Upload
lamnguyet
View
218
Download
2
Embed Size (px)
Citation preview
Editorial Team
Editorial in Chief
1. Ms. Aulia siti Aisjah, Editor IPTEK Journal for Technology and Sciense
Members
1. Dr Setiyo Gunawan, Chief Editor IPTEK Journal of Engineering, Indonesia
2. Prof. Gamantyo Hendrantoro, Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya,
Indonesia, Indonesia
3. Prof. Sarwoko Mangkoedihardjo, Inviromental Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia,
Indonesia
4. Mr. Mauridhi Hery Purnomo, Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia,
Indonesia
5. Mr Suhartono Suhartono, Chief Editor IPTEK Journal of Science, Indonesia
6. Prof. Imam Robandi, Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia, Indonesia
No 1 (2014) International Seminar on Applied Technology, Science, and Arts (APTECS) 2013
APTECS is an Annual International Seminar on Applied Technology, Science, and Arts. APTECS
has been held by LPPM-ITS since 2009. Starting from the year of 2013, the 4th APTECS, there will
be three main events, namely the International Conference, the Business Forum, and the Exhibition.
Table of Contents
Articles
Development of a ‘Fish Tail’ Rudder to Improve a Ship’s Maneuverability in Seaway
1-7
Aries Sulisetyono
Maximum Peak-Gain Margin 2DOF-IMC Tuning for a 2DOF-PID Filter Set Point
Controller Under Parametric Uncertainty
8-16
Nur Hidayah, Juwari Juwari, Renanto Handogo
Design of Curriculum Matrix for Robotics Education Derived from Bloom's
Taxonomy and Educational Curriculum of 2013
17-25
Eko Henfri Binugroho, Endah Suryawati Ningrum, Dwi Kurnia Basuki, Adnan
Rachmat Anom Besari
Viscous-Resistance Calculation and Verification of Remotely Operated Inspection
Submarine
26-30
Ardi Nugroho Yulianto, I Ketut Suastika, Aries Sulisetyono
Bioremoval of Chromium, Copper and Cadmium by Bacillus cereus in Simulated
Electroplating Wastewater
31-35
Yulinah Trihadiningrum
An Investigation into Hybrid Catamaran Fishing Vessel: Combination of Diesel
Engine, Sails and Solar Panels
36-41
Pramudya Imawan Santosa, I Ketut Arya Priya Utama
Synthesis of UiO-66 Using Solvothermal Method at High Temperature 42-46
Ika Diah Rahmawati, Ratna Ediati, Didik Prasetyoko
On-line State Estimator for Three Phase Distribution Networks Displayed on
Geographic Information System
47-50
Indri Suryawati, Ontoseno Penangsang, Adi Suprijanto, Dimas Fajar U. P.,
Mat Syai’in
Impacts of River Groove Propagation on Irrigation Infrastructural Failures 51-57
Kuntjoro Kuntjoro, Choirul Anwar, Didik Harijanto
Steering System Kinematic and Steady-State Cornering Analyses of the ITS Electric
Car
58-62
Unggul Wasiwitono, Indra Sidarta, Agus Sigit Pramono, Sutikno Sutikno, Alief
Wikarta
The Rate of Turbulent Kinetic Energy Dissipation in a Turbulent Boundary layer on
a Flat Plate
63-66
Sutardi Sutardi
The Influence of Burning Temperature of MIRHA On Mechanical Properties of
Foamed Concrete
67-72
Ridho Bayuaji
System Application of Genetic Algorithm for Scheduling Optimization Study Using 73-76
Java (Case Study : Department of Computer System UNTAN)
Fatma Agus Setyaningsih
Simulation of Direct Digital Synthesizer with LabView 77-81
Elan Djaelani Suardja
Technology Development of Kupang Processing with Dryer Machine Base on
Expert System
82-88
Dedin F Rosida, Dedid Cahya Happyanto
Kinetics of Hg and Pb Removal in Aqueous Solution Using Coal Fly Ash Adsorbent 89-92
Eko Prasetyo Kuncoro, Mochammad Zakki Fahmi
Microstructures Behavior in Biomedical Co-Cr-Mo-C-Si-Mn Alloys Containing
Nitrogen
93-96
Alfirano Alfirano
New Concept of PQR-Coordinate on Power Transformation for Harmonics
Reducing
97-101
Indriarto Yuniantoro, Rudy Setiabudy, Ridwan Gunawan
The Effect of High Switching Frequency on Inverter Against Measurements of
kWh-Meter
102-109
Isdawimah Isdawimah, Rudy Setiabudy, Ridwan Gunawan
Analysis of Buttering Method on Mechanical Properties Welded Material Low
Carbon Steel
109-113
Gathot Dwi Winarto, Rivai Wardhani, Irsyadus Syarif
Vibration and Cylinder Chamber Pressure Characteristics of an Air Reciprocating
Compressor
114-118
Bambang Daryanto Wonoyudo, David A. Siregar
The Effect of Chemical Substance and Immersion Time to Tensile Strength of
Bamboo Betung (Dendrocalamus asper) as Chemical Preservation Treatment
119-124
Afif Rizqi Fattah, Ken Ninez Nurpramesti Prinindya, Hosta Ardhyananta
Optimal Location of a Capacitor Bank in a Primary Feeder to Load up Linearly 125-129
Hermagasantos Zein, Erwin Dermawan
Power of Regenerative Braking with Kinetic Energy Recovery System 130-135
Mochamad Edoward Ramadhan, Harus Laksana Guntur
The Art and Sustainable Aspects of Natural Dyeing in KANAWIDA Hand Drawn
Batik (Green Batik)
136-143
July Hidayat, Fatmahwaty Fatmahwaty
Novel Hybrid Orthogonal Large Set Code Sequence for High Density Wireless
Networks
144-152
Nyoman Pramaita, P. L. Johnson
Novel Centralized Control Battery Operation, on Microgrids to Supply The Load
Priority
153-159
Hartono Budi Santoso, Wike Handini, Rudy Setiabudy, Budiyanto Budiyanto
Learning based on Virtual Class using combination of Second Life and Learning
Managment System
160-163
Firli Irhamni, Indah Agustien Siradjuddin, Arik Kurniawati, Ari
Kusumaningsih, Rima Triwahyuningrum
Physic Simulation Experiments using Augmented Reality 164-166
Surya Sumpeno, Christyowidiasmoro Christyowidiasmoro
Performance of Anaerobic Reactor in Attached and Suspended Growth Mechanisms
for the Removal of Tofu Wastewater
167-168
Rosvita Tri Jullyanti, H. Purnobasuki, T. Nurhariyati, F. N. Rachman, N. I.
Oktavitri
Analysis Characteristic of Province Travelling Intercity of AKDP Makassar-
Parepare Route, South Sulawesi
169-173
St. Maryam Hafram, Herman Parung, Tri Harianto, Muh. Isran Ramli
Investigation of Flow and Heat Transfer Characteristics in Two-Phase Flow
Through Evaporator of Diffusion Absorption Refrigerator (DAR)
174-180
Siti Masita Rakhmawati
Detection of Critical Situation of Longitudinal Vehicle Dynamics 181-187
Widya Nila Velayati, Sebastien Varrier
A Robust Frequency Control Approach in PV-Diesel Hybrid Power System 188-194
Heri Suryoatmojo, Adi Kurniawan, Feby Agung Pamuji, Nursalim ST MT, IGP
Suta Wijaya, Herbert Innah
Assessment the Role of Sediment in the Sumber Brantas Rivers Watershed Affected
by Agroforestry Activities
195-200
Barlah Rumhayati, Hari Siswoyo, MH. Chusnuddin Nurochman
Study at the Bolted Joint Assembly with Slotted Hole 201-210
Ramadhan Prasetya Utama, Alain Daidié
Augmented Reality Prototype to Introduce Gamelan Based on Web 211-217
Avriyasendy Ramadiyan, Sari Wijayanti
Power Flow Control of Power Systems Using UPFC Based on Adaptive Neuro
Fuzzy
218-223
Agus Jamal, Ramadoni Syahputra
Distribution Network Efficiency Improvement Based on Fuzzy Multi-objective
Method
224-229
Ramadoni Syahputra, Imam Robandi, Mochamad Ashari
Crystal Growth of IRMOF-3 (Isoreticular Metal-Organic Frameworks-3)
Synthesized using Solvothermal Method
230-234
Pemta Tia Deka, Ratna Ediati, Didik Prasetyoko
Utilization of Fertilizers for Improving The Process Rate of Organic Material
Degradation in Anaerobic Reactor
235-238
Adelia Anju Asmara, Agoes Soegianto, Trisnadi Widyaleksono Catur Putranto,
Hairul Amin, Nur Indradewi Oktavitri
Database Integration Model for Automatic Identification System and Shipping
Database In Real Time Traffic Monitoring
239-244
Akhmad Maulidi, Trika Pitana, Ketut Buda Artana, A.A. Bagus Dinariyana,
Muhammad Badrus Zaman, Agoes A. Masroeri, Ricky Randall Sembiring
Energy Efficiency Analysis of Trawlers (Case Study: Indonesian’s Trawler) 245-250
Alyuan Dasira, Jean Marc Laurens
Analysis of The Effect of Linear and Non-Linear Loads against The Quality of
Power at The Power Converter
251-257
Anicetus Damar Aji, Kusnadi Kusnadi
Interactive Whiteboard and Instant Quiz for Multimedia Classroom Activity 258-263
Ary Mazharuddin Shiddiqi, Royyana M. Ijtihadie, Emerson Eridiansyah Z,
Baskoro Adi Pratomo, Tohari Ahmad, Waskhito Wibisono
Chemical Bonds Visualization using Particle Effect and Augmented Reality 264-268
