scholarly journals Introduction of Balinese Script Handwriting Using Zoning and Multilayer Perceptron

2019 ◽  
Vol 1 (1) ◽  
pp. 1-10
Author(s):  
I Komang Arya Ganda Wiguna ◽  
Agus Muliantara
Keyword(s):  
Character Recognition ◽  
Extraction Method ◽  
Handwriting Recognition ◽  
The Other ◽  
Test Results ◽  
The Difference ◽  
Hidden Layer ◽  
The Many ◽  
Offline Testing ◽  
Value Of Learning

Handwriting identification is one out of the many research ever conducted. In its development, the handwriting can be written in real time by the user by using the mouse (online character recognition). Various studies on the traditional character handwriting recognition continue to be developed. One of them is the recognition of the Balinese characters. Balinese characters have their own unique characters compared with the other regions. The difference between the shapes of the characters with the other characters are quite similar, or there are some characters that can only be distinguished by a small sketch or doodle.This study uses Artificial Neural Network with Backpropagation algorithm to perform the Balinese characters recognition and zoning as a method of feature extraction. In a variation of the extraction method, the characteristics used are Image Centroid and Zone (ICZ), Zone Centroid and Zone (ZCZ) and normalization of features. Of the three methods, it will be determined the best method used in the Balinese characters recognition.From the test results of the extraction method, the combined characteristics of the ICZ, ZCZ and normalization of features were the most effective to be used for the recognition of the Balinese characters. The level of accuracy obtained from the results of the online testing was 71,28% and 72,31% for offline testing, with parameters of Backpropagation, which used the value of learning rate of 0,03, a momentum value of 0,5 and the number of neurons in the hidden layer of 130.

scholarly journals Differences in the Level of Self-Esteem in Science Class and Social Class Students of SMA Negeri 1 Taman Sidoarjo (in Terms of Gender)

2019 ◽  
Vol 6 (2) ◽  
pp. 50
Author(s):  
Noerma Rosalina ◽  
Najlatun Naqiyah ◽  
Tamsil Muis
Keyword(s):  
Social Class ◽  
Quantitative Research ◽  
Self Esteem ◽  
The Other ◽  
Science Class ◽  
Test Results ◽  
Class Status ◽  
The Difference ◽  
Difference Test ◽  
Anova Technique

This research aims to test methodologically and empirically whether or not there are differences in the level of self-esteem in science class and social class students in term of gender. The research variables consist of: (a) the level of self-esteem, (b) class status, and (c) gender measured using a modified Likert scale and using a level of self-esteem scale. This research is a type of quantitative research. The population was teenagers who attended SMANegeri1 TamanSidoarjo and aged between 15-17 years. The research sampling obtained 80 samples including 40 samples from superior class consisting of 20 males and 20 females and the other 40 samples from social class consisting of 20 males and 20 females. Data analysis of the researchapplies the two-way ANOVA technique. ANOVA test, using computer program assistance (SPSS 17.0 for windows), was used to test two or more variables and to find out whether or not the two variances are the same.After conducting the difference test using the two-way ANOVA technique with the help of SPSS 17.0 for windows, the basis for decision making is if the significance value is p> 0.05 then Ho is accepted and vice versa if the significance value is p <0.05 then Ho is rejected. The difference test results show that science class and social class students in term of gender.

scholarly journals Image Classification using Deep Learning Framework

2019 ◽  
Vol 8 (4) ◽  
pp. 10253-10258
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
The Other ◽  
Multilayer Perceptrons ◽  
Monitoring Methods ◽  
Data Set ◽  
Learning Framework ◽  
Flow Pressure ◽  
Hidden Layer ◽  
The Many

