检索结果-内蒙古大学图书馆

OdCFU-Net for Brain Tumor Segmentation Based on MRI

OdCFU-Net for Brain Tumor Segmentation Based on MRI

2024 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, CIVEMSA 2024

作者： Wu, Shang Yang, Sijing Li, Boyue Yin, Shimin Zhu, Jianming Li, Shiyong Chen, Zhencheng Guilin University of Electronic Science and Technology School of Computer and Information Security China School of Electronic Engineering and Automation Guilin University of Electronic Technology Guilin China Key Laboratory of Biomedical Sensors and Intelligent Instruments Guangxi Colleges and Universities Guilin China Guangxi Engineering Technology Research Center of Human-Physiological Information Noninvasive Detection Guilin China School of Computer and Information Security Guilin University of Electronic Science and Technology China

ISBN: (纸本)9798350322996

In the field of medical image analysis, the accurate segmentation of brain tumors plays a crucial role in the diagnosis and treatment of brain-related diseases. This study aims to address key challenges in this domain, with a particular focus on improving feature extraction, information integration, and model generalization capabilities. By concurrently introducing multi-dimensional attention mechanisms in convolutional operations, a method has been developed to dynamically generate convolution kernels in spatial, input channel, and output channel dimensions. This approach optimizes the limitations of traditional static convolutional kernels, maintaining high-performance efficiency while reducing the model's parameter count. To overcome the deficiencies of traditional convolutional networks in capturing global information, channel and spatial attention mechanisms have been integrated between convolutional layers. This enhances adaptability and global information retrieval capabilities, allowing the model to dynamically adjust the weight of feature maps based on different task requirements. Leveraging the advantages of Vision Transformer in handling global information and addressing its limitations in capturing details and training on small datasets, the algorithm aligns and learns feature representations effectively by incorporating channel attention and normalizing attention weights within its multi-head attention. When applied to the BraTs2021 multi-modal brain tumor image database, the proposed algorithm accurately delineates brain tumor regions, demonstrating excellent performance. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Interpretable Predictions for Crime Categories Using Log Loss Approach for Imbalanced Target Feature 2

Interpretable Predictions for Crime Categories Using Log Los...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Manasa, A. Sen, Snigdha Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Information Technology Manipal India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383652

Crime indicates activities that infringe laws and regulations constituted by a governing authority. These wrongdoings can range from minor aberrations such as petty theft to more serious crimes like assault, robbery, or murder. Understanding crime patterns, causes, and trends is important for creating effective law enforcement strategies and enforcing policies that facilitate to a risk-free and stable society. This paper explores the interpretability of crime category predictions generated by XGBoost and Random Forest models on San Francisco crime data ranging 12 years. Notably, in comparison to other models, such as k-Nearest Neighbors (KNN), Stochastic Gradient Descent(SGD) and Naïve Bayes, our XGBoost and Random Forest models featured superior predictive excellence, Obtaining competitive log-loss scores of 2.277761 and 2.283956, respectively, to augment interpretability we have employed Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) to clarify the decision-making processes of these models. This interpretability analysis would definitely add a deeper insight into the contributing factors of model's predictive behavior towards crime rate prediction. Additionally, we have dealt with imbalanced target feature as well. In comparison to existing research in the field, our work stands out by introducing advanced interpretability techniques, LIME and SHAP, enhancing transparency in crime prediction models. This innovative approach surpasses traditional methods, providing a more comprehensive understanding of crime dynamics and achieving superior predictive excellence. Innovation is introduced through the incorporation of advanced interpretability techniques, specifically Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models 41

RoboMP2: A Robotic Multimodal Perception-Planning Framework ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lv, Qi Li, Hao Deng, Xiang Shao, Rui Wang, Michael Yu Nie, Liqiang School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Engineering Great Bay University China School of Computing and Information Technology Great Bay University China

