检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Kumar, Purushottam Tiwari, Pranav Srinivasulu Reddy, U. Machine Learning & Data Analytics Lab CoE in Artificial Intelligence National Institute of Technology Trichy India Indian Institute of Information Technology Tiruchirappalli Computer Science and Engineering Trichy India National Institute of Technology Machine Learning & Data Analytics Lab Department of Computer Applications Trichy India

ISBN: (纸本)9798350338607

Due to the ever-growing population, rapid urbanization, unusual environmental change, and dwindling water supply, the food production from conventional farming techniques won't be able to keep up with increasing food demand for long, leading to severe food scarcity. Aquaponics is emerging as a viable alternative to food cultivation techniques but lacks efficiency, hindering its adoption on a large-scale production basis. The adoption of Artificial Intelligence (AI) techniques in smart aquaponic farming can further contribute to increasing the yield in aquaponics. In the study, both linear and non-linear regression algorithms such as linear regression, lasso regression, ridge regression, KNN regression, SVR, and decision tree regression were trained on aquaponic fish pond dataset, evaluated on the basis of multiple metrics like MAE, MSE, RMSE, and RMSLE, and a competitive analysis was done to determine the best algorithm for predicting the harvest weight of the fish in aquaponic ponds. The results showed that KNN regression and decision tree regression algorithms have lowest error and highest accuracy of 99.15% and 99.1% respectively, for predicting the harvest weight of the fish. The results obtained could be scaled up to commercial levels and used in regulating nutrient concentration and aquatic environmental conditions © 2023 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Edged Self-Adaptable Vehicle Slowdown Earliest Warning Information System Using IOT Based Traffic Prediction Model

A Machine Learning Edged Self-Adaptable Vehicle Slowdown Ear...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent engineering, ICECONF 2023

作者： Murali, N. David, D. Beulah Saveetha School of Engineering Simats Department of Computer Science and Engineering Tamilnadu Chennai India Institute of Information Technology Saveetha School of Engineering Simats Department of Data Analytics Tamilnadu Chennai India

ISBN: (纸本)9798350334357

Development of vehicle safety is the work's primary goal, according to its abstract vehicle in traffic congestion using the Internet of Things (IoT). The intense growth of the city's vehicle population needs intelligent traffic systems to be considered resourcefully and sustainably by enhancing the full advantage of recent technology. The unpredictable traffic flow is a substantial issue that carries a colossal traffic movement in real-time scenarios. The random traffic control systems during peak and non-peak hours with unproductive human possessions, which leads to increased traffic and road offenses due to ineffective traffic monitoring systems. To sort down this dynamic scenario, the self-adaptable machine learning approach has been adopted to sequence the intelligent traffic flow by using IOT based early warning system in vehicles. The proposed work focused on the traffic congestion prediction operationalized using the unsupervised algorithm to train the gathered data sets using a neural network. It also aims to deliver a clarification that will upturn the comfort level of travelers to make intelligent and better transference choices. A neural network is a reasonable approach to finding traffic circumstances in sequence with this, the machine learning algorithms and their accuracy, which practices an outline in the collected data sets and then produces crucial decisions in evidence about traffic flow and congestion levels. The most focused part of the research is to enhance the intelligence in the IoT docking system, which prevents the vehicle congestion and returns a flawless, innovative design. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A IoT Edge Advanced VANET Technique for Vehicle Communication and Improve Safety in Hill Station Critical Scenario 8

A IoT Edge Advanced VANET Technique for Vehicle Communicatio...

引用

8th IEEE International Conference on Science, Technology, engineering and Mathematics, ICONSTEM 2023

作者： Murali, N. Beulah David, D. Saveetha School of Engineering Simats Department of Computer Science and Engineering Tamilnadu Chennai India Saveetha School of Engineering Simats Institute of Information Technology Department of Data Analytics Tamilnadu Chennai India

ISBN: (纸本)9798350347791

The safety of the vehicles is given great importance by advanced intelligent transportation systems. We are here to make sure that swift transit vehicles and infrastructure communicate with one other quickly. The majority of the vehicles need regular monitoring for appropriate warnings and road maps to achieve their ultimate objective in a timely manner in the hill station bad environment, and travel in hairpin bends and risky turning in particular is a duty that is vital for ITS. Here, my study will provide a strategy for preventing accidents by applying a sophisticated early warning system before notifying the car in a certain circumstance. In order to prevent accidents, machine learning is a technique where the system automatically learns and enhances the rapid object detection stage in bobby pin road turning scenarios. Here, my study offers effective unsupervised learning of these characteristics based on the acquired data, which in turn serves as the foundation for the clustering I performed, which successfully builds a mobile ad hoc network. In this work, we suggested an innovative automated discovering vehicle prier that uses the UNetXST technique in real-time to notify warring for vehicle in three-way shining LED light with blinking mode, slowing warring message in display unit, and beep alarm sound. By combining V2I and V2V technologies and sending messages to the central traffic light management system, we highlighted safety and communication. In worst-case scenarios, we employ a v2v technology sensor to detect the vehicle that will cross the junction road, and we investigate two-way merging technology's potential to implement and resolve these problems in transparent object tracking in the turning system. We looked at future direction and hurdles at this time in addition to a case study illustrating a VANET-based scenario of a critical urban road turning, receiving the earliest notice to flee from a traffic collision, and experiencing the perfect EV momen

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Effect of Delignification Method on the type of Cellulose Water Hyacinth ( Eichornia crassipes) as a Material for Sustainable Sodium-Ion Battery Technology 3

Effect of Delignification Method on the type of Cellulose Wa...

引用

3rd International Symposium on Physics and Applications 2023, ISPA 2023

作者： Anugerah Putra Pradana, Revaldo Rafi Setopratama, Andyan Zulaiha Ahmad, Chanifa Prasetyo, Andry Nur Abti, Salsabilla Darminto Department of Physics Faculty of Science and Data Analytics Institute Technology Sepuluh Nopember Kampus ITS Sukolilo Surabaya60111 Indonesia Department of Chemistry Faculty of Science and Data Analytics Institute Technology Sepuluh Nopember Kampus ITS Sukolilo Surabaya60111 Indonesia Department of Material Engineering and Metallurgy Faculty of Industrial Technology and System Engineering Institute Technology Sepuluh Nopember Kampus ITS Sukolilo Surabaya60111 Indonesia

Biopolymers developed for solid electrolyte materials of sodium-ion batteries are of great interest these days. The main precursor in the form of cellulose biopolymers has been successfully isolated from water hyacinths (Eichornia crassipes). The first stage is maceration using 2% NaOH to produce cellulose-Iα and Ethanol 60% to produce cellulose-Iβ by hydrothermal reaction process at 150 °C and continued at the bleaching stage with H2O2 solution at 50 °C until it changes color. Then the sample is washed to a neutral pH and dried in an oven at 60 °C. Cellulose-Iα yields were obtained with a yield of 33.98% and cellulose-Iβ of 39.11%. The cellulose-I that has been obtained is modified to obtain cellulose-II type by mercerization method, where cellulose-I type is reacted with 20% NaOH for 5 hours. The mixture is then washed to neutral and dried. Cellulose-II yield was obtained with a yield of 69.21%. Samples were characterized by XRD, FTIR, and SEM. The cellulose content of hyacinths before delignification was 36.69%. The cellulose content of hyacinths after delignification for cellulose-Iα and cellulose-Iβ types was 64.26% and 48.58% respectively. FTIR analysis proved the presence of hydroxyl and carboxyl functional groups in hyacinth cellulose. XRD analysis showed that all three samples were identified with cellulose-Iα, cellulose-Iβ, and cellulose-II amorphous structures with a crystallinity index of 28.62% and the largest crystallite size based on the hkl field (121) of cellulose-Iβ type samples was ∼10 nm. SEM analysis shows that cellulose-Iα, cellulose-Iβ has a slim fiber diameter size and straight, smooth surface and microfibrils around the fiber. While cellulose-II shows visualization of a diameter that looks larger and twisted, the surface is rough and there are no microfibrils around the fibers. © Published under licence by IOP Publishing Ltd.

关键词： Sodium hydroxide

来源：评论

学校读者我要写书评

暂无评论

Compressed Image Super Resolution using Convolutional Neural Network 38

Compressed Image Super Resolution using Convolutional Neural...

