GERMI) Gandhinagar India

A case of household water tanks, 1000 L capacity, made of RCC, LLDPE and mild steel (stainless steel) was evaluated for life cycle analysis. The scope of the research comprised of the raw materials, energy inputs and corresponding emissions during all phases of product making such as extraction of raw material, it’s processing, followed by manufacturing and transport, as well as use and reuse of the product. Simapro 8 (System for Integrated environMental Assessment of PROducts), a modelling software, from Dutch PRé Consultants was used to conduct the life cycle analysis. Simapro 8 enables systematic and transparent modelling and analysis of complex life cycles based on the recommendations of the ISO 14040 series of standards. In the present study the most common method which is acceptable worldwide “Recipe Endpoint method” (ReCiPe) was employed. ReCiPe computes the impact categories and classifies them into two classes based on relevant arrays of characterization factors. Simapro addresses impact categories viz. ozone depletion, human toxicity, ionizing radiation, photochemical oxidant formation, particulate matter formation, terrestrial acidification, climate change, terrestrial ecotoxicity, agricultural land occupation, urban land occupation, natural land transformation, marine ecotoxicity, marine eutrophication, fresh water eutrophication, fresh water ecotoxicity, fossil fuel depletion, minerals depletion, fresh water depletion at the midpoint level. While at the Endpoint level, the impact categories are multiplied by corresponding damage factors and integrated to be represented as three Endpoint level categories, viz. human health, ecosystems and resource depletion. The three endpoint categories are normalized, weighted, and aggregated into a single score. LCA studies indicate that household water tanks of LLDPE have least environmental implications considering impacts on human health, ecosystems and resource depletion as compared to its counterparts viz. Househ

关键词： Life Cycle Assessment Water Tanks Linear Low-Density Polyethylene (LLDPE) RCC Mild Steel Recipe Endpoint Method

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

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

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：