检索结果-内蒙古大学图书馆

A comprehensive survey on weed and crop classification using machine learning and deep learning

Artificial Intelligence in Agriculture 2024年第3期13卷 45-63页

作者： Faisal Dharma Adhinata Wahyono Raden Sumiharto Department of Computer Science and Electronics Faculty of Mathematic and Natural SciencesUniversitas Gadjah MadaYogyakartaIndonesia Faculty of Informatics Institut Teknologi Telkom PurwokertoCentral JavaIndonesia

Machine learning and deep learning are subsets of Artificial Intelligence that have revolutionized object detection and classification in images or *** technology plays a crucial role in facilitating the transition from conventional to precision agriculture,particularly in the context of weed *** agriculture,which previously relied on manual efforts,has now embraced the use of smart devices for more efficient weed ***,several challenges are associated with weed detection,including the visual similarity between weed and crop,occlusion and lighting effects,as well as the need for early-stage weed ***,this study aimed to provide a comprehensive review of the application of both traditional machine learning and deep learning,as well as the combination of the two methods,for weed detection across different crop *** results of this review show the advantages and disadvantages of using machine learning and deep ***,deep learning produced superior accuracy compared to machine learning under various *** learning required the selection of the right combination of features to achieve high accuracy in classifyingweed and crop,particularly under conditions consisting of lighting and early growth ***,a precise segmentation stage would be required in cases of *** learning had the advantage of achieving real-time processing by producing smaller models than deep learning,thereby eliminating the need for additional ***,the development of GPU technology is currently rapid,so researchers are more often using deep learning for more accurate weed identification.

关键词： Deep learning Machine learning Precision agriculture Weed control Weed detection

来源：评论

学校读者我要写书评

暂无评论

The Beta Exponential Power Series Distribution

引用

Annals of Data science 2023年第5期10卷 1157-1178页

作者： Khojastehbakht, Nafiseh Ghatari, Amirhossein Samani, Ehsan Bahrami Department of Statistics Shahid Beheshti University Tehran Iran Department of Statistics Faculty of Mathematic and Computer Science Amirkabir University of Technolgy Tehran Iran

In this paper, we investigate to propose a new statistical distribution based on power series. We introduce a new family of distributions which are constructed based on a latent complementary risk problem and are obtained by compounding Beta Exponential (BE) and Power Series distributions. The new distribution contains, as special sub-models, several important distributions which are discussed in the literature, such as Beta Exponential Poisson (BEP) distribution, Beta Exponential Geometric (BEG) distribution, Beta Exponential Logarithmic (BEL) distribution, Beta Exponential Binomial (BEB) distribution as special cases. The hazard function of the BEPS distributions can be increasing, decreasing or bathtub shaped among others. The comprehensive mathematical properties of the new distribution is provided such as closed-form expressions for the density, cumulative distribution, survival function, failure rate function, the r-th raw moment, maximum likelihood estimation and also the moments of order statistics. The proposed type of distributions is used to modeling simulated and real datasets. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Human DNA Profile Identification Using DNA Database System 8

Human DNA Profile Identification Using DNA Database System

引用

8th International Conference on science and Technology, ICST 2022

作者： Dewi, Meira Parma Arymurthy, Aniati Murni Setiawan, Suryana Soedarsono, Nurtami Universitas Negeri Padang Mathematic Departement Indonesia Universitas Indonesia Faculty of Computer Science Indonesia Universitas Indonesia Faculty of Dentistry Indonesia

ISBN: (纸本)9781665456227

Measurement of the similarity of human DNA profiles is a process which undertaken to find out a person's biological identity based on the short tandem repeat (STR) of the DNA profile. The DNA profile database was built to store DNA profile data for Indonesian citizens. The DNA profile database will assist in the identification process of individuals based on the STR value contained in the DNA profile. Fuzzy similarity measure will be used to measure the similarity of a person's STR value with DNA data stored in the database. Comparisons were made for each allele found at 15 loci of DNA profiles. Dealing with the experiments, it has shown that 98% gave the appropriate results. © 2022 IEEE.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Experiments to Review Literature on Topic Trends in Technology Development in Educational Information Systems 7

Experiments to Review Literature on Topic Trends in Technolo...