Christyowidiasmoro Christyowidiasmoro, Surya Sumpeno
The Alternative Use Of Water Hyacinth and Reed As Attached Growth Of
Microbial In Waste Water Treatment
269-271
Hery Purnobasuki, Nur Indradewi Oktavitri, Tri Nurhariyati, B. Saadah,
Santini Ika Rafsanjani
Modelling and Analysis of the Dynamic Behavior of a Double Cylinder Inline 650cc
Gasoline Engine with Crank Angle 0o for Rubber Mount
272-278
Harus Laksana Guntur, Karina Yulia
The Erythemato-Squamous Dermatology Diseases Severity Determination using
Self-Organizing Map
279-284
Haryanto Haryanto, Miftahul Ulum, Diana Rahmawati Rahmawati, Koko Joni,
Ahmad Ubaidillah, Riza Alfita, Lilik Anifah, Bain Khusnul Khotimah
Location Time of Power Quality Disturbances and Noise Using Morphology
Gradient and Skeletonization in 3D
285-290
I Gusti Ngurah Agung Dwijaya Saputra, Henry Wu, Wenhu Tang
Pattern of Biogas Production and Removal of Chemical Oxygen Demand in Semi
Continues Hybrid Anaerobic Reactor
291-293
Nur Indradewi Oktavitri, Agoes Soegianto, T. Rahman, Bidayatus Saadah,
Deavy Trianingtyas
Three-Dimensional (3D) Reconstruction for Detecting Shape and Volume of Lung
Cancer Nodules
294-298
Rodiah Rodiah, Sarifuddin Madenda, Fitrianingsih Fitrianingsih
Thermal Performance of Apartment (High-Rise) in Surabaya with Precast Concrete
for the Building Envelope
299-305
Romanria Violina Mahardhika, Ima Defiana, V. Totok Noerwasito
Pretreatment of Sludge Milk Waste as Source Of Composting using Microbes 306-310
S. R. Juliastuti, Rian Setya Budi, Taufiqurrusydi Taufiqurrusydi
Further Investigation on Building and Benchmarking A Low Power Embedded
Cluster for Education
311-318
Sritrusta Sukaridhoto, Achmad Subhan Khalilullah, Dadet Pramadihanto
Real Time Train Monitoring using Google Maps 319-322
Supeno Djanali, Ary M. Shiddiqi, Hudan Studiawan, Henning T. Ciptaningtyas
Structural Damage Detection of A Steel-Truss Railway Bridge Using its Dynamic
Characteristics
323-329
T. Susanto, A. Budipriyanto
Android App for Information of Food Additives Contained in Packaged Foods 330-336
Umi Sa'adah, Tita Karlita, Muchammad Arfian
IPTEK, Journal of Proceeding Series, Vol. 1, 2014 (eISSN: 2354-6026) 279
The Erythemato-Squamous Dermatology
Diseases Severity Determination using
Self-Organizing Map
Haryanto1, Bain Khusnul Khotimah
2, Miftahul Ulum
1, Diana Rahmawati
1, Koko Joni
1,
Ahmad Ubaidillah1, Riza Alfita
1, and Lilik Anifah
1
AbstractA new approach based on the implementation of Self Organizing Map is presented for automated detection of
erythemato-squamous diseases. The purpose of clustering techniques is in order to determinate the severity of erythemato-
squamous dermatology diseases. The studied domain contained records of patients with known diagnosis. Self-Organizing Map
algorithm's task was to classify the data points, in this case the patients with attribute data, to one of the six clusters (psoriasis,
seboreic dermatitis, lichen planus, pityriasis rosea, cronic dermatitis, dan pityriasis rubra pilaris). The algorithm was used to
detect the six erythemato-squamous diseases when 33 features defining five disease indications were used. The purpose is to
determine an optimum classification scheme for this problem. The present research demonstrated that the features well
represent the erythemato-squamous diseases and SOM algorithm's task achieved high classification accuracies. The best
accuration for psoriasis 85,94%, seboreic dermatitis 40,48%, lichen planus 56,25%, and pityriasis rosea 82,61%, with learning
rate value were 0,1, 0,2, 0,9, and 0,4.
Keywords Erythemato-squamous, Self-Organizing Map, classification, dermatology.
I. INTRODUCTION1
he differential diagnosis of erythemato-squamous
diseases is a real problem in dermatology. They all
share the clinical features of erythema and scaling, with
very little differences. The diseases in this group are
psoriasis, seboreic dermatitis, lichen planus, pityriasis
rosea, cronic dermatitis, and pityriasis rubra pilaris.