Among all the monitoring methods, models with data that is driven have more success rate when compared to any other methods. However these methods are functional to the procedure of material features such as rate of flow, pressure and temperatures. In this we use Keras, in this a group the neurons forms a pair consisting of a unit from visible layer and hidden layer. Forming so they may be formed in a symmetry which provides us to detect the fault. There must not be type of connection between the nodes of a particular group. CNNs are regularized versions of one of the many multilayer perceptrons. Multilayer perceptrons generally means entirely linked networks, that is, each and every neuron that is present in one of the any layer is linked to all neurons in the rest of all layer. The "fully-connectedness" of these modeling networks makes all of them liable for the over-fitting cause of data. Classic ways for the regular use includes accumulation of magnitude measurement of weights by the loss function. On the other hand, CNN took an unusual move towards or step towards the regular use: they take the benefit of the current hierarchical outline in the data set and gather more and more difficult outline using smaller outlines. Thus, on comparing among the connectedness and difficulty, CNN’s are at the least limit.

scholarly journals Feldenkrais Exercise Mempangaruhi Peningkatan Aktivitas Fungsional Lebih Efektif daripada William Flexion Exercise terhadap Orang dengan Low Back Pain Miogenik

2018 ◽  
Vol 6 (1) ◽  
pp. 8-14
Author(s):  
Yuda Saputra ◽  
Ahmad Syakib
Keyword(s):  
Low Back Pain ◽  
Back Pain ◽  
Functional Activity ◽  
Muscle Tension ◽  
P Value ◽  
Low Back ◽  
Test Results ◽  
Lower Back ◽  
The Difference ◽  
The Many

Background :  Low Back Pain Miogenik is a lower back pain caused by muscle tension with avery high frequency of cases in workers. This research is done to identify the difference of influence between the approach of William Flexion Exercise and Feldenkrais exercise to functional activity inpatient low back pain miogenik because of the many cases that happened.. Methods : The type of research used is experimental research, research design used is a quasi experiment that compares between two different things. The targets of this study were factory workers with a sampel of 34 people divided into two groups. Result: Based on the result ofhypothesis paired t-test result p-value 0.000 shows both treatment there is significant improvement to functional activity. While on thetest Independentt-test results seen from the mean feldenkrais exercise 8.13 and william flexion exercise 3.25 concluded feldenkrais exercise more up than william flexion exercise.

scholarly journals Individuality Representation in Character Recognition

2015 ◽  
Vol 1 (2) ◽  
pp. 300
Author(s):  
Bayan Omar
Keyword(s):  
Pattern Recognition ◽  
Character Recognition ◽  
State Of The Art ◽  
Handwriting Recognition ◽  
The Other ◽  
Primary Reason ◽  
The Past ◽  
Other Hand ◽  
Interesting Study ◽  
High Chance

The task of recognition that is based on handwriting characters in the Kurdish language is an interesting study in the area of computer vision and pattern recognition. In the past couple of years, numerous state-of-the-art techniques and methods have been created for pattern recognition. On the other hand, Kurdish language handwriting recognition has been seen to be more difficult when compared to other different languages. The similarities in the properties in Kurdish characters is the primary reason of the great resemblance in the features of Kurdish handwriting characters, therefore the requirement for the recognition process is critical. Consequently, to obtain accurate and precise recognition on the basis of the Kurdish handwriting character, it is crucial for the resemblances in the character properties of Kurdish handwriting to be distinguished. To identify a particular character, the style of character handwriting may be evaluated to enable the implied representation of the hidden unique features of the user’s character. Unique features may guide in recognizing characters that may be important when recognizing the correct character among similar characters. On the other hand, the problem of the resemblances in the properties of handwriting of Kurdish characters were not taken into account ,consequently leaving a high chance of reducing the similarity error for any intra-class (of the same character),with the reduction of the similarity error for any inter-class (of different characters) as well. In order to obtain higher effectiveness, this study uses discretization features for reducing the similarity error for intra-class (of the same character),with the increase of the similarity error for inter-class (of different characters)in recognition of Kurdish Handwriting characters with MAE.

