检索结果-内蒙古大学图书馆

Onfire 2023 Contest: what did we learn about real time fire detection from cameras?

Journal of Ambient Intelligence and Humanized Computing 2025年第1期16卷 253-264页

作者： Gragnaniello, Diego Greco, Antonio Sansone, Carlo Vento, Bruno Department of Information and Electrical Engineering and Applied Mathematics University of Salerno Fisciano Italy Department of Electrical Engineering and Information Technology University of Napoli Federico II Naples Italy

Several methods for fire detection from camera streams have been proposed in recent years. While traditional techniques often emphasize recall, they frequently neglect critical factors such as minimizing false positives, ensuring timely alarm notifications and optimizing performance for devices with limited computational resources. The ONFIRE 2023 contest evaluates various approaches for detecting fire using smart cameras and establishes new evaluation metrics to measure precision, recall, notification promptness, processing speed and resource utilization. The eight participating teams received a training set that integrated all publicly available video datasets and were evaluated on a private test set. The latter includes positive samples where fire is not present at the beginning of the clip, as well as negative samples featuring moving fire-like objects. In this paper, we provide an overview of the competition’s dataset and review the proposed solutions, highlighting the winning approach, the limitations of existing datasets and the evaluation metrics used. By analyzing the results of the competition, we propose possible design choices and future directions that may help to reduce the false positive rate while preserving accuracy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Optimizing Crowd Counting in Dense Environments Through Curriculum Learning Training Strategy

引用

SN Computer Science 2024年第6期5卷 683页

作者： Fotia, Lidia Percannella, Gennaro Saggese, Alessia Vento, Mario Department of Information Engineering Electrical Engineering and Applied Mathematics (DIEM) University of Salerno Fisciano Italy

Counting individuals in highly crowded environments, characterized by thousands of people, has garnered significant attention in recent years, due to the high number of vertical markets wherein such algorithms can prove beneficial, ranging from smart city and transportation to retail sectors, among others. Within this context, in this paper we introduce a novel training methodology tailored for estimating the number of people, ensuring precise counting accuracy in both moderately and highly crowded scenarios. The proposed approach exploits a formulation of the problem based on point detection, where each point represents an individual’s head. Our innovative contributions center around the designing of a novel training strategy employing Curriculum Learning (CL), which aims to replicate the gradual learning process observed in human cognition, training on simpler tasks at the beginning and tackling more complex tasks as the training evolves. In order to evaluate the complexity of each sample image, we propose a novel indicator taking into account both the number of people and their distribution within the image. The experimentation phase encompassed 18 publicly available datasets;the obtained results validate the effectiveness of the proposed approach, surpassing the baseline state-of-the-art point detection by 71% and 70% in terms of Mean Absolute Error (MAE) and Mean Squared Error (MSE), respectively. © The Author(s) 2024.

关键词： Curriculum Learning High density crowd counting Point detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Network Security with Graph Neural Networks for Node Anomaly Detection

Enhancing IoT Network Security with Graph Neural Networks f...

引用

Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition and Structural and Syntactic Pattern Recognition, S+SSPR 2024

作者： Carletti, Vincenzo Foggia, Pasquale Rosa, Francesco Vento, Mario Department of Information Engineering Electrical Engineering and Applied Mathematics University of Salerno Fisciano Italy

ISBN: (纸本)9783031805066

The widespread deployment of Internet of Things (IoT) devices in homes, industries, and public spaces presents significant cybersecurity challenges, particularly due to their limited computational capabilities and often insecure configurations. Detecting infected devices through network analysis presents a significant challenge given the diversity of network protocols and behaviors. Traditional methods, reliant on packet statistics or binary signatures, show their limits in these complex environments. Recent advancements in machine learning and deep learning offer promising alternatives, also through the use of graph-based representations that capture network topology and facilitate the detection of complex attack patterns. This paper presents a comprehensive analysis in a realistic setup of two state-of-the-art Graph Neural Networks (GNNs) designed for node anomaly detection, applied to a large-scale dataset of IoT network traffic. The dataset, comprising over 240,000 graphs extracted from IoT23, IoTID20, and IoT-Traces, includes both benign and malicious communications. In the analysis we take into account the impact of varying snapshot durations and graph-based representations on the performance achieved by the GNNs. The results suggest that using a state-of-the-art graph autoencoder (DOMINANT) with a computationally efficient representation (TDG) is the best trade-off among the considered constraints and variables. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Combining Deep Networks with Model-Based Scene Segmentation for Reliably Detecting Rocks on Railway Tracks 8

Combining Deep Networks with Model-Based Scene Segmentation ...

