Land Mines

Donated on 12/19/2022

Detection of mines buried in the ground is very important in terms of safety of life and property. Many different methods have been used in this regard; however, it has not yet been possible to achieve 100% success. Mine detection process consists of sensor design, data analysis and decision algorithm phases. The magnetic anomaly method works according to the principle of measuring the anomalies resulting from the object in the magnetic field that disturbs the structure of it, the magnetic field, and the data obtained at this point are used to determine the conditions such as motion and position. The determination of parameters such as position, depth or direction of motion using magnetic anomaly has been carried out since 1970.

Dataset Characteristics

Tabular, Multivariate, Other

Subject Area

Engineering

Associated Tasks

Classification, Clustering

Feature Type

Real, Integer

# Instances

338

# Features

3

Dataset Information

For what purpose was the dataset created?

PhD thesis

Who funded the creation of the dataset?

Cemal YILMAZ Department of Electrical and Electronics Engineering, Gazi University, Ankara, Turkey, cemal@gazi.edu.tr Hamdi Tolga Kahraman Department of Software Engineering, Karadeniz Technical University, Trabzon,Turkey htolgakahraman@ktu.edu.tr Salih Soyler Institute of Science, Gazi University, Ankara, Turkey salih_sogler@yahoo.com

What do the instances in this dataset represent?

Land Mines

Are there recommended data splits?

no

Does the dataset contain data that might be considered sensitive in any way?

No

Was there any data preprocessing performed?

processing of missing

Additional Information

Yilmaz, C., Kahraman, H. T., & Söyler, S. (2018). Passive mine detection and classification method based on hybrid model. IEEE Access, 6, 47870-47888.

Has Missing Values?

No

Introductory Paper

Passive Mine Detection and Classification Method Based on Hybrid Model

By C. Yilmaz, H. Kahraman, Salih Söyler. 2018

Published in IEEE Access

Variables Table

Variable NameRoleTypeDescriptionUnitsMissing Values
VFeatureContinuousvoltage: output voltage value of FLC sensor due to magnetic distortionVno
HFeatureContinuoushigh: the height of the sensor from the groundcmno
SFeatureContinuoussoil type: 6 different soil types depending on the moisture condition [dry and sandy, dry and humus, dry and limy, humid and sandy, humid and humus, humid and limy]no
MTargetIntegermine type: mine types commonly encountered on land (5 different mine classes)no

0 to 4 of 4

Additional Variable Information

Class Labels

Null, Anti-Tank, Anti-personnel, Booby Trapped Anti-personnel, M14 Anti-personnel

Dataset Files

FileSize
Mine Dataset.rar7 MB
mingw-get-setup.exe84.5 KB

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download (7.1 MB)
1 citations
22353 views

Keywords

Creators

Hamdi Tolga KAHRAMAN

htolgakahraman@yahoo.com

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy