检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Shindo, Hikaru Dhami, Devendra Singh Kersting, Kristian AI and Machine Learning Group Dept. of Computer Science TU Darmstadt Germany Centre for Cognitive Science TU Darmstadt Germany Darmstadt Germany

Reasoning is an essential part of human intelligence and thus has been a longstanding goal in artificial intelligence research. With the recent success of deep learning, incorporating reasoning with deep learning systems, i.e., neuro-symbolic AI has become a major field of interest. We propose the Neuro-Symbolic Forward Reasoner (NSFR), a new approach for reasoning tasks taking advantage of differentiable forward-chaining using first-order logic. The key idea is to combine differentiable forward-chaining reasoning with object-centric (deep) learning. Differentiable forward-chaining reasoning computes logical entailments smoothly, i.e., it deduces new facts from given facts and rules in a differentiable manner. The object-centric learning approach factorizes raw inputs into representations in terms of objects. Thus, it allows us to provide a consistent framework to perform the forward-chaining inference from raw inputs. NSFR factorizes the raw inputs into the object-centric representations, converts them into probabilistic ground atoms, and finally performs differentiable forward-chaining inference using weighted rules for inference. Our comprehensive experimental evaluations on object-centric reasoning data sets, 2D Kandinsky patterns and 3D CLEVR-Hans, and a variety of tasks show the effectiveness and advantage of our approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Formal logic

来源：评论

学校读者我要写书评

暂无评论

Wavelength-Selective Distribution of Polarization Entanglement over Deployed Fiber

Wavelength-Selective Distribution of Polarization Entangleme...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Ramesh, Anirudh Chung, Joaquin Kanter, Gregory Peña, Cristián Plunkett, Robert K. Xie, Si Spentzouris, Panagiotis Kettimuthu, Rajkumar Kumar, Prem Data Science and Learning Division Argonne National Laboratory 9700 S Cass Ave LemontIL60439 United States Mathematics and Computer Science Division Argonne National Laboratory 9700 S Cass Ave. LemontIL60439 United States Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States NuCryptLLC 1460 Renaissance Dr #205 Park RidgeIL60068 United States Fermi National Accelerator Laboratory Kirk Rd and Pine St BataviaIL United States

ISBN: (纸本)9781957171258

We demonstrate distribution of polarization entangled photon-pairs across multiple channels in a 6 km loop of deployed fiber. We use an all-optical networking switch to route Bell-state photons in three different wavelength pairs and verify entanglement distribution in all channel pairs by measuring two-photon interference fringes. © Optica Publishing Group 2023 © 2023 The Author(s)

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Solar Cells, Lambert W and the LogWright Functions

Solar Cells, Lambert W and the LogWright Functions

引用

Electrical, Computer and Energy Technologies (ICECET), International Conference on

作者： Prabhat Lankireddy Sibibalan Jeevanandam Aditya Choudhary P. C. Deshmukh Ken Roberts S. R. Valluri Dept. of Electrical Engineering Indian Institute of Technology Tirupati Tirupati India India Center for Machine Intelligence and Data Science Indian Institute of Technology Bombay Mumbai India Dept. of Mechanical Engineering Indian Institute of Technology Tirupati Tirupati India Dept. of Mechanical Engineering Purdue University West Lafayette Indiana USA Dept. of Physics Center for Atomic Molecular and Optical Sciences & Technologies Indian Institute of Technology Tirupati Tirupati India Dept. of Physics Dayananda Sagar University Bengaluru India Dept. of Physics and Astronomy University of Western Ontario London ON Canada Dept. of Physics and Astronomy Dept. of Management Economics and Mathematics King's College University of Western Ontario London ON Canada

Algorithms that calculate the current-voltage (I-V) characteristics of a solar cell play an important role in processes that aim to improve the efficiency of a solar cell. I-V characteristics can be obtained from different models used to represent the solar cell, and the single diode model is a simple yet accurate model for common field implementations. However, the I-V characteristics are obtained by solving implicit equations, which involve repeated iterations and inherent errors associated with numerical methods used. Some methods use the Lambert W function to get an exact explicit formula, but often causes numerical overflow problems. The present work discusses an algorithm to calculate I-V characteristics using the LogWright function, a transformation of the Lambert W function, which addresses the problem of arithmetic overflow that occurs in the Lambert W implementation. An implementation of this algorithm is presented and compared against other algorithms in the literature. It is observed that in addition to addressing the numerical overflow problem, the algorithm based on the LogWright function offers speed benefits while retaining high precision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of CatBoost for Diabetes Prevention in Comparison to XGBoost: To avert mortality by developing an AI model capable of predicting the onset of diabetes

Evaluation of CatBoost for Diabetes Prevention in Comparison...

