检索结果-内蒙古大学图书馆

Entertainment robot simulation in interactive art process based on deep learning algorithms and gesture recognition

ENTERTAINMENT COMPUTING 2025年 52卷

作者： Lyu, Hanlu Daejin Univ Art & Convergence Pochon 11159 Gyeonggi Do South Korea

Entertainment robots, as a new type of entertainment device, have broad application prospects. Entertainment robots provide entertainment and entertainment experiences through interaction with users. This article designs a programming model to interpret and execute user gesture commands, and convert them into drawing actions that robots can process. By interacting with entertainment robots, users can guide robots to draw through gestures, making artistic creations more intuitive and interesting. We used deep learning algorithms for training and used existing art works as references to enable robots to learn and imitate the painting styles of different artists. Finally, by optimizing the algorithm, the optimal path for the entertainment robot to draw trajectories was determined, which improved the effectiveness and quality of the painting. Through the training of deep learning algorithms, entertainment robots can capture the characteristics and details of an artist's painting style, and simulate it during the painting process. This provides users with a personalized artistic creation experience, allowing them to interact with entertainment robots, participate in artistic creation, and experience a creative process similar to that of real artists.

关键词： deep learning algorithms Gesture recognition Entertainment robots Interactive Art

来源：评论

学校读者我要写书评

暂无评论

Optimization of a closed-loop supply chain system considering government incentives mechanism under deep learning algorithms

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2025年 205卷

作者： Guo, Jianquan Chen, Lian Wang, Zhen Univ Shanghai Sci & Technol Sino German Coll Shanghai 200093 Peoples R China

Against the backdrop of multiple uncertainties, our research endeavors to design a comprehensive closed-loop supply chain system that incorporates dual recycling channels and a series of manufacturing-remanufacturing processes. The focal point of this study lies in the establishment of a holistic profit model aimed at a thorough exploration of the effect of the government incentives mechanism (GIM) on this system. Additionally, we employ deep learning algorithms (DLA), a kind of AI technology, for calculation and solution analysis of the model. The results show: (1) Remanufacturers can develop reasonable recycling, remanufacturing, and manufacturing strategies based on different scenarios;(2) The quality level of recycled products, rather than different demands, has a significant impact on the amount of penalty and reward. Thus, when establishing a GIM to encourage recycling and remanufacturing, the government should primarily focus on the uncertainty of the recycled products' quality. (3) In the absence of a GIM, remanufacturers are reluctant to strive to improve the recovery rate, and are more inclined to choose informal channels to reduce recovery costs;(4) The GIM can stimulate and regulate enterprises' recycling activities. Hence, the government should formulate a reasonable GIM to regulate the recycling of enterprises and supervise and guide the transformation and upgrading of informal channels. This research provides profound insights for the establishment of a robust closed-loop supply chain under multiple uncertain environments, and also, this research combines AI technology to improve computational accuracy, provide more reasonable support for business decision-making and government supervision, and provide assistance in realizing a circular economy.

关键词： Closed-loop supply chain Recycling channels Manufacturing remanufacturing processes Government incentives mechanism deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Malicious software identification based on deep learning algorithms and API feature extraction

引用

EURASIP JOURNAL ON INFORMATION SECURITY 2025年第1期2025卷 1-15页

作者： Sun, Wei Heilongjiang Polytech Sch Informat Engn Harbin 150070 Heilongjiang Peoples R China

With the popularization of mobile Internet, the Android operating system has become the main target of malware attacks because of its openness. Traditional malware detection methods face challenges in handling complex feature representations, especially in utilizing the semantic information and call order of application programming interface call sequences. Therefore, this study develops a deep learning method to identify malicious software by analyzing the application programming interface calls and constructing heterogeneous graphs of Android applications. The results showed that the proposed method achieved accuracies of 92.80% and 94.24% on the Drebin and AndroZoo datasets, demonstrating excellent robustness and generalization ability. The ablation experiment showed that the accuracy of the complete model was 94.71%, verifying the key role of each part of the method. In comparison with existing methods, the proposed method led with an average accuracy of 94.27%, while maintaining detection time within 5-10 s, demonstrating high efficiency and practicality. This study contributes to the in-depth exploration of semantic information and behavioral patterns of application programming interface call sequences. The efficient malware identification method developed can cope with the constantly evolving malware threats.