Usually a biopsy is necessary for the diagnosis but
unfortunately these diseases share many
histopathological features as well [1].
Research about erythemato-squamous diseases has
been researched many researcher in the world.
Automatic detection of erythemato-squamous diseases
using k-means clustering has been investigated by
Ubeyli [2]. Classification of erythemato-squamous
diseases using Support Vector Machine investigated by
Derya [3] and another investigated by Loris [4].
Self-Organizing Map (SOM) invented by Kohonen [5],
[6]. SOM network learning some grop pattern and a
pattern made into a single cluster that has certain
characteristics [7]. SOM procedure is divided into three
parts, namely: Normalization, Trainings, and retrieval of
information from the training. The goal of normalization
is to avoid variable that has value too high against the
value of other data. Normalization process variable value
seeing a value between 0 and 1, is expected to be
detraining variable is normal with other data. After data
normalization, data matrix detraining shaped by a
particular procedure, recommended training held at least
500 times. The third step, namely the use trainings
results in the form of weights (weight) for each cluster.
Weight (weight) obtained is used to test the data that will
be tested.
1Haryanto, Miftahul Ulum, Diana Rahmawati, Koko Joni, Ahmad
Ubaidillah, Riza Alfita, and Lilik Anifah are with Departement of
Electrical Engineering, Trunojoyo University Madura, Bangkalan,
Indonesia. E-mail: [email protected];;;;;;. 2Bain Khusnul Khotimah are with Departement of Informatics
Engineering, Trunojoyo University Madura, Bangkalan, Indonesia.E-
mail: [email protected].
In this paper we present the application of a self-
organizing map to the problem of differential diagnosis
of erythemato-squamous diseases, which represents a
major issue in dermatology.
This paper is outlined as follows: In section 2 we
briefly describe material and the proposed method.
Experimental results and discussions will be presented in
section 3, followed by discussions in section 4,
conclusions in section 5, and future work in section 6.
II. MATERIAL AND METHOD
A. Material
We observed 231 erythemato-squamous diseases data
obtained from Machine Learning Repository (UCI)
dataset [1], included 30 training data and 201 testing
data. Training data contain 5 data for psoriasis, 5 data for
seboreic dermatitis, 5 data for lichen planus, 5 data for
pityriasis rosea, 5 data for cronic dermatitis, and 5 data
for pityriasis rubra pilaris.
The dataset constructed for this domain, the family
history feature has the value 1 if any of these diseases
has been observed in the family, and 0 otherwise. The
age feature simply represents the age of the patient.
Every other feature (clinical and histopathological) was
given a degree in the range of 0 to 3.
Hardware specification used in this research is Dell
Inspiron N3010 with Processor Intel(R) Core(TM) i5
CPU M430 @2,27 GHz installed memory (RAM) 2,00
GB.
B. Method
Method of Self Organizing Map (SOM) has been
progressing rapidly both in the substance of the SOM
and its application to clustering in various fields.
Modular network SOM developed by Kazuhiro
Tokunaga and Tetsuo Furukawa [9]. Networks Artificial
Counterpropagation developed by Davide Ballabio,
Viviana Consonni, and Roberto Todeschini [10]. SOM
of SOMs developed by Tetsuo Furukawa [11], Dieter
Müller developed a self-organized mapping of clusters of
T
280 IPTEK, Journal of Proceeding Series, Vol. 1, 2014 (eISSN: 2354-6026)
data into groups of neurons [12]. Comparision between
SOM-based optimization and particle swarm
optimization for minimized construction time from a
secant pile wall is researched by Jieh-Haur Chen [13].
Still a lot of research about other SOM. Figure of classic
SOM configuration is figured in fig 1.
Erythemato-squamous diseases classification in this
research using classic SOM. This research is divided into
9 experiments described in Table 1.
The clasters of this research are divided into 6 clasters
described in Table 2. Clasters of this research are
Psoriasis, Seboreic dermatitis, Lichen planus, Pityriasis
rosea, Cronic dermatitis and Pityriasis rubra pilaris.
