Sensor networks are composed of multiple tiny,
low power, low cost sensor nodes which are capable to collect
data from environment i.e. pressure, temperature , weather ,
thermal etc and collaborate to forward it to their centralized
backend such as sink or base station for further processing
.There are lots of sensors & clusters of sensor which are
connected to internet for the purpose of sharing ,
Communicating data over internet. In addition to this there
are various web logs, sensor logs where big data posted by
various users. It requires an efficient mining strategy to
manage such a big data generated by sensors, also sensor
networks collects data from dynamic environment that
change over time. Such a dynamic behavior need machine
learning techniques to provide appropriate, selective & useful
information to users. This paper presents literature review of
machine learning techniques used for mining purpose &
proposed a high level algorithm for the unstructured,
unsupervised dataset generated by sensor networks.
Shreya P. Amilkanthwar : Department of Computer Engineering, Savitribai Phule Pune University,
Pune, Maharashtra 411041, India
Poonam Railkar : Department of Computer Engineering, Savitribai Phule Pune University,
Pune, Maharashtra 411041, India
P. N. Mahalle : Department of Computer Engineering, Savitribai Phule Pune University,
Pune, Maharashtra 411041, India
Sensor Networks
Data Mining
Internet Sensor
Information
Machine Learning
As our objective is to enable clusters of sensor to share
data over internet, and to apply machine learning
algorithm for data mining of such data formed by sensors .
Here paper presents study of various data mining
algorithms as well as machine learning approaches used in
data mining. Along with this here studied lightweight
supervised machine learning algorithm. As we go through
various types’ machine learning data mining algorithms, it
seems that the unsupervised machine learning approach is
more efficient. Since Supervised machine learning
algorithms have some limitations, So we are going to
design an Un-supervised machine learning algorithm for
mining of Internet Sensor information. Our future work is
to build a proposed work &to implement it.
[1] www.statsoft.com/textbook/data-mining-techniques.
[2] Nor LiyanaMohdShuib, HarunaChiroma, Rukaini
Abdullah, Mohammad Hafiz Ismail ,Ahmad
SofiyuddinMohdShuib&NurFaizahMohdPahme“Data
Mining Approach: Relevance Vector Machine for the
Classification of Learning Style based on Learning
Objects” 2014 UKSim-AMSS 16th International
Conference on Computer Modelling and Simulation.
[3] Ignacio Ponzoni, Francisco J. Azuaje, Juan Carlos
Augusto, and David H. Glass “Inferring Adaptive
Regulation Thresholds and Association Rules from
Gene Expression Data through Combinatorial
Optimization Learning”
[4] Negar Hariri, Carlos Castro-Herrera, Mehdi
Mirakhorli, Student Member, IEEE, Jane Cleland-
Huang, Member, IEEE, BamshadMobasher, Member,
IEEE“Supporting Domain Analysis through Mining
and Recommending Features from Online Product
Listings”
[5] Dong-Jun Yu , Member, IEEE, Jun Hu, Qian-Mu Li,
Zhen-Min Tang, Jing-Yu Yang, and Hong-Bin
Shen*“Constructing Query-Driven Dynamic Machine
Learning Model With Application to Protein-Legend
Binding Sites Prediction”
[6] BalakrishnaGokaraju, Surya S. Durbha, Member,
IEEE, Roger L. King, Senior Member, IEEE, and
Nicolas H. Younan, Senior Member, IEEE “A Machine
Learning Based Spatio-Temporal Data Mining
Approach for Detection of Harmful Algal Blooms”
[7] CesareFurlanello, Maria Serafini, Stefano Merler, and
Giuseppe Jurman“Semisupervised Learning for
Molecular Profiling”
[8] Jyothibellary,BhargaviPeyakunta,SekharKonetigari“Hybrid
Machine Learning Approach In Data Mining”
[9] Mario Di Mauro, Cesario Di Sarno“A framework for
Internet data real-time processing:a machine-learning
approach”
[10] Lei Wu, Steven C.H. Hoi, Member, IEEE, Rong Jin,
Jianke Zhu, and Nenghai Yu“Learning Bregman
Distance Functions for Semi-Supervised Clustering”
[11] Phurivit Sangkatsaneea , Naruemon
Wattanapongsakorn a , ChalermpolCharnsripinyob
“Practical real-time intrusion detection using machine
learning approaches”