关键词： Malicious software detection deep learning algorithms Application programming interface Feature extraction techniques Relational Graph Convolutional Network

来源：评论

学校读者我要写书评

暂无评论

Effect of Urban Morphology on Solar Energy Potential for Buildings Based on deep learning algorithms 9th

Effect of Urban Morphology on Solar Energy Potential for Bui...

引用

9th International Building Physics Conference

作者： Tian, Jia Ooka, Ryozo Univ Tokyo Grad Sch Engn Tokyo Japan Univ Tokyo Inst Ind Sci Tokyo Japan

ISBN: (纸本)9789819783113;9789819783090;9789819783083

Building integrated photovoltaics is an important measure to promote low-carbon urban growth. However, the solar utilization performance of buildings in a block is greatly influenced by the shadings from surrounding buildings with di-verse layouts and morphologies. Therefore, this study evaluates the effect of urban morphology on solar energy potential for buildings in diverse urban environments using the parametric modelling and deep learning approaches. By con-trolling urban morphology parameters in different ranges, thousands of block models are randomly generated for residential buildings based on a parametric approach. Then, the solar energy potential, including the solar radiation and photovoltaics power potential, can be evaluated for building roofs and facades. The contribution of morphological parameters to building solar energy potential are prioritized using Global Sensitivity Analysis. The different input combinations of morphology parameters can be obtained based on the total contribution of each parameter. These input combinations are inserted into deep learning models to explore different prediction performances on the target values. Correspondingly, the influential parameters that can well predict the solar performance of building roofs and facades are selected. The proposed approach and findings are expected to offer inspirations for solar design and utilization in urban buildings.

关键词： Solar energy potential Urban residential buildings Photovoltaic power Solar radiation deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Signal Detection in the Internet of Things Based on deep learning algorithms 24

Research on Intelligent Signal Detection in the Internet of ...

引用

3rd International Conference on algorithms, Data Mining, and Information Technology, ADMIT 2024

作者： Liu, Xingcen School of Information and Communication Engineering Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9798400718120

With the rapid development of Internet of Things technology, intelligent signal detection has become a highly challenging key issue. Traditional manual feature extraction methods are no longer able to cope with complex and ever-changing practical environments. In response to this issue, this study proposes an intelligent signal detection model for the Internet of Things based on deep learning. This model adopts a convolutional neural network structure, which can automatically learn local pattern features in signals, thereby improving its adaptability to complex environments. Research a large-scale wireless signal dataset constructed based on real IoT scenarios, and adopt reasonable data preprocessing and augmentation strategies. Through scientific model training and multi-dimensional evaluation index settings, a comprehensive evaluation of the proposed model was conducted on the test set. The experimental results show that the model has achieved excellent performance over traditional methods in key indicators such as accuracy, recall, and F1 score, especially in complex signal recognition scenarios. © 2024 Copyright held by the owner/author(s).

关键词： deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Time-of-Use Operation Optimization and Trading Models in Electric Power Based on deep learning algorithms 24

Research on Time-of-Use Operation Optimization and Trading M...

引用

2024 International Symposium on Integrated Circuit Design and Integrated Systems, ICDIS 2024

作者： Hu, Benran Peng, Luhai Wang, Libin Zhang, Shuwei Yu, Cheng Yu, Jufeng Heilongjiang Electric Power Trading Center Co. Ltd Harbin China