Algorithm of this research is figured in fig 2. The step
of learning using SOM are initialization, determination
the number of classes, setting a learning rate parameter,
determination of the iteration value, and calculating the
distance between random data into each input weight. The classic SOM network learning algorithm can be
formulated as follows [6]: a. Set learning iteration number t = 0. Then initialize all
weights wij with small random values (or initialize
the weights using input data). Set the initial
topological neighborhood (d0). Set the initial learning
rate (0) and set the total number of iterations (T)
b. While iteration number (t) is less than T, repeat Step
3–Step 6.
c. Choose an input vector x randomly in the training set.
d. Determine the neuron j so that its weight vector wj is
the closest to the input vector and call it as the winner
neuron. The winner neuron j has the closest distance,
Dmin(t) to the input pattern x(t), where Dmin(t) is
given:
e. 2
min ))()((min)(min)( twtxtDtDj
ijiji ∑ −==
f. Update the weight vectors of both the winner neuron
j and its neighbors as:
g.
i
iii
Ni
tWxttWtW
∈∀−•+=+ ))(()()()1( α
h. where α(t) is a learning rate function that
exponentially decreases with time. Further, we define a neighborhood order function d(t) which
exponentially decreases with time. In this paper, the
following equations are used for α(t) and d(t):
i. [ ]Tt
Tt
edtd
et
3/
0
3/
0
)(
)(
−
−
=
=αα
j. where [y] denotes the largest integer less or equal to
y.
k. Set t = t+ 1 and if t < T go to Step 3, and otherwise
STOP.
III. RESULT AND DISCUSSION
Difficulty for the differential diagnosis is that a disease
may show the features of another disease at the
beginning stage and may have the characteristic features
at the following stages.
Patients were first evaluated clinically with 12 features.
Afterwards, skin samples were taken for the evaluation
of 22 histopathological features. The values of the
histopathological features are determined by an analysis
of the samples under a microscope. The Clinical
Attributes areerythema, scaling, definite borders, itching,
koebner phenomenon, polygonal papules, follicular
papules, oral mucosal involvement, knee and elbow
involvement, scalp involvement, family history, and
Age. Histopathological Attributes melanin incontinence,
eosinophils in the infiltrate, PNL infiltrate, fibrosis of the
papillary dermis, exocytosis, acanthosis, hyperkeratosis,
parakeratosis, clubbing of the rete ridges, elongation of
the rete ridges, thinning of the suprapapillary epidermis,
spongiform pustule, munro microabcess, focal
hypergranulosis, disappearance of the granular layer,
vacuolisation and damage of basal layer, spongiosis,
saw-tooth appearance of retes, follicular horn plug,
perifollicular parakeratosis, inflammatory monoluclear
inflitrate, and band-like infiltrate.
Parameters of learning are described in Table 1 for
minimal value, Table 2 for maximal value and Table 3
for average value. Table 3, 4, and 5 shows that the some
parameters had the overlap value among clasters and it is
not linear. That is why we try to overcome to classify
automatically using SOM.
Accuracy of each group is shown in fig 4, fig 5, fig 6,
fig 7, fig 8, and fig 9. Fig 4 is figured the accuray of the
fisrt group (Psoriasis), fig 5 is figured the accuray of the
second group (Seboreic dermatitis), fig 6 is figured the
accuray of the second group (Lichen planus dermatitis),
fig 7 is figured the accuray of the second group
(Pityriasis rosea), fig 8 is figured the accuray of the
second group ( Cronic dermatitis) and fig 9 is figured the
accuray of the second group ( Pityriasis rubra pilaris).
Fig 4 shows that the accuracy of cluster 1 (Psoriasis
group), first experiment and second experiment are
85,9375%. Thirth, fourth, and fifth experiment have
accuracy 84,375 % but sixth, seventh, eighth and ninth
experiment give accuracy 0%.
Fig 5 shows that the accuracy of second cluster
(Seboreic dermatitis group), first experiment and second
experiment are 40,476%, thirth has accuracy 0%, fourth
and sixth 21,428%, fifth 40,476, seventh and ninth have
accuracy 35,714%, and eighth experiment has accuracy
38,095%.
Fig 6 shows that the accuracy of thirth cluster (Lichen
planus group), first and second experiment are 31,25%,
thirth has accuracy 18,75%, fourth, fifth and sixth
12,5%, seventh 0%, eighth has accuracy 18,75% and
ninth experiment has accuracy 56,25%.
Fig 7 shows that the accuracy of fourth cluster
(Pityriasis rosea group), first experiment and second
experiment are 78,26%. Thirth is 69,565%, fourth has
accuracy 82,61%,fifth experiment has accuracy 4,34 %,
sixth has accuracy 60,869%, eighth has 17,39% but
seventh and ninth 0%.
Fig 8 shows that the accuracy of fifth cluster (Cronic
dermatitis group), first experiment and second
experiment are 86,49%. Thirth is 43,24%, fourth has
accuracy 35,13%, fifth experiment has accuracy 13,51%,
sixth has accuracy 37,84%, seventh and eighth have
48,65% but ninth has accuracy 10,81%.
Fig 9 shows that the accuracy of sixth cluster
(Pityriasis rubra pilaris group), first, second, thirth,
fourth, and seventh experiment 93,33%, fifth has
accuracy 7,14%, sixth experiment has accuracy 6,67%,
eighth has accuracy 100%, and ninth has accuracy 0%.