引用

Electronic Systems and Intelligent Computing (ICESIC), International Conference on

作者： G. Gifta Jerith S. Jagadeesh P. Ponmathi Jeba Kiruba C Mahesh S. Anantha Babu S. Samsudeen Shaffi Dept. of CSE (Artificial Intelligence and Machine Learning) School of Engineering Malla Reddy University Hyderabad India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science and Engineering Saveetha Engineering College Chennai India Department of Information Technology Panimalar Engineering College Chennai India Department of Computer Science and Engineering GITAM School of Technology GITAM University Bangalore India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

Diabetes is a metabolic condition defined by consistently elevated blood glucose levels. Hyperglycemia is characterized by heightened hunger, thirst, and urination. Numerous consequences may arise from untreated diabetes. Diabetic ketoacidosis, hyperosmolarity, hyperglycemia, and even mortality may occur as acute consequences. Heart disease, stroke, chronic renal failure, foot ulcers, and eye impairment are some of the worst long-term consequences. A total of 463 million individuals were found to have diabetes in 2019, according to the worldwide diabetes organisation. Assuming predictions come true, that number will soar to 700 million by 2045, up 578 million by 2030. It has modern medical applications, allowing for the rapid and precise diagnosis of illness. Thus, we may use machine learning to avert mortality by developing an AI model capable of predicting the onset of diabetes; to determine which algorithm is most suited for this task, we will compare the CatBoost and XGBoost methods. In the end, the research compared two diabetes prediction models, XGBoost and CatBoost, using a variety of health indicators from the dataset. Using a real-world dataset obtained from Kaggle, our suggested system is trained and built using Python. Performance assessment criteria such as precision, recall, F1score and accuracy measurements are used to thoroughly analyse our methods. In comparison to XGBoost's 88.33% accuracy rate, 85.25 percent precision, 85.63 percent recall, and an F1 Score of 86.50. CatBoost's 91.08% percent accuracy, 85.25 percent precision, 85.63 percent recall, and 87.38 F1 Score. CatBoost marks it as the most successful ensemble approach.

关键词： Deep learning Heart Accuracy machine learning algorithms Prevention and mitigation Mortality Medical services Predictive models Prediction algorithms Diabetes

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in IoT Environment Using Stochastic Gradient Descent with Warm Restarts and Gated Recurrent Unit

Intrusion Detection in IoT Environment Using Stochastic Grad...

引用

data science and Network Security (ICDSNS), International Conference on

作者： Revatthy Krishnamurthy Haider Alabdeli Rajani N Vankudoth Ramesh Bura Vijay Kumar Department of Artificial Intelligence & Machine Learning Rajalakshmi Engineering College Chennai India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Dept. of ECE Nitte Meenakshi Institute of Technology Bengaluru India Department of CSE-DS CVR College of Engineering Mangalpalle India School of Computer Science and Artificial Intelligence SR University Warangal India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

The rapid growth of Internet of Things (IoT) has attracted the cybercriminals which resulted in increase of cyber-attacks on IoT devices. If the cyber-attacks are undetected for a longer time, it causes serious service interruptions, identity protection threats. To handle these issues, this research proposes a novel intrusion detection system by employing Stochastic Gradient Descent with warm Restarts and Gated Recurrent Unit (SGDR-GRU) method. The data is normalized to obtain common scaled data by using z-score normalization technique and the feature selection is performed by Stochastic Gradient Descent with warm Restarts (SGDR). The SGDR is an optimization technique that escapes local minima, reduces overfitting and improves the performance by adjusting learning rate. Finally, classification of normal and anomaly data is carried out by Gated Recurrent Unit (GRU) that deals with gradient descent problem and captures long-range dependencies. The performance of the proposed model is evaluated on NSL-KDD dataset and achieved high accuracy 99.12%, precision 99.45%, recall 99.23% in identifying intrusion over IoT devices. The proposed method surpassed existing intrusion detection models such as stacked-deep polynomial network (SDPN), Hybrid Chicken Swarm Genetic Algorithm (HCSGA).

