Klasifikasi Citra Pigmen Kanker Kulit Menggunakan Convolutional Neural Network

Skin cancer is a very common form of cancer that can be found in the United States with annual treatment costs exceeding $ 8 billion. New innovations in the classification and detection of skin cancer using artificial neural networks continue to develop to help the medical and medical world in analyzing images accurately and accurately. Researchers propose to classify skin cancer pigments by focusing on two classes, namely non-melanocytic malignant and benign, where the skin cancer category which is classified into the non-melanocytic class is Actinic keratoses, Basal cell carcinoma. While skin cancers that are classified into Benign are Benign keratosis like lesions, dermatofibrama, vascular lessions. The method used in this study is Convolutional Neural Network (CNN) with a model architecture using 8 Convolutional 2D layers which have filters (16, 16, 32, 32, 64, 64, 128, 128). The first input layers are (20,20). and the following layers (5,5 and 3,3), the types of pooling used in this study are MaxPooling and AveragePooling. The Fully Connected Layer used is (256, 128) and uses a Dropout (0.2). The dataset is obtained from the International Skin Imaging Collaboration (ISIC) 2018 with a total of 10015 images. Based on the results of the test and evaluation reports, an accuracy of 75% is obtained. with the highest precision and recall values found in the Benign class, namely 0.80 and 0.82 respectively and the f1_score value of 0.81.

Download Full-text

Binary and Multiclass Text Classification by Means of Separable Convolutional Neural Network

Inventions ◽

10.3390/inventions6040070 ◽

2021 ◽

Vol 6 (4) ◽

pp. 70

Author(s):

Elena Solovyeva ◽

Ali Abdullah

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Recurrent Neural Networks ◽

Low Cost ◽

Computational Cost ◽

High Accuracy ◽

Activation Functions ◽

Fully Connected ◽

Fully Connected Networks

In this paper, the structure of a separable convolutional neural network that consists of an embedding layer, separable convolutional layers, convolutional layer and global average pooling is represented for binary and multiclass text classifications. The advantage of the proposed structure is the absence of multiple fully connected layers, which is used to increase the classification accuracy but raises the computational cost. The combination of low-cost separable convolutional layers and a convolutional layer is proposed to gain high accuracy and, simultaneously, to reduce the complexity of neural classifiers. Advantages are demonstrated at binary and multiclass classifications of written texts by means of the proposed networks under the sigmoid and Softmax activation functions in convolutional layer. At binary and multiclass classifications, the accuracy obtained by separable convolutional neural networks is higher in comparison with some investigated types of recurrent neural networks and fully connected networks.

Download Full-text

An application of convolutional neural network for deterioration modeling of highway bridge components in the United States

Structure and Infrastructure Engineering ◽

10.1080/15732479.2021.1979597 ◽

2021 ◽

pp. 1-14

Author(s):

Heng Liu ◽

Jean Nehme ◽

Ping Lu

Keyword(s):

Neural Network ◽

United States ◽

Convolutional Neural Network ◽

The United States ◽

Highway Bridge

Download Full-text

Building Extraction at Scale Using Convolutional Neural Network: Mapping of the United States

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ◽

10.1109/jstars.2018.2835377 ◽

2018 ◽

Vol 11 (8) ◽

pp. 2600-2614 ◽

Cited By ~ 41

Author(s):

Hsiuhan Lexie Yang ◽

Jiangye Yuan ◽

Dalton Lunga ◽

Melanie Laverdiere ◽

Amy Rose ◽

...

Keyword(s):

Neural Network ◽

United States ◽

Convolutional Neural Network ◽

The United States ◽

Building Extraction ◽

Network Mapping

Download Full-text

Introspective analysis of convolutional neural networks for improving discrimination performance and feature visualisation

PeerJ Computer Science ◽

10.7717/peerj-cs.497 ◽

2021 ◽

Vol 7 ◽

pp. e497

Author(s):

Shakeel Shafiq ◽

Tayyaba Azim

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Discrimination Performance ◽

Input Image ◽

Data Sets ◽

Discrimination Power ◽

Level Information ◽

Fully Connected

Deep neural networks have been widely explored and utilised as a useful tool for feature extraction in computer vision and machine learning. It is often observed that the last fully connected (FC) layers of convolutional neural network possess higher discrimination power as compared to the convolutional and maxpooling layers whose goal is to preserve local and low-level information of the input image and down sample it to avoid overfitting. Inspired from the functionality of local binary pattern (LBP) operator, this paper proposes to induce discrimination into the mid layers of convolutional neural network by introducing a discriminatively boosted alternative to pooling (DBAP) layer that has shown to serve as a favourable replacement of early maxpooling layer in a convolutional neural network (CNN). A thorough research of the related works show that the proposed change in the neural architecture is novel and has not been proposed before to bring enhanced discrimination and feature visualisation power achieved from the mid layer features. The empirical results reveal that the introduction of DBAP layer in popular neural architectures such as AlexNet and LeNet produces competitive classification results in comparison to their baseline models as well as other ultra-deep models on several benchmark data sets. In addition, better visualisation of intermediate features can allow one to seek understanding and interpretation of black box behaviour of convolutional neural networks, used widely by the research community.