引用

7th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2023

作者： Santiko, Irfan Soeprobowati, Tri Retnaningsih Surarso, Bayu Universitas Amikom Purwokerto Faculty of Computer Science Informatic Departement Indonesia School of Post Graduate Diponegoro University Information System Departement Semarang Indonesia School of Post Graduate Diponegoro University Faculty of Science and Mathematic Semarang Indonesia

ISBN: (纸本)9798350382266

The smart campus is a phenomenon that occurs in the industrial era 4.0. Many people understand that a smart campus is a campus where all resources can work and produce learning with high effectiveness and maximum efficiency. Everyone talks about elements of information technology that play a role in the sustainability of smart campuses. However, what actually makes the definition of a smart campus itself is not defined with certainty. This is because the world of education itself is experiencing major disruption. This causes innovation in the world of education, especially learning, to pay less attention to the actual aspects of education. This means that education has relied too much on technology which will actually cause a shift in the essence of education itself. In this paper, we will review how effective and efficient learning concepts actually are using information technology. The method used is an analysis of the literature review with an experimental survey and bibliometric analysis. As a result, it will be known that information technology that is in accordance with the essence of education is a matter that does not only focus on technical aspects but also needs to pay attention to aspects of methods, materials, and media. So that the results that are known will provide insight into the development of learning models on an ongoing basis according to the true essence of education. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Towards Smart Mariculture Application: Providing Smart Monitoring System Mobile Apps to Supports Groupers Cultivator in Kepulauan Seribu, Indonesia 2

Towards Smart Mariculture Application: Providing Smart Monit...

引用

2nd International Conference on ICT for Rural Development, IC-ICTRuDev 2021

作者： Hermadi, Irman Rahmadani, Afriyadi Yanuar Asfarian, Auzi Effendi, Irzal Department of Computer Science Faculty of Mathematic and Natural Sciences Bogor Indonesia Department of Computer Science Faculty of Mathematic and Natural Sciences Bogor Indonesia Department of Computer Science Faculty of Mathematic and Natural Sciences Bogor Indonesia Department of Aquaculture Faculty of Fisheries and Marine Science Bogor Indonesia

ISBN: (纸本)9781665433754

Fish farmers in The Thousand Islands, Indonesia, especially in the Sea Farming Community, are currently focused on groupers (Epinephelus fuscoguttatus-lanceolatus) cultivation. Grouper's cultivation is affected by various factors, e.g., disease and water condition, which will affect the cultivation activity and treatment. Timely monitoring is essential to ensure a high yield of the cultivation. However, the current practice is to monitor the cultivation condition in-person using paper-based records, resulting in inadequate data and a significant burden on the cultivators. This research develops a Smart Mariculture K1000 Application: a mobile-based smart monitoring system that supports groupers cultivators. The application served as a front-end to our previously developed internet-of-things and sensor network to monitor water and environment condition. Moreover, the cultivators can also record their production activity to the system, allowing automatic analysis and monitoring. We develop the application using *** to ensure the portability of the application. The application connected to the back-end server and sensor networks using ***. We tested the application to the Sea Farming community member using usability testing. The task success measured is 96.8%, and the usability problem found already fixed in the implementation. We hope this application can be our first step to create smart maritime-culture (mariculture) in Indonesia to achieve sustainable marine cultivation. © 2021 IEEE

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Integrating Ambulance into GIS in Smart City: Problems and Prospect with P-Median Model 4

Integrating Ambulance into GIS in Smart City: Problems and P...

引用

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Dewi, Rafiqa Tulus Zarlis, Muhammad Nababan, Erna Budhiarti North Sumatera University Faculty of Computer Science and Information Technology North Sumatera Medan Indonesia North Sumatera University Faculty of Mathematic North Sumatera Medan Indonesia

ISBN: (纸本)9781665453950

Among the main pillars of a smart city is smart health, and part of smart health is the availability of accurate and fast ambulance services. This study proposes an ambulance system that is integrated with GIS in a smart city with a number of problems that are solved by the P-Median model, namely determining the location of the patient, determining the location of the ambulance, and recommending the destination hospital. The scope of this project starts from the patient making a call accompanied by sending the patient's location point and incident information to the ambulance authority server through the patient application interface. Then the authority will receive the patient's identity, location and incident information through the authority's application interface. Through the authority application, a map of the available ambulance will be shown and the one that best suits the patient's condition. Next the authority will contact the recommended ambulance by sending the patient information. The simulation results of this project show that the proposed system can solve the problem in an acceptable time. © 2022 IEEE.

关键词： Ambulances

来源：评论

学校读者我要写书评

暂无评论

New insight in cervical cancer diagnosis using convolution neural network architecture

arXiv

引用

arXiv 2024年

作者： Khozaimi, Ach Mahmudy, Wayan Firdaus Department of Computer Science Faculty of Engineering Universitas Trunojoyo Madura Indonesia Department of Mathematics Faculty of Mathematic and Natural Sciences Brawijaya University Malang Indonesia Department of Informatics Engineering Faculty of Computer Science Brawijaya University Malang Indonesia

The Pap smear is a screening method for early cervical cancer diagnosis. The selection of the right optimizer in the convolutional neural network (CNN) model is key to the success of the CNN in image classification, including the classification of cervical cancer Pap smear images. In this study, stochastic gradient descent (SGD), root mean square propagation (RMSprop), Adam, AdaGrad, AdaDelta, Adamax, and Nadam optimizers were used to classify cervical cancer Pap smear images from the SipakMed dataset. Resnet-18, Resnet-34, and VGG-16 are the CNN architectures used in this study, and each architecture uses a transfer-learning model. Based on the test results, we conclude that the transfer learning model performs better on all CNNs and optimization techniques and that in the transfer learning model, the optimization has little influence on the training of the model. Adamax, with accuracy values of 72.8% and 66.8%, had the best accuracy for the VGG-16 and Resnet-18 architectures, respectively. Resnet-34 had 54.0%. This is 0.034% lower than Nadam. Overall, Adamax is a suitable optimizer for CNN in cervical cancer classification on Resnet-18, Resnet-34, and VGG-16 architectures. This study provides new insights into the configuration of CNN models for Pap smear image analysis. © 2024, CC BY-SA.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Building a Weighted Performance Indicator Concept utilized the Respondent's Opinion Approach 3

Building a Weighted Performance Indicator Concept utilized t...

