检索结果-内蒙古大学图书馆

2023 MTS/IEEE U.S. Gulf Coast, OCEANS 2023

作者： Shindo, Kazuto Katayama, Takafumi Song, Tian Shimamoto, Takashi Tokushima University Department of Science and Engineering Minami-Josanjima 2-1 Tokushima City770-8506 Japan Institute of Technology and Science Graduate School of Engineering Tokushima University Computer Systems Engineering Minami-Josanjima 2-1 Tokushima City770-8506 Japan

ISBN: (纸本)9798218142186

In this paper, we propose a highly efficient underwater image correction method that leverages structural similarity evaluation along with real-time performance from a traditional FUnIEGAN algorithm. The proposed approach is designed for implementation on an embedded GPU module (Jetson Xavier NX), ensuring its practicality and versatility. Furthermore, our method incorporates algorithmic enhancements to significantly enhance color correction performance. To optimize computational resources, we employ automatic mixed precision (AMP), effectively reducing redundancy and enabling rapid processing. As a result, our method demonstrates improved object detection outcomes, achieving an impressive increase in frames per second (FPS) from approximately 55 FPS to about 77 FPS. © 2023 The Marine Technology Society (MTS).

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Random Number Generator for Securing Data Exchange in Smart Factory: Recent Trends and Best Practices

Random Number Generator for Securing Data Exchange in Smart ...

引用

computer Technologies (ICCTech), International Conference on

作者： Andi Sama Meyliana Yaya Heryadi Taufik Roni Sahroni Computer Science Department Binus Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia Information System Department School of Information System Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program-Doctor of Computer Science Jakarta Jakarta Indonesia Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350395419

ISBN: (纸本)9798350395426

IT/OT convergence in the form of a Cyber-Physical System (CPS) presents an opportunity to apply recent Information Technology (IT) advancements to Operational Technology (OT). The IT/OT convergence introduces cyber security threats for OT. The OT communication protocols, for example, have limited or no security capabilities for securing data exchange beyond basic authentication. The RNG (Random Number Generator) function is crucial in PLC for producing the encryption keys or the initial seed for security algorithms. The software-based PRNG (Pseudo RNG) is the most common approach for RNG in OT, instead of hardware-based RNG. This study provides a systematic literature review of the most recent evidence in digital transformation to secure data exchange in smart factories, within OT, or across OT and IT settings. It does this by looking at the PRNG on PLC and identifying the most recent trends and best practices. The findings include up-to-date data on author countries' distribution, published journals, research trends, industries, and industry types. The findings also address whether data flow is encrypted or shared in plaintext to ensure secure data transfer between IT and legacy OT environments. This paper concludes that while there is known RNG implementation in the actual embedded system in ICS, there is no evidence in the literature for using RNG in ICS networks for PLC implementation to secure data transfer with encryption.

关键词： Industries Systematics Market research Data transfer Control systems Generators Encryption

来源：评论

学校读者我要写书评

暂无评论

Mobile Application Implementation as Agriculture 4.0 Strategy for Sugarcane Yield Prediction 9

Mobile Application Implementation as Agriculture 4.0 Strateg...

引用

9th International HCI and UX Conference in Indonesia, CHIuXiD 2023

作者： Mawandha, Hangger Gahara Rahutomo, Reza Suparyanto, Teddy Pardamean, Bens Institut Pertanian Stiper Faculty of Agricultural Technology Yogyakarta55282 Indonesia Bina Nusantara University School of Information Systems Information Systems Department Jakarta 11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta 11480 Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta 11480 Indonesia