关键词： Performance evaluation Accuracy Intrusion detection Stochastic processes Transforms Logic gates Feature extraction Internet of Things Optimization Cyberattack

来源：评论

学校读者我要写书评

暂无评论

Development of a Calibration-Free Brain-Computer Interface Utilizing Common Spatial Patterns and Artificial Neural Networks for EEG Signal Analysis

Development of a Calibration-Free Brain-Computer Interface U...

引用

Human-Computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Korhan Cengiz Shreyas J Udayaprasad P K Gururaj H L Dilip Kumar S M College of Information Technology University of Fujairah UAE Faculty of Organization and Informatics University of Zagreb Croatia Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal Karnataka India Department of Artificial Intelligence & Machine Learning Global Academy of Technology Bengaluru India Dept. of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore India

ISBN: (数字)9798350394634

ISBN: (纸本)9798350394641

A brain computer interface (BCI) system uses a technique known calibration, that takes 20 to 30 minutes to accomplish. For the objective of creating a reliable decoder, the calibration process is challenging and expensive. In order to address the drawbacks of the current system, a spectral-spatial technique has been suggested. The motor imagery (MI) data set, comprising 15 electroencephalography (EEG) signals and fourteen test subjects, is taken into consideration. The two modules are designed to extract characteristics and process data. An artificial neural network (ANN) is used to independently train and test the suggested spectral-spatial algorithm. Based on it, a variety of machine learning techniques, including random forest (RF), neural networks (NN), and XGboost, are used to classify the data, that is then sent to the hidden layer (Lth layer). The obtained results indicates 2% of improvement in comparison with existing methodology.

关键词： Training machine learning algorithms Artificial neural networks Electroencephalography Brain-computer interfaces Calibration Reliability

来源：评论

学校读者我要写书评

暂无评论

Psi-zeta Approach for Assessing Network Efficiency in Log-Normal Fading and Spectrum Sharing Interference Environments

Psi-zeta Approach for Assessing Network Efficiency in Log-No...

引用

Advancement in Computation & Computer Technologies (InCACCT), International Conference on

作者： Preeti Narooka Shekhar Verma Abhishek Dwivedi Keshav Kaushik Vineeta Singh Priyanka Gaur Artificial Intelligence and Machine Learning School of Computer and Engineering Manipal University Jaipur Rajasthan India Department of Computer Applications School of Engineering and Technology Chhatrapati Shahu ji Maharaj University Kanpur India Sharda School of Computer Science & Engineering Sharda University Greater Noida India Department of Computer Science and Engineering School of Engineering and Technology Chhatrapati Shahu ji Maharaj University Kanpur India Dept. of Computer Applications Chandigarh Group of Colleges Jhanjheri Mohali India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

The paper introduced the Psi-zeta computation of network efficiency under a scenario of log-normal fading and spectrum sharing interferences. This model is aimed to improve different performance metrics such as throughput, Signal-to-Interference-plus-Noise-Ratio (SINR), energy efficiency and finally outage probability also reducing. Simulations demonstrate that when evaluating the overall performance, Psi-zeta is superior to traditional methods by managing interference and resource allocation agilely. The results, especially under high load and heavy interference conditions, exhibit remarkable enhancements in network performance. The strong modifiability and expandability of psi-zeta show that it can be a good candidate for improving network efficiency in future wireless networks like 6G, where parameters like performance, reliability and energy efficiency are the key factors. This work has significant potential to enable the next-generation communication systems.

关键词： Fading channels Wireless networks Interference Probability Throughput Energy efficiency Power system reliability Reliability Next generation networking Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A scalable generative model for dynamical system reconstruction from neuroimaging data

arXiv

引用

arXiv 2024年

作者： Volkmann, Eric Brändle, Alena Durstewitz, Daniel Koppe, Georgia Medical Faculty Mannheim Heidelberg University Mannheim Germany Institute for Machine Learning Johannes Kepler University Linz Austria Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany Faculty of Physics and Astronomy Heidelberg University Heidelberg Germany Hector Institute for AI in Psychiatry Dept. for Psychiatry and Psychotherapy CIMH Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany

