Accurate and compact convolutional neural network based on stochastic computing

Abdellatef, Hamdan; Khalil-Hani, Mohamed; Shaikh-Husin, Nasir; Ayat, Sayed Omid

doi:10.1016/j.neucom.2021.10.105

Cited by 32 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Each video frame is an independent image, so the video-based information hiding technology can directly apply the image-based hiding technology to video information hiding. Wan et al [17] proposed a video information-hiding algorithm based on H.264/AVC lowfrequency domain based on the existing video informationhiding algorithm, combined with the characteristics of H.264/ AVC video low-frequency domain coefficients [18,19].…”

mentioning

confidence: 99%

Retracted: Blockchain‐based covert software information transmission for bitcoin

Reis¹,

Barbosa

Albuquerque

et al. 2023

IET Software

View full text Add to dashboard Cite

Blockchain-based data transmission will become a new development direction of data concealment transmission, which is of great significance for developing a secure transmission technology for special applications. To meet the needs of efficient, secure, concealed and stable transmission of confidential information, the transaction data structure of Bitcoin and the location and capacity of potential covert channels are analysed. The data transmission model for covert storage channels based on Bitcoin blockchain is also proposed. It cannot destroy the original transaction format, do not increase the particularity of the transaction content, overcome the defects of the concealed channel characteristics in the existing network environment, ensure that the data is not detected, and protect the sender and receiver of the hidden data transmission. | Information hidingInformation hiding methods can be divided into three categories according to the different information hiding carriers:This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

mentioning

confidence: 99%

Retracted: Blockchain‐based covert software information transmission for bitcoin

Reis¹,

Barbosa

Albuquerque

et al. 2023

IET Software

View full text Add to dashboard Cite

show abstract

“…The artificial intelligence (AI) is more prevalent in the current era. The problems related to the orthodontic field are also being solved through AI and most specifically through the ML and DL (Abdellatef et al, 2022). There are several versions of AI for obtaining automation in the field of orthodontics and dentofacial deformities.…”

Section: Discussionmentioning

confidence: 99%

A novel coarse‐to‐fine computational method for three‐dimensional landmark detection to perform hard‐tissue cephalometric analysis

et al. 2023

View full text Add to dashboard Cite

Cephalometric analysis has an important and essential role to treat the patients with craniofacial and dentofacial deformities. Cephalometric analysis is a relationship of human geometry which can be quantified and derived from the linear and angular measurements. To treat any patient, such analysis is required to be performed on the Head X‐ray image of the patient. The objective of the proposed work is to detect cephalometric landmarks automatically on CT (computational tomography) images. Twenty cephalometric landmarks were automatically localized on 100 CT scans using hybrid coarse‐to‐fine computational method. The mean error for landmark detection was computed as 2.88 mm and standard deviation of 1.85 mm. The highest detection rate for cephalometric landmarks was received as 100% for Nasion landmark under 4‐mm error and the highest detection rate was received as 99% for Nasion landmark under 3‐mm error. The less number of datasets were used for the training and higher number of datasets were used for the testing. Compared to the literature methods, our method used higher number of datasets to demonstrate the accuracy of the proposed method.

show abstract

“…Deep learning adalah proses pembelajaran yang lebih mendalam sehingga memungkinkan mesin untuk mempelajari informasi yang kompokes dan mengekstrak representasi data dari berbagai tingkatan informasi. Convolutional Neural Network (CNN) adalah salah satu metode deep learning yang diakui sebagai salah satu jenis ANN yang memiliki tingkat akuraasi terbaik dalam proses pengenalan dan deteksi [17]. Jenis-jenis deteksi yang dapat dilakukan dengan menggunakan metode CNN yaitu face recognition [18], target recognition [19], image classification [20] dan handwritten recognition [21].…”

Section: Pendahuluanunclassified

Komparasi Metode Backpropagation Neural Network dan Convolutional Neural Network Pada Pengenalan Pola Tulisan Tangan

Maharani

Saputra²,

Wirastuti³

2022

J-Cosine

View full text Add to dashboard Cite

Historical manuscripts are one of documents that important to be preserved because they contain a lot of information, one example of them is script as the historical documents . Historical document mostly still use handwriting in so many reserch. Currently, there are many research regarding the preservation of characters. One way of preservation that can be used is the digitization process. Digitizing’s process tanable by recognizing existing information using technology. The technology that can be used is machine learning. Handwriting is a complex case because of the many variations of these characters and the output of the author where variations of the author will produce different writings. The relevant fields for text and documents are Optical Chacarter Recognition (OCR) and handwriting recognition. There are several methods that can be used in the machine learning process, including Artificial Neural Network (ANN) and Convolutional Neural Network (CNN). Both of these methods are methods that can accept complex image input to be processed and recognized, therefore this method is highly recommended for processing handwriting.

show abstract

Accurate and compact convolutional neural network based on stochastic computing

Cited by 32 publications

References 23 publications

Retracted: Blockchain‐based covert software information transmission for bitcoin

Retracted: Blockchain‐based covert software information transmission for bitcoin

A novel coarse‐to‐fine computational method for three‐dimensional landmark detection to perform hard‐tissue cephalometric analysis

Komparasi Metode Backpropagation Neural Network dan Convolutional Neural Network Pada Pengenalan Pola Tulisan Tangan

Contact Info

Product

Resources

About