检索结果-内蒙古大学图书馆

Optimizing Supply Chain Efficiency: Integrating Deep Learning and Blockchain Technologies 1

Optimizing Supply Chain Efficiency: Integrating Deep Learnin...

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems, iTech SECOM 2023

作者： Shanmugapriyaa, K.R. Swetha, S. Janani, N. Bavithra, K. Padmavathi, K. Coimbatore Institute of Technology Department of Artificial Intelligence and Data Science Tamilnadu India Kathir College of Engineering Department of Computer Engineering Tamilnadu India Psg Institute of Technology and Applied Research Department of Electrical and Electronics Engineering Tamilnadu India Hindusthan Polytechnic College Department of Computer Engineering Tamilnadu India

ISBN: (纸本)9798350371185

The research introduces an innovative supply chain management system tailored for agriculture, aiming to enhance operational efficiency and transparency through cutting-edge technologies such as deep learning and blockchain. The system comprises four modules, each leveraging machine learning algorithms to optimize various agricultural processes. The first module utilizes LSTM models to predict crop yields and diseases, empowering farmers with valuable insights into crop health and potential yields. The second module focuses on inventory management optimization using DQN algorithms, enabling farmers to efficiently utilize resources and minimize waste. The third module employs GNN technology to optimize routes for accessing industry-specific points of interest, simplifying farmers' access to relevant information and resources. Lastly, the fourth module addresses significant challenges in agriculture, including crop demand, rotation planning, market trends, pricing strategies, and market identification, employing a DBN model. This study showcases the transformative power of machine learning algorithms in revolutionizing productivity and profitability within the agriculture sector, offering actionable insights and optimization tools to farmers. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

DeePaGait: Motor Assessment of Parkinson’s Disease Using a Multi-Layer 1D Convolutional Neural Network on Smartphone Gait Data

DeePaGait: Motor Assessment of Parkinson’s Disease Using a ...

引用

IEEE International Conference on Big Data

作者： Hamza Abujrida Emmanuel Agu Kaveh Pahlavan Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (纸本)9781665480468

Nearly 1 million people in the USA and 10 million people worldwide are living with Parkinson’s disease (PD) [1]. The progression of the disease can be inferred from the changes in the patients’ gait to inform early intervention. Due to their near-ubiquitous ownership, smartphone sensing is a very effective, highly available way of assessing gait. Objectives: In this work, we explore the inference of PD gait, by analyzing the patient’s walk data collected from a smartphone in the patients’ homes, using Deep Learning (DL) methods. Specifically, we investigate DL models to classify the severity of the motor part of the UPDRS (MDS-UPDRS 2.10-2.13). Methodology: Using data from the mPower study [2], we selected 152 PD patients who recorded at least 3 walks before taking their medication. We extracted gait cycles from the accelerometer and gyroscope sensor records and fed them to DeePaGait; our DL multi-layer Conventional Neural Network (CNN). DeePaGait operates on 1Dimensional convolution filters to classify 30 seconds of walking data into one of five severity levels (Normal, Slight, Mild, Moderate, Severe). Results: Our DeePaGait DL network was able to Classify the PD Walking-Balance, Shaking/Tremor, and Freeze of Gait (FoG) symptoms, with an accuracy of: 99.1%,98.4%, and 98.2% respectively. Conclusion: Despite the challenges of working with a patient-labeled, crowdsourced dataset, we were able to demonstrate that gait classification based on smartphone sensor data is a viable approach to infer the severity of PD gait anomalies.

关键词： Legged locomotion Neural networks Predictive models Big Data Data models Sensors Planning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Magnetic Induction Sensors for Non-Obtrusive Vital Signs Monitoring: Impact of Current Control on Operational Quality

Optimizing Magnetic Induction Sensors for Non-Obtrusive Vita...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Mahdi Momeni Adrian Radomski Ulkuhan Guler Daniel Teichmann SDU Health Informatics and Technology The Maersk Mc-Kinney Moller Institute University of Southern Denmark Denmark Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

This paper investigates the advancement of magnetic induction-based heart and respiration rate sensing by actively controlling the coil current. This is realized through the implementation of a current-starved inverter mechanism. Experiments show a notable level of accuracy of the proposed circuit in measuring heart and respiration activity when compared to a reference sensor. The direct manipulation of current levels was found to have a direct impact on the signal strength. Incrementing the overall current within the proposed circuit from 60 mA to 100 mA resulted in an augmentation of the output amplitude of the heart rate signal from 8.5 mV to 27 mV, accompanied by a marginal enhancement in beat-to-beat interval accuracy. Moreover, the proposed sensor demonstrates noteworthy precision in monitoring the respiratory rate when compared with the reference sensor under different current values, exhibiting the same trend in signal strength. This finding offers valuable insight for the development of future power-optimized magnetic induction sensors with enhanced robustness.