scholarly journals KANNADA CHARACTER RECOGNITION SYSTEM USING NEURAL NETWORK

2012 ◽  
pp. 206-208
Author(s):  
SURESH KUMAR D S ◽  
AJAY KUMAR B R ◽  
K SRINIVASA KALYAN
Keyword(s):  
Neural Network ◽  
Character Recognition ◽  
Recognition Accuracy ◽  
Handwriting Recognition ◽  
Recognition System ◽  
Indian Language ◽  
Research Areas ◽  
The Neural Network ◽  
Feed Forward Neural Networks ◽  
Hidden Layer

Handwriting recognition has been one of the active and challenging research areas in the field of pattern recognition. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form[1]. As there are no sufficient number of works on Indian language character recognition especially Kannada script among 15 major scripts in India[2].In this paper an attempt is made to recognize handwritten Kannada characters using Feed Forward neural networks. A handwritten kannada character is resized into 20x30 pixel.The resized character is used for training the neural network. Once the training process is completed the same character is given as input to the neural network with different set of neurons in hidden layer and their recognition accuracy rate for different kannada characters has been calculated and compared. The results show that the proposed system yields good recognition accuracy rates comparable to that of other handwritten character recognition systems.

scholarly journals Achievement in Training: Recorded Video Compared to Face-to-Face Environments

2021 ◽  
pp. 1-3
Author(s):  
Kate Quigley
Keyword(s):  
Student Achievement ◽  
Instructional Methods ◽  
The Other ◽  
Test Results ◽  
Face To Face ◽  
Video Lectures ◽  
Significant Difference ◽  
Similar Vein ◽  
The Many ◽  
Full Face

During the 2020-2021 years, it has been necessary for organizations to rethink how they conduct their daily operations in light of COVID-19 restrictions. One of the many activities within organizations is to provide new and recurrent training to their employees. In a similar vein, universities also had to make adaptations to instructional methods. This change provided an opportunity to compare student achievement in two different instructional modalities; one with lectures delivered in a full face-to-face format, and the other with recorded video lectures delivered in online platform. Both formats were conducted in morning and afternoon sessions. Three sets of test results were measured to compare the outcomes between two years. This study had mixed results, two of the three test results sets between the years showed no significant difference between face-to-face and recorded video lectures, while one of the three test results provided evidence that the results were different between instructional methods. The results of this study could provide applicable information to organizations and help to provide a roadmap for providing training in different formats. It is noteworthy that providing instruction in recorded video formats could be less expensive to organizations and also provide more flexibility for employees to fit recurrent t into their daily schedules.

Improvement of Suction Performance Using Splitter Impeller and Inducer

2017 ◽  
Author(s):  
K. Hayashi ◽  
S. Konno ◽  
M. Hayakawa ◽  
Y. Kawata
Keyword(s):  
Flow Rate ◽  
Industrial Applications ◽  
Flow Coefficient ◽  
The Other ◽  
Suction Pressure ◽  
Test Results ◽  
Pressure Condition ◽  
The Many ◽  
Suction Performance ◽  
Onset Of Cavitation

Suction performance is one of the most important characteristics of the industrial pump to keep the pump capability against the cavitation under the low suction pressure condition. Inducers have been developed to improve the suction performance of pumps. They are used for rocket turbo pumps and recently for many industrial applications. It is one of the competitiveness of the industrial pumps to downsize the scale with higher rotational speed by adopting inducer. The authors had proved that pump with splitter impeller with inducer can further improve the suction performance. The splitter impeller was specially designed to be resistant to the cavitation choke. The other very important requirement for the pump against cavitation is that it does not occur cavitation surge. The cavitation surge arises at the partial flow rate of the pump. In contrast to this the suction performance become better at the partial flow rate. So the precise compromise is necessary to satisfy these requirements. This paper presents the experimental and CFD results to improve and optimize the suction performance without generating cavitation surge. The many design and combination of splitter impeller and inducer are tested to get the better performance. The test results of pumps with different inlet flow coefficient are compared not only suction performance but also the onset of cavitation surge.

