the Internet of things has seamlessly integrated into various facets of our daily lives, playing a pivotal role in sectors like security, transportation, smart homes, and healthcare. Across these domains, IoT employs ...
详细信息
Dynamic time warping (DTW) has been applied to a wide range of machinelearning problems involving the comparison of time series. An important feature of such time series is that they can sometimes be sparse in the se...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Dynamic time warping (DTW) has been applied to a wide range of machinelearning problems involving the comparison of time series. An important feature of such time series is that they can sometimes be sparse in the sense that the data takes zero value at many epochs. this corresponds for example to quiet periods in speech or to a lack of physical activity. However, employing conventional DTW for such sparse time series runs a full search ignoring the zero data. Sparse dynamic time warping (SDTW) was previously developed which yields the exact DTW solution while reducing the time complexity by the order of a suitably defined sparsity ratio. this paper focuses on the development and analysis of a fast approximate algorithm for dynamic time warping based on the SDTW framework. We call this fast sparse dynamic time warping (FSDTW). this study includes numerical experiments which compare the performance and complexity of FSDTW with DTW, SDTW and other algorithms that approximate DTW for sparse time series. It is shown that FSDTW reduces the time complexity relative to SDTW by the order of the sparsity ratio with negligible error relative to the exact DTW distance.
Mobility patternrecognition is a central aspect of transportation and datamining research. Despite the development of various machinelearning techniques for this problem, most existing methods face challenges such ...
详细信息
ISBN:
(纸本)9783031398308;9783031398315
Mobility patternrecognition is a central aspect of transportation and datamining research. Despite the development of various machinelearning techniques for this problem, most existing methods face challenges such as reliance on handcrafted features (e.g., user has to specify a feature such as "travel time") or issues withdata imbalance (e.g., fewer older travelers than commuters). In this paper, we introduce a novel data Balancing Generative Adversarial Network (DBGAN), which is a specifically designed attention mechanism-based GAN model to address these challenges in mobility patternrecognition. DBGAN captures both static (e.g., travel locations) and dynamic (e.g., travel times) features of different passenger groups, and avoids using handcrafted features that may result in information loss, based on a sequence-to-image embedding method. Our model is then applied to overcome the data imbalance issue and perform mobility patternrecognition. We evaluate the proposed method on real-world public transportation smart card data from Suzhou, China, and focus on recognizing two different passenger groups: older people and students. the results of our experiments demonstrate that DBGAN is able to accurately identify the different passenger groups in the data, withthe detected mobility patterns being consistent withthe ground truth. these results highlight the effectiveness of DBGAN in overcoming data imbalance in mobility patternrecognition, and demonstrate its potential for wider use in transportation and datamining applications.
A machinelearning (ML) fairness estimator, which is used to assess an ML model's fairness, should satisfy several conditions when used in real-life settings. Specifically, it should: i) support a comprehensive fa...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
A machinelearning (ML) fairness estimator, which is used to assess an ML model's fairness, should satisfy several conditions when used in real-life settings. Specifically, it should: i) support a comprehensive fairness evaluation that explores all ethical aspects;ii) be flexible and support different ML model settings;iii) enable comparison between different evaluations and ML models;and iv) provide reasoning and explanations for the fairness assessments produced. Existing methods do not sufficiently satisfy all of the above conditions. In this paper, we present FEPC (Fairness Estimation using Prototypes and Critics for tabular data), a novel method for fairness assessment that provides explanations and reasoning for its assessments by using an adversarial attack and customized fairness measurement. Given an ML model and data records, FEPC performs a comprehensive fairness evaluation and produces a fairness assessment for each examined feature. FEPC was evaluated using two benchmark datasets (ProPublica COMPAS and Statlog datasets) and a synthetic dataset containing two features, one of which is biased and one of which is fair, and compared to existing fairness assessment methods. the evaluation demonstrates that FEPC satisfies all of the conditions, making it suitable for real-life settings, and outperforms existing methods.
this paper focuses on human activity recognition using LSTM (Long Short-Term Memory) for handling time series data issues. Because LSTM can better deal withthe correlation and long-term correlation of time-series dat...
详细信息
Artificial Intelligence (AI) and machinelearning (ML) models have proven to be scalable approaches for handling several biomedical problems. Recent availability of high-quality datasets which captures various factors...
详细信息
Withthe expanding application areas of IoT, smart fitness has become an area of growing interest. IoT based fitness trackers are already playing an important role in the smart fitness domain. this paper presents a hi...
详细信息
this research presents the development and evaluation of SPEAR, an advanced voice-activated personal desktop assistant designed to address challenges in existing virtual assistant technology, such as limited language ...
详细信息
the proceedings contain 23 papers. the topics discussed include: efficient, immutable and privacy preserving e-healthcare systems using blockchain;an untraceable monitoring for patients using wireless medical sensor n...
ISBN:
(纸本)9798350337211
the proceedings contain 23 papers. the topics discussed include: efficient, immutable and privacy preserving e-healthcare systems using blockchain;an untraceable monitoring for patients using wireless medical sensor networks;angle estimation using weighted beam pattern in frequency diverse array radar;co-clustering based hybrid collaborative filtering model;mosquitoes species classification using acoustic features of wing beats;detection and analysis of mental health illness using social media;reduce emergency response time using machinelearning technique;protection mechanism against software supply chain attacks through blockchain;electricity theft detection via deep learning;data centers sustainability: approaches to green data centers;a comparative analysis of implementation of privacy by design principles on different blockchain platforms;and machinelearning based encrypted content type identification.
the terms of using machinelearning and the protection of privacy via the use of federated learning in healthcare, specifically in the case of the ASCO program, have now come to a close. this study focuses on the curr...
详细信息
暂无评论