Machine Learning

The proliferation of efficient edge computing has enabled a paradigm shift of how we monitor and interpret urban air quality. Coupled with the dense spatiotemporal resolution realized from large-scale wireless sensor networks, we can achieve highly accurate realtime local inference of airborne pollutants. In this paper, we introduce a novel Deep Neural Network architecture targeted at latent time-series regression tasks from continuous, exogenous sensor measurements, based on the Transformer encoder scheme and designed for deployment on low-cost power-efficient edge processors.

This is a protein negative interaction dataset, generated by our proposed method the “Features Dissimilarity-based Negative Generation” approach to generate protein negative sampling based on sequence data. It measures similarity of sequence characteristics without alignment based on Protein similarity. It achieved results of 97% compared to randomly generated negative dataset.

The dataset represents the input data on which the article Bayesian CNN-BiLSTM and Vine-GMCM Based Probabilistic Forecasting of Hour-Ahead Wind Farm Power Outputs, is based. The data consist of a two-year hourly time series of measured wind speed and direction, air density, and production of two wind farms (WTs) in Croatia (Bruška and Jelinak). In addition to the two listed WTs, measurements of two nearby WTs (Glunca and Zelengrad) are also attached in training files (these WPPs are not directly analyzed in the article).

This dataset maps mood to information about the events that influenced the mood. The dataset was obtained using a web-based data collection interface developed by us. The dataset consists of 5245 days of data from 134 participants in the experiment.

In this project, we propose a new comprehensive realistic cyber security dataset of IoT and IIoT applications, called Edge-IIoTset, which can be used by machine learning-based intrusion detection systems in two different modes, namely, centralized and federated learning. Specifically, the proposed testbed is organized into seven layers, including, Cloud Computing Layer, Network Functions Virtualization Layer, Blockchain Network Layer, Fog Computing Layer, Software-Defined Networking Layer, Edge Computing Layer, and IoT and IIoT Perception Layer.

English (for details, see https://osf.io/e4rvz/)

1. Why the Research and Importance: Taiwan Indigenous Peoples (TIPs) are a branch of Polynesian-Malaysian (or Austronesian) ethnic groups in genetic and linguistic context. Since early 17th Century, TIPs had been playing a crucial role during the Great Marine Times of East Asia trades. There was a rich body of ethnographic, official and academic records on TIPs before 1940.

This dataset has been employed in the following articles:

https://ieeexplore.ieee.org/document/9682692

https://ieeexplore.ieee.org/document/9871051

https://content.iospress.com/articles/technology-and-health-care/thc202198

The millimeter-wave radar has the ability to sense the subtle movement of hand. However, the traditional hand gesture recognition methods are not robust in the scenario with dynamic interference. To address this issue, a robust hand gesture recognition method is proposed based on the self-attention time-series neural networks. Firstly, the original radar echo is constructed in terms of frame, sequence and channel at the input terminal of network.

The measurement and diagnosis of the severity of failures in rotating machines allow the execution of predictive maintenance actions on equipment. These actions make it possible to monitor the operating parameters of the machine and to perform the prediction of failures, thus avoiding production losses, severe damage to the equipment, and safeguarding the integrity of the equipment operators. This paper describes the construction of a dataset composed of vibration signals of a rotating machine.

Power system state estimation (PSSE) plays a vital role in stable operation of modern smart grids, while it is vulnerable to cyber attacks. False data injection attacks (FDIA), one of the most common cyber attacks, can tamper with measurement data and bypass the bad data detection (BDD) mechanism, leading to incorrect PSSE results.