ISBN: (纸本)9798350304084

Information engineering strategies play a significant and transformative role in shaping the landscape of digital agriculture. It drives innovation and efficiency in modern farming practices, with a specific focus on enhancing the value of agricultural commodities, such as sugarcane. The application of mobile technology plays a crucial part in achieving increased sugarcane productivity. Mobile applications, equipped with advanced developer features, offer rapid and user-friendly access to vital information. Traditional methods of estimating sugarcane production relied on manual data recording on paper, followed by data transfer to computer systems, typically managed by sugar factory junior plant officers. This conventional approach presents several inherent weaknesses, including time and effort intensiveness during data recording and entry. Additionally, the potential for errors in calculation and data input is a concern. The storage capacity for paper-based documents is finite, and farmers are often unable to autonomously assess their production potential. The objective of this research is to confront these obstacles by creating a sugarcane production application for Android. This application functions as an information engineering approach focused on forecasting sugarcane yields for plantation owners and their assistants. The development procedure adhered to the systematic waterfall method, following the principles of the Software Development Life Cycle (SDLC) model. Data collection was carried out through observations, while interviews with junior plant officers provided valuable insights into sugarcane estimation techniques. Analysis involved the synthesis of observational and interview data to inform the design of the application's interface and algorithmic system. The resulting application significantly simplifies the process of estimating production potential for farmers, enabling them to access sugarcane productivity data during harvest. Consequently, sugar

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Mobile Based Brand and Car Type Detection Using Convolutional Neural Network 8

Mobile Based Brand and Car Type Detection Using Convolutiona...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Ramadhan, Cahaya Saputra, Hasta Ragil Dewi, Ratna Sari Suharjito Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta11480 Indonesia Industrial Engineering Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

Although the parking lot is equipped with CCTV surveillance, car theft incidents still occur occasionally. These thieves exploit a loophole in the system that prevents the identification of the car's brand and model upon entering and exiting the parking lot using the same ticket. Therefore, the aim of this research is to develop a system capable of detecting the brand and model of cars. The study utilizes convolutional neural network technology and specifically focuses on the EfficientNet, MobileNet, and MobileNetV2 architectures due to their low resource requirements. Training images for the study are sourced from an online marketplace for used cars, with each of the 20 car brand and model variations consisting of 100 photographs. creates a model after being processed. For the prototype, the approach is put into practice through a mobile application. This study compares EfficientNet, MobileNetV1, and MobileNetV2 as the end result. EfficientNet scored 74%, MobileNetV1 74%, and MobileNetV2 66% on the test of accuracy. The accuracy increases to 80% after the EfficientNet has been tuned. © 2023 The Authors. Published by Elsevier B.V.

关键词： Convolutional Neural Network EfficientNet MobileNet V2 MobileNetV1 Parking system Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Q-Learning Energy Management System (Q-EMS) in Wireless Sensor Network

Q-Learning Energy Management System (Q-EMS) in Wireless Sens...

引用

2024 International Conference on Smart Computing, IoT and Machine Learning, SIML 2024

作者： Ardiansyah, Deden Mustafid Mantoro, Teddy Universitas Diponegoro Doctoral Program of Information Systems School of Postgraduate Central Java Semarang Indonesia Universitas Pakuan Vocational School Computer Engineering Department West Java Bogor Indonesia Sampoerna University Media-Tech-Lab Computer Science Department DKI Jakarta Indonesia

ISBN: (纸本)9798350364101

The energy control of a Wireless Sensor Network (WSN) often leads to an unbalanced state between the battery storage system, energy extraction through photovoltaic systems energy, and energy utilization in the WSN. These disparities result in suboptimal wireless sensor network performance. The reliance on batteries is a major factor contributing to this problem. The Q-Learning Energy Management System (Q-EMS) is designed to address these challenges and improve energy management strategies. The Q-EMS algorithm used a learning process resulting in optimal actions for sensor nodes in different situations. The rewards or punishments nodes receive determine their decisions, which are determined by the Q-EMS algorithm. The Q-learning model approach is aimed at reducing energy consumption and supply in WSNs. Energy supply is categorized into battery-based, transfer-based, and harvesting, while energy consumption can be classified into task-cycle, mobility-based, and data-driven. The development of the Q Learning algorithm model has three scenarios: determining energy needs for WSN, effective energy harvesting strategy, and effective energy transfer. As a result, effective energy demand, harvesting and transfer using the Q-learning algorithm are balanced. However, it needs to be studied in more depth using real data in the field. In future research, I will use real data and optimize the use of the Q-Learning algorithm. © 2024 IEEE.