Time needs to process of each experiment is described
in Table 7. First, seventh, eighth, and ninth experiment
IPTEK, Journal of Proceeding Series, Vol. 1, 2014 (eISSN: 2354-6026) 281
need 0,2028 second to process. Second and fourth
experiment need 0,187 second, thirth experiment needs
0,218 second, fifth and sixth experiments consume 0,265
and 0,234 second. Graph of time-consuming for each
experiment is figured in fig 10.
IV. CONCLUSION
In this research, we proposed an effective Erythemato-
squamous diseases classification system without the need
for user interaction. Experimental results have been
provided to show the successful of the system that could
help medical doctors as decision support system to
determine the claster of erythemato-squamous diseases.
A. Future Work
The system could classify the six claster (Psoriasis,
Seboreic dermatitis, Lichen planus, Pityriasis rosea,
Cronic dermatitis and Pityriasis rubra pilaris), the future
work we develop the more effective and robust
classification machine.
ACKNOWLEDGEMENT
This research was supported by UC Irvine Machine
Learning Repository (UCI).
REFERENCES
[1]. http://archive.ics.uci.edu/ml/
[2]. Ubeyli, Elif Derya and Erdoğan Doğdu 2008, Automatic detection of erythemato-squamous diseases using k-means
clustering has been investigated Journal of Mecidal System
Volume 34, Number 2, 179-184, DOI: 10.1007/s10916-008-
9229-6
[3]. Kohonen, T., 1982. Self-organized formation of topologically
correct feature maps. Biological Cybernetics 43, 59e69.
[4]. Kohonen, T., 1982. Analysis of a simple self-organizing process.
Biological Cybernetics 44, 135e140.
[5]. Kohonen, T., 2001. Self-Organizing Maps. Springer-Verlag,
Berlin.
[6]. A.M. Kalteh, 2008, Review of the self-organizing map (SOM)
approach in water resources: Analysis, modelling and
application, Environmental Modelling & Software 23 (2008)
835e845, Science Direct Elsevier.
[7]. Haykin, S., 1999, Neural Networks: A Comprehensive
Foundation, Prentice Hall Upper Saddle River, New Jersey.
[8]. Vesanto, J., Alhoniemi, E., 2000, Clustering of the self-
organizing map. IEEE, Transactions on Neural Networks 11 (3),
586e600. Woolf AD, Pfleger B. “Burden of major musculoskeletal conditions”, Bull World Health Organ
2003;81:646-656.
[9]. Kazuhiro Tokunaga, Tetsuo Furukawa, Modular network SOM,
Neural Networks 22 (2009) 82-90, Science Direct Elsevier,
2009.
[10]. Davide Ballabio, Viviana Consonni, Roberto Todeschini, The
Kohonen and CP-ANN toolbox: A collection of MATLAB
modules for Self Organizing Maps and Counterpropagation
Artificial Neural Networks, Chemometrics and Intelligent Laboratory Systems xxx (2009) xxx–xxx, Science Direct
Elsevier, 2009.
[11]. Tetsuo Furukawa, SOM of SOMs, Neural Networks 22 (2009)
463§478, Science Direct Elsevier, 2009.
[12]. Dieter Müller, Self organized mapping of data clusters to neuron
groups, Neural Networks 22 (2009) 415-424, Science Direct
Elsevier, 2009.
[13]. Jieh-Haur Chen, Comparison of SOM-based optimization and
particle swarm optimization for minimizing the construction
time of a secant pile wall, Automation in Construction 18 (2009)
844–848, Science Direct Elsevier, 2009.
Figure 1. Configuration of SOM
Figure 2. Algorithm of classic SOM
Figure 3. System accuracy using learning rate value 0,1 to 0,9
Figure 4. System accuracy using learning rate value 0,1 to 0,9 of cluster
1 (Psoriasis group)
Figure 5. System accuracy using learning rate value 0, 1 to 0, 9
of cluster 2 (Seboreic dermatitis group)
0
50
100
1 2 3 4 5 6 7 8 9
0
20
40
60
80
100
1 2 3 4 5 6 7 8 9
0
10
20
30
40
50
1 2 3 4 5 6 7 8 9
Start
Number of Iteration
Choose input vector
t=number of iteration
End
Find the minimum distance
Weight update
Y
N
282 IPTEK, Journal of Proceeding Series, Vol. 1, 2014 (eISSN: 2354-6026)
Figure 7. System accuracy using learning rate value 0,1 to 0,9
of cluster 4 (Pityriasis rosea group)
Figure 8. System accuracy using learning rate value 0,1 to 0,9
of cluster 5 (Cronic dermatitis group)
Figure 9. System accuracy using learning rate value 0,1 to 0,9
of cluster 6 (Pityriasis rubra pilaris group)
Figure 10. Time-consuming for each experiment
Figure 11. Comparison of each experiment accuracy
TABLE 1.
