NIM : 5181131004
FAKULTAS TEKNIK
UNIVERSITAS NEGERI MEDAN
TAHUN 2021
1
KATA PENGANTAR
Puji dan syukur kehadirat Tuhan yang Maha Esa karena telah mendukung dan
mendorong niat penulis untuk memenuhi tugas Critical Journal Review yang berjudul “Teknik
Pengaturan sistem kendali”
Tujuan dari pembuatan Critical Journal Review ini adalah menganalisis dan memberi
tanggapan dan saran terhadap jurnal yang akan dikritik. Pembuatan ini juga bertujuan untuk
melatih penulis lebih teliti dalam memahami teori penelitian, mengungkapkan metode dan subjek
penelitian serta kelebihan dan kelemahan penelitian.
Dalam penyusunan critical journal review ini, penulis merasa masih terdapat banyak
kekurangan maupun kesalahan dalam kalimat-kalimat serta kesalahan materi yang disampaikan.
Oleh karena itu, penulis mengharapkan kritik dan saran yang bersifat membangun demi
kesempurnaan critical review journal ini.
Akhir kata semoga critical review journal ini dapat bermanfaat bagi penulis dan pembaca
yang menikmati makalah ini.
Maya Gustina
DAFTAR ISI
KATA PENGANTAR...............................................................................................................2
DAFTAR ISI..............................................................................................................................3
BAB I PENDAHULUAN..........................................................................................................4
1.3 Manfaat........................................................................................................................4
BAB II PEMBAHASAN...........................................................................................................5
3.1 Kesimpulan...................................................................................................................17
3.2 Saran..............................................................................................................................18
DAFTAR PUSTAKA..............................................................................................................19
BAB I
PENDAHULUAN
1.2 Tujuan
Mengkritisi sebuah jurnal yang berjudul teknik pengaturan (Sistem Kendali) Yang
dikritisi dalam jurnal tersebut yaitu kelengkapan pembahasannya, keterkaitan antar
babnya, dan kelemahan dan kelebihan pada jurnal yang dianalisis.
1.3 Manfaat
Manfaat yang dapat kita simpulkan pada hal diatas ialah :
1) Menambah wawasan pengetahuan tentang Teknik pengaturan (system
kendali)
2) Mempermudah pembaca mendapatkan inti dari sebuah jurnal yang telah di
lengkapi dengan ringkasan jurnal, pembahasan isi jurnal, serta kekurangan
dan kelebihan jurnal tersebut.
3) Melatih mahasiswa merumuskan serta mengambil kesimpulan atas jurnal
yang dianalisis tersebut.
BAB II
PEMBAHASAN
1. Identitas Jurnal 1
2. Identitas Jurnal 2
3. Identitas Jurnal 3
Judul Artikel Introduction to Artificial Neural Network
Nama Jurnal International Journal of Engineering and Innovative Technology
(IJEIT)
Download https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.1082.13
23&rep=rep1&type=pdf
Volume dan Vol 02 No 1
Halaman
Tahun 2012
Penulis Dongare. A.D dkk
Reviewer Maya gustina
Tanggal Jumat 28, Mei 2021
4. Identitas Jurnal 4
Judul Artikel Predicting Overall Car Performance Using Artificial Neural Network
Nama Jurnal International Journal of Academic and Applied Research (IJAAR)
Download Filehttp://dstore.alazhar.edu.ps/xmlui/bitstream/handle/123456789/
127/ALMPOCv1.pdf?sequence=1&isAllowed=ye:///C:/Users/Hp/D
ownloads/1-1-3-1-10-20171019.pdf
Volume dan Vol 3No 1
Halaman
Tahun 2013
Penulis Al-Mubayyed. Osama M dkk
Reviewer Maya gustina
Tanggal Jumat 28, Mei 2021
5. Identitas Jurnal 5
1. Pembahasan Jurnal 1
2. Pembahasan Jurnal 2
b). methodology
At this stage, value data collection is carried out academic students obtained from the
database Academic Faculty of Dentistry, Unissula. From academic database, obtained
demographic data and Academic scores have been collected starting in 2009 until
2013. At this stage, data exploration done to then be used to determination of input
variables.
c). Research result
The ANN Session 299 architecture uses counts 7 hidden neurons and parameters
learning rate of 0.5 and momentum of 0.1. The iteration used is 9000. The ANN
architecture is the most optimum in the research this is only limited to 750 trials
done. This means that research can be developed by optimizing some aspects is
thought to improve the performance of ANN. As for example, experiments with
parameter combinations training different from the one used on this research and
so on.