scholarly journals Analisis Performa Pre-Trained Model Convolutional Neural Network dalam Mendeteksi Penyakit Tuberkulosis

2021 ◽  
Vol 8 (4) ◽  
pp. 805
Author(s):  
Ovy Rochmawanti ◽  
Fitri Utaminingrum ◽  
Fitra A. Bachtiar
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Computation Time ◽  
The Other ◽  
X Rays ◽  
Test Results ◽  
Image Size ◽  
The Difference ◽  
The Right ◽  
Disease Testing

<p>Tuberkulosis (TB) merupakan salah satu penyakit berbahaya yang dapat menular lewat udara dan sering menyebabkan kematian apabila tidak cepat ditangani. Penyakit TB bisa disembuhkan dengan deteksi dini sehingga penderita dapat segera mendapatkan pengobatan yang tepat. Metode Convolutional Neural Network (CNN) digunakan untuk mendeteksi penyakit TB melalui foto rontgen dada. Penelitian ini bertujuan untuk menentukan model CNN yang mampu menghasilkan performa paling baik dalam mendeteksi penyakit TB. Pengujian dilakukan dengan menggunakan lima pre-trained model yang telah disediakan oleh Keras yaitu <em>ResNet50</em>, <em>DenseNet121</em>, <em>MobileNet</em>, <em>Xception</em>, <em>InceptionV3</em>, dan <em>InceptionResNetV2</em>. Perbedaan ukuran gambar yag digunakan pada saat pelatihan dan pengujian juga akan dianalisis pengaruhnya terhadap nilai akurasi yang dihasilkan dan waktu komputasinya. Hasil pengujian menunjukkan bahwa model <em>DenseNet121</em> mampu menghasilkan nilai akurasi tertinggi dalam mendeteksi penyakit TB, yaitu 91,57%. Sedangkan model <em>MobileNet</em> merupakan model dengan waktu komputasi tercepat untuk semua ukuran gambar yang diuji. Semakin besar ukuran citra maka semakin tinggi nilai akurasinya, namun di sisi lain waktu komputasi juga akan semakin lama. </p><p> </p><p><strong>Abstract</strong></p><p><strong> </strong></p><p class="Abstract"><em>Tuberculosis (TB) is one of the dangerous disease that can be transmitted through the air and often causes death if not treated quickly. This illness can be cured with early detection, so that sufferers can immediately get the right treatment. The Convolutional Neural Network (CNN) method is used to detect TB disease through chest X-rays. This study aims to determine which CNN model is able to produce the best performance in detecting TB disease. Testing was carried out using five pre-trained models provided by Keras namely ResNet50, DenseNet121, MobileNet, Xception, InceptionV3, and InceptionResNetV2. The difference in image size used during training and testing will also be analyzed for its effect on the resulting accuracy value and its computation time. The test results showed that the DenseNet121 model was able to produce the highest accuracy value in detecting TB disease, namely 91.57%. Meanwhile, the MobileNet model is the model with the fastest computation time for all image sizes tested. The bigger the image size, the higher the accuracy value, but on the other hand the computation time will also be longer.</em></p>

scholarly journals Perception of industrialized orange juice

2018 ◽  
Author(s):  
Alice Raissa Honorio ◽  
Alline Artigiani Lima Tribst ◽  
Geovanna S. Pereira ◽  
Bruna R. Gasparetto ◽  
Carla M.A. Lopes
Keyword(s):  
High Temperature ◽  
Orange Juice ◽  
The Other ◽  
Food Technology ◽  
Test Results ◽  
Process Characteristics ◽  
Correct Information ◽  
Other Hand ◽  
The Difference ◽  
Ultra High Temperature

