检索结果-内蒙古大学图书馆

Artificial Intelligence-Driven Aircraft Systems to Emulate Autopilot and GPS Functionality in GPS-Denied Scenarios Through Deep Learning

引用

DRONES 2025年第4期9卷 250-250页

作者： Garcia-Gascon, Cesar Castello-Pedrero, Pablo Chinesta, Francisco Garcia-Manrique, Juan A. Univ Politecn Valencia Design & Mfg Res Inst Valencia 46022 Spain Arts & Metiers Inst Technol PIMM Lab CNRS ENSAM F-75013 Paris France CNRS CREATE Ltd 1 Create Way08-01 CREATE Tower Singapore 138602 Singapore

This paper presents a methodology for training a Deep Learning model aimed at flight management tasks in a fixed-wing unmanned aerial vehicle (UAV), specifically autopilot control and GPS prediction. In this formulation, sensor data and the most recent GPS signal are first processed by an LSTM to produce an initial coordinate prediction. This preliminary estimate is then merged with additional sensor inputs and passed to an MLP, which replaces the conventional autopilot algorithm by generating the control commands for real-time navigation. The approach is particularly valuable in scenarios where the aircraft must follow a predetermined route-such as surveillance operations-or maintain a remote ground link under varying GPS availability. The study focuses on Class I UAVs;however, the proposed methodology can be adapted to larger classes (II and III) by adjusting sensor configurations and network parameters. To collect training data, a small fixed-wing aircraft was instrumented to record kinematic and control inputs, which then served as inputs to the neural network. Despite the limited sensor suite and the use of an open-source flight controller (SpeedyBee), the flexibility of the proposed approach allows for easy adaptation to more complex UAVs equipped with additional sensors, potentially improving prediction accuracy. The performance of the neural network, implemented in PyTorch, was evaluated by comparing its predicted data with actual flight logs. In addition, the method has been shown to be robust to both short and prolonged GPS outages, as it relies on waypoint-based navigation along previously explored routes, ensuring reliable performance in known operational contexts.

关键词： artificial intelligence (AI) Deep Learning (DL) Unmanned Aerial Systems (UASs) unmanned aerial vehicle (UAV)

来源：评论

学校读者我要写书评

暂无评论

Enhancing limonene production by probing the metabolic network through time-series metabolomics data

引用

METABOLOMICS 2025年第3期21卷 1-13页

作者： Khanijou, Jasmeet Kaur Scipion, Clement P. M. Borkar, Shreyash Chen, Xixian Chew, Wee ASTAR Singapore Inst Food & Biotechnol Innovat SIFBI Singapore 138673 Singapore CNRS CREATE 1 Create Way08-01 Create Tower Singapore 138602 Singapore

IntroductionLimonene is a monoterpene with diverse applications in food, medicine, fuel, and material science. Recently, engineered microbes have been used to biosynthesize target biochemicals such as *** engineering has shown that factors such as feedback inhibition, enzyme activity or abundance may contribute to the loss of target biochemicals. Incorporating a hypothesis driven experimental approach can help to streamline the process of improving target *** this work, time-series intracellular metabolomics data from Escherichia coli cultures of a wild-type strain engineered to overproduce limonene (EcoCTs3) was collected, where we hypothesized having more carbon flux towards the engineered mevalonate (MEV) pathway would increase limonene yield. Based on the topology of the metabolic network, the pathways involved in mixed fermentation were possibly causing carbon flux loss from the MEV pathway. To prove this, knockout strains of lactate dehydrogenase (LDH) and aldehyde dehydrogenase-alcohol dehydrogenase (ALDH-ADH) were *** knockout strains showed 18 to 20 folds more intracellular mevalonate accumulation over time compared to the EcoCTs3 strain, thus indicating greater carbon flux directed towards the MEV pathway thereby increasing limonene yield by 8 to 9 *** high intracellular mevalonate concentration is therefore a good strategy to enhance limonene yield and other target compounds using the MEV pathway. Once high intracellular mevalonate concentration has been achieved, the limonene producing strain can then be further modified through other strategies such as enzyme and protein engineering to ensure better conversion of mevalonate to downstream metabolites to produce the target product limonene.