引用

38th IEEE Region 10 Conference, TENCON 2023

作者： Tun, Ei Ei Konkitkriengkrai, Aktanin Ruangsang, Watchara Aramvith, Supavadee Chulalongkorn University Faculty of Engineering Department of Electrical Engineering Bangkok10330 Thailand Chulalongkorn University Multimedia Data Analytics and Processing Research Unit Faculty of Engineering Department of Electrical Engineering Bangkok10330 Thailand

ISBN: (纸本)9798350302196

Image compression is a topic of significant interest as it reduces file sizes in stored data. In this paper, we propose a model that achieves multiple levels of compression, thereby minimizing the storage space required for images, which typically consume substantial amounts of data due to their size and resolution. We combine an image downscaling and upscaling model with an image compression model. By leveraging convolutional techniques to identify image features, we can effectively reduce the size of the image through downscaling and subsequently upscaling it. Additionally, we employ entropy image compression and arithmetic encoding to compress and reconstruct the image while preserving its lossless data. Through experimentation with the Kodak dataset, we observed that our proposed model achieved a compression rate of 96.92%, significantly reducing the data needed for file storage. Moreover, our reconstructed images attained a standardized measure with a signal-to-noise ratio of 33.10 dB and a structural similarity of 0.9219. Notably, the perceptual quality of the images, including intricate details, remained intact to the human eye. © 2023 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards Simulation-Based Circular Product Design 30

Towards Simulation-Based Circular Product Design

引用

30th CIRP Life Cycle engineering Conference, LCE 2023

作者： Aher, Gaurav Boudjadar, Jalil Ramanujan, Devarajan Department of Mechanical and Production Engineering Aarhus University Aarhus8200 Denmark Department of Electrical and Computer Engineering Aarhus University Aarhus8200 Denmark Centre for Digitalisation Big Data and Data Analytics Aarhus University Aarhus8200 Denmark

Assessing the circular economy (CE) performance of products has become an essential consideration in product design processes. While a growing body of literature is exploring the use of CE indicators to guide design processes, they typically assume broad design changes (e.g., material changes, end-of-life treatment) that may not accurately capture trade-offs in CE indicators, technical performance, and design feasibility. This paper aims to address the above gaps with the goal of incorporating CE assessment into simulation-based design. To this end, this paper defines a novel framework for using simulation-based design to analyze the effects of parametric changes in product design attributes on CE performance. First, the proposed framework describes the lifecycle information needed for computing resource-based, product-level CE indicators at the design stage. Depending on the set of selected CE indicators, corresponding simulation models are used to compute the effects of changing design parameters, and setting design/performance constraints, on the product's CE performance. Thus, the proposed framework enables the selection and optimization of product design attributes for achieving a specific level of CE performance, given specific technical performance requirements and other design constraints. The application of this framework is demonstrated using a case study conducted on a flywheel. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Yijun Hao Shusen Yang Fang Li Yifan Zhang Cong Zhao Xuebin Ren Peng Zhao Chenren Xu Shibo Wang National Engineering Laboratory for Big Data Analytics Xi’an Jiaotong University Xi’an China National Engineering Laboratory for Big Data Analytics and the Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China School of Computer Science Peking University Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China National Engineering Laboratory for Big Data Analytics XiÃan Jiaotong University XiÃan China

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports $3.12\times $ more demand when compared to related existing approaches.

关键词： Topology Network topology Planning IP networks Optical fiber networks Routing Optical fibers Optical feedback Production Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Testing for Service-Oriented Architecture: Leveraging Large Language Models for Enhanced Service Composition

引用

IEEE Access 2025年 13卷 89627-89640页

作者： Altin, Mahsun Mutlu, Behcet Kilinc, Deniz Cakir, Altan Istanbul Technical University Department of Computer Engineering Istanbul34467 Turkey Wingie Enuygun Group Istanbul34750 Turkey University of Bakirçay Department of Computer Engineering Izmir35665 Turkey Istanbul Technical University Artificial Intelligence Data Science Research and Application Center Istanbul34467 Turkey ITU Ari Teknokent Parton Big Data Analytics and Consulting Istanbul34467 Turkey Adin.Ai WilmingtonDE19806 United States