We evaluated the difference about industrialized orange juice perception among consumers that studied food technology/science/engineering (food experts) and lay consumers. The research used online questionnaires (blind and informed about processes/products characteristics) with check-all-that-apply (CATA) test. Results showed that food experts and lay consumers have the same concept about fresh squeezed orange juice and about powdered drink mix. On the other hand, the term "industrialized juice" and the samples "not from concentrated" (pasteurized) and "ultra-high temperature" (sterilized) were associated to durability and process characteristics for food experts, and to depreciatory terms by lay consumers. Better evaluation of this samples were observed in informed questionnaire, highlighting that correct information allows consumers to make more conscious choices about their juices.

scholarly journals PENAFSIRAN SURAT AL-DHUHA MENURUT AL-BAIDHAWI DAN BINTU AL-SYATHI’

2020 ◽  
Vol 5 (2) ◽  
pp. 98
Author(s):  
Aditya Faruq Alfurqan ◽  
Maizuddin Maizuddin
Keyword(s):  
Analytical Method ◽  
The Other ◽  
Data Sources ◽  
Human Being ◽  
Data Source ◽  
The Difference ◽  
The Many ◽  
Existing Data

The Alquran is a guide for every human being, to understand the meaning contained herein it takes a science that is the interpreter science. There are different interpretations because of the methods, features and shapes used by a mufassir, and because the other is the period in which a mufasir lives, or other names are classical and contemporary periods, a period is a factor in the difference of interpretations, because of the many contemporary problems or the absence of ancient evidence. The method that researchers use is a descriptive analytical method of collecting existing data sources and then being properly analyzed, whereas the data source that researchers refer to are the interpretive books themselves, here researchers use interpresir Anwaru al-Tanzil wa Asraru al-Ta’wil as the classic interpretive reference, to the interpretation of contemporary researchers refer to Tafsir al-Bayani li al-Qur`an al-Karim treatise for Bintu al-Syathi. One example that became a difference in interpretation was lafadz taqhar surah al-Dhuha serves 9, Baidhawi interpret by the reach that you possess his possessions is because of his weaknesses, whereas Bintu al-Syathi interprets not arbitrary not to give property to them, but there is a treatment that offends them like harsh words, a cynical stare which the deed is committed without any deliberate measure.Abstrak: Al-Qur`an merupakan pedoman bagi setiap manusia. Untuk memahami makna yang terkandung di dalamnya, maka dibutuhkan sebuah ilmu yaitu ilmu tafsir. Adanya perbedaan penafsiran disebabkan karena metode, corak dan bentuk yang dipakai oleh seorang mufasir. Sebab lainnya adalah masa di mana seorang mufasir hidup, atau sebutan lainnya adalah periode klasik dan periode kontemporer. Masa menjadi salah satu faktor terjadi perbedaan penafsiran, karena banyaknya permasalahan di zaman kontemporer ini atau hal-hal lain yang tidak didapati di zaman terdahulu. Seperti yang terlihat dalam tulisan ini, yaitu perbedaan penafsiran pada surat al-Dhuha. Metode yang peneliti gunakan adalah analitis deskriptif yaitu mengumpulkan sumber-sumber data yang ada, lalu dianalisa secara tepat. Sumber data yang menjadi rujukan adalah kitab-kitab tafsir, khususnya Tafsir Anwaru al-Tanzil wa Asraru al-Ta’wil sebagai rujukan tafsir klasik. Untuk tafsir kontemporer merujuk kepada Tafsir al-Bayani li al-Qur`an al-Karim karya Bintu al-Syathi’. Salah satu contoh yang menjadi perbedaan penafsiran pada surat al-Dhuha (93): 9 adalah pada lafal taqhar. Al-Baidhawi menafsirkan dengan “janganlah kamu menguasai hartanya dikarenakan kelemahannya”, sedangkan Bintu al-Syathi’ menafsirkan bukan kesewenang-wenang tidak memberikan harta terhadap mereka, tetapi ada perlakuan yang menyakiti hati seperti perkataan yang kasar, tatapan sinis yang mana perbuatan tersebut dilakukan tanpa unsur kesengajaan. 

Sign in / Sign up

Export Citation Format

Share Document