关键词： Energy management systems

来源：评论

学校读者我要写书评

暂无评论

Treatment of Resampling Frequency and Epoch Length for RR interval in Autonomic Nervous System Analysis 4

Treatment of Resampling Frequency and Epoch Length for RR in...

引用

4th IEEE Global Conference on Life sciences and Technologies, LifeTech 2022

作者： Yamada, Miyu Ayabe, Makoto Okayama Prefectural University Graduate School of Computer Science and Systems Engineering Okayama Japan Okayama Prefectural University Human Information Engineering Okayama Japan

ISBN: (纸本)9781665419048

This investigation aimed to clarify the effects of the frequency of resampling of the RR interval and length of the analysis interval to simplify the analysis of heart rate variability (HRV) for the evaluation of the autonomic nerve system (ANS). The subjects were 15 male university students, and the experiment consisted of 10 min of rest and 10 min of a pleasant-emotion-induction task, for a total of 20 min. The heart rate and pulse rate were detected from the measured electrocardiogram and pulse waves. RR intervals were used to analyze sympathetic and parasympathetic nerve activity. The resampling frequency was set to 2, 4, and 10 Hz. The analysis times were 30, 60, 120, 300, and 600 s for the 10-min resting period and 30, 60, and 300 s for the changes associated with the induction of pleasant emotions. The total power (TP), high-frequency (HF) power, and low-frequency (LF) power exhibited an interaction between the resampling frequency and analysis time. In the pleasant-emotion-induction task, significant differences were observed among HF/TP, LF/TP, and LF/HF at 2, 4, and 10 Hz. However, when the analysis time was set to 30 s, the number of measurement points where statistically significant differences were obtained was limited. The present investigation demonstrates that the sensitivity of the relative ANS index may decrease with decreasing analysis time. The results of this investigation suggest that while a shorter measurement time is consistent with adequate rest, the sensitivity of the ANS index to capture minute changes in the body needs to be considered. © 2022 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of SAAS Model and NPC Integration for Enhancing VR Shopping Experiences

引用

Applied sciences (Switzerland) 2024年第15期14卷 6573页

作者： Doungtap, Surasachai Wang, Jenq-Haur Phanichraksaphong, Varinya International Graduate Program of Electrical Engineering and Computer Science National Taipei University of Technology Taipei10608 Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei10608 Taiwan

This article examines the incorporation of the Shopping Assistance Automatic Suggestion (SAAS) model into Virtual Reality (VR) environments in order to improve the online shopping experience. The SAAS model employs sophisticated deep learning methods to offer customized product recommendations, which are conveyed by non-player characters (NPCs) via voice-based interactions. Our goal is to develop an interactive shopping experience that replicates real-life interactions by integrating AI-powered recommendations with immersive VR technology. We gather and standardize data from several open commerce databases, such as Amazon Product and Customer Reviews. The SAAS model, in conjunction with GPT-3, BERT, and T5, undergoes training and testing to evaluate its effectiveness across multiple criteria. The results demonstrate that the SAAS model surpasses other models in delivering contextually aware and pertinent recommendations. The integration process outlines the specific steps involved in capturing, processing, and transforming user interactions in virtual reality (VR) into vocal suggestions provided by non-player characters (NPCs). This strategy improves customization and utilizes the immersive features of virtual reality to effectively engage people. The results of our research establish a higher standard for e-commerce, with the goal of enhancing the user experience of online purchasing by making it more instinctive, engaging, and pleasurable. © 2024 by the authors.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

The Impact of Recommendation System Provided Based on Online Learning Readiness in the MOOC Environment 24

The Impact of Recommendation System Provided Based on Online...