Multimodal Large Language Models (MLLMs) have shown impressive reasoning abilities and general intelligence in various domains. It inspires researchers to train end-to-end MLLMs or utilize large models to generate policies with human-selected prompts for embodied agents. However, these methods exhibit limited generalization capabilities on unseen tasks or scenarios, and overlook the multimodal environment information which is critical for robots to make decisions. In this paper, we introduce a novel Robotic Multimodal Perception-Planning (RoboMP2) framework for robotic manipulation which consists of a Goal-Conditioned Multimodal Preceptor (GCMP) and a Retrieval-Augmented Multimodal Planner (RAMP). Specially, GCMP captures environment states by employing a tailored MLLMs for embodied agents with the abilities of semantic reasoning and localization. RAMP utilizes coarse-to-fine retrieval method to find the k most-relevant policies as in-context demonstrations to enhance the planner. Extensive experiments demonstrate the superiority of RoboMP2 on both VIMA benchmark and real-world tasks, with around 10% improvement over the baselines. Copyright 2024 by the author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Enabled Cooperative Cluster-Based Data Collection for Unmanned Aerial Vehicles

引用

computers, Materials & Continua 2022年第11期73卷 3351-3365页

作者： R.Rajender C.S.S.Anupama G.Jose Moses E.Laxmi Lydia Seifedine Kadry Sangsoon Lim Department of Computer Science Engineering Lendi Institute of Engineering&TechnologyDenkada535005India Department of Electronics&Instrumentation Engineering V.R.Siddhartha Engineering CollegeVijayawada520007India Department of Computer Science Engineering Malla Reddy Engineering College500100India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansand4612Norway Department of Computer Engineering Sungkyul UniversityAnyang14097Korea

In recent times,sixth generation(6G)communication technologies have become a hot research topic because of maximum throughput and low delay services for mobile *** encompasses several heterogeneous resource and communication standard in ensuring incessant availability of *** the same time,the development of 6G enables the Unmanned Aerial Vehicles(UAVs)in offering cost and time-efficient solution to several applications like healthcare,surveillance,disaster management,*** UAV networks,energy efficiency and data collection are considered the major process for high quality network *** these procedures are found to be challenging because of maximum mobility,unstable links,dynamic topology,and energy restricted *** issues are solved by the use of artificial intelligence(AI)and energy efficient clustering techniques for UAVs in the 6G *** this inspiration,this work designs an artificial intelligence enabled cooperative cluster-based data collection technique for unmanned aerial vehicles(AECCDC-UAV)in 6G *** proposed AECCDC-UAV technique purposes for dividing the UAV network as to different clusters and allocate a cluster head(CH)to each cluster in such a way that the energy consumption(ECM)gets *** presented AECCDC-UAV technique involves a quasi-oppositional shuffled shepherd optimization(QOSSO)algorithm for selecting the CHs and construct *** QOSSO algorithm derives a fitness function involving three input parameters residual energy of UAVs,distance to neighboring UAVs,and degree of *** performance of the AECCDC-UAV technique is validated in many aspects and the obtained experimental values demonstration promising results over the recent state of art methods.

关键词： 6G unmanned aerial vehicles resource allocation energy efficiency artificial intelligence clustering data collection

来源：评论

学校读者我要写书评

暂无评论

Biometric Web based Vote Cast using Blocks 3

Biometric Web based Vote Cast using Blocks

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Abinaya, M. Priya, P.Kaviya Mirza, Mohsina Anbumani, A. Sathya, R. Sethuram, M. Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India P.A College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Global College of Engineering and Technology Department of Electrical and Electronic Engineering India Paavai College of Engineering Department of Computer Science and Engineering Coimbatore India Kongunadu College of Engineering and Technology Department of Information Technology Trichy India Hindusthan College of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798350343632

Web based vote casting is a form of voting in which the voter is able to cast their votes through any web portal wherever in the world. In the Biometric method, voter can cast the votes using their finger impression. In this method the voter can selects the login portal which is particularly designed for an election commission. Each person needs to register the election commission website, using the registration details substantiate themselves before the machine authorize the user to sight the ballot visible on the screen. The voter is then allowed to pick their selected candidate and then cast the votes which would be passed to the election server for the refining process. In 'E-Voting' method a voter can cast their votes through online without any difficulty. If all the entries provided by the user are precise user can login the system using the user ID and password voter can cast their votes through online wherever in the world. If an information given by the voter is not correct then the entry will be discarded and it shows the error message. This technique is mainly implemented to reduce the difficulty of the election commission and voter. It is a user-friendly approach, also it avoids the unwanted crowds during the election period. Here, this study has used immutable ledger technology that is a blockchain based application, which provides the security and also increase the efficiency of the voting process. © 2023 IEEE.