EXPERIMENTS OF THE RESEARCH
No Experiment Learning
rate Iteration
1 Experiment 1 0,1 500
2 Experiment 2 0,2 500
3 Experiment 3 0,3 500
4 Experiment 4 0,4 500
5 Experiment 5 0,5 500
6 Experiment 6 0,6 500
7 Experiment 7 0,7 500
8 Experiment 8 0,8 500
9 Experiment 9 0,9 500
TABLE 2.
CLASTER OF THE RESEARCH
No Claster Group
1 Claster 1 Psoriasis
2 Claster 2 Seboreic Dermatitis
3 Claster 3 Lichen Planus
4 Claster 4 Pitriasis Rosea
5 Claster 5 Cronic Dermatitits
6 Claster 6 Pityriasis Rubra Pilaris
0
20
40
60
80
100
1 2 3 4 5 6 7 8 9
0
50
100
1 2 3 4 5 6 7 8 9
0
50
100
150
1 2 3 4 5 6 7 8 9
0
0.1
0.2
0.3
0 5 10
0
20
40
60
80
100
120
Claster 1 Claster 2 Claster 3
Claster 4 Claster 5 Claster 6
IPTEK, Journal of Proceeding Series, Vol. 1, 2014 (eISSN: 2354-6026) 283
TABLE 3.
MINIMAL VALUE OF LEARNING PARAMETERS
Parameter 1 2 3 4 5 6
1: Erythema 0 1 0 1 0 1
2: Scaling 1 1 0 1 0 1
3: Definite borders 1 0 0 0 0 0
4: Itching 0 0 0 0 0 0
5: Koebner phenomenon 0 0 0 0 0 0
6: Polygonal papules 0 0 0 0 0 0
7: Follicular papules 0 0 0 0 0 1
8: Oral mucosal involvement 0 0 0 0 0 0
9: Knee and elbow involvement 0 0 0 0 0 0
10: Scalp involvement 0 0 0 0 0 0
11: Family history, (0 or 1) 0 0 0 0 0 0
12: Melanin incontinence 0 0 0 0 0 0
13: Eosinophils in the infiltrate 0 0 0 0 0 0
14: PNL infiltrate 0 0 0 0 0 0
15: Fibrosis of the papillary
dermis 0 0 0 0 1 0
16: Exocytosis 0 0 0 0 0 0
17: Acanthosis 0 0 0 0 1 1
18: Hyperkeratosis 0 0 0 0 0 0
19: Parakeratosis 0 0 0 0 0 0
20: Clubbing of the ridges 0 0 0 0 0 0
21: Elongation of the rete ridges 1 0 0 0 0 0
22: Thinning of the suprapaillary
Epidermis 0 0 0 0 0 0
23: Spongiformpustule 0 0 0 0 0 0
24: Munro microabcess 0 0 0 0 0 0
25: Focal hypergranulosis 0 0 0 0 0 0
26: Disappearance of the granular
Layer 0 0 0 0 0 0
27: Vacuolisation and damage of
Basal layer 0 0 0 0 0 0
28: Spongiosis 0 0 0 0 0 0
29: Saw-tooth appearance of retes 0 0 0 0 0 0
30: Follicular horn plug 0 0 0 0 0 0
31: Perifollicular parakeratos is 0 0 0 1 0 1
32: Inflammatory monoluclear
Infiltrate 0 0 0 0 0 0
33: Band-like infiltrate 0 0 0 0 0 0
34: Age (linear) 8 10 16 12 8 7
TABLE 4.