Download Full-text

Deteksi Dini Kanker Kulit menggunakan K-NN dan Convolutional Neural Network

Jurnal Teknologi Informasi dan Ilmu Komputer ◽

10.25126/jtiik.2020702602 ◽

2020 ◽

Vol 7 (2) ◽

pp. 373

Author(s):

Teresia R. Savera ◽

Winsya H. Suryawan ◽

Agung Wahyu Setiawan

Keyword(s):

Neural Network ◽

Neural Networks ◽

Skin Cancer ◽

Convolutional Neural Network ◽

Learning Algorithm ◽

Detection Systems ◽

Deep Learning Algorithm ◽

Artificial Neural ◽

Processing Techniques ◽

Further Development

Kanker kulit adalah salah satu jenis kanker yang dapat menyebabkan kematian sehingga diperlukan sebuah aplikasi perangkat lunak yang dapat digunakan untuk membantu melakukan deteksi dini kanker kulit dengan mudah. Sehingga diharapkan deteksi dini kanker kulit dapat terdeteksi lebih cepat. Pada penelitian ini terdapat dua metode yang digunakan untuk melakukan deteksi dini kanker kulit yaitu deteksi dengan klasifikasi secara regresi dan artificial neural network dengan arsitektur convolutional neural network. Akurasi yang diperoleh dengan menggunakan klasifikasi secara regresi adalah sebesar 75%. Sementara, akurasi deteksi yang didapatkan dengan menggunakan convolutional neural network adalah sebesar 76%. Hasil yang diperoleh dari kedua metoda ini masih dapat ditingkatkan pada penelitian lanjutan, yaitu dengan cara melakukan prapengolahan pada set data citra yang digunakan. Sehingga set data yang digunakan memiliki tingkat pencahayaan, sudut (pengambilan), serta ukuran citra yang sama. Apabila tersedia sumber daya komputasi yang besar, akan dilakukan penambahan jumlah citra yang digunakan, baik itu sebagai set data latih maupun uji. AbstractSkin cancer is one type of cancer that can cause death for many people. Because of this, an application is needed to easily detect skin cancer early that the cancer can be handled with more quickly. In this study there were two methods used to detect skin cancer, namely detection by regression classification and detection by classifying using artificial neural networks with network convolutional architecture. Detection with regression classification gives an accuracy of 75%. While detection using convolutional neural networks gives an accuracy of 76%. These proposed early detection systems can be improved to increase the accuracy. For further development, several image processing techniques will be applied, such as contrast enhancement and color equalization. For future works, if there is more computational resource, more images can be used as dataset and implement the deep learning algorithm to improve the accuracy.

Download Full-text

Application of convolutional neural networks in optical text recognition to junk data filtering

Journal of Physics Conference Series ◽

10.1088/1742-6596/2127/1/012024 ◽

2021 ◽

Vol 2127 (1) ◽

pp. 012024

Author(s):

T E Razumov ◽

D V Churikov ◽

O V Kravchenko

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Image Classification ◽

Text Recognition ◽

Data Filtering ◽

Service Architecture ◽

C Language ◽

Software Application ◽

Fully Connected

Abstract In this paper, the problem of constructing a model for detecting and filtering unwanted spam messages is solved. A fully connected convolutional neural network (FCNN) was chosen as the model of the classifier of unwanted emails in email. It allows you to divide emails into two categories: spam and not spam. The main result of the research is a software application in the C++ language, which has a micro-service architecture and solves the problem of image classification. The app can handle more than 106 requests per minute in real-time.

Download Full-text

Predicting road quality using high resolution satellite imagery: A transfer learning approach

PLoS ONE ◽

10.1371/journal.pone.0253370 ◽

2021 ◽

Vol 16 (7) ◽

pp. e0253370

Author(s):

Ethan Brewer ◽

Jason Lin ◽

Peter Kemper ◽

John Hennin ◽

Dan Runfola

Keyword(s):

Neural Network ◽

United States ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Satellite Imagery ◽

The United States ◽

Accurate Information ◽

Learning Approach ◽

Road Infrastructure ◽

Health And Economic Development

Recognizing the importance of road infrastructure to promote human health and economic development, actors around the globe are regularly investing in both new roads and road improvements. However, in many contexts there is a sparsity—or complete lack—of accurate information regarding existing road infrastructure, challenging the effective identification of where investments should be made. Previous literature has focused on overcoming this gap through the use of satellite imagery to detect and map roads. In this piece, we extend this literature by leveraging satellite imagery to estimate road quality and concomitant information about travel speed. We adopt a transfer learning approach in which a convolutional neural network architecture is first trained on data collected in the United States (where data is readily available), and then “fine-tuned” on an independent, smaller dataset collected from Nigeria. We test and compare eight different convolutional neural network architectures using a dataset of 53,686 images of 2,400 kilometers of roads in the United States, in which each road segment is measured as “low”, “middle”, or “high” quality using an open, cellphone-based measuring platform. Using satellite imagery to estimate these classes, we achieve an accuracy of 80.0%, with 99.4% of predictions falling within the actual or an adjacent class. The highest performing base model was applied to a preliminary case study in Nigeria, using a dataset of 1,000 images of paved and unpaved roads. By tailoring our US-model on the basis of this Nigeria-specific data, we were able to achieve an accuracy of 94.0% in predicting the quality of Nigerian roads. A continuous case estimate also showed the ability, on average, to predict road quality to within 0.32 on a 0 to 3 scale (with higher values indicating higher levels of quality).

