Machine Learning
This is a test dataset for comparison with the latest multi-objective evolutionary algorithms. We have split the experiment into two groups in high and low dimensions respectively, and the experimental results are outstanding. We used IGD as the performance metric, and the data in parentheses are the std of 20 independent repetitions of the experiment and were analyzed for significance.
- Categories:
67 Views
This dataset accompanies a research paper on leveraging Machine Learning (ML) techniques for regression to predict the optimum DC bias in direct current in optical orthogonal frequency division multiplexing (DCO-OFDM). The dataset comprises a set of features to facilitate the prediction of the required DC bias to mitigate the impact of clipping distortion at the transmitter. MATLAB software was utilized for modelling the DCO-OFDM transmission and generating the research dataset.
- Categories:
66 Views
The Comprehensive Hindi Hostile Post Detection Dataset (CM-HTHPD) is collection of Twitter posts written in the Hindi language, focusing on various forms of hostile content. The dataset was gathered using the Twitter Developer API and subsequently annotated manually with sentiment labels using the Label Studio platform. The dataset is primarily aimed at facilitating research and analysis in the domain of hostile content detection and sentiment analysis in Hindi-language social media discourse. The size of the dataset is approx 8300.
- Categories:
63 Views
16.00
Normal
0
false
false
false
EN-GB
X-NONE
X-NONE
- Categories:
272 Views
This dataset is data support for a research paper named “Natural Gas Triethylene Glycol Dehydration Equipment Digital Twin and Condition Evaluation Application”. The paper has been submitted to IEEE Transactions on Industrial Informatics.
- Categories:
90 Views
In the data set acquisition phase, the system will automatically record the following data: frontal video recording: the frame rate of the video is 10Hz per second, and the video contains the patient's movement, posture and facial information; hemodynamic data: the acquisition frequency is 10Hz per second, covering the area of the prefrontal lobe of the brain, and including the hemodynamic information of 22 channels; kinematic data: the acquisition frequency is 10Hz per second, and including the hand velocity, shoulder angular velocity, elbow angular velocity and sitting posture information
- Categories:
382 Views
As the field of human-computer interaction continues to evolve, there is a growing need for new methods of gesture recognition that can be used in a variety of applications, from gaming and entertainment to healthcare and robotics. While traditional methods of gesture recognition rely on cameras or other optical sensors, these systems can be limited by factors such as lighting conditions and occlusions.
- Categories:
862 Views
The dataset comprises image files of size 640 x 480 pixels for various grit sizes of Abrasive sheets. The data collected is raw. It can be used for analysis, which requires images for surface roughness. The dataset consists of a total of 8 different classes of surface coarseness. There are seven classes viz. P80, P120, P150, P220, P320, P400, P600 as per FEPA (Federation of European Producers of Abrasives) numbering system and one class viz. 60 as per ANSI (American National Standards Institute) standards numbering system for abrasive sheets.
- Categories:
290 Views
The dataset encompasses a diverse array of electrical signals representing Power Quality Disturbances (PQD), both in single and combined forms, meticulously generated in adherence to the IEEE 1159 guideline. Crucially, the dataset includes both raw data and corresponding labels, facilitating supervised learning tasks and enabling the development and evaluation of classification algorithms.
- Categories:
918 Views
Our DeepCoAST dataset specifically explores the vulnerabilities of various traffic-splitting Website Fingerprinting (WF) Defenses, such as TrafficSliver, HyWF, and CoMPS. Our dataset comprises defended traces generated from the BigEnough dataset, which includes Tor cell trace instances of 95 websites, each represented by 200 instances collected under the standard browser security level. We simulated the traffic-splitting defenses assuming there are two split traces from the vanilla trace.
- Categories:
33 Views