检索结果-内蒙古大学图书馆

2021 International Conference on Artificial Intelligence and Mechatronics Systems, AIMS 2021

作者： Purwanto Hermawan Suherman Widodo, Djoko Adi Iksan, Nur School of Postgraduates Studies Universitas Diponegoro Doctoral Program of Environmental Science Faculty of Engineering Department of Chemical Engineering Semarang Indonesia Universitas Negeri Semarang Faculty of Engineering Department of Electrical Engineering Semarang Indonesia

ISBN: (纸本)9781665424820

The implementation of smart grid on a micro scale in this study was for household electricity fulfillment needs. The use of renewable energy sources such as solar power will be integrated through a smart grid so that households can become independent in providing electricity and not depend on state electricity. Besides, it can also reduce monthly electricity costs when integrated with the state electricity network. Smart Micro Grid also enables the availability of energy management services such as monitoring, prediction, forecasting, scheduling and decision-making that was supported by some technologies such as artificial intelligent, smart sensors so that consumer use of electricity was more efficient. In this research, the forecasting method developed using the Deep Neural Network (DNN) and the Gate Recurrent Unit (GRU) as the architectural model. The GRU model was chosen because it has better performance compared to other models, namely LSTM, Auto-LSTM, Auto-GRU with MAE and MSE values of 0.0342 and 0.00245. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evaluation of ultrasonic-range Vibratory Microinjection System at a frequency of 35 kHz using fertilized mouse eggs

引用

Journal of Mammalian Ova Research 2012年第1期29卷 48-54页

作者： Kudereti, Dilidaer Miyawaki, Fujio Kobayashi, Kenji Hasegawa, Jun Graduate School of Advanced Science and Technology Doctoral Program Tokyo Denki University Saitama 350-0394 Japan Graduate School of Engineering Takushoku University Tokyo 193-0985 Japan

To facilitate pronuclear microinjection, we have been developing the Vibratory Microinjection Systems (VMSs) that provides a micropipette with longitudinal vibration. The current VMS utilizes any frequency up to 100 kHz. We compared 35-kHz vibratory microinjection (VM) with ordinary microinjection (OM). Fourteen micropipettes were used to inject 420 BDF1 zygotes. Each micropipette finished its injection quota of 30 eggs, which were manipulated one by one alternately using the two types of microinjections, even when it repeatedly pulled out nuclear components. All microinjections were conducted at a compensation pressure of 30 hPa and digitally recorded for subsequent image analysis. VM resulted in slightly better embryonic development in 4-day culture than OM, but significantly shortened the time spent on microinjection and the time spent swelling the pronucleus by 25% and 30%, respectively. These pronuclear swelling times, together with the almost identical degrees of pronuclear swelling in both groups, suggested that VM injected a GFP solution at a 42% higher speed. VM significantly reduced the incidence of pulling out nuclear components, suggesting VM's capability of removing the nuclear components already adhering to the micropipettes. These results indicate VMS is a useful option which is capable of raising the efficiency of microinjection significantly by saving time, labor and cost of microinjection. © 2012 Japanese Society of Mammalian Ova Research.

关键词： Injection speed Longitudinal vibration Microinjection Ultrasonic-range vibration Working efficiency

来源：评论

学校读者我要写书评

暂无评论

Matching Images on the Face of A Buddha Statue Using the Scale Invariant Feature Transform (SIFT) Method 7

Matching Images on the Face of A Buddha Statue Using the Sca...

引用

7th International Conference on Information Technology, Computer, and Electrical engineering, ICITACEE 2020

作者： Marlinda, Linda Rustad, Supriadi Basuki, Ruri Suko Budiman, Fikri Fatchan, Muhamad Universitas Dian Nuswantoro Doctoral Program of Computer Science Semarang Central Java Indonesia Universitas Pelita Bangsa Informatica Engineering Cikarang West Java Indonesia

ISBN: (纸本)9781728172255

The condition of the statue in Indonesia at this time many are missing, especially the face of the statue. 504 Buddha statues in the Borobudur temple, there are 248 statues which are now in a headless condition. The condition of the lost statue face is due to being stolen, still buried in the area around the temple, or has changed hands to another party. To find the statue's head according to the face, a matching image is needed, one of which uses the sift method. Buddha face statue matching can be done based on the characteristics of hair, eyebrow shape, lips, head shape or attributes found on the head of the statue. The image matching method can describe an image with a specific keypoint using Scale Invariant Feature Transform (SIFT), where each keypoint has a gradient orientation (GO) and gradient magnitude (GM) which are processed into features in the image registration process. The purpose of this study is to match the face images of Buddha statues with different angles. This study aims to match the face image of the original statue with the image of the statue chosen from different angles. The results of this study are that the same image with different angles obtains 90% accuracy. © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Real-time fall detecting system using a tri-axial accelerometer for home care

Real-time fall detecting system using a tri-axial accelerome...