3. Pembahasan Jurnal 3
a) BIOLOGICAL INSPIRATION
Human brain is made up of a network of neurons that are coupled with receptors
and effectors. Receptors are called “dendrites” and effectors are called “axons”.
[3] Fig. 1 shows that the dendrites collects the signals from many other neurons in
a limited area; a cell body or soma that integrates collected signals & generates a
response signal & along branching axon that distributes the response through
contacts with dendrite trees of many other neurons.
b) ANN METHODOLOGY
ANNs are basically massive parallel computational models that imitate the function
of human brain. An ANN consists of large number of simple processors linked by
weighted connections. By analogy, the processing nodes may be called “neurons”.
Each node output depends only on the information that is locally available at the
node, either stored internally or arriving via the weighted connections. Each unit
receives inputs from many other nodes transmits its output to yet another nodes. By
itself, a single processing element is not very powerful; it generates a scalar output
with single numerical value, which is a simple non-linear function of its inputs. The
power of the system emerges
When creating a functional model of the biological neuron, there are three basic
components of importance. First, the synapses of the neuron are modeled as weights. The
strength of the connection between an input and a neuron is noted by the value of the
weight. Negative weight values reflect inhibitory connections, while positive values
designate excitatory connections [Haykin]. The next two components model the actual
activity within the neuron cell. An adder sums up all the inputs modified by their
respective weights. This activity is referred to as linear combination. Finally, an
activation function controls the amplitude of the output of the neuron. An acceptable
range of output is usually between 0 and 1, or -1 and 1. Mathematically, this process is
described in the figure.
d). Supervised learning or Associative learning in which the network is trained by
providing it with Input and matching output patterns. These input-output pairs can be
provided by an external teacher, or by the system which contains the neural network
(self- supervised). Example: An archaeologist discovers a human skeleton and has to
determine whether it belonged to man or woman. In doing this, the archaeologist is
guided by many past examples of male and female skeletons
4. Pembahasan Jurnal 4
a) The output variables embody some likely levels of performance of cars in terms
of Excel file with a study summary performance of cars as shown in table 2.
There are 1728 instances in the car data set. The data set then was divided into
training set and validation set. The ANN model was trained with data set and
validated with the validation data set. Furthermore, the Importance of the factors
was determined and the most influential factor was known.
5. Pembahasan Jurnal 5
a) Biological neuron
The human nervous system consists of billions of neurons of various types and
lengths relevant to their location in the body (Schalkoff, 1997). Fig. 1a shows a
schematic of an oversimplified biological neuron with three major functional
units
— dendrites, cell body, and axon. The cell body has a nucleus that contains
information about heredity traits, and a plasma that holds the molecular
equipment used for producing the material needed by the neuron (Jain e al.,
1996). The dendrites receive signals from other neurons and pass them over to the
cell body.
b). The crude analogy between
artificial neuron and towards the post-synaptic membrane, and eventually biological
neuron is that the connections between into the dendrites of neighboring neurons, thus
nodes represent the axons and dendrites, the conforcing them (depending on the threshold
of the nection weights represent the synapses, and the receiving neuron) to generate a
new electrical signal. threshold approximates the activity in the soma (Jain The generated
signal passes through the second et al., 1996). Fig. 2 illustrates n biological neurons
neuron(s) in a manner identical to that just described. with various signals of intensity x
and synaptic The amount of signal that passes through a receiving strength w feeding into
a neuron with a threshold of neuron depends on the intensity of the signal emanat- b, and
the equivalent artificial neurons system. ing from each of the feeding neurons, their
synaptic Integration of the signals in artificial neuronal sys
d). Statistics
Cheng and Titterington (1994) and White (1989) at discrediting ANNs research to
redirect funding provide excellent discussions about ANNs from a back to AI.