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Murad, Dina Fitria Toha, Mohamad Mayatopani, Hendra Dewi, Meta Amalya Leandros, Riyan Murad, Silvia Ayunda Heryadi, Yaya Wijanarko, Bambang Dwi Bina Nusantara University Information Systems Department Binus Online Learning Jakarta Indonesia Universitas Terbuka Jakarta Indonesia Pradita University Department of Information System Tangerang Indonesia Bina Nusantara University Computer Science Department Binus Graduate Program Doctor of Computer Science Jakarta Indonesia Bina Nusantara University School of Computer Science Jakarta Indonesia

ISBN: (纸本)9798350384307

MOOCs are one of the developments or impacts of e-learning or online learning. Massive Open Online Course (MOOC) is one of the choices for students to increase their knowledge through non-formal channels. Our research aims to determine the level of readiness of students regarding MOOC learning and opportunities for utilizing recommendation systems in students' decision-making regarding selecting MOOCs that suit their interests and needs. We conducted a survey regarding the constraints and needs of learner readiness through 5 aspects, namely 1) technical aspect, (2) social aspect, (3) communication aspect, (4) lecture readiness aspect, and (5) online discussion. The results of this research show that the main challenges that MOOC participants may face in a MOOC environment are Technical Aspects (28.25%), Social Aspects (21.47%), and Communication Aspects (18.93%). Meanwhile, the greatest strength of online learning in the MOOC environment is the social aspect (21%), the most influential and continued with technical and other aspects. Meanwhile, the lecture readiness aspect is quite good, and the online discussion aspect is the biggest aspect that influences the success of MOOC learning. Other results of this research indicate the importance of a recommendation system for MOOC students to make it easier for students to choose the right MOOC according to their interests and needs. © 2023 IEEE.

关键词： MOOC personalization Recommendation system student competency Technology Enhanced Learning

来源：评论

学校读者我要写书评

暂无评论

Activation Functions for Detection of Bacteria from Gram Stained Smears Images by YOLOv8 16

Activation Functions for Detection of Bacteria from Gram Sta...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Kagemoto, Kouya Hirata, Kouichi Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Kawazu 680-4 Iizuka820-8502 Japan Kyushu Institute of Technology Department of Artificial Intelligence Kawazu 680-4 Iizuka820-8502 Japan

ISBN: (纸本)9798350377903

In this paper, we investigate the activation functions appropriate to detect bacteria from Gram stained smears images by YOLOv8. First, we detect bacteria by replacing all the occurrences of the default activation function SiLU at the convolution layers in YOLOv8 with other activation functions. Next, by focusing on the activation functions providing higher performance than SiLU to detect bacteria, we investigate which of occurrences of SiLU in several convolution layers in YOLOv8 replacing with the activation functions improves the results to detect bacteria. © 2024 IEEE.

关键词： activation function detection of bacteria Gram stained smears images object detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Comparison with Detection of Bacteria from Gram Stained Smears Images by Various Object Detectors 16

Comparison with Detection of Bacteria from Gram Stained Smea...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Tanaka, Tsubasa Hirata, Kouichi Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Kawazu 680-4 Iizuka820-8502 Japan Kyushu Institute of Technology Department of Artificial Intelligence Kawazu 680-4 Iizuka820-8502 Japan

ISBN: (纸本)9798350377903

In this paper, we detect bacteria from Gram stained smears images by the object detectors of SSD, M2Det, RT-DETR and YOLOv8. Then, we show that SSD and M2Det are not appropriate for detecting bacteria. Also we show that RT-DETR with pre-training and the variation of YOLOv8 shifting convolution layers are more appropriate to detect bacteria than standard YOLOv8. © 2024 IEEE.

关键词： Bacteria

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：