This special issue explores how emerging machine learning (ML) and artificial intelligence (AI) algorithms can help computer networks become smarter. The final goal is to disseminate cutting-edge research findings and...
详细信息
This special issue explores how emerging machine learning (ML) and artificial intelligence (AI) algorithms can help computer networks become smarter. The final goal is to disseminate cutting-edge research findings and computer network advances on innovative data-driven methodologies and technologies to grow innovation in ML-empowered communication networks. This particular issue aims to present advances on cross-cutting edge machine learning solutions tailored to the computer communication networking area, focusing on algorithmic aspects. The objective is to present which ML methodologies are the most effective and promising ones in the networking context so that they can inspire other researchers and practitioners in the research area of computer networks.
Electric Vehicles (EVs) represent a paradigm shift in the automotive industry, offering a sustainable alternative to traditional engines. However, the efficient diagnosis of EV performance remains a formidable challen...
详细信息
ISBN:
(纸本)9798350387032;9798350387025
Electric Vehicles (EVs) represent a paradigm shift in the automotive industry, offering a sustainable alternative to traditional engines. However, the efficient diagnosis of EV performance remains a formidable challenge, exacerbated by the intrinsic noise interference associated with speed variations. This paper introduces an innovative approach to mitigate these diagnostic challenges by harnessing constant speed subranges as a strategic diagnostic window. The methodology centers on the identification of the most frequent constant speed subranges, which serve as optimal periods for signal recording from EV electric motors. We propose a novel algorithm that identifies these subranges, initially trained, tested, and validated using the Worldwide Harmonized Light Vehicles Test Cycle (WLTC) dataset, the model is compared with four other models and show less variation ratio in the detected subranges. The crux of this approach lies in the recording and analysis of key motor signals - current, vibration, among others - within these identified subranges. The data derived from these periods are then utilized to train diagnostic algorithms, specifically tuned to the nuances of each subrange. The implementation of this strategy in real-world driving conditions involves the dynamic selection of appropriate diagnostic models aligned with the detected speed subranges. This targeted approach diminishes the impact of noise interference and paves the way for personalized data-driven diagnostics. The proposed method aims to reduces the complexity and enhances the efficacy of diagnostic algorithms, offering a tailored diagnostic solution that adapts to individual driving patterns.
In today's fast-paced world, many individuals struggle to maintain a balanced diet, leading to various nutritional deficiencies. Effective management and education on these deficiencies are crucial for improving p...
详细信息
ISBN:
(纸本)9798331540661;9798331540678
In today's fast-paced world, many individuals struggle to maintain a balanced diet, leading to various nutritional deficiencies. Effective management and education on these deficiencies are crucial for improving public health. Traditional methods of addressing nutritional deficiencies often lack personalization and user engagement. The NutriGuide application, developed using the Flutter framework, aims to revolutionize nutritional management by providing a user-centric, cross-platform solution. Utilizing a comprehensive database of nutrients and symptoms, the application offers personalized dietary recommendations based on user inputs. The dataset includes detailed information on common deficiencies, symptoms, and nutrient-rich foods. Experimental results indicate high user satisfaction, with an average satisfaction score of 4.5 out of 5, and significant improvements in nutritional intake, such as a 28.6% increase in Vitamin A intake and a 50% increase in Vitamin D intake. In conclusion, NutriGuide presents an innovative approach to nutritional health, combining modern technology with evidence-based recommendations to empower users in managing their dietary needs.
The work covers the development of a data-driven algorithm and computes the performance of learning models for lithium-ion battery state of health (SOH) estimation. A wide range of environmental and temperature condit...
详细信息
The work covers the development of a data-driven algorithm and computes the performance of learning models for lithium-ion battery state of health (SOH) estimation. A wide range of environmental and temperature conditions (15 degree celsius, 25 degree celsius, and 35 degree celsius) at different charging and discharging rates of 1C and 2C are used for electric vehicle battery health estimation. The result of the tested data of cell 'a' is validated with a different set of cell 'b' on identical test parameters, and the results are tabulated and compared. At 25 degree celsius, the mean absolute errors for the regression algorithms decision tree (DT), k-nearest neighbor (KNN), and random forest (RF) are 3.78641E-03, 3.62524E-03, and 6.16931E-03. The mean absolute percent error for regression algorithms DT, KNN, and RF is 1.48921E-03, 1.40631E-03, and 2.40260E-03. The root mean square error for regression algorithms DT, KNN, and RF is 1.26813E-02, 9.73320E-03, and 1.17238E-02, and the mean squared error for regression algorithms DT, KNN, and RF is 1.60816E-04, 9.47351E-05, and 1.37448E-04. The results show that the KNN and DT methods accurately estimate the SOH under diversified operating conditions in comparison with RF methods and can foster advanced battery health monitoring systems.
Different clusters of abnormal activities often arise within same temporal domain of drilling operations. This contrasts with employing simplified scenarios, such as anomaly detection models for specific issues like s...
