检索结果-内蒙古大学图书馆

24th International Conference on control Systems and computer science, CSCS 2023

作者： Ciolofan, Sorin N. Dragoicea, Monica Popeanga, Daniel-Catalin Politehnica University of Bucharest Department of Computer Science Bucharest Romania Politehnica University of Bucharest Department of Automatic Control and Systems Engineering Bucharest Romania

ISBN: (纸本)9798350313390

An important aspect related to the effects of agricultural activities on the environment is represented by the nutrient loss in water and air (specifically nitrogen). The interactions between catchments hydrological processes, management of farm activities, climate changes and nitrogen losses constitute a complex phenomenon yet not well understood, being an important concern from the sustainable agriculture perspective. Nitrogen can be lost with water as leaching or runoff, or as gas as ammonia volatilization. Nitrous oxide (N2O) is particularly problematic because it is also a powerful greenhouse gas. The goal of the current article is to present innovative digital techniques to advance in understanding of this phenomena through an Information System that integrates Artificial Intelligence techniques such as Semantic Technologies and Machine Learning (ML) into Cyber-Physical Systems (CPS) to support smart farming and sustainable agriculture. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON PATH PLANNING ALGORITHM OF TAKEAWAY ROBOTS FOR TERMINAL DELIVERY 2

RESEARCH ON PATH PLANNING ALGORITHM OF TAKEAWAY ROBOTS FOR T...

引用

2nd International Conference on Mechatronic Automation and Electrical Engineering, ICMAEE 2024

作者： Wan, Yuhang Faculty of Automatic Control Electronics and Computer Science Silesian Technical University Gliwice44-100 Poland

ISBN: (纸本)9781837242672

Takeaway delivery has become an important part of urban life. However, terminal deliveries are often blocked by security measures that often prevent them from arriving on time. Designing a takeaway delivery robot can solve this problem to a large extent. In this paper, path planning algorithm level of designing a takeaway robot is researched. In this paper, the research is carried out by closely focusing on the current stage of the path planning algorithm related difficulties. Three typical algorithms are selected for simulation testing within the scope of graph search algorithms. These three algorithms are Dijkstra algorithm, A∗ algorithm and rapidly-exploring random tree (RRT) algorithm. The final comparison is made with the simulation test results. And to find the optimal path planning algorithm for takeaway delivery robots within the range of graph search algorithms. This paper provides a reference for the path planning algorithm level of takeaway delivery robot design. At the same time, it helps to improve the delivery service of takeaway terminal. © The Institution of Engineering & Technology 2024.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Optimizing a Convolutional Neural Network using Particle Swarm Optimization 14

Optimizing a Convolutional Neural Network using Particle Swa...

引用

14th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2022

作者： Mihai, Alexandru-Cosmin Iancu, David-Traian Automatic Control and Computer Science University Politehnica of Bucharest Bucharest Romania

ISBN: (数字)9781665495356

ISBN: (纸本)9781665495356

This study presents the application of the Particle Swarm Optimization (PSO) algorithm, a swarm algorithm which is based on the particle movement, to optimize the parameters of a Deep Neural Network (DNN), namely an architecture based on Convolutional Neural Networks (CNN). The model is optimized with respect to the image classification task on the MNIST dataset, consisting of images of handwritten digits. The study presents the results of training the model using different PSO hyperparameters and also compares the obtained performances with those obtained when training the model using gradient based optimizers such as Stochastic Gradient Descend (SGD) and Adam. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Skin Lesions from Dermatoscopic Images Using Convolutional Neural Networks 24

Classification of Skin Lesions from Dermatoscopic Images Usi...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Oniga, Maria Sultana, Alina-Elena Popescu, Dan Merezeanu, Daniel-Marian Ichim, Loretta University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania University Politehnica of Bucharest Faculty of Electronics Telecommunications and Information Technology Bucharest Romania 'St. S. Nicolau' Institute of Virology Bucharest Romania