ISBN: (纸本)9798400718229

The increasing complexity of electric power systems necessitates advanced methods for optimizing time-of-use (TOU) operations and trading models. This paper addresses the challenge of efficiently managing electricity distribution across different time periods to reduce costs and improve grid stability. We propose a hybrid deep learning algorithm combining convolutional neural networks (CNN) and long short-term memory (LSTM) networks to leverage historical consumption data for demand pattern prediction. The CNN layers capture local correlations in electricity usage, while the LSTM layers handle long-term dependencies, resulting in a highly accurate demand prediction model. The demand forecast is subsequently used in a reinforcement learning-based optimization framework to dynamically adjust electricity distribution and pricing. This approach minimizes operational costs through adaptive scheduling and dynamic pricing based on real-time feedback. Experimental results demonstrate that our method reduces peak load demands and operational costs by up to 15%, outperforming traditional optimization techniques. The conclusion highlights the potential of deep learning in revolutionizing electric power operations and suggests avenues for future research. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： deep learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Social robot assisted music course based on speech sensing and deep learning algorithms

引用

ENTERTAINMENT COMPUTING 2025年 52卷

作者： Dan, Xiao Qilu Normal Univ Coll Mus Jinan 210031 Peoples R China

In the field of social robot teaching, research has focused on how to use technological means to provide better learning support and personalized interactive experiences. Social robots can interact with students and provide personalized learning support, thereby improving their learning effectiveness and engagement. The speech sensing model of social robots can perceive students' emotions and feedback in real-time through technologies such as speech recognition and sentiment analysis, thereby providing intelligent responses and guidance. The deep learning recommendation model for music course resources extracts music features through deep learning techniques, and combines session interest extraction techniques to personalized recommend music resources suitable for students' interests and abilities. By analyzing students' interests and learning goals, robots can provide music learning resources that meet their needs based on recommendation algorithms, further stimulating their learning interest and enthusiasm. The experimental results show that the use of social robots in the learning environment significantly improves the learning effectiveness and participation of students. Through personalized interaction and intelligent response guidance, students are more likely to understand and master music knowledge, while experiencing joyful and positive learning emotions. The study validated the effectiveness of social robot assisted music courses based on speech sensing and deep learning algorithms, demonstrating its advantages in improving student learning effectiveness and engagement.

关键词： Speech sensing deep learning algorithms Social robots Course in music

来源：评论

学校读者我要写书评

暂无评论

deep learning algorithms based landslide vulnerability modeling in highly landslide prone areas of Tamil Nadu, India

引用

GEOSCIENCES JOURNAL 2024年第6期28卷 1013-1038页

作者： Saha, Sunil Barman, Aparna Saha, Anik Hembram, Tusar K. Pradhan, Biswajeet Alamri, Abdullah Univ Gour Banga Dept Geog Malda 732103 W Bengal India Nistarini Coll Dept Geog Purulia 723101 W Bengal India Univ Technol Sydney Fac Engn & Informat Technol Ctr Adv Modelling & Geospatial Informat Syst CAMGI POB 123 Sydney NSW 2007 Australia King Saud Univ Coll Sci Dept Geol & Geophys POB 2455 Riyadh 11451 Saudi Arabia

Landslide is a common hazard in Tamil Nadu's Nilgiri district of. While much work on landslide susceptibility have been done worldwide, understanding society's vulnerability to landslides, considering house structure and socio-economic conditions, remains lacking. This research presents landslide vulnerability mapping using advanced computing deep learning models in the Nilgiri district, India. Compared to traditional ML techniques, the deep learning neural network (DLNN) architecture demonstrates greater accuracy, particularly when dealing with more samples or significant amounts of big data. Although the standardized characteristics of multi-layer NNs are widely known, the key benefit of DL is its organized method for training DLNN-layer organizations how to govern themselves. Therefore, one deep learning neural network and three conventional machine learning models i.e., MLP classifier and RBF neural network were opted. A total of twenty-eight physical, climatological, hydrological and socio-economic factors were considered to produce socio-economic and relative landslide vulnerability maps. Multi-collinearity diagnosis was performed to select the appropriate factors. Several physical as well as human related factors are highly important for making the area vulnerable to land-slide. To justify the vulnerability maps, several statistical methods were applied. The best model DLNN, with an area under the curve of 89.07%, shows that 43.31%, and 37.72% of areas are highly to very-highly vulnerable to landslides. The framework presented in this work establishes an ideal link between human activities and landslide vulnerability, aiding planners in making informed decisions for landslide management.