引用

2012 International Conference on Biomedical engineering and Biotechnology, iCBEB 2012

作者： Lan, Chien-Cheng Hsueh, Ya-Hsin Hu, Rong-Yuan Graduate School of Electronic Engineering Doctoral Program National Yunlin University of Science and Technology Yunlin Taiwan Department of Electronic Engineering National Yunlin University of Science and Technology Yunlin Taiwan

ISBN: (纸本)9780769547060

There has been a considerable increase in the population proportion of senior people among global population. Fall often happens among these senior people, which is also the leading cause of their death. A real-time fall detection system may help us to detect fall events among elderly people in time and reduce the overall casualty rate. This paper proposed a home-based, real-time fall detection system that not only can distinguish up to 4 different kinds of fall events (forward, backward, rightward and leftward), but is also portable, low-cost and with high accuracy rate. The system includes a real-time fall detection band, a home server, and GSM instant messaging function which can transfer fall alert, send emergency help messages. © 2012 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

SIBI Syllable Recognition System With LSTM

SIBI Syllable Recognition System With LSTM

引用

International Conference on Smart Green Technology in Electrical and Information Systems (ICSGTEIS)

作者： Juli Sulaksono Ida Ayu Dwi Girinatari Made Sudarma Ida Bagus Alit Swarmardika Engineering Science Doctoral Program Udayana University Indonesia

Deaf people are people who are unable to communicate with spoken language. Deaf people communicate with the Indonesian Sign System or commonly known as SIBI. In fact, deaf people often communicate and socialize with normal people, but not all normal people understand and understand SIBI. We as researchers want to provide a way out so that deaf people can convey information to normal people, who do not understand SIBI. The input of this research is SIBI movement which is saved in Video format, then the video is processed with the LSTM algorithm. Video The results of the processing are in the form of classified words, the output of this research is in the form of text. The word data set in this study consisted of 3 words, each word contained 30 data sets. The level of accuracy of this study when recognizing words in SIBI that do not hit the face is 100%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Indoor Vertical Farming with DDPG Reinforcement Learning: Enhancing Control of Nutrient Levels, Climate Conditions, and Plant Health 5

Optimizing Indoor Vertical Farming with DDPG Reinforcement L...

引用

5th IEEE International Conference on Technology, Informatics, Management, engineering and Environment, TIME-E 2024

作者： Albert Panggabean, Good Fried Romadhon, Rahmat Lubis, Ramot Joelianto, Endra Institut Teknologi Bandung Doctoral Program in Engineering Physics Bandung Indonesia Institut Teknologi Del Faculty of Informatics and Electrical Engineering Toba Indonesia Institut Teknologi Bandung Engineering Physics Study Program Bandung Indonesia Institut Teknologi Bandung Instrumentation Control and Automation Research Group Bandung Indonesia

ISBN: (纸本)9798350364743

In indoor vertical farming systems, managing dynamic and complex environments poses significant challenges. Traditional control strategies often fall short in adapting to rapid changes in critical parameters such as nutrient levels, climate conditions, and plant health indicators. To address these challenges, this paper presents a novel approach for optimizing indoor vertical farming using Deep Deterministic Policy Gradient (DDPG), a reinforcement learning algorithm well-suited for environments with continuous action spaces. Our study focused on the control and monitoring of key parameters, including nutrient levels (pH and EC), climate conditions (temperature, humidity, light, and CO2 levels), and plant health indicators (biomass accumulation and leaf size structure). By defining a comprehensive state and action space, we simulated an indoor farming environment and trained the DDPG model to maximize crop yield and health. © 2024 IEEE.

关键词： DDPG indoor vertical farming precision agriculture reinforcement learning smart farming

来源：评论

学校读者我要写书评

暂无评论

Modeling and analysis of three-phase active power filter integrated photovoltaic as a reactive power compensator using the simulink matlab tool 5

Modeling and analysis of three-phase active power filter int...

引用

5th International Conference on Informatics and Computing, ICIC 2020

作者： Setiyono Arief Sudiro, Sunny Prasetyo Wibowo, Eri Department of Electrical Engineering Gunadarma University Jakarta Indonesia Jakarta Indonesia Stmik Jakarta Stik Jakarta Indonesia It Doctoral Program Gunadarma University Jakarta Indonesia

ISBN: (纸本)9781728180472

This paper presents an analysis of the modeling of reactive power compensation using renewable energy from sunlight through photovoltaic to eliminate harmonic signals in the electricity network with a three-phase active power system filter. Electric energy supply comes from three-phase electricity sources in the form of a sinusoid. Non-linear loads such as electronic devices and electrical equipment connected to the grid generate harmonics signals;can make the format of electrical energy distorted. This nonlinear load draws electric current in the form of non-sinusoid. This format increases Total Harmonic Distortion (THD), thereby worsening the performance of electrical equipment. An active power filter is a very effective method in reducing harmonics signals and increasing the quality performance of electricity. This power filter works by injecting compensation current into the grid. The energy that is injected comes from the direct current output voltage (DC) of the photovoltaic link stored in the capacitor via a Voltage Source Inverter (VSI) switch. The compensation current has the same format as the harmonics current but differs in 180°. The main parts of this power filter include the Reference Signal Generating Unit, PI Controller, VSI Switch Signal Ignition Gate Generator, Energy Storage Circuit (Battery), and Photovoltaic. Simulation modeling using Matlab Simulink Tools to reduce THD levels by IEEE 519 standards. Simulation results show a significant decrease in Total Harmonic Distortion (THD), where the grid before compensation contains THD of 29.74% and after injection of 2.25%. So this modeling is worth proposing as an active filter in a power system. © 2020 IEEE.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Effective Loss Function for Unbalanced Breast Thermal Image Segmentation

Effective Loss Function for Unbalanced Breast Thermal Image ...