关键词： Blockchain Electronic Voting (E-Voting) Personnel computer (PC)

来源：评论

学校读者我要写书评

暂无评论

An Advanced Tactile-Haptic Controller for Smart Home 32nd

An Advanced Tactile-Haptic Controller for Smart Home

引用

32nd International Conference on Organization and technology of Maintenance, OTO 2023

作者： Radić, Miloš Keser, Tomislav Blažević, Damir Faculty of Electrical Engineering Computer Science and Information Technology Osijek University of Osijek Kneza Trpimira 2b Osijek31000 Croatia

ISBN: (纸本)9783031514937

A smart home philosophy strongly relies on a technical principle of automatization almost every aspect of today’s way of living. Sole automation of does not only manage system processes in household, or living environment in general, but all adjacent systems and corresponding subsystems which helps to maintain system-in-whole in operational state. From control of environmental temperature, air conditioning, lighting, utility control, etc., all existing "smart" systems predominantly control actuation part of smart home. Very miniscule "smart" systems do manage and serve human-machine interaction part of it and, if are made "smart", they rely on solutions that utilizes some sort of existing ICT technologies that are mainly optimized for communication and visual presentation, not for in-situ smart home interaction. This paper deals with the problem of development of a tactile-haptic solution for control of smart home specific subsystem and that utilize IoT platform, giving feel and user experience similar to traditional one in form of an advanced switch with regulation ability. Tactile commanding with haptic feedback is presented and applied in smart home temperature regulation. Finally, an IoT platform solution is developed, tactile-haptic relation investigated with optimal solution established, and its functionality is verified as well as is proven in real time environment. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Image Segmentation in the Marine Atmosphere for Time-Sensitive Contextualisation using Convolutional Long Short-Term Memory 2

Enhancing Image Segmentation in the Marine Atmosphere for Ti...

引用

2nd International Conference on Advances in Computation, Communication and information technology, ICAICCIT 2024

作者： Reethika, A. Rajeshwari, R. Vijayalakshmi, S. Malathy, S. Gnanasaravanan, S. Suresh Kumar, M. Department of Electronics and Communication Engineering Sri Ramakrishna Engineering College Coimbatore India Department of Computer Science and Engineering CMR Institute of Technology Bengaluru India Department of Information Technolog KPR Institute of Engineering and Technology Coimbatore India Department of Biomedical Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Information Technology Sri Ranganathar Institute of Engineering and Technology Coimbatore India

ISBN: (纸本)9798331541217

The work investigates autonomous surface vehicle obstacle avoidance and detection using computer vision techniques. It recognizes boundaries in marine environments by using the temporal context from video feeds from unmanned surface vehicles. The study shows how successful LSTM cells are in the CNN topologies that are currently in use, emphasizing how they might perform better. Nevertheless, datasets and network training techniques are not perfect. The work also uses a benchmarking approach to compare new network configurations. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Different Optimization Techniques in AlexNet for Plant Disease Classification: SGD, Adadelta, ASGD and Adagrad 5

A Comparison of Different Optimization Techniques in AlexNet...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Ponnila, P. Bazila Banu, A. Bannari Amman Institute of Technology Department of Information Technology Erode Tamilnadu Sathyamangalam India Kpr Institute of Engineering and Technology Department of Computer Science and Business Systems Tamilnadu Coimbatore India