详细信息
Different clusters of abnormal activities often arise within same temporal domain of drilling operations. This contrasts with employing simplified scenarios, such as anomaly detection models for specific issues like stuck pipe or loss circulation. The dynamic nature of drilling environments demands a holistic framework that can adapt to evolving conditions and detect anomalies beyond predefined categories. There exists a need to evaluate the performance of various data -driven models and achieve a broader applicability of anomaly detection instead of focusing on a single abnormal activity type. This study presents a generalized framework designed to detect anomalous events in drilling operations. Three different unsupervised learning algorithms, principal component analysis (PCA), isolation forest (IF) and lstm-autoencoder (LSTM-AE), are used to determine abnormal patterns and irregularities in the drilling data. PCA is chosen for its interpretability and efficiency in handling high -dimensional data by reducing the dimensionality. IF is selected for its effectiveness in isolating anomalies, making it robust for scenarios where anomalies exhibit distinct patterns. LSTM-AE is employed due to its capability to capture temporal dependencies and nonlinear patterns in time series data. A multivariate time series of drilling data from an offshore well is collected to use in this work. The dataset comprises approximately six months of drilling operations, including drilling and non -drilling periods. The input variables are chosen from the common controllable parameters continuously monitored by the drilling crew. The pre-processed drilling data with input features is organized into groups based on each drilling section. These unlabeled data is split into train, validation and test sets. Cross -validation (CV) is applied into train and validation sets to prevent overfitting and tune the hyperparameters. The test data is used to evaluate the generalizability and robustness
data-driven algorithms can adapt their internal structure or parameters to inputs from unknown application-specific distributions, by learning from a training sample of inputs. Several recent works have applied this a...
详细信息
data-driven algorithms can adapt their internal structure or parameters to inputs from unknown application-specific distributions, by learning from a training sample of inputs. Several recent works have applied this approach to problems in numerical linear algebra, obtaining significant empirical gains in performance. However, no theoretical explanation for their success was known. In this work we prove generalization bounds for those algorithms, within the PAC-learning framework for data-driven algorithm selection proposed by Gupta and Roughgarden (SICOMP 2017). Our main results are closely matching upper and lower bounds on the fat shattering dimension of the learning-based low rank approximation algorithm of Indyk et al. (NeurIPS 2019). Our techniques are general, and provide generalization bounds for many other recently proposed data-driven algorithms in numerical linear algebra, covering both sketching-based and multigrid-based methods. This considerably broadens the class of data-driven algorithms for which a PAC-learning analysis is available.
In this paper, a novel method is proposed based on a windowed one-dimensional convolutional neural network (1D CNN) for multiclass damage identification using vibration responses of a full-scale bridge. The measured d...
详细信息
In this paper, a novel method is proposed based on a windowed one-dimensional convolutional neural network (1D CNN) for multiclass damage identification using vibration responses of a full-scale bridge. The measured data are first augmented by extracting samples of windows of raw acceleration time series to alleviate the problem of a limited training data set. 1D CNN is developed to classify the windowed time series into multiple damage classes. The damage is quantified using the predicted class probabilities, and the damage is localized if the predicted class is equal to the assigned damage class, exceeding a threshold associated with majority voting. The proposed network is optimally tuned with respect to various hyperparameters such as window size and random initialization of weights to achieve the best classification performance using a global 1D CNN model. The proposed method is validated using a benchmark bridge data for multiclass classification for two different damage scenarios, namely, pier settlement and rupture of tendons, under the various extents of damage. The damage identification is carried out on various bridge components to collectively identify the structural component with a damaged signature. The results show that the proposed windowed 1D CNN method achieves an accuracy of 97%, and performs well with different types of damage.
We study the moment matching problem for linear systems in a discrete-time setting and introduce a family of reduced-order models that can replicate the steady-state response of the underlying system. We show that red...
详细信息
The online knapsack problem is a classic online resource allocation problem in networking and operations research. Its basic version studies how to pack online arriving items of different sizes and values into a capac...
详细信息
The online knapsack problem is a classic online resource allocation problem in networking and operations research. Its basic version studies how to pack online arriving items of different sizes and values into a capacity-limited knapsack. In this paper, we study a general version that includes item departures, while also considering multiple knapsacks and multi-dimensional item sizes. We design a threshold-based online algorithm and prove that the algorithm can achieve order-optimal competitive ratios. Beyond worst-case performance guarantees, we also aim to achieve near-optimal average performance under typical instances. Towards this goal, we propose a data-driven online algorithm that learns within a policy-class that guarantees a worst-case performance bound. In trace-driven experiments, we show that our data-driven algorithm outperforms other benchmark algorithms in an application of online knapsack to job scheduling for cloud computing.
Robots that operate in social settings must be able to recognize, understand, and reason about human conversational groups (i.e., F-formations). While several algorithms have been developed for identifying such groups...
详细信息
ISBN:
(数字)9781665407311
ISBN:
(纸本)9781665407311
Robots that operate in social settings must be able to recognize, understand, and reason about human conversational groups (i.e., F-formations). While several algorithms have been developed for identifying such groups, there has been little research on how robots might reason about inaccuracies following group classification (e.g., recognizing only 4 of 5 group members). We address this gap through a data-driven approach that builds knowledge of human group positioning. By analyzing multiple conversational group data sets, we have developed a system for identifying high probability regions that indicate areas where people are likely to stand in a group relative to a single anchor participant. We use knowledge of these regions to train two models, which we implement on a social robot. The first model can estimate the true size of a partially-observed conversational group (i.e., a group where only some of the participants were detected). Our second model can predict the locations where any undetected participants are likely to reside. Together, these models may improve F-formation detection algorithms by increasing robustness to noisy input data.
暂无评论