关键词： Heart rate Current control Accuracy Power demand Inverters Robustness Sensors Biomedical monitoring Monitoring Magnetic circuits

来源：评论

学校读者我要写书评

暂无评论

Strategic multi-task coordination over regular networks of robots with limited computation and communication capabilities 57

Strategic multi-task coordination over regular networks of r...

引用

57th Annual Conference on Information Sciences and Systems, CISS 2023

作者： Wei, Yi Vasconcelos, Marcos M. Virginia Polytechnic Institute State University Commonwealth Cyber Initiative The Bradley Department of Electrical and Computer Engineering ArlingtonVA22203 United States FAMU-FSU College of Engineering Florida State University Department of Electrical and Computer Engineering TallahasseeFL32306 United States

ISBN: (纸本)9781665451819

Coordination is a desirable feature in multiagent systems, allowing the execution of tasks that would be impossible by individual agents. We study coordination by a team of strategic agents choosing to undertake one of the multiple tasks. We adopt a stochastic framework where the agents decide between two distinct tasks whose difficulty is randomly distributed and partially observed. We show that a Nash equilibrium with a simple and intuitive linear structure exists for diffuse prior distributions on the task difficulties. Additionally, we show that the best response of any agent to an affine strategy profile can be nonlinear when the prior distribution is not diffuse. Finally, we state an algorithm that allows us to efficiently compute a data-driven Nash equilibrium within the class of affine policies. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

On Rejecting Low Quality Images to Improve Deep Smartphone Wound Assessment

On Rejecting Low Quality Images to Improve Deep Smartphone W...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Apiwat Ditthapron Emmanuel O. Agu Peder Pedersen Clifford Lindsay Bengisu Tulu Diane Strong Computer Science Dept. Worcester Polytechnic Institute (WPI) Worcester MA Electrical and Computer Engineering Dept. Worcester Polytechnic Institute (WPI) Worcester MA Department of Radiology Univ. Massachusetts Medical School Worcester MA Foisie Business School Worcester Polytechnic Institute (WPI) Worcester MA

Automatic assessment of wounds using smartphones can facilitate the tracking of healing progress outside the clinic. Prior work proposed SS-PMG-EfficientNets, a state-of-the-art, multi-scale, convolutional neural network architecture for accurate wound assessment. However, the model was previously only trained and evaluated on high-quality wound images captured in controlled environments. This study systematically evaluated the effects of low-quality images on SS-PMG-EfficientNets, finding that the model's performance and consistency are reduced when input wound images are blurry or captured in adverse lighting (too bright or too dark), two factors previously identified as the most prevalent issues in crowdsourced images. Specifically, SS-PMG-EfficientNet was first trained on three high-quality wound datasets containing images labeled with Photographic Wound Assessment Tool (PWAT) wound healing scores, stages of pressure injury wounds, and wound types, respectively. The model was then evaluated on a test wound dataset that was augmented with real-world image luminance, blur, and image compression effects and found that wound assessment accuracy decreased by up to 27%. To improve model performance, we propose a method for instant image quality assessment on the smartphone, enabling low-quality wound images to be rejected immediately after image capture so that the nurse or patient can be prompted to recapture the image. Our evaluation of the proposed image quality assessment and rejection method showed that it increases average accuracy from 73 % to 87%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hands-On Learning: Teaching Parallel and Distributed Computing through Unplugged Activities in Undergraduate CS Courses

Hands-On Learning: Teaching Parallel and Distributed Computi...

引用

2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024

作者： Dasgupta, Anurag Margapuri, Venkat Shamoun, Simon Taneja, Shubbhi Toups, Matthew Valdosta State University Computer Science and Engineering Technology ValdostaGA31698 United States Villanova University Department of Computing Sciences VillanovaPA19085 United States Hofstra University Department of Computer Science HempsteadNY11549 United States Worcester Polytechnic Institute Department of Computer Science WorcesterMA01609 United States Tulane University Computer Science Department New OrleansLA70118 United States

ISBN: (纸本)9798350355543

The authors present and evaluate an unplugged activity to introduce parallel computing concepts to undergraduate students. Students in five CS classrooms used a deck of playing cards in small groups to consider how parallelization can improve performance and how improvement decreases with increased parallelization. Before and after the activity, students took a short survey about their solution and their ideas about parallelism. The authors carried out this activity in seven courses at five institutions in the 2023-2024 academic year. The results showed that students had an increased appreciation for parallelization and this type of activity. © 2024 IEEE.

