检索结果-内蒙古大学图书馆

Deep Reinforcement Learning Approach for Prioritized Heterogeneous Object Tracking in UAV Swarms

Deep Reinforcement Learning Approach for Prioritized Heterog...

2023 IEEE International Conference on Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security, iQ-CCHESS 2023

作者： Nithya, B. Subash, Neethu Vignesh, Hari National Institute of Technology Dept. of Computer Science and Engg Tiruchirappalli India St.Joseph's College Department of Data Science Tiruchirappalli India

ISBN: (纸本)9798350314946

Deep Reinforcement learning(DRL) has recently showcased its boundless potential in Multi-agent collaboration. There exist DRL-based models that strive to unravel the Unmanned aerial vehicle (UAV) Multi-target tracking predicaments, however, the conundrum of tracing desired targets persists as most research endeavors solely focus on the agents' policies while neglecting the dynamic environment, which harbors elusive and unpredictable targets. The proposed model executes Prioritized Heterogeneous Object Tracking (PHOT) using DRL, to furnish a solution for preferred Multi-target tracking by upholding the policy of UAV swarms. Tracking preferred targets assumes paramount importance as these targets necessitate meticulous monitoring within the ever-changing environmental backdrop, particularly during surveillance missions employing UAV swarms, which can harness the full potential of the UAV swarms in real-time. A YOLO v4-based algorithm is put forth, which can trail prioritized targets in a tracking by detection paradigm. To maintain the policy of UAV swarms, a dueling double deep Q-learning algorithm is deployed, complemented by a reward function that stimulates UAVs to track the preferred targets instantaneously. The UAVDT dataset is employed for the simulations, and the results evince that PHOT exhibits robustness, suitable for deployment in a real-time environment, amassing a highly commendable average cumulative reward over time, and enabling actions predicated on unidentical prioritized targets. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Efficient MILP Decomposition in Quantum Computing for ReLU Network Robustness 4

Efficient MILP Decomposition in Quantum Computing for ReLU N...

引用

4th IEEE International Conference on Quantum Computing and Engineering, QCE 2023

作者： Franco, Nicola Wollschläger, Tom Poggel, Benedikt Günnemann, Stephan Lorenz, Jeanette Miriam Fraunhofer Institute for Cognitive Systems Iks Munich Germany Technical Univ. of Munich Dept. of Computer Science Munich Data Science Institute Germany

ISBN: (纸本)9798350343236

Emerging quantum computing technologies, such as Noisy Intermediate-Scale Quantum (NISQ) devices, offer potential advancements in solving mathematical optimization problems. However, limitations in qubit availability, noise, and errors pose challenges for practical implementation. In this study, we examine two decomposition methods for Mixed-Integer Linear Programming (MILP) designed to reduce the original problem size and utilize available NISQ devices more efficiently. We concentrate on breaking down the original problem into smaller subproblems, which are then solved iteratively using a combined quantum-classical hardware approach. We conduct a detailed analysis for the decomposition of MILP with Benders and Dantzig-Wolfe methods. In our analysis, we show that the number of qubits required to solve Benders is exponentially large in the worst-case, while remains constant for Dantzig-Wolfe. Additionally, we leverage Dantzig-Wolfe decomposition on the use-case of certifying the robustness of ReLU networks. Our experimental results demonstrate that this approach can save up to 90% of qubits compared to existing methods on quantum annealing and gate-based quantum computers. © 2023 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Pre-Trained Whisper Model and Levenshtein Distance for Audio Buginesse Transcription

Leveraging the Pre-Trained Whisper Model and Levenshtein Dis...

引用

2024 Beyond Technology Summit on Informatics International Conference, BTS-I2C 2024

作者： Mukmin, Amirul Adnan Jalil, Abdul Pallawabonang, Mahabintang Prakasa, Esa Yuyun Handayani University of Makassar Dept. of informatics engineering Makassar Indonesia Handayani University of Makassar Dept. of computer system Makassar Indonesia Research center for data and information science National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9798331508579

This research aims to transcribe audio into text using the pre-trained Whisper model, focusing on Bugis, a low-resource language. A key challenge in transcribing local languages like Bugis is the limited availability of language model. To address this, we implemented an algorithmic correction approach that does not require extensive datasets or computationally demanding customizations. The Whisper model provides an initial transcription, serving as a foundation;however, the output often lacks accuracy due to the absence of specific adjustments for Bugis. To enhance accuracy, we applied the Levenshtein distance algorithm to correct word errors by comparing transcription results with entries in a Bugis language dataset based on similarity. Although this method is not fully precise and depends on the completeness of the reference dataset, evaluation results indicate that it effectively lowers the word error rate (WER) and improves transcription accuracy. This research produces SRT files containing transcripts that have been corrected using the Levenhstein distance algorithm, which not only improves accessibility but also contributes to the preservation of Bugis language through digital media. This approach is expected to provide a practical solution to improve transcription accuracy and support more accurate documentation in Bugis language preservation efforts. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection

Diffusion Denoised Smoothing for Certified and Adversarial R...

