检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Sarlakifar, Faezeh Asl, Mohammadreza Mohammadzadeh Khaledi, Sajjad Rezvani Salimi-Badr, Armin Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran Faculty of Electrical Engineering Shahid Beheshti University Tehran Iran

Traditional Long Short-Term Memory (LSTM) networks are effective for handling sequential data but have limitations such as gradient vanishing and difficulty in capturing long-term dependencies, which can impact their performance in dynamic and risky environments like stock trading. To address these limitations, this study explores the usage of the newly introduced Extended Long Short-Term Memory (xLSTM) network in combination with a deep reinforcement learning (DRL) approach for automated stock trading. Our proposed method utilizes xLSTM networks in both actor and critic components, enabling effective handling of time series data and dynamic market environment. Proximal Policy Optimization (PPO), with its ability to balance exploration and exploitation, is employed to optimize the trading strategy. Experiments were conducted using financial data from major tech companies over a comprehensive timeline, demonstrating that the xLSTM-based model outperforms LSTM-based methods in key trading evaluation metrics, including cumulative return, average profitability per trade, max earning rate, maximum pullback, and Sharpe ratio. These findings mark the potential of xLSTM for enhancing DRL-based stock trading systems. © 2025, CC BY-NC-ND.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Ensemble Feature Selection for Multi-label Classification: A Rank Aggregation Method 1

引用

International Conference on Cyber Security, Privacy and Networking, ICSPN 2022

作者： Hashemi, Amin Dowlatshahi, Mohammad Bagher Rafsanjani, Marjan Kuchaki Hsu, Ching-Hsien Department of Computer Engineering Faculty of Engineering Lorestan University Khorramabad Iran Department of Computer Science Shahid Bahonar University of Kerman Kerman Iran College of Information and Electrical Engineering Asia University Taichung Taiwan

ISBN: (数字)9783031220180

ISBN: (纸本)9783031220173

Multi-label classification is an important task in machine learning applications. However, today, these methods have more challenges due to high-dimensional data. Existing methods in the literature have not yet reached an acceptable performance, and as the number of labels in the dataset increases, their performance becomes weaker. Thus providing effective feature selection methods is necessary and is suitable for all data. Ensemble feature selection is also a new approach based on combining the results of several feature selection methods. Ensemble approaches have been used in many single-label applications and have provided adequate results. However, this technique is less considered in multi-label feature selection. For this purpose, in this article, we have presented a method based on an ensemble of feature selection methods. This paper presents an ensemble multi-label feature method using rank aggregation algorithms. Three filter rankers with different structures are utilized to obtain the final ranking. This rank aggregation process is treated like an election where the rankers are assumed to be the voters, and the features are the alternatives. The Weighted Borda Count (WBC) method conducts the election process. Finally, the performance and results obtained by the proposed method are compared with the nine filter-based algorithms used based on six multi-label datasets. Most of the selected datasets have a high number of class labels, and the proposed method has recorded the best classification performance in all these datasets. Also, the results show that this method is not well affected by the adverse effects of the algorithms used. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Autonomous Quadrotor Path Planning Through Dueling Double Deep Recurrent Q-Learning with Monocular Depth Estimation

SSRN

引用

SSRN 2024年

作者： Khojasteh, Mahdi Shahbazi Salimi-Badr, Armin Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

Autonomous navigation is a formidable challenge for Unmanned Aerial Vehicles (UAVs) operating in dense and dynamic environments. Traditional path planning and obstacle avoidance algorithms have shortcomings as the UAVs have limited load, energy, and computational capacity. This paper proposes a path-planning approach based on deep reinforcement learning for a quadcopter drone equipped with a monocular camera. The proposed method adopts a two-stage structure comprising a depth estimation and a navigation decision-making module. The depth estimation module uses a supervised pre-trained convolutional neural network, and the decision-making module uses a dueling double deep recurrent Q-learning to address decisions in high-dimensional and partially observable state spaces. The encoder of the depth estimation network learns to infer image depth from visual cues in a self-supervised manner, with the output serving as an input for the decision-making module. To accelerate training and reduce meaningless explorations, we propose the Insight memory pool alongside the regular memory pool to provide a rapid boost in learning by prioritizing early sampling from the Insight pool and relying on the agent’s experiences later, controlled through an adaptive sampling strategy. In addition, we postpone exploration until the agent accumulates sufficient knowledge from the insightful data. Upon acquisition, we enable exploration by employing the Boltzmann behavior policy to guide targeted exploration, following the more accurate Q-values. The process of populating the Insight memory pool involves using samples generated by the classical Bug2 algorithm and the experiences of a previously trained agent before the training begins. To validate the performance of the proposed approach, we applied the trained model in three large-scale, distinct, and realistic 3D environments simulated using AirSim: a dynamic city street, an obstacle-laden downtown, and a static pillar world, each presenting

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning Approach Combining Technical and Fundamental Analyses with a Large Language Model for Stock Trading

A Deep Reinforcement Learning Approach Combining Technical a...