引用

2021 International Conference on Computer System, Information Technology, and Electrical engineering, COSITE 2021

作者： Roslidar, Roslidar Saddami, Khairun Irhamsyah, Muhammad Arnia, Fitri Syukri, Maimun Munadi, Khairul Universitas Syiah Kuala Doctoral Program Post Graduate Program School of Engineering Banda Aceh23111 Indonesia Universitas Syiah Kuala Department of Electrical and Computer Engineering Banda Aceh23111 Indonesia Universitas Syiah Kuala Medical Faculty Banda Aceh23111 Indonesia

ISBN: (纸本)9781665425094

The convolutional neural network's ability to learn images has reigned in computer vision tasks of object detection, classification, and segmentation. In segmentation, the CNN architectures of U-Net and SegNet have shown a good performance;thus, we implemented these networks to take the region of interest (ROI) of the breast thermal images from database for mastology research (DMR). We fine-tuned the networks to find the optimal hyperparameter that can result in the best learning performance. The networks were trained using the stochastic gradient descent optimization algorithm, and weights were updated using the error backpropagation of the algorithm. To minimize the error, the loss function is applied to evaluate a candidate solution of the weights. Thus, we conducted a preliminary study on finding the optimal loss function for breast thermal image segmentation. We applied loss functions of cross-entropy, dice, and focal and figured out the one that provides the highest segmentation accuracy. Then, to evaluate the segmentation result, we calculated the pixel accuracy rate and the dice coefficient to obtain the overlapping index measuring the overlay area between ground truth and predicted output. The result shows that the SegNet model with cross-entropy loss function can take the ROI of breast thermal images at the highest pixel accuracy and optimum dice coefficient of 0.8845 and 0.7928, respectively. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Seafloor Imaging Maps by Incorporating Side Scan Sonar Technology on Hybrid Autonomous Underwater Glider 6

Seafloor Imaging Maps by Incorporating Side Scan Sonar Techn...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Atmaja, Ardian Budi Kusuma Hidayat, Egi Muhammad Idris Riyanto Trilaksono, Bambang Siregar, Simon Habibullah, Natsir School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Institut Teknologi Bandung Telkom University Doctoral Program of Electrical Engineering Department Computer Engineering Faculty of Applied Science Indonesia

ISBN: (纸本)9798350358346

This research aims to construct a two-dimensional image to represent an underwater geometry map with a Side Scan Sonar (SSS) mounted on a Hybrid Autonomous Underwater Glider (HAUG). Building the underwater map has two stages of the process. The first stage is preprocessing which includes Time-varying gains (TVG), slant range correction, and ground range correction. The second is HAUG navigation, the movement of HAUG orientation to the angle and distance of SSS readings and plotting the geometry of the grid map. With these two stages, a two-dimensional grid map will be formed. Meanwhile, the 3D plot utilizes slant range and ground range correction to obtain the surface height of the bottom of the pool. From the experiments conducted to conduct mapping in the pool, two-dimensional and three-dimensional visual forms of the pool floor and pool walls were produced. The results of the estimated measurement of the width of the pool obtained 14.05 meters and the height of the pool 3.199 meters with an SSS beam angle of 58 degrees. © 2023 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

The effect of fiber volume fraction on tensile and impact properties of eleusine indica grass reinforced polypropylene bio composite 1

The effect of fiber volume fraction on tensile and impact pr...

引用

1st International Conference on Design, Energy, Materials and Manufacture, ICDEMM 2018

作者： Lokantara, I.P. Suardana, N.P.G. Surata, I.W. Winaya, I.N.S. Doctoral Study Program of Engineering Science Faculty of Engineering Udayana University Kampus Sudirman Denpasar-Bali Indonesia Mechanical Engineering Department Udayana University Street of Bukit Jimbaran Bali Badung Indonesia

The purpose of this research was to investigate the tensile strength and impact strength of eleusine indica grass fiber-reinforced polypropylene recycle composite. In this study, the fiber was treated with alkali at 5% NaOH for 2 hours. The eleusine indica grass fiber cut with a length of 3 cm and the matrix used recycle polypropylene. In this research, the volume fraction of eleusine indica grass fiber varied by 20%, 25%, and 30% respectively. The composite molded with a hot press at temperature 200°C with a holding time for 2 hours. Tensile test used ASTM D3039 and impact test used ASTM D256. The highest tensile and impact strength results on fiber volume fraction 30%. © Published under licence by IOP Publishing Ltd.

关键词： Polypropylenes

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：