MAXIMAL VALUE OF LEARNING PARAMETERS
Parameter 1 2 3 4 5 6
1: Erythema 3 3 3 3 3 3
2: Scaling 3 3 3 2 3 2
3: Definite borders 3 2 3 2 3 2
4: Itching 3 3 3 3 3 2
5: Koebner phenomenon 3 2 3 3 0 0
6: Polygonal papules 0 0 3 0 0 0
7: Follicular papules 2 1 0 0 2 3
8: Oral mucosal involvement 0 2 3 0 0 0
9: Knee and elbow involvement 3 1 2 0 1 3
10: Scalp involvement 3 0 1 0 0 2
11: Family history, (0 or 1) 1 1 0 0 0 1
12: Melanin incontinence 0 0 3 0 0 0
13: Eosinophils in the infiltrate 2 2 2 1 1 0
14: PNL infiltrate 3 3 0 1 0 1
15: Fibrosis of the papillary dermis 0 0 2 0 3 0
16: Exocytosis 2 3 3 3 2 3
17: Acanthosis 3 3 3 2 3 2
18: Hyperkeratosis 3 3 2 2 2 2
19: Parakeratosis 3 3 3 2 2 2
20: Clubbing of the ridges 3 0 0 0 0 1
21: Elongation of the rete ridges 3 2 0 0 3 1
22: Thinning of the suprapaillary
Epidermis 3 1 0 0 1 0
23: Spongiformpustule 3 2 0 0 0 1
24: Munro microabcess 3 0 3 1 0 0
25: Focal hypergranulosis 0 0 3 0 0 1
26: Disappearance of the granular
Layer 3 0 2 2 0 0
27: Vacuolisation and damage of
Basal layer 1 0 3 0 0 0
28: Spongiosis 0 3 3 3 2 3
29: Saw-tooth appearance of retes 0 0 3 1 0 0
30: Follicular horn plug 0 1 1 0 1 3
31: Perifollicular parakeratos is 0 1 0 0 0 3
32: Inflammatory monoluclear
Infiltrate 3 3 3 3 3 3
33: Band-like infiltrate 1 2 3 0 1 1
34: Age (linear) 75 75 75 75 75 75
284 IPTEK, Journal of Proceeding Series, Vol. 1, 2014 (eISSN: 2354-6026)
TABLE 5.
AVERAGE VALUE OF LEARNING PARAMETERS
Parameter 1 2 3 4 5 6
1: Erythema 3 3 3 3 3 3
2: Scaling 3 3 3 2 3 2
3: Definite borders 3 2 3 3 3 2
4: Itching 3 3 3 3 3 2
5: Koebner phenomenon 3 2 3 3 1 0
6: Polygonal papules 0 0 3 3 0 0
7: Follicular papules 2 1 0 0 2 3
8: Oral mucosal involvement 0 0 3 2 0 0
9: Knee and elbow involvement 3 3 2 0 1 3
10: Scalp involvement 3 3 1 0 0 2
11: Family history, (0 or 1) 1 1 0 0 0 1
12: Melanin incontinence 0 0 3 2 0 0
13: Eosinophils in the infiltrate 2 2 2 1 1 0
14: PNL infiltrate 3 3 1 1 0 1
15: Fibrosis of the papillary
dermis 0 0 2 0 3 3
16: Exocytosis 2 3 3 3 2 3
17: Acanthosis 3 3 3 2 3 3
18: Hyperkeratosis 3 3 2 2 2 2
19: Parakeratosis 3 3 3 2 2 2
20: Clubbing of the ridges 3 3 0 0 0 1
21: Elongation of the rete ridges 3 2 0 0 3 2
22: Thinning of the suprapaillary
Epidermis 3 3 0 0 1 0
23: Spongiformpustule 3 2 0 0 0 1
24: Munro microabcess 3 2 3 1 0 0
25: Focal hypergranulosis 0 0 3 3 0 1
26: Disappearance of the granular
Layer 3 2 2 2 0 0
27: Vacuolisation and damage of
Basal layer 1 0 3 2 0 0
28: Spongiosis 0 3 3 3 2 3
29: Saw-tooth appearance of retes 0 0 3 1 0 0
30: Follicular horn plug 0 1 1 0 1 3
31: Perifollicular parakeratos is 0 1 0 0 0 3
32: Inflammatory monoluclear
Infiltrate 3 3 3 3 3 3
33: Band-like infiltrate 2 2 3 3 1 1
34: Age (linear)
7
5
7
0
6
5
7
0
7
0
5
6
TABLE 6.
ACCURACY OF WHOLE SYSTEM
No Experiment Accuracy (%)
1 Experiment 1 (with learning rate 0,1) 70,149
2 Experiment 2 (with learning rate 0,1) 70,149
3 Experiment 3 (with learning rate 0,1) 51,243
4 Experiment 4 (with learning rate 0,1) 55,223
5 Experiment 5 (with learning rate 0,1) 39,800
6 Experiment 6 (with learning rate 0,1) 50,248
7 Experiment 7 (with learning rate 0,1) 23,880
8 Experiment 8 (with learning rate 0,1) 20,398
9 Experiment 9 (with learning rate 0,1) 13,930
TABLE 7.
TIME-CONSUMING FOR EACH EXPERIMENT
Learning Rate Time (Second)
Experiment 1 (learning Rate 0,1) 0,2028013
Experiment 2 (learning Rate 0,2) 0,1872012
Experiment 3 (learning Rate 0,3) 0,2184014
Experiment 4 (learning Rate 0,4) 0,1872012
Experiment 5 (learning Rate 0,5) 0,2652017
Experiment 6 (learning Rate 0,6) 0,2348015
Experiment 7 (learning Rate 0,7) 0,2028013
Experiment 8 (learning Rate 0,8) 0,2028013
Experiment 9 (learning Rate 0,9) 0,2028013