ISBN: (纸本)9798350313390

Skin cancer is one of the most common types of cancer, and it is caused by a variety of dermatological conditions. Identifying abnormalities from skin images is an important pre-diagnostic step to assist physicians in determining the patient's condition. Thus, to aid dermatologists in the diagnosis process, we proposed five CNN-based classification approaches namely ResNet-101, DenseNet-121, GoogLeNet, VGG16, and MobileNetV2 architectures on which the transfer learning process was applied. The HAM10000-N database consisting of 7,120 images, which was obtained from the original HAM10000 dataset through an augmentation process, was used to train the proposed methods. Moreover, the images from the HAM10000-N were pre-processed by removing hair with the DullRazor algorithm. To evaluate and compare the performance of all networks five metrics were calculated: accuracy, precision, recall, and Fl-score. The best results for the seven-class classification of the HAM10000-N dataset were obtained for DenseNet-121 architecture with 87% accuracy, 0.871 precision, 0.87 recall and 0.872 F1-score. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models

arXiv

引用

arXiv 2024年

作者： Catruna, Andy Cosma, Adrian Radoi, Emilian Faculty of Automatic Control and Computer Science POLITEHNICA Bucharest Romania

Gait, an unobtrusive biometric, is valued for its capability to identify individuals at a distance, across external outfits and environmental conditions. This study challenges the prevailing assumption that vision-based gait recognition, in particular skeleton-based gait recognition, relies primarily on motion patterns, revealing a significant role of the implicit anthropometric information encoded in the walking sequence. We show through a comparative analysis that removing height information leads to notable performance degradation across three models and two benchmarks (CASIA-B and GREW). Furthermore, we propose a spatial transformer model processing individual poses, disregarding any temporal information, which achieves unreasonably good accuracy, emphasizing the bias towards appearance information and indicating spurious correlations in existing benchmarks. These findings underscore the need for a nuanced understanding of the interplay between motion and appearance in vision-based gait recognition, prompting a reevaluation of the methodological assumptions in this field. Our experiments indicate that"in-the-wild" datasets are less prone to spurious correlations, prompting the need for more diverse and large scale datasets for advancing the field. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild

arXiv

引用

arXiv 2024年

作者： Catruna, Andy Cosma, Adrian Radoi, Emilian Faculty of Automatic Control and Computer Science POLITEHNICA Bucharest Romania

Gaze estimation, the task of predicting where an individual is looking, is a critical task with direct applications in areas such as human-computer interaction and virtual reality. Estimating the direction of looking in unconstrained environments is difficult, due to the many factors that can obscure the face and eye regions. In this work we propose CrossGaze, a strong baseline for gaze estimation, that leverages recent developments in computer vision architectures and attention-based modules. Unlike previous approaches, our method does not require a specialized architecture, utilizing already established models that we integrate in our architecture and adapt for the task of 3D gaze estimation. This approach allows for seamless updates to the architecture as any module can be replaced with more powerful feature extractors. On the Gaze360 benchmark, our model surpasses several state-of-the-art methods, achieving a mean angular error of 9.94◦. Our proposed model serves as a strong foundation for future research and development in gaze estimation, paving the way for practical and accurate gaze prediction in real-world scenarios. © 2024, CC BY-NC-ND.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Cat Swarm Optimization for Solving the N-Queens Problem 14

Cat Swarm Optimization for Solving the N-Queens Problem

引用

14th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2022

作者： Clara, Barbu Iancu, David-Traian Automatic Control and Computer Science University Politehnica of Bucharest Bucharest Romania