关键词： Intracellular metabolomics Quantitative metabolomics Metabolic network Limonene Mevalonate pathway

来源：评论

学校读者我要写书评

暂无评论

Function+Data Flow: A Framework to Specify Machine Learning Pipelines for Digital Twinning 1

Function+Data Flow: A Framework to Specify Machine Learning ...

引用

1st ACM International Conference on AI-Powered Software, AIware 2024, co-located with the ACM International Conference on the Foundations of Software Engineering, FSE 2024

作者： De Conto, Eduardo Genest, Blaise Easwaran, Arvind Nanyang Technological University Singapore Singapore CNRS@CREATE Singapore Singapore Ipal Singapore Singapore Cnrs CNRS@CREATE Singapore Singapore

ISBN: (纸本)9798400706851

The development of digital twins (DTs) for physical systems increasingly leverages artificial intelligence (AI), particularly for combining data from different sources or for creating computationally efficient, reduced-dimension models. Indeed, even in very different application domains, twinning employs common techniques such as model order reduction and modelization with hybrid data (that is, data sourced from both physics-based models and sensors). Despite this apparent generality, current development practices are ad-hoc, making the design of AI pipelines for digital twinning complex and time-consuming. Here we propose Function+Data Flow (FDF), a domain-specific language (DSL) to describe AI pipelines within DTs. FDF aims to facilitate the design and validation of digital twins. Specifically, FDF treats functions as first-class citizens, enabling effective manipulation of models learned with AI. We illustrate the benefits of FDF on two concrete use cases from different domains: predicting the plastic strain of a structure and modeling the electromagnetic behavior of a bearing. © 2024 Owner/Author.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Third-Order Analysis of Channel Coding in the Small-to-Moderate Deviations Regime

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第9期70卷 6139-6170页

作者： Yavas, Recep Can Kostina, Victoria Effros, Michelle CALTECH Dept Elect Engn Pasadena CA 91125 USA CNRS CREATE Singapore 138602 Singapore

This paper studies the third-order characteristic of nonsingular discrete memoryless channels and the Gaussian channel with a maximal-power constraint. The third-order term in our expansions employs a new quantity here called the channel skewness, which affects the approximation accuracy more significantly as the error probability decreases. For the Gaussian channel, evaluating Shannon's 1959 random coding bound and Vazquez-Vilar's 2021 meta-converse bound in the central limit theorem (CLT) regime enables exact computation of the channel skewness. For discrete memoryless channels, this work generalizes Moulin's 2017 bounds on the asymptotic expansion of the maximum achievable message set size for nonsingular channels from the CLT regime to include the moderate deviations (MD) regime, thereby refining Altug and Wagner's 2014 MD result. For an example binary symmetric channel and most practically important (n,& varepsilon;) pairs, including n is an element of [100,500] and & varepsilon;is an element of [10(-10),10(-1)] , an approximation up to the channel skewness is the most accurate among several expansions in the literature. A derivation of the third-order term in the type-II error exponent of binary hypothesis testing in the MD regime is also included;the resulting third-order term is similar to the channel skewness.

关键词： Error probability Channel coding Monte Carlo methods Encoding Accuracy Gaussian channels Testing Moderate deviations large deviations discrete memoryless channel Gaussian channel hypothesis testing dispersion skewness

来源：评论

学校读者我要写书评

暂无评论

Variable-Length Sparse Feedback Codes for Point-to-Point, Multiple Access, and Random Access Channels

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第4期70卷 2367-2394页

作者： Yavas, Recep Can Kostina, Victoria Effros, Michelle CALTECH Dept Elect Engn Pasadena CA 91125 USA CNRS CREATE Singapore 138602 Singapore

