Comparisions on KNN, SVM, BP and the CNN for Handwritten Digit Recognition

Liu, Wenfei; Wei, Jingcheng; Meng, Qingmin

doi:10.1109/aeeca49918.2020.9213482

Cited by 34 publications

(13 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the proposed data‐driven demultiplexing model achieved perfect crystal identification without any additional decoding error. Compared with other classical or conventional machine learning techniques such as the look‐up table or k‐nearest neighbor (kNN), which are trained by simply memorizing the features and labels of the training dataset while requiring extensive computational resources during the prediction process, 30 the CNN method spends most of the time on training the model to optimize parameters and learn generalizable representations which combined with GPU‐based parallel processing can perform data demultiplexing substantially faster.…”

Section: Discussionmentioning

confidence: 99%

Interleaved signal multiplexing readout in depth encoding Prism‐PET detectors

LaBella

Zeng

et al. 2023

Medical Physics

View full text Add to dashboard Cite

Background Given the large number of readout pixels in clinical positron emission tomography (PET) scanners, signal multiplexing is an indispensable feature to reduce scanner complexity, power consumption, heat output, and cost. Purpose In this paper, we introduce interleaved multiplexing (iMux) scheme that utilizes the characteristic light‐sharing pattern of depth‐encoding Prism‐PET detector modules with single‐ended readout. Methods In the iMux readout, four anodes from every other silicon photomultiplier (SiPM) pixels across rows and columns, which overlap with four distinct light guides, are connected to the same application‐specific integrated circuit (ASIC) channel. The 4‐to‐1 coupled Prism‐PET detector module was used which consisted of a 16 × 16 array of 1.5 × 1.5 × 20 mm3 lutetium yttrium oxyorthosilicate (LYSO) scintillator crystals coupled to an 8 × 8 array with 3 × 3 mm2 SiPM pixels. A deep learning‐based demultiplexing model was investigated to recover the encoded energy signals. Two different experiments were performed with non‐multiplexed and multiplexed readouts to evaluate the spatial, depth of interaction (DOI), and timing resolutions of our proposed iMux scheme. Results The measured flood histograms, using the decoded energy signals from our deep learning‐based demultiplexing architecture, achieved perfect crystal identification of events with negligible decoding error. The average energy, DOI, and timing resolutions were 9.6 ± 1.5%, 2.9 ± 0.9 mm, and 266 ± 19 ps for non‐multiplexed readout and 10.3 ± 1.6%, 2.8 ± 0.8 mm, and 311 ± 28 ps for multiplexed readout, respectively. Conclusions Our proposed iMux scheme improves on the already cost‐effective and high‐resolution Prism‐PET detector module and provides 16‐to‐1 crystal‐to‐readout multiplexing without appreciable performance degradation. Also, only four SiPM pixels are shorted together in the 8 × 8 array to achieve 4‐to‐1 pixel‐to‐readout multiplexing, resulting in lower capacitance per multiplexed channel.

show abstract

Section: Discussionmentioning

confidence: 99%

Interleaved signal multiplexing readout in depth encoding Prism‐PET detectors

LaBella

Zeng

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Image normalization; in this group, a standard is established for all the images of the ordered letters; in this way all classifiers receive the same input properties. Intelligent algorithms; in this group, algorithms (Makkar et al, 2017;Liu et al, 2020) are applied from which the training and tests will be carried out, in order to identify letters on the license plate.…”

Section: Methodsmentioning

confidence: 99%

Model for the identification of license plates in Mexico City using machine learning algorithms

Martínez-Prado

Pescador-Hernandez

Martínez

et al. 2021

RevTaya

View full text Add to dashboard Cite

Computer vision is one of the fields of Artificial Intelligence that is flourishing because it focuses on the development and improvement of techniques that allow computers to identify, process and classify images, in a way that resembles human vision. This feature makes them an excellent tool for vehicle control systems. For this reason, we developed a system for the recognition of Mexico City license plates using artificial vision techniques, image processing and automatic learning, in order to monitor and speed up response times, when a stolen vehicle is found.

show abstract

“…ey can also be quite powerful for classifying nonimage statistics, including audio, time collection, and sign information. In addition, packages that call for item recognition and pc vision-such as self-riding automobiles and face-recognition packages-depend heavily on CNN [26][27][28].…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

A Machine Learning and Deep Learning Approach for Recognizing Handwritten Digits

Sharma

Bhardwaj

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Optical character recognition (OCR) can be a subcategory of graphic design that involves extracting text from images or scanned documents. We have chosen to make unique handwritten digits available on the Modified National Institute of Standards and Technology website for this project. The Machine Learning and Depp Learning algorithms are used in this project to measure the accuracy of handwritten displays of letters and numbers. Also, we show the classification accuracy comparison between them. The results showed that the CNN classifier achieved the highest classification accuracy of 98.83%.

show abstract

Comparisions on KNN, SVM, BP and the CNN for Handwritten Digit Recognition

Cited by 34 publications

References 2 publications

Interleaved signal multiplexing readout in depth encoding Prism‐PET detectors

Interleaved signal multiplexing readout in depth encoding Prism‐PET detectors

Model for the identification of license plates in Mexico City using machine learning algorithms

A Machine Learning and Deep Learning Approach for Recognizing Handwritten Digits

Contact Info

Product

Resources

About