Machine Learning

 The drawback of inter-subcarrier interference in OFDM systems makes the channel estimation and signal detection performance of OFDM systems with few pilots and short cyclic prefixes (CP) poor. Thus, we use deep learning to assist OFDM in recovering nonlinearly distorted transmission data. Specifically, we use a self-normalizing network (SNN) for channel estimation, combined with a convolutional neural network (CNN) and a bidirectional gated recurrent unit (BiGRU) for signal detection, thus proposing a novel SNN-CNN-BiGRU network structure (SCBiGNet). 


Future 6G networks will consist of fully soft-warized networks that incorporate in-network intelligence for self-management. However, this intelligent management will require massive data mining, analytics, and processing. Therefore, we need resources like quantum technologies to help achieve 6G key performance indicators. We use Quantum Machine Learning (QML) to solve the controller placement problem for a multi-controller Software Defined Network (SDN). Network delay depends on the controller’s position.


Industrial cyber-physical systems (ICPS), which is the backbone of Industry 4.0, are the result of adapting emerging information communication technologies (ICT) to the industrial control systems (ICS). ICPS utilize autonomous robotic arms to accomplish manufacturing tasks. These arms follow a certain predetermined trajectory during the task. 

In this dataset, we present four files generated from a setup that contains two Universal Robot UR3e collaborative robotic arms:


The data collection questionnaire consisted of two sections. One section involved the collection of data via Google Forms questionnaires, and the other involved the collection of WhatsApp voice samples. There were three subsections in the questionnaire section. The first consisted of the individual's basic information, such as email address, name, and identification number. The second was the personal health questionnaire depression scale (PHQ8), which included 8 groups of statements, and the third was the Beck Depression Inventory-II, which contained 21 groups of statements.


One of the most consequential creations in the human evolution phase is handwriting. Due to writing, today we are conveying our reflections, making business pacts, rendering an understandable world and making hitherto tasks austerer. Determining gender using offline handwriting is an applied research problem in forensics, psychology, and security applications, and with technological evolution, the need is growing. The general problem of gender detection from handwriting poses many difficulties resulting from interpersonal and intrapersonal differences.


The dataset contains performance values, Area Under the ROC Curve (AUC) and Average Precision (AP), of popular anomaly detection (AD) algorithms taken over a set of 9k AD benchmark datasets.

Datasets were initially published with the following paper:

Kandanaarachchi, S., Muñoz, M. A., Hyndman, R. J., & Smith-Miles, K. (2020). On normalization and algorithm selection for unsupervised outlier detection. Data Mining and Knowledge Discovery, 34(2), 309-354.


In this paper, a novel time-constrained global and local nonlinear analytic stationary subspace analysis (Tc-GLNASSA) is proposed to enhance blast furnace ironmaking process (BFIP) monitoring. Although existing analytic stationary subspace analysis method has been available for deriving process consistent relationships. However, the presence of complex nonlinear, periodic nonstationary and time-varying smelting conditions renders the satisfactory estimation of stationary projections unattainable.


This dataset contains one month of the binary activity of the 4060 urban IoT nodes. Each record in the dataset presents the node ID, the time stamp, the location of the IoT node in latitude and longitude, and also the binary activity of the IoT node. The main purpose of this dataset is to be used as part of distributed denial of service (DDoS) attack research.


Accurate detection and segmentation of apple trees are crucial in high throughput phenotyping, further guiding apple trees yield or quality management. A LiDAR and a camera were attached to the UAV to acquire RGB information and coordinate information of a whole orchard. The information was integrated by simultaneous localization and mapping network to form a dataset of RGB-colored point clouds. The dataset can be used for methods related to apple detection and segmentation based on point clouds.


The Zip file contain the videos of the indoor/outdoor test, as well as the data logged during the flights and the CAD files to replicate the balloon systems.