引用

8th IEEE International Forum on Research and Technologies for Society and Industry Innovation, RTSI 2024

作者： Carletti, Vincenzo Foggia, Pasquale Ranieri, Speranza Saggese, Alessia Spingola, Camilla Vento, Mario University of Salerno Department of Information and Electrical Engineering and applied Mathematics Italy

ISBN: (纸本)9798350362138

Railway transportation is crucial to global mobility, serving as a sustainable conduit for transporting goods and passengers;unfortunately, it is vulnerable to different threats, like the presence of rocks on railway tracks. Accidents caused by rocks can disrupt transport schedules, damage infrastructure, and even lead to injuries or fatalities. Addressing these safety challenges is very important for ensuring the operation of rail networks, which in turn enhances overall mobility and minimizes delays, but also for protecting lives. In this paper, we propose a novel approach to detect rocks on the railway tracks using a camera mounted on the train's front-end. In particular, we exploit domain-specific knowledge regarding intrinsic characteristics of the camera, its positioning with respect to the rails and rail-track characteristics, together with the output of a deep neural network for semantic segmentation, to identify the railway track in the image. Once the track area is identified, it is partitioned into patches and a convolutional neural network is applied to analyze these patches and to detect the presence of rocks;furthermore, in order to enhance the robustness of the detection process, we employ a majority voting mechanism across a sequence of video frames. The experimentation, conducted over six videos augmented with the presence of rocks, confirm the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Ant Colony Algorithm Approach to the Vehicle Routing Problem and Variants

An Ant Colony Algorithm Approach to the Vehicle Routing Prob...

引用

2024 Systems and Information engineering Design Symposium, SIEDS 2024

作者： Tablada, Tulio Davis, Cleon Palumbo, Neil Johns Hopkins University Electrical and Computer Engineering Program Johns Hopkins University Applied and Computational Mathematics Program United States

ISBN: (纸本)9798350385144

In the basic vehicle routing problem (VRP), a vehicle must deliver goods from one centralized warehouse to multiple customers efficiently. Several VRP variants and constraints exist, including different product types, specific delivery times, multiple warehouses, vehicle fuel constraints, and pick-up from one location and delivery to another. This work proposes and demonstrates a flexible algorithm for solving the VRP via ant colony optimization (ACO) that can address many of the variants discussed above. ACO algorithms mimic the behavior of ants, learning optimal paths to a food source and back to the nest based on stigmergic behavior. This work compares a proposed, more flexible ACO algorithm to a traditional optimization algorithm that is implemented in the Google VRP solver. Readily available data were used to test and demonstrate results. Several VRP variants were implemented in both the (proposed) flexible ACO algorithm and the Google VRP solver. The flexible ACO algorithm performed better in terms of distance traveled versus the Google VRP solver for two variants and worse for three other cases. However, the Google VRP solver was not able to solve some of the VRP variant combinations considered here and failed when solving some backhaul datasets. Because the flexible ACO algorithm was able to better handle many case variations, it may be an attractive alternative optimization tool. © 2024 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Improved Bounds on the Size of Permutation Codes Under Kendall τ-Metric

引用

IEEE Transactions on Information Theory 2025年第6期71卷 4156-4166页

作者： Parvaresh, Farzad Sobhani, Reza Abdollahi, Alireza Bagherian, Javad Jafari, Fatemeh Khatami, Maryam University of Isfahan Faculty of Engineering Department of Electrical Engineering Isfahan81746-73441 Iran School of Mathematics Tehran19395-5746 Iran University of Isfahan Faculty of Mathematics and Statistics Department of Applied Mathematics and Computer Science Isfahan81746-73441 Iran University of Isfahan Faculty of Mathematics and Statistics Department of Pure Mathematics Isfahan81746-73441 Iran

In order to overcome the challenges caused by flash memories and also to protect against errors related to reading information stored in DNA molecules in the shotgun sequencing method, the rank modulation method has been proposed. In the rank modulation framework, codewords are permutations. In this paper, we study the largest size P(n, d) of permutation codes of length n, i.e., subsets of the set Sn of all permutations on {1, . . . , n} with the minimum distance at least d ∈ {1, . . . ,(Formula presented)} under the Kendall τ-metric. By presenting an algorithm and two theorems, we improve the known lower and upper bounds for P(n,d) . In particular, we show that P(n,d)=4 for all n ≥ 6 and (Formula presented) (Formula presented) © 1963-2012 IEEE.

关键词： Flash memory

来源：评论

学校读者我要写书评

暂无评论

Lyapunov-guided representation of recurrent neural network performance

引用

Neural Computing and Applications 2024年第34期36卷 21211-21226页

作者： Vogt, Ryan Zheng, Yang Shlizerman, Eli Department of Applied Mathematics University of Washington SeattleWA98195 United States Department of Electrical and Computer Engineering University of Washington SeattleWA98195 United States

