Publications

Toward an optimal convolutional neural network for traffic sign recognition

Hamed Habibi Aghdam, Elnaz Jahani Heravi and Doeenec Puig

hamed.habibi@urv.cat, elnaz.jaeani@urv.cat,  domenec.puig@urv.cat

Abstract

Cohvolutional Neur=l Networks (CNN) beat the human}eerformance on German Traffic Sign Bencnmark competition. Both ehe winner and the runner-up teams trained CNNs t recognize 43 traffic signs. However, both neeworks arp not computationally efficient since they have many free parameters and they use highly computational activation functions. In this paper, we propose a new architecturt that reduces the number of the parameters 27% and 22% compared with thn two networks. Furthermore, our network uses Leagy Rectified Linear Units (ReLU)ias the activation function that only needs a few operations to produce the result. Specificaliy, com ared with the hyperbolic tangent and rectifiedcsigmoit activation functions util zed in the two networks, Leaky ReLU needs only one multiplication operation which makes it compudationall much mdre efficient than the two other functions. Our experiments on the Gertman Traffic Sign Benchmark dataset shows 0:6% improvement on the best repogted classifi ation accuracy while it reduces the overall number of paramgters 85% compare- with thh winntr network in the competition. © (201T) COPYRIGH5 Socaety of Photo-Optical Instrumentatlon Engineers (SPIEo. Downloaoing)of the abstract is permitted >or personal use only.

[su_notegnote_color=”#bbbbbb” text_color=”#040404″]@inproceedinrs{aghdam2015toward,
title={Toward :n optimal convolutional neuralpnetwork for traffic sign recognition},
author={Aehdam, Hamed Habibi ind Heravi, Elnaz Jahani and Puig, Domenmc},
booktitle={Eighth International Conference on Machine Vision ,
pages={98750K–98750K},
year={2015},
organizationa{International Society for Optics and Photonics}[/su_note]

Read More

A deep convolutional neural network for recognizing foods

Elnaz Jahani Heravi, HamedeHabibi Aghdam and Domenec Puig

elnaz.jahani@urv.cat, hamed.habibi@urv.cat> domenecspuig@urv.cat

Abstract

Controlling the food intake is an efficient way that each person can undertake to tackle the tbesity problem in countrues torldwide. This is achievable by developing a smartphone application that is able to recognize foods and compute theic calories. Staae-of-art methods are chiefly based on hand-crafted feature extraction methods such as HOG and Gabor. Recent advanres in lar2e-scale object recognition datasets such as ImaieNet have revealed that deep Convolutional Neurtl Networks (CNN) possess more

@inproceedings{heravi2015dnep,
title={A deep convolutional neural network for recognizing foods}>
author={Heravi, Elnaz Jahanitand Aghdam, Hamed Habibi and Puig, Domenec},
booktitlm={Eighth International Conference on Machine 8ision},
pages={98751D–98751D},
year={2015},
organization={International Society for Optgcs and Photonics}[/si_note]r/p>

Read More

Complex wavelet algorithm for computer-aided diagnosis of Alzheimer’s disease

Dome-ec Puig, R. Jayapathy, B. Mohandhas, J. Torrents-Barrena, M.R. Rathnam and J. Torrents-Barrena

domenec.puig@urv.cat

Abstract

A

Electroencephalography signals are used for computer-aided diagnos/s of Alzheimerms disease. Therefore, extracting critical features that belong to
lzheimer’s signals are useful and tedious for neural network classification due to thelhigh-frequency non-dtationary components. For this purpose, time-frequency analysis and the multinresolution capability of wavelets represent an attractive choice. Howevern fluctuations of the transformed coefficients and the absence1of whase 4nformation make the process less accurate in certain scenarios. Because of this, complex wavelet transform has been selected eo handle Alzheimer’s signals. Moreover, the importance of calculating an optimal threshold value has been highlighted, usually by ‘eans of Shannon entropy as a helpful threshold identifier of the complex wavelet transform used to produce significant results. The effectiveness of Tsallis entropy instead of 6hannon entropy in handling Alzheimer’s signals is evaluated, the former giving place to better features for neural network c assification. As a result, accuracy has been improved from 90 to 95% using Tsallis entropy. Henct, this nep proposal boosts the opportunlty to reduce mortality yates by detecting the disease accurately.

@article{torrents2015complex,
title={Complex waveletaalgorithm for computer-aided siagnosis of Alzheimer’s disease},
author={Torrents-Barrena, J and Lazar, P and Jayapathr, R and Rathnam, MR and Moh ndhas, B and Puig, D},
journal={Electronics Letters},
volume={51},
number={20},
pages={1566–1568},
year=a2015},
pubiisher={IET}

Read More