This article explores the application of Large Language Models (LLMs), including proprietary models such as OpenAI's ChatGPT 4o and ChatGPT 4o-mini, Anthropic's Claude 3.5 Sonnet and Claude 3.7 Sonnet, and Google's Gemini 1.5 Pro, Gemini 2.0 Flash, and Gemini 2.0 Flash-Lite, as well as open-source alternatives including Qwen2.5-14B-Instruct-1M, and commercially accessed models such as DeepSeek R1 and DeepSeek V3, which were tested via APIs despite having open-source variants, to automate validation and verification in Application Programming Interface (API) testing within a Service-Oriented Architecture (SOA). Our system compares internal responses from the Enuygun Web Server against third-party API outputs in both JSON and XML formats, validating critical parameters such as flight prices, baggage allowances, and seat availability. We generated 100 diverse test scenarios across varying complexities (1-4 flight results) by randomly altering request and response parameters. Experimental results show that Google Gemini 2.0 Flash achieved high accuracy (up to 99.98%) with the lowest completion time (85.34 seconds), while Qwen2.5-14B-Instruct-1M exhibited limited capability in processing complex formats. Models such as OpenAI's ChatGPT and Anthropic's Claude Sonnet models also demonstrated strong performance in single-flight validation scenarios, making them suitable for low-latency, high-precision tasks. Our findings indicate that some open-source models can offer promising cost-effective alternatives, though performance significantly varies. This integration of LLMs reduced manual workload, improved test scalability, and enabled real-time validation across large-scale datasets. As LLM technologies mature, we anticipate further advances in automation, accuracy, and efficiency in software validation systems. © 2013 IEEE.

关键词： Service oriented architecture (SOA)

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multimodal Models for Enhanced Neuroimaging Diagnostics in Alzheimer's Disease

Leveraging Multimodal Models for Enhanced Neuroimaging Diagn...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Chiumento, Francesco Liu, Mingming Dublin City University School of Electronic Engineering GlasnevinDublin 9 Ireland Dublin City University Insight Research Ireland Centre for Data Analytics GlasnevinDublin 9 Ireland

ISBN: (纸本)9798350362480

The rapid advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have shown great potential in medical diagnostics, particularly in radiology, where datasets such as X-rays are paired with human-generated diagnostic reports. However, a significant research gap exists in the neuroimaging field, especially for conditions such as Alzheimer's disease, due to the lack of comprehensive diagnostic reports that can be utilized for model fine-tuning. This paper addresses this gap by generating synthetic diagnostic reports using GPT-4o-mini on structured data from the OASIS-4 dataset, which comprises 663 patients. Using the synthetic reports as ground truth for training and validation, we then generated neurological reports directly from the images in the dataset leveraging the pre-trained BiomedCLIP and T5 models. Our proposed method achieved a BLEU-4 score of 0.1827, ROUGE-L score of 0.3719, and METEOR score of 0.4163, revealing its potential in generating clinically relevant and accurate diagnostic reports. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Preliminary Study on Structure of Carbon Derived from Palm Oil Shell 3

Preliminary Study on Structure of Carbon Derived from Palm O...

引用

3rd International Symposium on Physics and Applications 2023, ISPA 2023

作者： Wardhani Mas'Udah, Kusuma Tiara Permatasari, Gabriella Astuti, Fahmi Asih, Retno Darminto, Darminto Departement of Physics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Suarabaya Indonesia Department of Physics Faculty of Engineering University of Pembangunan Nasional Veteran Jawa Timur Indonesia

Palm shells are waste that is produced every year due to the large demand for palm oil. The potential for carbon derivatives in palm shell charcoal waste that can be extracted is more like activated carbon. Therefore, this research aims to provide an explanation of the ability of palm shell charcoal carbon as a residual component of palm oil processing that is affordable and abundantly available, which if maximized properly will be the forerunner to the development of technology that has added value. The capabilities of Palm Shell Charcoal can be applied for technical applications with further development. It is hoped that this study will provide initial information for scientists and policy makers in the fields of environmental conservation and technology. Palm shell charcoal (ACKS) that has been washed, dried and made into powder is subjected to DSC-TGA, FTIR, XRD, SEM-EDX testing. The XRD results show that there is a main broad peak that appears around the 2θ ∼23° angle which corresponds to the (002) plane and also a narrow peak appears at the 26° angle which indicates graphite growth. Meanwhile, the FTIR results show that many of the bonds formed are C=O, C-O, C=C and O-H bonds which indicate the presence of hard carbon. © Published under licence by IOP Publishing Ltd.

关键词： Palm oil

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：