Real-time traffic prediction offers valuable tools for efficient traffic operation through timely and accurate information to road users and agencies. Despite the prevalence of data-driven approaches in traffic predic...
详细信息
ISBN:
(纸本)9798350399462
Real-time traffic prediction offers valuable tools for efficient traffic operation through timely and accurate information to road users and agencies. Despite the prevalence of data-driven approaches in traffic prediction with the advent of big data, these methods struggle to respond to unforeseen traffic situations during real-time prediction. To address this issue, we propose a hybrid model that integrates both data-driven and model-based approaches. Our model augments historical data using traffic simulation for unexpected traffic situations such as sudden speed drops on a road section, which can cause significant prediction errors. An artificial neural network is used to balance between the collected historical data and the augmented data. The proposed model was evaluated by predicting traffic conditions of an actual road section and significantly improved prediction accuracy. Our proposed method represents a state-of-the-art solution for enhancing realtime traffic prediction under the hybrid framework.
Seizures pose a significant health hazard for over 50 million individuals with epilepsy worldwide, with approximately 56% experiencing uncontrollable seizures according to the CDC. Predicting seizures is challenging e...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
Seizures pose a significant health hazard for over 50 million individuals with epilepsy worldwide, with approximately 56% experiencing uncontrollable seizures according to the CDC. Predicting seizures is challenging even with the availability of various sensors (gyroscopes, pulse rate sensors, heart rate monitors, etc). Electroencephalography (EEG) data can directly measure the activity of the brain and has been the choice of leveraging deep learning (DL) models for seizure prediction. Despite DL models achieving over 95% accuracy on retroactive clinical-grade EEG data, this performance fails to translate in real-world settings where the accuracy goes down to 66% which warrants further investigation. Moreover, consumer-grade wearable EEG headsets, characterized by lower data quality and a varying number of channels across brands, present additional challenges. In this paper, we estimate the robustness of DL models which are trained on clinical-grade EEG data but tested on the type of data expected from consumer-grade wearable EEG headsets. We select the previously published model SPERTL to estimate its robustness when: (1) predicting with data from less leads/channels, (2) predicting when faced with streaming data, (3) evaluating performance on imbalanced data with more interictal segments. Our results are compared against baseline results from the SPERTL model which we have re-configured to operate independently of the number of channels with an average baseline area under the curve (AUC) score of 98.56%. Our results demonstrate that though the model is surprisingly resilient to streaming and noisy data, reducing the number of channels and a higher class imbalance have a more severe degradation. The AUC across all cross-validation sets degrades only by 2% and 3% on average for noisy and streaming data, respectively. However, a performance reduction, on average, is observed by 32% when imbalance is increased with higher percentage of interictal samples, and up to 16
Indoor Air Quality (IAQ) significantly impacts people's health and comfort in buildings. Although IAQ research spans two decades, a comprehensive assessment of factors affecting indoor air pollution remains elusiv...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
Indoor Air Quality (IAQ) significantly impacts people's health and comfort in buildings. Although IAQ research spans two decades, a comprehensive assessment of factors affecting indoor air pollution remains elusive. Recent efforts focus on real-time monitoring using virtual sensing, a computational technique in engineering and datascience. This paper presents a novel IAQ monitoring system emphasizing dynamic sensor placement for enhanced efficiency. The system employs random sensor positions and calculates measurement predictability, allowing identification and removal of less useful sensors, reducing data volume, and saving energy. Multiple reduction strategies are available, depending on the target number of edge devices or the desired maximum prediction error. Importantly, the system operates locally, without relying on internet connectivity. It consists of edge devices using air quality sensors, a gateway for data gathering and algorithm initiation, by training and evaluating multiple different machine learning techniques to determine point combination predictability. Deployed in two indoor settings, one with HVAC and the other naturally ventilated, the system's effectiveness is assessed, shortcomings identified, and conclusions drawn for future work.
Quantum computers, leveraging superposition and entanglement, offer significant qubit efficiency for data processing compared to classical systems. However, encoding classical data into quantum states, given the curre...
Graph Neural Network (GNN)-based recommendation systems have become very popular in recent years. Their popularity stems from the fact that nodes can access higher-order neighbor information and there are well-designe...
详细信息
Blockchain technology ensures secure and trust-worthy data flow between multiple participants on the chain, but interoperability of on-chain and off-chain data has always been a difficult problem that needs to be solv...
详细信息
Searchable encryption enables secure searches over encrypted data in the cloud. Among all paradigms, public key encryption with keyword search (PEKS) is particularly desirable by privacy-preserving distributed computi...
详细信息
ISBN:
(纸本)9798350339864
Searchable encryption enables secure searches over encrypted data in the cloud. Among all paradigms, public key encryption with keyword search (PEKS) is particularly desirable by privacy-preserving distributed computing and IoT applications, since it allows multiple parties (i.e., writers) to independently contribute encrypted data. However, a PEKS search usually requires a linear scan over the entire dataset for keyword search, causing unacceptable latency when facing a large amount of data. All existing efforts to speed up multi-writer searchable encryption are based on conventional hardness assumptions for security, which can be broken provided the advent of quantum computers. In this work, we propose a lattice-based multi-writer searchable encryption scheme, which lets writers build indices for their outsourced data to make keyword searches faster. Meanwhile, the security of the proposed solution relies on the learning with errors assumption, which is known to withstand the potential attack from quantum computers.
In recent years, the underwater acoustic sensor network (UASN) is emerging as an effective means for marine data collection. However, due to the limited bandwidth of acoustic channel, the limited constrained energy su...
详细信息
ISBN:
(纸本)9798350386288;9798350386271
In recent years, the underwater acoustic sensor network (UASN) is emerging as an effective means for marine data collection. However, due to the limited bandwidth of acoustic channel, the limited constrained energy supply of underwater sensors and data redundancy, it is impossible to deliver all the raw data generated by underwater sensors. Hence, to compress time-redundant data at a sensor node is of great significance for data collection from underwater sensors. Moreover, the underwater acoustic transmission link is unreliable, the issue of data collection with certain packet error resilience should be resolved. In this paper, a packet-loss-and-error-resilient data collection method based on convolutional auto-encoder (CAE) is proposed to collect the time-series data from underwater sensors, named as the PLER-CAE data collection method. In the proposed method, the auto-encoder is used to reduce data redundancy of the time-series data. The encoder deployed at the collection end compresses the data for transmission through the underwater channel, and the decoder deployed at the receiving end reconstructs the original data. Moreover, the proposed method complements the retransmission mechanism and the error correction technique in order to enhance data reconstruction quality. Numerical results show that the proposed PLER-CAE data collection method is effective.
With the development of cloud computing, Internet of Things, big data and other digital technologies, more and more scholars have begun to pay attention to the research related to data empowerment, but the existing re...
详细信息
作者:
Wang, BohanNew York University
Tandon School of Engineering Department of Computer Science and Engineering BrooklynNY United States
Computational Fluid Dynamics (CFD) is crucial in engineering applications such as aerospace and bioengineering, but it often require substantial computational resources. Learning-based simulation methods have the pote...
详细信息
暂无评论