ISBN: (数字)9781665495356

ISBN: (纸本)9781665495356

Many swarm intelligence algorithms study the behavior of animals and make animal-based systems for solving various tasks. Cat swarm optimization (CSO) is a swarm intelligence algorithm which was originally inspired by the resting and tracking behaviors observed naturally in cats. The N-Queens problem is a classical and complex constraint satisfaction problem which has been used as a benchmark for testing AI techniques for years. This paper aims to adapt the original CSO algorithm to the N-Queens problem by replacing the continuous addition/subtraction operations with swapping operations. The results report very fast convergence at smaller numbers of queens and point towards quicker convergence than similar work at larger numbers of queens, with improvements still needed for perfecting the algorithm. © 2022 IEEE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Decentralized Machine Learning for Face Recognition 22

Decentralized Machine Learning for Face Recognition

引用

22nd International Symposium on Parallel and Distributed Computing, ISPDC 2023

作者： Branescu, Ioana Ciobanu, Radu-Ioan Dobre, Ciprian Mavromoustakis, Constandinos University Politehnica of Bucharest Faculty of Automatic Control and Computers Romania National Institute for Research and Development in Informatics Bucharest Romania University of Nicosia Department of Computer Science Cyprus

ISBN: (纸本)9798350341270

As the fields of machine learning and computer vision are developing, facial recognition systems are becoming increasingly popular and are slowly being widely used in various fields like security, surveillance and medicine. This paper presents the design and development of a facial recognition solution that works in a distributed context, given that the devices used for capturing the images do not have the ability to train models capable of achieving good enough accuracy on large amounts of data. Thus, a method is presented in which the detection of human faces and the characteristics extraction are done locally based on a pre-trained FaceNet model. These characteristics are sent to a strong processing unit where a global model is trained and then transferred back to the clients, where it can be used for recognition. Through experimental evaluation, we show that our solution is efficient and exhibits high accuracy values. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

How capable are state-of-the-art language models to cope with sarcasm? 24

How capable are state-of-the-art language models to cope wit...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Baroiu, Alexandru -Costin Trausan-Matu, Stefan Politehnica University of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania Romanian Academy Research Institute for Artificial Intelligence 'Mihai Drǎganescu' Academy of Romanian Scientists Bucharest Romania

ISBN: (纸本)9798350313390

Sarcasm detection has established itself as one of the more difficult Natural Language Processing tasks, due to the complex nature of sarcasm. This paper aims to benchmark the performance of state-of-the-art models like BERT, RoBERTa, ALBERT and GPT-3 when faced with this task. The dataset selected is MUStARD, which has increased in popularity in recent years, especially for multimodal tasks, and is one of the most qualitative and data rich dataset. An untuned GPT-3 based model was selected as the baseline and all the other models were fine-tuned using the textual data present in MUStARD, mainly the context and utterance information. The best performer was found to be the GPT-3 fine-tuned model, with an F1 score of 77. This is in line with the reported feats of GPT-3 based models that have popularized in recent months and reaffirms the superiority of GPT-3. Future avenues of research are then presented and explored, and the conclusions are drawn. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement for Facial Landmark Detection 21

Image Enhancement for Facial Landmark Detection

引用

21st RoEduNet Conference on Networking in Education and Research, RoEduNet 2022

作者： Ciuntu, Victor Chiornita, Traian Boiangiu, Costin-Anton Tarba, Nicolae Voncila, Mihai-Lucian Rosner, Daniel Politehnica University Faculty of Automatic Control and Computers Computer Science and Engineering Department Bucharest Romania

ISBN: (数字)9781665455282

ISBN: (纸本)9781665455282

Facial landmark detection (FLD) is a field of study in computer vision that specializes in detecting and tracking key points from human faces. There are many applications, such as detecting a human's head pose (position and rotation), tracking whether drivers are paying attention or not, applying augmented reality, etc. This paper proposes to evaluate and decide what are the optimal techniques of image enhancement that can be used to improve different algorithms of FLD. After proposing different pipelines of contrast enhancement and grayscale conversion to enhance the image before applying the FLD algorithm, the results show that the performance will not increase drastically if an image enhancement pipeline is used, but for the reason that this step will not consume a lot of time in the process of detection, it is a step worth considering. © 2022 IEEE.

关键词： Face recognition

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：