Download Full-text

Skin Cancer Screening

Psycho-Oncology ◽

10.1093/med/9780190097653.003.0013 ◽

2021 ◽

pp. 87-92

Author(s):

Jennifer L. Hay ◽

Stephanie N. Christian

Keyword(s):

United States ◽

Cancer Screening ◽

Skin Cancer ◽

Task Force ◽

New Technology ◽

Clinical Trial Data ◽

Skin Surface ◽

The United States ◽

Skin Cancer Screening ◽

Skin Cancers

Skin cancers are exceedingly common malignancies in the United States and include keratinocyte cancers, which have low mortality rates but are costly to treat, and melanomas, which can be deadly if diagnosed at later stages. Skin cancer screening for the general population has not received recommendation by the United States Preventive Services Task Force, given the paucity of clinical trial data documenting utility, yet there are sound arguments for the utility of risk-based screening, based on increased skin cancer risk. Such risk factors include skin type, high mole number, genetic susceptibility, and family or personal history of skin cancers. Screening can involve an inspection of the entire skin surface performed by a dermatologist or other health care provider, or self-screening, whereby individuals conduct an examination of their skin surface at home, which can be facilitated through the use of a mirror, as well as a family member or friend to facilitate skin inspection. Rates of physician screening as well as skin self-examination are low in the United States. This chapter reviews the current evidence and recommendations for skin cancer screening in the United States. It also reviews the current rates of screening, both overall and in higher-risk subgroups. The chapter discusses the recent evidence for the use of interventions to enhance skin cancer screening. It also presents some innovative use of new technology to increase skin cancer screening as well as future directions for this research.

Download Full-text

Deep learning for quark–gluon plasma detection in the CBM experiment

International Journal of Modern Physics A ◽

10.1142/s0217751x20430022 ◽

2020 ◽

Vol 35 (33) ◽

pp. 2043002 ◽

Cited By ~ 1

Author(s):

Fedor Sergeev ◽

Elena Bratkovskaya ◽

Ivan Kisel ◽

Iouri Vassiliev

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Quark Gluon Plasma ◽

Heavy Ion ◽

Gluon Plasma ◽

Ion Collisions ◽

Validation Set ◽

Fully Connected

Classification of processes in heavy-ion collisions in the CBM experiment (FAIR/GSI, Darmstadt) using neural networks is investigated. Fully-connected neural networks and a deep convolutional neural network are built to identify quark–gluon plasma simulated within the Parton-Hadron-String Dynamics (PHSD) microscopic off-shell transport approach for central Au+Au collision at a fixed energy. The convolutional neural network outperforms fully-connected networks and reaches 93% accuracy on the validation set, while the remaining only 7% of collisions are incorrectly classified.

Download Full-text

Using local convolutional neural networks for genomic prediction

10.1101/2020.05.12.090118 ◽

2020 ◽

Author(s):

Torsten Pook ◽

Jan Freudenthal ◽

Arthur Korte ◽

Henner Simianer

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Genomic Prediction ◽

Linear Models ◽

Predictive Ability ◽

High Heritability ◽

Fully Connected

ABSTRACTThe prediction of breeding values and phenotypes is of central importance for both livestock and crop breeding. With increasing computational power and more and more data to potentially utilize, Machine Learning and especially Deep Learning have risen in popularity over the last few years. In this study, we are proposing the use of local convolutional neural networks for genomic prediction, as a region specific filter corresponds much better with our prior genetic knowledge of traits than traditional convolutional neural networks. Model performances are evaluated on a simulated maize data panel (n = 10,000) and real Arabidopsis data (n = 2,039) for a variety of traits with the local convolutional neural network outperforming both multi layer perceptrons and convolutional neural networks for basically all considered traits. Linear models like the genomic best linear unbiased prediction that are often used for genomic prediction are outperformed by up to 24%. Highest gains in predictive ability was obtained in cases of medium trait complexity with high heritability and large training populations. However, for small dataset with 100 or 250 individuals for the training of the models, the local convolutional neural network is performing slightly worse than the linear models. Nonetheless, this is still 15% better than a traditional convolutional neural network, indicating a better performance and robustness of our proposed model architecture for small training populations. In addition to the baseline model, various other architectures with different windows size and stride in the local convolutional layer, as well as different number of nodes in subsequent fully connected layers are compared against each other. Finally, the usefulness of Deep Learning and in particular local convolutional neural networks in practice is critically discussed, in regard to multi dimensional inputs and outputs, computing times and other potential hazards.

Download Full-text