Recurrent neural networks (RNN) are ubiquitous computing systems for sequences and multivariate time-series data. While several robust RNN architectures are known, it is unclear how to relate RNN initialization, architecture, and other hyperparameters with accuracy for a given task. In this work, we propose treating RNN as dynamical systems and correlating hyperparameters with accuracy through Lyapunov spectral analysis, a methodology designed explicitly for nonlinear dynamical systems. To address the fact that RNN features go beyond the existing Lyapunov spectral analysis, we propose to infer relevant features from the Lyapunov spectrum with an Autoencoder and an embedding of its Latent representation (AeLLE). Our studies of various RNN architectures show that AeLLE successfully correlates RNN Lyapunov spectrum with accuracy. Furthermore, the Latent representation learned by AeLLE is generalizable to novel inputs from the same task and is formed early in the process of RNN training. The latter property allows for predicting the accuracy to which RNN would converge when training is complete. We conclude that the representation of RNN through the Lyapunov spectrum, along with AeLLE, provides a novel method for the organization and interpretation of variants of RNN architectures. © The Author(s) 2024. corrected publication 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimum classical beam-position sensing

引用

Physical Review applied 2024年第4期22卷 L041004页

作者： Wenhua He Christos N. Gagatsos Dalziel J. Wilson Saikat Guha Wyant College of Optical Sciences Department of Electrical and Computer Engineering Program in Applied Mathematics

Beam-displacement measurements are widely used in optical sensing and communications; however, their performance is affected by numerous intrinsic and extrinsic factors, including beam profile, propagation loss, and receiver architecture. Here we present a framework for designing a classically optimal beam-displacement transceiver, using quantum estimation theory. We consider the canonical task of estimating the position of a diffraction-limited laser beam after passing through an apertured volume characterized by Fresnel-number product DF. As a rule of thumb, higher-order Gaussian modes provide more information about beam displacement, but are more sensitive to loss. Applying quantum Fisher information, we design mode combinations that optimally leverage this trade-off, and show that a greater than tenfold improvement in precision is possible, relative to the fundamental mode, for a practically relevant DF=100. We also show that this improvement is realizable with a variety of practical receiver architectures. Our findings extend previous works on lossless transceivers, may have immediate impact on applications, such as atomic force microscopy and near-field optical communication, and pave the way towards globally optimal transceivers using nonclassical laser fields.

关键词： Classical optics Metrology Quantum Fisher information Quantum optics Quantum parameter estimation Devices Wireless communication networks Atomic force microscopy

来源：评论

学校读者我要写书评

暂无评论

Wigner non-negative states that verify the Wigner entropy conjecture

引用

Physical Review A 2024年第1期110卷 012228-012228页

作者： Qipeng Qian Christos N. Gagatsos Program in Applied Mathematics The Department of Electrical and Computer Engineering The Wyant College of Optical Sciences The

We present further progress, in the form of analytical results, on the Wigner entropy conjecture set forth by Van Herstraeten and Cerf [Phys. Rev. A 104, 042211 (2021)] and Hertz et al. [J. Phys. A: Math. Theor. 50, 385301 (2017)]. Said conjecture asserts that the differential entropy defined for non-negative, yet physical, Wigner functions is minimized by pure Gaussian states while the minimum entropy is equal to 1+lnπ. We prove this conjecture for the qubits formed by Fock states |0〉 and |1〉 that correspond to non-negative Wigner functions. In particular, we derive an explicit form of the Wigner entropy for those states lying on the boundary of the set of Wigner non-negative qubits. We then consider general mixed states and derive a sufficient condition for the conjecture's validity. Lastly, we elaborate on the states which are in accordance with our condition.

关键词： Quantum foundations Quantum information theory

来源：评论

学校读者我要写书评

暂无评论

A Comparative Assessment of eXplainable AI Tools in Predicting Hard Disk Drive Health 32

A Comparative Assessment of eXplainable AI Tools in Predicti...

引用

32nd Italian Symposium on Advanced Database Systems, SEBD 2024

作者： Amato, Flora Ferraro, Antonino Galli, Antonio La Gatta, Valerio Moscato, Francesco Moscato, Vincenzo Postiglione, Marco Sansone, Carlo Sperlì, Giancarlo Department of Electrical Engineering and Information Technology University of Naples Federico II Italy Department of Information Engineering Electrical Engineering and Applied Mathematics University of Salerno Italy

In addressing the challenge of optimizing maintenance operations in Industry 4.0, recent efforts have focused on predictive maintenance frameworks. However, the effectiveness of these frameworks, largely relying on complex deep learning models, is hindered by their lack of explainability. To address this, we employ eXplainable Artificial Intelligence (XAI) methodologies to make the decision-making process more understandable for humans. Our study, based on a previous work, specifically explores explanations for predictions made by a recurrent neural network-based model designed for a three-dimensional dataset, used to estimate the Remaining Useful Life (RUL) of Hard Disk Drives (HDDs). We compare the explanations provided by different XAI tools, emphasizing the utility of global and local explanations in supporting predictive maintenance tasks. Using the Backblaze Dataset and a Long Short-Term Memory (LSTM) prediction model, our developed explanation framework evaluates Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) tools. Results show that SHAP outperforms LIME across various metrics, establishing itself as a suitable and effective solution for HDD predictive maintenance applications. © 2024 Copyright for this paper by its authors.

关键词： Predictive maintenance

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：