关键词： computer science CS CS education hands-on learning parallel distributed computing unplugged

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Traffic Management of Vehicles using Deep Learning Approach in Smart Cities 3

An Intelligent Traffic Management of Vehicles using Deep Lea...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Elov, Botir Dauletov, Adilbek Sucharitha, Yadala Khalilova, Feruza Latipova, Mukhayyo Abdullayeva, Mukhtasarkhon Alisher Navo'i Tashkent State University of Uzbek Language and Literature Tashkent Uzbekistan Alfraganus University Department of Digital Technologies Tashkent Uzbekistan Vnr Vignana Jyothi Institute of Engineering and Technology Department of Computer Science and Engineering Hyderabad India Fergana Polytechnic Institute Department of Electrical Power Engineering Fergana Uzbekistan

ISBN: (纸本)9798331508456

Smart traffic management of automobiles has been one of the utmost sought-after issues in the academic community due to the ever-increasing pace of urbanization and civilization over the last several centuries. Vehicle dissection, traffic density appraisal, and vehicle tracing are the three main components of smart traffic management. This problem becomes more difficult to resolve when there are occlusions, background clutter, and fluctuations in traffic density. In light of this need, we explore a deeper learning approach based on R-CNN s for faster vehicle segmentation in this study. There is adaptive backdrop modeling in the computational framework. It solves problems with lighting and shadows as well. The use of topological active net deformable models allows for segmentation that is more precise. The deformations mentioned can be accomplished with the aid of topological and stretched topological active nets. Minimizing energy allows for mesh deformation. Using a tweaked version of the stretched topological active net improves the segmentation accuracy to 98.3%. The investigational findings show that this framework is better than other methods. © 2025 IEEE.

关键词： Highway administration

来源：评论

学校读者我要写书评

暂无评论

Autonomous Search of Semantic Objects in Unknown Environments

arXiv

引用

arXiv 2023年

作者： Qian, Zhentian Fu, Jie Xiao, Jing Robotics Engineering Department Worcester Polytechnic Institute WorcesterMA United States Department of Electrical and Computer Engineering University of Florida GainesvilleFL United States

This paper addresses the problem of enabling a robot to search for a semantic object, i.e., an object with a semantic label, in an unknown and GPS-denied environment. For the robot in the unknown environment to detect and find the target semantic object, it must perform simultaneous localization and mapping (SLAM) at both geometric and semantic levels using its onboard sensors while planning and executing its motion based on the ever-updated SLAM results. In other words, the robot must be able to conduct simultaneous localization, semantic mapping, motion planning, and execution in real-time in the presence of sensing and motion uncertainty. This is an open problem as it combines semantic SLAM based on perception and real-time motion planning and execution under uncertainty. Moreover, the goals of the robot motion change on the fly depending on whether and how the robot can detect the target object. We propose a novel approach to tackle the problem, leveraging semantic SLAM, Bayesian Networks, Markov Decision Process, and Real-Time Dynamic Programming. The results in simulation and real experiments demonstrate the effectiveness and efficiency of our approach. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Virtual-Coordinate Based Sampling and Embedding for Machine Learning with Graph Data

Virtual-Coordinate Based Sampling and Embedding for Machine ...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Zheyi Qin Anura P. Jayasumana Randy Paffenroth Electrical and Computer Engineering Colorado State University Fort Collins USA Mathematical Sciences Computer Science and Data Science Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Graph embedding techniques remains the only alternative for Graph Neural Networks (GNNs) in machine learning for applications for which data in the form of graphs. GNNs, however, require substantial computational resources and are not able to provide certain advantages of conventional neural networks, such as transfer learning. The existing embedding based techniques, however, rely on random walk based strategies, which are not efficient in capturing the topology information, or use more structured strategies followed by feature engineering to achieve the required embedding. We propose VCNN (VirtualCoordinate based Neural Networks) technique that directly uses distances to an extremely small set (< 1 %) of random nodes (anchors) for network sampling and embedding, thus eliminating the feature engineering step. Experiments with two benchmark datasets show that a simple shallow neural network configuration using VC can achieve comparable performance to existing embedding-based techniques requiring deeper neural networks, thus also eliminating the need to experiment with multiple neural network configurations. This finding is particularly relevant for applications where computational efficiency is crucial. This research extends the machine learning toolbox for networks and data in the form of networks, highlighting the importance of strategic parameter use and model simplicity.

关键词： Network topology Social networking (online) Neural networks Transfer learning Machine learning Benchmark testing Predictive models Data models Topology Tuning

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Proactive Sensor Placement In Probabilistic Attack Graphs

Synthesis of Proactive Sensor Placement In Probabilistic Att...

引用

American Control Conference (ACC)

作者： Lening Li Haoxiang Ma Shuo Han Jie Fu Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA Department of Electrical & Computer Engineering University of Florida Gainesville FL USA Department of Electrical & Computer Engineering University of Illinois at Chicago Chicago IL USA

This paper studies the deployment of joint moving target defense (MTD) and deception against multi-stage cyber-attacks. Given the system equipped with MTD that randomizes between different configurations, we investigate how to allocate a bounded number of sensors in each configuration to optimize the probability of detecting the attack before the attacker achieves its objective. Specifically, two types of sensors are considered: intrusion detectors that are observable by the attacker and stealthy sensors that are not observable to the attacker. We propose a two-step optimization-based approach: Firstly, the defender allocates intrusion detectors assuming the attacker will best respond to evade detection. Secondly, the defender will allocate stealthy sensors, given the best response attack strategy computed in the first step, to further reduce the attacker’s chance of success. We illustrate the effectiveness of the proposed methods using a cyber defense example.

关键词：

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：