Minsky and Pappert published their book statistics perspective. While there are many
differPerceptrons in 1969 in which they over exaggerated ences between ANNs and
statistics, there are also the limitations of the Rosenblatt’s perceptron as many
similarities (Hanson, 1995; Wythoff, 1993). being incapable of solving nonlinear
classification Some ANN models (e.g., feedforward networks with problems,
although such a limitation was already no hidden units) may be viewed as
generalizations to known (Hecht-Nielsen, 1990; Wythoff, 1993). Un- some statistical
models, some are closely related to fortunately, this campaign achieved its planned
goal, statistical modeling (e.g., Hebbian learning), and and by the early 1970s many
ANN researchers others (e.g., Kohonen networks) appear to have no
BAB III
PENUTUP
3.1 Kesimpulan
a. This review considers the application of artificial neural networks (ANNs) to rainfall–
runoff modelling and flood forecasting. This is an emerging field of research,
characterized by a wide variety of techniques, a diversity of geographical contexts, a
general absence of intermodel comparisons, and inconsistent reporting of model skill.
This article begins by outlining the basic principles of ANN modelling, common network
architectures and training algorithms. The discussion then addresses related themes of the
division and preprocessing of data for model calibration/validation; data standardization
techniques; and methods of evaluating ANN model performance. A literature survey
underlines the need for clear guidance in current modelling practice, as well as the
comparison of ANN methods with more conventional statistical models. Accordingly, a
template is proposed in order to assist the construction of future ANN rainfall–runoff
models. Finally, it is suggested that research might focus on the extraction of
hydrological ‘rules’ from ANN weights, and on the development of standard
performance measures that penalize unnecessary model complexity.
b. In this study, it was tested with using the Artificial Neural Network (ANN) method by
using a training algorithm backpropagation. In this method, determinationa combination
of the number of hidden neurons with training parameters namely learning rate,
momentum and epoch has an important role in achieving the optimum value. But because
there are no rules default to define parameters then the trial and error process must be
carried out.
c. As the ANN is an emerging technology it can be used for data analysis in applications
such as pattern recognition, prediction, system identification & control. From above
theories it can be seen that ANN is a radial basis function back propagation network. The
network is capable of predicting the parameters by experimental system.
d. An artificial Neural Network model for predicating overall performance of the car was
presented. The model used feed forward backpropagation algorithm for training. The
factors for the model were obtained from expert in the field. This study showed the
potential of the artificial neural network for predicating overall performance of the car.
e. Artificial neural networks (ANNs) are relatively new computational tools that have found
extensive utilization in solving many complex real-world problems. The attractiveness of
ANNs comes from their remarkable information processing characteristics pertinent
mainly to nonlinearity, high parallelism, fault and noise tolerance, and learning and
generalization capabilities. This paper aims to familiarize the reader with ANN-based
computing (neurocomputing) and to serve as a useful companion practical guide and
toolkit for the ANNs modeler along the course of ANN project development. The history
of the evolution of neurocomputing and its relation to the field of neurobiology is briefly
discussed. ANNs are compared to both expert systems and statistical regression and their
advantages and limitations are outlined. A bird’s eye review of the various types of
ANNs
and the related learning rules is presented, with special emphasis on backpropagation
(BP) ANNs theory and design. A generalized methodology for developing successful
ANNs projects from conceptualization, to design, to implementation, is described. The
most common problems that BPANNs developers face during training are summarized in
conjunction with possible causes and remedies. Finally, as a practical application,
BPANNs were used to model the microbial growth curves of S.
3.2 Saran
Penulis menyadari terdapat banyak kekurangan dari jurnal tersebut untuk itu penulis sangat
mengharapkan kritik dan saran yang dapat membangun untuk melengkapi hasil jurnal in
untuk itu penulis mengucapkan terimakasih.
DAFTAR PUSTAKA
https://www.researchgate.net/profile/Robert-
Wilby/publication/246404185_Hydrological_Modelling_Using_Artificial_Neural_Networks/
links/545a2ef30cf2bccc4913260b/Hydrological-Modelling-Using-Artificial-Neural-
Networks.pdf
file:///C:/Users/Hp/Downloads/10896-29497-1-PB.pdf
https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.1082.1323&rep=rep1&type=pdf
Filehttp://dstore.alazhar.edu.ps/xmlui/bitstream/handle/123456789/127/ALMPOCv1.pdf?seq
uence=1&isAllowed=ye:///C:/Users/Hp/Downloads/1-1-3-1-10-20171019.pdf
http://ethologie.unige.ch/etho5.10/pdf/basheer.hajmeer.2000.fundamentals.design.and.applic
ation.of.neural.networks.review.pdf