This paper investigates variable-length stop-feedback codes for memoryless channels in point-to-point, multiple access, and random access communication scenarios. The proposed codes employ L decoding times n(1),n(2),& mldr;,n(L) for the point-to-point and multiple access channels and KL+1 decoding times for the random access channel with at most K active transmitters. In the point-to-point and multiple access channels, the decoder uses the observed channel outputs to decide whether to decode at each of the allowed decoding times n(1),& mldr;,n(L), at each time telling the encoder whether or not to stop transmitting using a single bit of feedback. In the random access scenario, the decoder estimates the number of active transmitters at time n0 and then chooses among decoding times n(k,1),& mldr;,n(k,L) if it believes that there are k active transmitters. In all cases, the choice of allowed decoding times is part of the code design;given fixed value L, allowed decoding times are chosen to minimize the expected decoding time for a given codebook size and target average error probability. The number L in each scenario is assumed to be constant even when the blocklength is allowed to grow;the resulting code therefore requires only sparse feedback. The central results are asymptotic approximations of achievable rates as a function of the error probability, the expected decoding time, and the number of decoding times. A converse for variable-length stop-feedback codes with uniformly-spaced decoding times is included for the point-to-point channel.

关键词： Variable-length coding multiple-access random-access feedback codes sparse feedback second-order analysis channel dispersion moderate deviations sequential hypothesis testing

来源：评论

学校读者我要写书评

暂无评论

Your data is not perfect: Towards cross-domain out-of-distribution detection in class-imbalanced data

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 267卷

作者： Fang, Xiang Easwaran, Arvind Genest, Blaise Suganthan, Ponnuthurai Nagaratnam Nanyang Technol Univ Energy Res Inst NTU Interdisciplinary Grad Programme Singapore Singapore Nanyang Technol Univ Coll Comp & Data Sci Singapore Singapore CNRS Paris France CNRS Singapore Singapore CNRS CREATE IPAL IRL 2955 Paris France CNRS CREATE IPAL IRL 2955 Singapore Singapore Qatar Univ Coll Engn KINDI Comp Res Ctr Doha Qatar

Out-of-distribution detection (OOD detection) aims to detect test samples drawn from a distribution that is different from the training distribution, in order to prevent models trained on in-distribution (ID) data from providing unavailable outputs. Current OOD detection systems typically refer to a single-domain class-balanced assumption that both the training and testing sets belong to the same domain and each class has the same size. Unfortunately, most real-world datasets contain multiple domains and class-imbalanced distributions, which severely limits the applicability of existing works. Previous OOD detection systems only focus on the semantic gap between ID and OOD samples. Besides the semantic gap, we are faced with two additional gaps: the domain gap between source and target domains, and the class-imbalance gap between different classes. In fact, similar objects from different domains should belong to the same class. In this paper, we introduce a realistic yet challenging setting: class-imbalanced cross-domain OOD detection (CCOD), which contains a well-labeled (but usually small) source set for training and conducts OOD detection on an unlabeled (but usually larger) target set for testing. We do not assume that the target domain contains only OOD classes or that it is class-balanced: the distribution among classes of the target dataset need not be the same as the source dataset. To tackle this challenging setting with an OOD detection system, we propose a novel uncertainty-aware adaptive semantic alignment (UASA) network based on a prototype-based alignment strategy. Specifically, we first build label- driven prototypes in the source domain and utilize these prototypes for target classification to close the domain gap. Rather than utilizing fixed thresholds for OOD detection, we generate adaptive sample-wise thresholds to handle the semantic gap. Finally, we conduct uncertainty-aware clustering to group semantically similar target samples to relieve the

关键词： Class-imbalanced data Label-driven prototype building Prototype-guided domain alignment Adaptive threshold generation Uncertainty-aware target clustering

来源：评论

学校读者我要写书评

暂无评论

Periodic Hamiltonian Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1194-1202页

作者： Khoo, Zi-Yu Wu, Dawen Low, Jonathan Sze Choong Bressan, Stephane National University of Singapore School of Computing 117417 Singapore CNRS@CREATE 117417 Singapore 636732 Singapore

Modeling dynamical systems is a core challenge for science and engineering. Hamiltonian neural networks (HNNs) are state-of-the-art models that regress the vector field of a dynamical system under the learning bias of Hamilton's equations. A recent observation is that embedding biases regarding invariances of the Hamiltonian improve regression performance. One such invariance is the periodicity of the Hamiltonian, which improves extrapolation performance. We propose periodic HNNs that embed periodicity within HNNs using observational, learning, and inductive biases. An observational bias is embedded by training the HNN on data that reflects the periodicity of the Hamiltonian. A learning bias is embedded through the loss function of the HNN. An inductive bias is embedded by a periodic activation function in the HNN. We evaluate the performance of the proposed models on interpolation and extrapolation problems that either assume knowledge of the periods a priori or learn the periods as parameters. We show that the proposed models can interpolate well but are far more effective than the HNN at extrapolating the Hamiltonian and the vector field for both problems and can even extrapolate the vector field of the chaotic double pendulum Hamiltonian system. © 2020 IEEE.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