data-driven inference of the generative dynamics underlying a set of observed time series is of growing interest in machine learning and the natural sciences. In neuroscience, such methods promise to alleviate the need to handcraft models based on biophysical principles and allow to automatize the inference of inter-individual differences in brain dynamics. Recent breakthroughs in training techniques for state space models (SSMs) specifically geared toward dynamical systems (DS) reconstruction (DSR) enable to recover the underlying system including its geometrical (attractor) and long-term statistical invariants from even short time series. These techniques are based on control-theoretic ideas, like modern variants of teacher forcing (TF), to ensure stable loss gradient propagation while training. However, as it currently stands, these techniques are not directly applicable to data modalities where current observations depend on an entire history of previous states due to a signal's filtering properties, as common in neuroscience (and physiology more generally). Prominent examples are the blood oxygenation level dependent (BOLD) signal in functional magnetic resonance imaging (fMRI) or Ca2+ imaging data. Such types of signals render the SSM's decoder model non-invertible, a requirement for previous TF-based methods. Here, exploiting the recent success of control techniques for training SSMs, we propose a novel algorithm that solves this problem and scales exceptionally well with model dimensionality and filter length. We demonstrate its efficiency in reconstructing dynamical systems, including their state space geometry and long-term temporal properties, from just short BOLD time series. © 2024, CC BY-NC-SA.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

The Frontier of Geospatial AI Deep learning Applications in data Mining and Spatial Analysis

The Frontier of Geospatial AI Deep Learning Applications in ...

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： Ajit Kumar Mishra Vikash Verma R. Manivannan N. Krishna Kumar Mudunuru Srividya Sanskriti Sharma Department of Electrical & Electronics Engineering IES College of Technology Bhopal M.P India Dept of Artificial Intelligence & Machine Learning GGITS Jabalpur M.P India School of Computing Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai TN India Dept.of CSE Guru Nanak Institutions Technical Campus Ibrahimpatam Hyderabad Telangana India Dept. of CSE MLR Institute of Technology Hyderabad Telangana India Dept of Computer Science & Business System GGITS Jabalpur M.P India

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

Modern artificial intelligence uses geographical data mining and regional analysis to analyze large datasets. Deep learning is a new geographic AI method. Example: Geographic Deep Mining Network (GDMN). The Spatial Feature Extractor (SFE), Temporal Geospatial Attention Mechanism (TGAM), and Geospatial data Fusion Module (GDFM) comprise this technique. We examined six popular approaches and found GDMN performed best. It worked successfully for several reasons. GDMN always outperforms its competitors in memory, F1 score, IoU, training time, and inference time. This is always true. These findings suggest that GDMN might boost geospatial AI’s data mining and location analysis abilities. After all the effort, we have developed a solid basis for location intelligence, making it useful in various subject areas. Because it’s versatile, mapping specialists may use GDMN for better environmental monitoring or city development. Deep learning helps GDMN make better space choices and uncover insights in large, challenging data sets that no one knew about. GDMN’s cutting-edge approaches make space and time research and prediction simpler. This wide perspective offers a more full and all-encompassing picture of today’s challenges than previous techniques. This makes it impossible to overstate how significant this work is to location intelligence. Its unmatched research and insights usher in a new era.

关键词： Deep learning Training Urban areas Transforms Feature extraction Solids Spatial databases Geospatial analysis data mining Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification using G-XGB

Human Activity Classification using G-XGB

引用

data science and Network Security (ICDSNS), International Conference on

作者： Aman Kataria Vikram Puri Piyush Kumar Pareek Sita Rani Amity Institute of Defence Technology Amity University Noida India Center of Visualization and Simulation Duy Tan University Da Nang Vietnam Dept. of Artificial Intelligence and Machine Learning and IPR Cell Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering Guru Nanak Dev Engineering College Ludhiana India

Wearable body sensors have recently gained popularity because they monitor user behaviors and vital indicators. These sensors are designed to monitor various physiological factors, such as motion, temperature, and heart rate, among others. Making sense of the data gathered by these sensors requires separating the dependent and independent features. The dependent parameters are those that body-worn sensors can read in this scenario. Examples of such elements include blood oxygen levels, heart rate, temperature, mobility, and airflow. These sensors capture data about a person's activity and health. The independent parameters in wearable body sensors are related to the dependent parameters, whereas the dependent parameters are those that the sensors can measure directly. Such characteristics include age, sex, weight, and environmental influences. For example, humidity and airflow might impair a temperature sensor's accuracy. The user's age or level of physical fitness may also influence the accuracy of a heart rate monitor. Activity monitors are used in this study to capture the actions of various people. Static and dynamic properties are derived from the activity monitor recording. The performance evaluations of the eight distinct machine-learning models that were created using the retrieved features are discussed in this paper. The Grid Search method is used to enhance the performance of the XGB model.

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：