Emotion recognition from syllabic units using k-nearest-neighbor classification and energy distribution

Agrima, Abdellah; Mounir, Ilham; Farchi, Abdelmajid; Elmaazouzi, Laila; Mounir, Badia

doi:10.11591/ijece.v11i6.pp5438-5449

Cited by 5 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In that 206 are normal images and 113 are breast cancer images [22]. The proposed approach is compared with other classifiers like Naive Bayes (NB) [23], k-nearest neighbor (KNN) [24], decision tree (DT) [23], support vector machine (SVM) [24] and random forest (RF) [25].…”

Section: Resultsmentioning

confidence: 99%

Automated breast cancer detection system from breast mammogram using deep neural network

Chittineni¹,

Edara²

2022

IJEECS

View full text Add to dashboard Cite

All over the world breast cancer is a major disease which mostly affects the women and it may also cause death if it is not diagnosed in its early stage. But nowadays, several screening methods like magnetic resonance imaging (MRI), ultrasound imaging, thermography and mammography are available to detect the breast cancer. In this article mammography images are used to detect the breast cancer. In mammography image the cancerous lumps/microcalcifications are seen to be tiny with low contrast therefore it is difficult for the doctors/radiologist to detect it. Hence, to help the doctors/radiologist a novel system based on deep neural network is introduced in this article that detects the cancerous lumps/microcalcifications automatically from the mammogram images. The system acquires the mammographic images from the mammographic image analysis society (MIAS) data set. After pre-processing these images by 2D median image filter, cancerous features are extracted from the images by the hybridization of convolutional neural network with rat swarm optimization algorithm. Finally, the breast cancer patients are classified by integrating random forest with arithmetic optimization algorithm. This system identifies the breast cancer patients accurately and its performance is relatively high compared to other approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Automated breast cancer detection system from breast mammogram using deep neural network

Chittineni¹,

Edara²

2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…A first work [46], published in 2021, highlighted this finding. Indeed, by working on plosive consonants extracted from the MADED natural database, and by proposing a set of features based essentially on the energy and its variations, quite satisfactory recognition rates were obtained using the K-nearest neighbors (K-NN) algorithm.…”

Section: Experimental Validationmentioning

confidence: 86%

Emotion recognition based on the energy distribution of plosive syllables

Agrima¹,

Mounir

Farchi³

et al. 2022

IJECE

Self Cite

View full text Add to dashboard Cite

We usually encounter two problems during speech emotion recognition (SER): expression and perception problems, which vary considerably between speakers, languages, and sentence pronunciation. In fact, finding an optimal system that characterizes the emotions overcoming all these differences is a promising prospect. In this perspective, we considered two emotional databases: Moroccan Arabic dialect emotional database (MADED), and Ryerson audio-visual database on emotional speech and song (RAVDESS) which present notable differences in terms of type (natural/acted), and language (Arabic/English). We proposed a detection process based on 27 acoustic features extracted from consonant-vowel (CV) syllabic units: \ba, \du, \ki, \ta common to both databases. We tested two classification strategies: multiclass (all emotions combined: joy, sadness, neutral, anger) and binary (neutral vs. others, positive emotions (joy) vs. negative emotions (sadness, anger), sadness vs. anger). These strategies were tested three times: i) on MADED, ii) on RAVDESS, iii) on MADED and RAVDESS. The proposed method gave better recognition accuracy in the case of binary classification. The rates reach an average of 78% for the multi-class classification, 100% for neutral vs. other cases, 100% for the negative emotions (i.e. anger vs. sadness), and 96% for the positive vs. negative emotions.

show abstract

“…But there is a profound question regarding the selection of features and methods in human emotion classification, as the performance of the model is highly based upon these parameters. Emotions can be recognized through speech [1], [2], facial expressions [3] [6], textual data [7], [8], body gestures, audio-visual features [9], human interaction with devices and physiological signals such as electroencephalogram (EEG), electrocardiogram [10], electromyogram, electrodermal activity, skin temperature, and respiration. Over the years, EEG has gained a lot of attraction as a powerful technique for exploring the study of emotions due to its inexpensiveness and portable nature.…”

Section: Introductionmentioning

confidence: 99%

Electroencephalogram based human emotion classification for valence and arousal using machine learning approach

Chunawale,

Bedekar

2024

IJEECS

View full text Add to dashboard Cite

Humans have unique ability to express emotions and electroencephalogram (EEG) signals are one of the sought-after ways to analyze a person’s emotional state. However, extracting proper emotion related features from EEG and finding corresponding emotion is challenging because of complex nature of emotions and underlying brain activities. The objective of this paper is to address this issue for more accurate emotion classification based on EEG. It also compares feature extraction methods namely fast fourier transform (FFT) and discrete wavelet transform (DWT). DEAP dataset is used for classification of human emotions through support vector machine (SVM) and K-nearest neighbor (KNN) algorithms by considering features such as standard deviation, mean, variance, power spectrum density (PSD) for FFT; and energy, entropy for DWT. It is observed that feature extraction from FFT yielded better results than DWT and KNN gave more accuracy of 96.61% for valence and 96.42% for arousal as compared to SVM. The proposed method based on PSD and FFT fared better than other existing ones in terms of accuracy when compared against different features and feature extraction techniques. This approach is expected to help researchers to understand feature extraction from EEG signals and decide proper features and techniques for better implementation.

show abstract

Emotion recognition from syllabic units using k-nearest-neighbor classification and energy distribution

Cited by 5 publications

References 42 publications

Automated breast cancer detection system from breast mammogram using deep neural network

Automated breast cancer detection system from breast mammogram using deep neural network

Emotion recognition based on the energy distribution of plosive syllables

Electroencephalogram based human emotion classification for valence and arousal using machine learning approach

Contact Info

Product

Resources

About