引用

International eConference on computer and Knowledge engineering (ICCKE)

作者： Mahan Veisi Sadra Berangi Mahdi Shahbazi Khojasteh Armin Salimi-Badr Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

ISBN: (数字)9798331511272

ISBN: (纸本)9798331511289

Stock trading strategies are essential for successful investment, yet developing a profitable approach is challenging due to the stock market's complex and dynamic nature. This paper introduces a Deep Reinforcement Learning (DRL) framework for automated stock trading that integrates technical and fundamental analyses with a large language model. We model the trading environment as a Partially Observable Markov Decision Process (POMDP) and propose a hybrid architecture that combines Long Short-Term Memory (LSTM) with Proximal Policy Optimization (PPO) to capture intricate temporal patterns in stock data and make informed trading decisions. Our model in-corporates market indicators alongside financial news headlines, processed through the FinBERT language model, to create a rich state representation. Additionally, we integrate a drawdown penalty into the reward function to further improve portfolio stability. Evaluations on a dataset of 30 U.S. stocks demonstrate that our model outperforms benchmarks in cumulative return, maximum earning rate, and Sharpe ratio, indicating that the hybrid approach yields more resilient and profitable trading strategies than existing methods.

关键词： Social networking (online) Large language models Computational modeling Soft sensors Deep reinforcement learning Data models Stability analysis Long short term memory Portfolios Optimization

来源：评论

学校读者我要写书评

暂无评论

Cluster Sampling: A Cluster-Driven Sampling Strategy for Deep Metric Learning

Cluster Sampling: A Cluster-Driven Sampling Strategy for Dee...

引用

International eConference on computer and Knowledge engineering (ICCKE)

作者： Hamideh Rafiee Ahmad Ali Abin Seyed Soroush Majd Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

ISBN: (数字)9798331511272

ISBN: (纸本)9798331511289

Deep metric learning has gained significant attention recently due to its promising performance in image retrieval, face recognition, and clustering tasks. Deep metric learning algorithms map the original data from the initial feature space to a new embedded space by learning a mapping function, where the discriminative power of the samples is increased. Sampling strategies are a critical aspect of deep metric learning algorithms, as they determine the choice of training samples that shape the network's learning process. This research introduces a novel sampling approach designed to optimize this selection for improved model performance. Given the high dimensionality of embedded spaces, choosing a sampling strategy is critical for enhancing the quality of learned representations and improving model performance. However, existing sampling methods often face significant challenges, such as slow convergence and the tendency to get trapped in suboptimal local minima. To address these challenges, this research proposes a novel sampling approach that leverages the clustering of sample representations within training batches to identify and select the most informative samples for effective training. This approach ensures a more dynamic learning process by clustering data based on shared features and selecting samples both within clusters and between related clusters. The selected samples enable the model to better learn the underlying data structure, thereby enhancing the discriminative power and robustness of the learned metrics. The effectiveness of the proposed approach is validated through empirical evaluations on the cars196 dataset, where it outperforms existing sampling methods.

关键词： Measurement Training Knowledge engineering Shape Face recognition Image retrieval Clustering algorithms Sampling methods Extraterrestrial measurements Robustness

来源：评论

学校读者我要写书评

暂无评论

Integrating Innovative Pedagogies in engineering: The Impact of Temperature on PV Cells 10

Integrating Innovative Pedagogies in Engineering: The Impact...

引用

10th International Conference on Control, Instrumentation and Automation, ICCIA 2024

作者： Samadani, Mehraneh Moradi, Elahe Gavagsaz-Ghoachani, Roghayeh Islamic Azad University Science and Research Branch Environmental Science and Engineering Department Tehran Iran Shahre Rey Branch Department of Electrical and Computer Engineering Tehran Iran Shahid Beheshti University Faculty of Mechanical and Energy Engineering Renewable Energy Engineering Department Tehran Iran

ISBN: (纸本)9798331509972

This paper explores the impact of temperature on photovoltaic (PV) cell performance, emphasizing the critical role of innovative teaching methods in engineering education. By integrating illustrative representations and analogies, such as the popcorn analogy, complex concepts related to solar energy, and PV cell efficiency are made accessible. The study examines key factors, like the Shockley five-parameter model and the effects of environmental conditions on PV cell efficiency, highlighting how higher temperatures reduce open-circuit voltage (VOC) and overall power output. Using visual aids and storytelling techniques, aims to enhance student understanding and retention of these intricate topics. The findings underscore the importance of educational strategies that foster deeper comprehension and critical thinking, ultimately preparing future engineers to contribute effectively to sustainable energy solutions. This approach not only aids in better grasping the technical aspects but also cultivates a sense of environmental responsibility among students. © 2024 IEEE.