引用

3rd International Conference on Electronics Representation and Algorithm, ICERA 2021

作者： Hartono, Yusuf Ermatita Rini, Dian Palupi Terttiaavini Sriwijaya University Faculty of Mathematic Science South Sumatera Indonesia Indo Global Mandiri University Faculty of Computer Science South Sumatera Indonesia

ISBN: (纸本)9781665434003

This study discusses building the concept of weighting performance indicators based on respondents' opinions. The opinion of respondents has the power to provide an assessment. So far, the performance appraisal is determined based on the Balanced Scorecard method, AHP, Topics, and others where the dimensions of this method are limited. In companies, performance appraisals are carried out by the HR Department. The specified indicator is sometimes too high, therefore it is considered achieved. The most flexible approach in which the determination of indicators is determined by the respondent who will implement the rule. Weighted performance indicators are constructed by developing an association rule method and ranking method. Performance appraisal structures in the form of multi values and multidimensional can be built using this concept. Items that meet the support value and minimum weight are determined based on the higher frequency. This concept is a new proposal from a mining method developed to produce a performance appraisal model that can be applied to various needs. © 2021 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

mathematical Model of Damping of UAV Oscillations in the Cargo Delivery Problem 4

Mathematical Model of Damping of UAV Oscillations in the Car...

引用

4th IEEE KhPI Week on Advanced Technology, KhPI Week 2023

作者： Kucherov, Dmytro Tkachenko, Valerii Shmelova, Tetiana Miroshnichenko, Ignat Poshyvailo, Olexii Ogirko, Ihor Dept. Computerized Control Systems Faculty of Computer Science and Technology National Aviation University Kyiv Ukraine Dept. Air Navigation Systems Faculty of Air Navigation Electronics and Telecommunications National Aviation University Kyiv Ukraine Dept. Mathematic Ukrainian Academy of Printing City Lviv Ukraine

ISBN: (纸本)9798350395532

Currently, the use of unmanned vehicles for the delivery of goods is becoming a trend in many areas of human activity. At the same time, it is necessary to solve the problem of the integrity of the cargo because of its possible fluctuations. The paper deals with the problem of delivering cargo attached to a 4-motor UAV on a rigid cable. A control system is needed to achieve the UAV equilibrium position that can compensate for significant mismatches in the XY coordinate plane. A combination of two control algorithms is proposed for solving this problem, one of which provides a given position in the horizontal plane at small mismatch angles and the second at large mismatch angles. The first controller uses the PID controller algorithm with the corresponding optimal setting of its parameters, and the second one uses the bang-bang control scheme. An additional controller is used to coordinate these controllers, which ensures their timely switching. Some simulation is also proposed. © 2023 IEEE.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

360Degree Data Analysis and Visualization for COVID-19 Mitigation in Indonesia

360Degree Data Analysis and Visualization for COVID-19 Mitig...

引用

2021 International Conference on Data science, Artificial Intelligence, and Business Analytics, DATABIA 2021

作者： Riasetiawan, Mardhani Ashari, Ahmad Prastowo, Bambang Nurcahyo Universitas Gadjah Mada Faculty of Mathematic and Natural Scienves Dept.of Computer Science and Electronics Yogyakarta Indonesia

ISBN: (纸本)9781665426800

COVID-19 in the world and Indonesia are faced with a situation and the need for reliable data to capture the current situation. Data on COVID-19 is very urgent and important because we need it as a guide against an invisible virus, and we still do not know much about the knowledge to help predict the pattern of its spread, increase, and prevention strategies. The spread of the COVID-19 virus in Indonesia is one of the cases that require Big Data support to obtain data on its movement and distribution, analysis of its distribution and growth patterns, and mitigation and prevention strategies in the future. The research developed and produces a dashboard and visualization that have a data mitigation approach and displays the distribution and growth statistics of cases that have occurred in Indonesia. Then it will run an analytical and computational platform to facilitate the use case process and modeling of the mitigation options to be taken. A COVID-19 analysis model has been produced that supports mapping and portraits of current conditions which can be accessed through http://***/analysis. The approach has produced a 360-degree concept that has can view data as a capture of a certain situation that reflects current conditions (cut-off), projections, predictions, and cognitive. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：