On-the-Fly Learning With Mixed-Mode Spiking Neural Network and Passive Memristive Array: Application to Neuromorphic Cameras

引用

IEEE ACCESS 2023年 11卷 146103-146121页

作者： Lewden, Pierre Vincent, Adrien F. Tomas, Jean Saighi, Sylvain CNRS CREATE Singapore 138602 Singapore Univ Bordeaux CNRS Bordeaux INP IMSUMR 5218 F-33400 Talence France

The massive deployment of the Internet of Things (IoT) combined with the need to reduce its impact on global energy consumption calls for the design of intelligent sensors. These sensors must be able to process information in situ to reduce the amount of data to be transferred, and to perform computing at low energy cost. Therefore, the design of intelligent sensors requires a compromise between performance and energy consumption. Spiking neural networks (SNNs) are good candidates for achieving the goal of an efficient intelligent sensor, as they use event-based computation. Interest for hardware implementation of SNNs has bloomed since the first experimental observation of memristors in 2008. In this paper, we study, by simulation means, the impact of the main technological parameters of Ferroelectric Tunnel Junctions (FTJs) synapses and of analog Leaky Integrate-and-Fire (LIF) neurons on the system learning capabilities. This allows us to determine which parameters are critical for the design of such systems and to suggest mitigation solutions as well as guidelines on how to build a SNN-based smart vision sensor in the context of unsupervised or reward-modulated learning. In particular, we show that splitting up the passive crossbar array of memristors could help dealing with the detrimental effect of the input voltage offset of the postsynaptic neurons.

关键词： Edge computing memristors passive crossbar reward-modulated learning spiking neural networks unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Updates on the Complexity of SHAP Scores 33

Updates on the Complexity of SHAP Scores

引用

33rd International Joint Conference on Artificial Intelligence (IJCAI)

作者： Huang, Xuanxiang Marques-Silva, Joao CNRS CREATE Singapore Singapore Univ Lleida ICREA Lleida Spain

ISBN: (纸本)9781956792041

SHAP scores represent one of the most widely used methods of explainability by feature attribution, as illustrated by the explainable AI tool SHAP. A number of recent works studied the computational complexity of the exact computation of SHAP scores, covering a comprehensive range of families of classifiers. This paper refines some of the existing complexity claims, including families of classifiers for which the computation of SHAP scores is computationally hard and those for which there exist polynomial-time algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Event-based Line Detection on SpiNNaker 6

Neuromorphic Event-based Line Detection on SpiNNaker

引用

6th International Conference on AI Circuits and Systems (AICAS)

作者： Gruel, Amelie Vincent, Adrien F. Martinet, Jean Saighi, Sylvain Univ Bordeaux Lab Integrat Mat Syst Bordeaux INP CNRS Talence France Univ Cote dAzur CNRS Lab I3S Sophia Antipolis France CNRS CREATE 1 Create Way08-10 Create Tower Singapore 138602 Singapore

ISBN: (纸本)9798350383638;9798350383645

The combined use of Spiking Neural Networks (SNNs) and neuromorphic data in recent years makes for a promising solution to the challenges currently raised in computer vision. Indeed, the natural match between SNNs and event data leads to improvements in terms of biological inspiration, energy savings, latency and memory use for dynamic visual data processing, especially when such networks are implemented on neuromorphic hardware. We propose to draw advantages from these technologies to propose, to the best of our knowledge, the first end-to-end neuromorphic model for straight line detection, a standard task in robotics and computer vision. Our architecture relies on SNN intrinsic dynamics and ensures the accurate detection of moving lines recorded by an event-based camera with no learning. It reaches an overall performance of over 90% with a limited number of neurons and synapses allowing for its deployment on the neuromorphic board SpiNNaker.

关键词： neuromorphic spiking neural network event-based camera SpiNNaker

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：