引用

2023 IJCAI Joint Workshop on Artificial Intelligence Safety and Safe Reinforcement Learning, AISafety-SafeRL 2023

作者： Franco, Nicola Korth, Daniel Lorenz, Jeanette Miriam Roscher, Karsten Günnemann, Stephan Fraunhofer Institute for Cognitive Systems IKS Munich Germany Dept. of Computer Science & Munich Data Science Institute Technical Univ. of Munich Germany

As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an "Out-Of-Distribution" (OOD) sample. In addition, adversaries can manipulate OOD samples in ways that lead a classifier to make a confident prediction. In this study, we present a novel approach for certifying the robustness of OOD detection within a 2-norm around the input, regardless of network architecture and without the need for specific components or additional training. Further, we improve current techniques for detecting adversarial attacks on OOD samples, while providing high levels of certified and adversarial robustness on in-distribution samples. The average of all OOD detection metrics on CIFAR10/100 shows an increase of-13%/5% relative to previous approaches. Code: https://***/FraunhoferIKS/distro © 2023 CEUR-WS. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

HGDL: Heterogeneous Graph Label Distribution Learning 38

HGDL: Heterogeneous Graph Label Distribution Learning

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jin, Yufei Lian, Heng He, Yi Zhu, Xingquan Dept. of Elec. Eng. & Computer Sci. Florida Atlantic University Boca RatonFL33431 United States Dept. of Data Science William & Mary WilliamsburgVA23185 United States

Label Distribution Learning (LDL) has been extensively studied in IID data applications such as computer vision, thanks to its more generic setting over single-label and multi-label classification. This paper advances LDL into graph domains and aims to tackle a novel and fundamental heterogeneous graph label distribution learning (HGDL) problem. We argue that the graph heterogeneity reflected on node types, node attributes, and neighborhood structures can impose significant challenges for generalizing LDL onto graphs. To address the challenges, we propose a new learning framework with two key components: 1) proactive graph topology homogenization, and 2) topology and content consistency-aware graph transformer. Specifically, the former learns optimal information aggregation between meta-paths, so that the node heterogeneity can be proactively addressed prior to the succeeding embedding learning;the latter leverages an attention mechanism to learn consistency between meta-path and node attributes, allowing network topology and nodal attributes to be equally emphasized during the label distribution learning. By using KL-divergence and additional constraints, HGDL delivers an end-to-end solution for learning and predicting label distribution for nodes. Both theoretical and empirical studies substantiate the effectiveness of our HGDL approach. Our code and datasets are available at https://***/Listener-Watcher/HGDL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Sarcoma Based on Genomic data Using Machine Learning Models

引用

Procedia computer science 2025年 252卷 317-330页

作者： Pratham Gala Yash Pandloskar Shubham Godbole Fayed Hakim Pratik Kanani Lakshmi Kurup Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India Dept. of Artificial Intelligence and Data Science Dwarkadas J. Sanghvi College of Engineering Mumbai India

The proposed work provides a new machine-learnt classification approach for the various types of soft tissue sarcoma based on genomics data which addresses a considerable gap in sarcoma diagnostics. The previous studies have investigated various aspects of sarcoma but this study is unique in that it targets the predicting sarcoma variant types using genetic information, which has not been done before. Random Forest was used as the meta-estimator and a stacking ensemble model comprising of Random Forest, Extreme Gradient Boosting and LightGBM were used for this study. The model which was trained and validated on a complete dataset of 206 adult soft tissue sarcoma samples containing genomic alterations, transcriptomic, epigenomic and proteomic data achieved an accuracy of 89.44% at a precision level as high as 91%. Stratified k-fold cross validation is employed to ensure that class imbalance is not a hindrance to performance. This innovative approach outmatches single classifiers and traditional single model methods at great length hence making it possible and effective to use machine learning on genomic data for predicting sarcoma variants. Thus, the findings from this research could change cancer diagnosis forever; they promise more accurate classification as well as personalized treatment modalities while also providing a framework for analogous applications in other rare complex cancers.

关键词： Sarcoma Classification Stacking Ensemble Model Genomic data

来源：评论

学校读者我要写书评

暂无评论

Grammar Error Correction in Indonesian Sports News: Comparing the Performance of Pre-Trained T5 and BART Models

Grammar Error Correction in Indonesian Sports News: Comparin...

引用

2024 Beyond Technology Summit on Informatics International Conference, BTS-I2C 2024

作者： Adnan, Muh Prakasa, Esa Yuyun Umar, Najirah Nasrullah Sadli, Adi Anatasya, A. Edeth Fuari Hazriani Razak, Mashur Handayani University of Makassar Dept. of informatics engineering Makassar Indonesia Research center for data and information science National Research and Innovation Agency Bandung Indonesia Handayani University Makassar Dept. of computer system Makassar Indonesia

