Real-time raindrop detection based on cellular neural networks for ADAS

Machot, Fadi Al; Ali, Mouhannad; Mosa, Ahmad Haj; Schwarzlmüller, Christopher; Gutmann, Markus; Kyamakya, Kyandoghere

doi:10.1007/s11554-016-0569-z

Cited by 26 publications

(16 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the history of inputs might affect the outputs. Thus, the used model should have a memory that considers the history of its inputs; this is considered by our CNN model; ( b ) because of the high parallelism of the CNN processor, this makes our CNN model a real-time model than can be implemented on embedded platforms easily [ 54 ]; and ( c ) using the paradigm of CNN for classification purposes showed promising results in the state-of-the-art [ 55 , 56 ].…”

Section: Discussionmentioning

confidence: 99%

A Globally Generalized Emotion Recognition System Involving Different Physiological Signals

Ali¹,

Machot

Mosa³

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

Machine learning approaches for human emotion recognition have recently demonstrated high performance. However, only/mostly for subject-dependent approaches, in a variety of applications like advanced driver assisted systems, smart homes and medical environments. Therefore, now the focus is shifted more towards subject-independent approaches, which are more universal and where the emotion recognition system is trained using a specific group of subjects and then tested on totally new persons and thereby possibly while using other sensors of same physiological signals in order to recognize their emotions. In this paper, we explore a novel robust subject-independent human emotion recognition system, which consists of two major models. The first one is an automatic feature calibration model and the second one is a classification model based on Cellular Neural Networks (CNN). The proposed system produces state-of-the-art results with an accuracy rate between 80% and 89% when using the same elicitation materials and physiological sensors brands for both training and testing and an accuracy rate of 71.05% when the elicitation materials and physiological sensors brands used in training are different from those used in training. Here, the following physiological signals are involved: ECG (Electrocardiogram), EDA (Electrodermal activity) and ST (Skin-Temperature).

show abstract

Section: Discussionmentioning

confidence: 99%

A Globally Generalized Emotion Recognition System Involving Different Physiological Signals

Ali¹,

Machot

Mosa³

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is also shown that combining those traditional methods with dynamical neural networks like cellular neural networks can result in a significant performance improvement. For example, Al Machot et al [ 11 ] showed that combining SVM with cellular neural networks considerably improves the SVM performance; this new resulting hybrid model can thus be used as a very fast and robust detector/classifier instead of using the sole SVM model.…”

Section: Introductionmentioning

confidence: 99%

A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction

Tavakkoli

Mohsenzadegan

Kyamakya

2020

Sensors

Self Cite

View full text Add to dashboard Cite

The core objective of this paper is to develop and validate a comprehensive visual sensing concept for robustly classifying house types. Previous studies regarding this type of classification show that this type of classification is not simple (i.e., tough) and most classifier models from the related literature have shown a relatively low performance. For finding a suitable model, several similar classification models based on convolutional neural network have been explored. We have found out that adding/involving/extracting better and more complex features result in a significant accuracy related performance improvement. Therefore, a new model taking this finding into consideration has been developed, tested and validated. The model developed is benchmarked with selected state-of-art classification models of relevance for the “house classification” endeavor. The test results obtained in this comprehensive benchmarking clearly demonstrate and validate the effectiveness and the superiority of our here developed deep-learning model. Overall, one notices that our model reaches classification performance figures (accuracy, precision, etc.) which are at least 8% higher (which is extremely significant in the ranges above 90%) than those reached by the previous state-of-the-art methods involved in the conducted comprehensive benchmarking.

show abstract

“…CNN is chosen for the method of detection in medical image processing due to its efficiency in pattern recognition and image processing [16]- [20]. CNN algorithm is also applied in memristor [21]- [23], srobotics [24], ditributed network [25] and raindrop detection [26]. Hence, in this study, a new detection method by using CNN algorithm will be used to detect the cancerous cervical cells in a shorter time.…”

Section: Introductionmentioning

confidence: 99%

Cervical cancer detection method using an improved cellular neural network (CNN) algorithm

Abdullah

Giong

Zahri

2019

IJEECS

View full text Add to dashboard Cite

<span>Cervical cancer is the second most common in Malaysia and the fourth frequent cancer among women in worldwide. Pap smear test is often ignored although it is actually useful, beneficial and essential as screening tool for cervical cancer. However, Pap smear images have low sensitivity as well as specificity. Therefore, it is difficult to determine whether the abnormal cells are cancerous or not. Recently, computer-based algorithms are widely used in cervical cancer screening. In this study, an improved cellular neural network (CNN) algorithm is proposed as the solution to detect the cancerous cells in real-time by undergoing the image processing of Pap smear images. A few templates are combined and modified to form an ideal CNN algorithm to detect the cancerous cells in total of 115 Pap smear images. A MATLAB based CNN is developed for an automated detection of cervix cancerous cells where the templates segmented the nucleus of the cells. From the simulation results, our proposed CNN algorithm can detect the cervix cancer cells automatically with more than 88% accuracy.</span>

show abstract

Real-time raindrop detection based on cellular neural networks for ADAS

Cited by 26 publications

References 33 publications

A Globally Generalized Emotion Recognition System Involving Different Physiological Signals

A Globally Generalized Emotion Recognition System Involving Different Physiological Signals

A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction

Cervical cancer detection method using an improved cellular neural network (CNN) algorithm

Contact Info

Product

Resources

About