ISBN: (纸本)9798331504403

Plant diseases are a biggest challenge for the farmers. Agriculture relies heavily on its production, and diagnosis of plant disease in an accurate manner will help in identification of the appropriate disease. If correct identification was not performed, there might be a significant financial loss that could have an impact on both farmers and the national economy. For resolving this issue, the AlexNet was employed, a convolutional neural network method. In this research, AlexNet is used to classify the diseases occurring in chilli, cauliflower and sunflower. This AlexNet model, with Stochastic Gradient Descent(SGD) algorithm optimization techniques had achieved 82% accuracy for the overall classification of the test images of chilli plant, 98% accuracy for the overall classification of the test images of cauliflower plant and 91% accuracy for the overall classification of the test images of sunflower plant;with Adadelta optimization 86%, 99% and 93% accuracy was achieved for the overall classification of the test pictures of chilli plant, cauliflower plant and sunflower plant respectively. After using the Asynchronous Stochastic Gradient(ASGD) optimization with AlexNet model, the accuracy obtained are 88% for the test images of chilli plant, 98% for the test images of cauliflower plant and 91% for the test images of sunflower plant;and finally, AdaGrad optimization with AlexNet achieved accuracy of 80% for the test images of chilli plant, 9 8% for the test images of cauliflower plant and 93% for the test images of sunflower plant. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Less Carbon Footprint in Edge Computing by Joint Task Offloading and Energy Sharing

IEEE Networking Letters

引用

IEEE Networking Letters 2023年第4期5卷 245-249页

作者： Yu, Zhanwei Zhao, Yi Deng, Tao You, Lei Yuan, Di Uppsala University Department of Information Technology Uppsala751 05 Sweden Soochow University School of Computer Science and Technology Suzhou215006 China Technical University of Denmark Department of Engineering Technology Ballerup2750 Denmark

We address reducing carbon footprint (CF) in the context of edge computing. The carbon intensity of electricity supply largely varies spatially as well as temporally. We consider optimal task scheduling and offloading, as well as battery charging to minimize the total CF. We formulate this optimization problem as a mixed integer linear programming model. However, we demonstrate that, via a graph-based reformulation, the problem can be cast as a minimum-cost flow problem, and global optimum can be admitted in polynomial time. Numerical results using real-world data show that optimization can reduce up to 83.3% of the total CF. © 2019 IEEE.

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based Smart Traffic Control System 2nd

Artificial Intelligence-Based Smart Traffic Control System

引用

2nd International Conference on Innovations in Data Analytics, ICIDA 2023

作者： Tiwari, Amit Kumar Pandey, Raghvendra Kumar Singh, Saharsh Tiwari, Gaurav Kumar, Ambuj Mishra, Prateek Department of Computer Science and Engineering United Institute of Technology Uttar Pradesh Prayagraj211008 India Department of Information Technology United Institute of Technology Uttar Pradesh Prayagraj211008 India

ISBN: (纸本)9789819749270

The fundamental aim of this research paper is to make Machine Learning-Based Smart Traffic Control System. The traffic light timer timing changes on detecting the traffic density count at each crossroad. Traffic congestion is most common problem in the major highly populated cities across the world, and it has made traveling very tough from one place to other. Traditional traffic lights run on the fixed timer concept assigned to each side of the road which can’t be changed as per changing vehicles density. In some situation lane with higher density demands longer green time as compared to the basic fixed time. The object or vehicles in the traffic signal are detected using cameras then processed into a simulator then its threshold is assumed on the basis of vehicle count in respect to each lane and compute the total number of vehicles present in the given area. After computing the total number of vehicles the system will acknowledge that which side the density of vehicles is high and based on the density the signals will be allotted for a particular side. Traffic mishaps or accidents are very common at overcast, rainy day, night when no street lights are available, foggy day and many others when there is minimum visibility. Traffic light control is one of the severe technical hazards of the Major cities in almost every country across the world. This is due to exponential rate of growth in the number of vehicles. In respect to minimize the time, a system has to be come up with the technology of artificial intelligence which makes a machine to think themselves. This modern developed technology will help the traffic light to switch the traffic signals from green to red based upon traffic density. This paper is related with the enhancement of traffic control system using machine learning which will be base on the different density on each lane. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Traffic congestion

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：