ISBN: (纸本)9798331508579

This research compares the performance of two pre-trained models based on the transformer, namely text-to-text transfer transformer (T5) and bidirectional and auto-regressive transformer (BART), through a fine-tuned for correcting grammar in Indonesian sports news texts. We used vennify/t5-base-grammar-correction and onionLad/grammar-correction-bart-base, was trained using a dataset of 10,075 sentences from Indonesian language sports news sites. We tested the model performance using bilingual evaluation understudy (BLEU), google's language evaluation understanding (GLEU), training loss, and validation loss. The results show that BART was more efficient in learning data patterns and has better generalization ability, supported by BLEU and GLEU scores of 0.8560 and 0.9655. Meanwhile, T5 maintains simpler sentence structures, supported by BLEU and GLEU scores of 0.8120 and 0.9564. BART excels at handling more complex contexts, making it more effective at accurately correcting errors in dynamic sports news. Both models have their respective advantages, with BART being better at correcting detailed grammatical errors, while T5 offers consistent correction of more simple sentence structures. © 2024 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Windmill Pitch Prediction And Error Correction With Adaptive Control And Current Generation Analysis Using data Analysis

Windmill Pitch Prediction And Error Correction With Adaptive...

引用

Energy, Materials and Communication Engineering (ICEMCE), International Conference on

作者： M. S. Minu Rohit Suryaa S Jovan Titus J Sharan S Dept. of Computer Science Engineering SRM Institute of Science and Technology Chennai India Dept. Computer Science Engineering Specialization With Big Data Analytics SRM Institute of Science and Technology Chennai India

The growing prominence of wind energy as an eco-friendly power alternative amplifies the need for optimal turbine performance. Central to this is the ability to accurately predict and modulate the wind turbine pitch. Our research focuses on integrating adaptive control strategies with advanced power generation analytics to enhance pitch prediction precision. We have processed and analyzed vast amounts of wind data using state-of-the-art data analytics to discern patterns in wind velocity changes accurately. The continuous stream of real-time data is the backbone of our adaptive controls, ensuring perpetual pitch adjustments that optimize energy capture. In tandem with this, we present a thorough analysis linking momentary wind shifts to power production, ensuring consistent and efficient power output. The culmination of these methodologies offers a breakthrough solution in wind energy optimization. Preliminary results highlight the paramount importance of real-time data analytics in revolutionizing green energy advancements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

vRecruit: An Automated Smart Recruitment Webapp using Machine Learning

vRecruit: An Automated Smart Recruitment Webapp using Machin...

引用

2022 International Conference on Innovative Trends in Information Technology, ICITIIT 2022

作者： Mhadgut, Sanika Koppikar, Neha Chouhan, Nikhil Dharadhar, Parag Mehta, Parthak MPSTME NMIMS University Dept. of Data Science Mumbai India MPSTME NMIMS University Dept. of Computer Science Mumbai India

ISBN: (纸本)9781665406703

The need for global online recruitment has risen tremendously in recent years. However, this procedure presents difficulties for recruiters in managing the flood of applications and maintaining contact with the applicants. Historically, little attention has been paid to a practical solution for virtual recruitment. As a result, the paper proposes "vRecruit - A machine learning-based web application"for virtual recruitment in the current paper. vRecruit's primary features include a client-specific interview process that leverages Machine Learning-based references to context provided by the client, as well as a text-based sentiment analysis engine. All components work in unison to ensure the webapp's end-to-end functionality, which was finally launched on flask. The face recognition method using the face api model achieved a 96% accuracy. The speech to text conversion using the Mozilla DeepSpeech model had a 7.55% word error rate, whereas the rasa Natural Language Understanding (NLU) model trained for chatbots had a 95% accuracy. The webapp provides a hassle-free virtual recruiting experience for candidates and interviewers. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Exploring the Intersection of Blockchain and Distributed Quantum Computing: Synergies, Challenges, and Future Directions

Exploring the Intersection of Blockchain and Distributed Qua...

引用

Microwave, Antenna and Communication (MAC), International Conference on

作者： Madhusudan Singh Bharat Rawal Department of Data Analytics Long Island University Brooklyn New York USA Dept. of Computer Science Granbling State University Louisiana USA

ISBN: (数字)9798350350104

ISBN: (纸本)9798350350111

Distributed quantum computing has become a potential way to solve hard computing problems by combining the power of many quantum devices that are connected to each other. But it's hard to make sure that distributed quantum computer nodes can trust each other, stay safe, and work together well. The decentralized and open nature of blockchain technology holds significant potential in addressing these challenges and revolutionizing the domain of distributed quantum computing. This scholarly essay examines the potential of blockchain technology in facilitating the coordination, resource sharing, and data management within distributed quantum computing networks, with a focus on ensuring safety and efficiency. We provide an overview of the primary advantages, challenges, and potential applications of integrating blockchain technology into distributed quantum computing frameworks. This has the potential to result in a quantum computing environment that is both more stable and scalable. The objective of this scholarly essay is to elucidate the potential impact of integrating blockchain technology into distributed quantum computing. Distributed quantum computing networks may effectively coordinate, share resources, and manage data by using the decentralized, transparent, and secure nature of blockchain technology.

关键词： Microwave antennas Quantum computing Scalability Collaboration Termination of employment Blockchains Computational efficiency Resource management Research and development Standards

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：