关键词： landslide modelling socio-economic landslide vulnerability artificial intelligence deep learning algorithms Nilgiri district

来源：评论

学校读者我要写书评

暂无评论

deep learning algorithms for Predicting Histone Post-Translational Modifications and Single Guide RNA CRISPR Efficiency

Deep Learning Algorithms for Predicting Histone Post-Transla...

引用

作者： Baisya, Dipankar Ranjan University of California Riverside

学位级别：Ph.D., Doctor of Philosophy

In this dissertation, we investigate two problems in computational biology that can be solved using machine learning methods, specifically using deep learning architectures. In this first, we study the problem of predicting histone post-translational modifications (PTMs) from transcription factor binding data and the primary DNA sequence. Histone PTMs are involved in a variety of essential regulatory processes in the cell, including transcription control. Here we introduce a deep learning architecture called deepPTM for predicting histone PTMs. Extensive experimental results show that deepPTM outperforms the prediction accuracy of the model proposed in Benveniste et al. (PNAS, 2014) and deepHistone (BMC Genomics, 2019). The competitive advantage of our framework lies in the synergistic use of deep learning combined with an effective pre-processing step. Our classification framework has also enabled the discovery that the knowledge of a small subset of transcription factors (which are histone-PTM and cell-type-specific) can provide almost the same prediction accuracy that can be obtained using all the transcription factors data. In the second, we investigate the problem of predicting single guide RNA (sgRNA) CRISPR-Cas9 and CRISPR-Cas12a activity from the primary sequence of the sgRNA. A negative selection screen in the absence of non-homologous end-joining (the dominant DNA repair mechanism) is used to generate single guide RNA (sgRNA) activity profiles for both SpCas9 and LbCas12a for the non-conventional yeasts Yarrowia lipolytica and Kluyveromyces marxianus. This genome-wide data serves as input to a deep learning algorithm, deepGuide, that is able to accurately predict guide activity. deepGuide uses unsupervised learning to obtain a compressed representation of the genome, followed by supervised learning to map sgRNA sequence, genomic context, and epigenetic features with guide activity. Experimental validation, both genome-wide and with a subset of selected gen

关键词： RNA CRISPR efficiency deep learning algorithms Histone

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Using deep learning algorithms in Network Intrusion Detection

引用

IEEE ACCESS 2024年 12卷 58851-58870页

作者： Elsayed, Salwa Mohamed, Khalil Madkour, Mohamed Ashraf Al Azhar Univ Fac Engn Syst & Comp Engn Dept Nasr City 11765 Cairo Egypt

This study introduces a deep learning approach for network intrusion detection (NIDS), which excels in both binary and multi-classification tasks. This approach combines the strengths of six distinct deep learning algorithms: DNN, CNN, RNN, LSTM, GRU, and a Hybrid CNN-LSTM architecture. The NSL-KDD dataset, a widely recognized benchmark for intrusion detection research, was utilized for implementation and evaluation. In binary classification, the approach demonstrates exceptional capabilities, with the GRU approach outperforming others. Similarly, the DNN, LSTM, CNN, and RNN approaches exhibit robust performance, showcasing their efficacy in detecting anomalies within network data. In the multi-classification setting, the DNN approach stands out with outstanding performance. While other approaches, including RNN, CNN, LSTM, GRU, and the Hybrid CNN-LSTM approach, also maintain commendable results, the DNN approach proves to be the most effective in handling complex network patterns. This research provides valuable insights into the application of deep learning approaches using the NSL-KDD dataset for network anomaly detection, emphasizing their versatility and reliability across different classification scenarios. The findings lay the groundwork for further exploration and utilization of deep learning methodologies in enhancing network security.

关键词： Network security Intrusion detection anomaly detection NIDS deep learning algorithms NSL-KDD dataset binary classification multi-classification

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：