关键词： Cell engineering

来源：评论

学校读者我要写书评

暂无评论

Integrative Deep Learning Framework for Parkinson's Disease Early Detection using Gait Cycle Data Measured by Wearable Sensors: A CNN-GRU-GNN Approach

arXiv

引用

arXiv 2024年

作者： Rashnu, Alireza Salimi-Badr, Armin Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

Efficient early diagnosis is paramount in addressing the complexities of Parkinson's disease because timely intervention can substantially mitigate symptom progression and improve patient outcomes. In this paper, we present a pioneering deep learning architecture tailored for the binary classification of subjects, utilizing gait cycle datasets to facilitate early detection of Parkinson's disease. Our model harnesses the power of 1D-Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Graph Neural Network (GNN) layers, synergistically capturing temporal dynamics and spatial relationships within the data. In this work, 16 wearable sensors located at the end of subjects’ shoes for measuring the vertical Ground Reaction Force (vGRF) are considered as the vertices of a graph, their adjacencies are modeled as edges of this graph, and finally, the measured data of each sensor is considered as the feature vector of its corresponding vertex. Therefore, The GNN layers can extract the relations among these sensors by learning proper representations. Regarding the dynamic nature of these measurements, GRU and CNN are used to analyze them spatially and temporally and map them to an embedding space. Remarkably, our proposed model achieves exceptional performance metrics, boasting accuracy, precision, recall, and F1 score values of 99.51%, 99.57%, 99.71%, and 99.64%, respectively. © 2024, CC BY-NC-ND.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Model Evaluation and Anomaly Detection in Temporal Complex Networks using Deep Learning Methods

arXiv

引用

arXiv 2024年

作者： Rashnu, Alireza Aliakbary, Sadegh Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

Modeling complex networks allows us to analyze the characteristics and discover the basic mechanisms governing phenomena such as disease outbreaks, information diffusion, transportation efficiency, social influence, and even human brain function. Consequently, various network generative models (called temporal network models) have been presented to model how the network topologies evolve dynamically over time. Temporal network models face the challenge of results evaluation because common evaluation methods are appropriate only for static networks. This paper proposes an automatic approach based on deep learning to handle this issue. In addition to an evaluation method, the proposed method can also be used for anomaly detection in evolving networks. The proposed method has been evaluated on five different datasets, and the evaluations show that it outperforms the alternative methods based on the error rate measure in different datasets. © 2024, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

An All-in-one Approach for Accelerated Cardiac MRI Reconstruction

arXiv

引用

arXiv 2024年

作者： Hamedani, Kian Anvari Razizadeh, Narges Nabavi, Shahabedin Moghaddam, Mohsen Ebrahimi Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

Cardiovascular magnetic resonance (CMR) imaging is the gold standard for diagnosing several heart diseases due to its non-invasive nature and proper contrast. MR imaging is time-consuming because of signal acquisition and image formation issues. Prolonging the imaging process can result in the appearance of artefacts in the final image, which can affect the diagnosis. It is possible to speed up CMR imaging using image reconstruction based on deep learning. For this purpose, the high-quality clinical interpretable images can be reconstructed by acquiring highly undersampled k-space data, that is only partially filled, and using a deep learning model. In this study, we proposed a stepwise reconstruction approach based on the Patch-GAN structure for highly undersampled k-space data compatible with the multi-contrast nature, various anatomical views and trajectories of CMR imaging. The proposed approach was validated using the CMRxRecon2024 challenge dataset and outperformed previous studies. The structural similarity index measure (SSIM) values for the first and second tasks of the challenge are 99.07 and 97.99, respectively. This approach can accelerate CMR imaging to obtain high-quality images, more accurate diagnosis and a pleasant patient experience. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Decisions of Goalkeeper and Kicker Players in the RoboCup 2D Simulation League through Behavioral Cloning

Enhancing Decisions of Goalkeeper and Kicker Players in the ...

引用

International Symposium on Artificial Intelligence and Signal Processing (AISP)

作者： Mohammad Hesam Nasiri Seyed Hassan Majid Zonouzi Armin Salimi-Badr Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran

RoboCup is recognized as a landmark project in the robotics and artificial intelligence industry, providing a crucial platform for the advancement of research and innovations in autonomous and multi-agent systems. This study delves into the use of behavioral cloning in the RoboCup 2D Simulation League to imitate the best decisions and improve the performance of the goalkeeper along with the kicker players. To improve the performance of our soccer team in the league, we have developed a new approach that combines behavioral cloning and game log parsing. To achieve this, we played extensively against the champion team Helios and analyzed the actions and decisions of their goalkeeper and kicker players. This data was used to create a large dataset that our team could use to improve their imitation skills. Our innovative log generator tool and game logs parser made the labeling process easier and will also be useful for future research in the league. Novel features are extracted to represent the state of the game considering the limitations of each player including their head direction along with their field of view. Next, a neural structure is trained to imitate the behavior of kicker players and the goalkeeper. Moreover, the time limit for decision-making in each turn is considered. This study showed that using behavioral cloning for imitation learning noticeably improved our team’s actions and decisions due to the enhancement of the number of accurate passes, on-target shoots, and saves by the goalkeeper.

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：