Music Emotion Classification

In this paper the question of whether the Phrygian mode is always associated with perceived emotional responses of negative valence is looked into. To this end, we carried out a series of experiments. Music from two musical traditions where the Phrygian mode is very common, flamenco and Galician music, were chosen for listening tests. Our subjects were 124 children of age 4-7. Some subjects were complete unfamiliar with both traditions and some were familiar with the Galician tradition; none was familiar with flamenco music. Results showed that the perceived emotion was in all cases of positive valence, flamenco music having less valence than Galician music.

The perceptual attributes of timbre have inspired a considerable amount of multidisciplinary research, but because of the complexity of the phenomena, the approach has traditionally been confined to laboratory conditions, much to the detriment of its ecological validity. In this study, we present a purely bottom-up approach for mapping the concepts that emerge from sound qualities. A social media () is used to obtain a wide sample of verbal descriptions of music (in the form of tags) that go beyond the commonly studied concept of genre, and from this the underlying semantic structure of this sample is extracted. The structure that is thereby obtained is then evaluated through a careful investigation of the acoustic features that characterize it. The results outline the degree to which such structures in music (connected to affects, instrumentation and performance characteristics) have particular timbral characteristics. Samples representing these semantic structures were then submitted to a similarity rating experiment to validate the findings. The outcome of this experiment strengthened the discovered links between the semantic structures and their perceived timbral qualities. The findings of both the computational and behavioural parts of the experiment imply that it is therefore possible to derive useful and meaningful structures from free verbal descriptions of music, that transcend musical genres, and that such descriptions can be linked to a set of acoustic features. This approach not only provides insights into the definition of timbre from an ecological perspective, but could also be implemented to develop applications in music information research that organize music collections according to both semantic and sound qualities.

BACKGROUND The automatic prediction of emotional content in music is nowadays a growing area of interest. Several algorithms have been developed to retrieve music features and computational models using these features are continuously being created in order to predict music emotional content.

Detecting emotion features in a song remains as a challenge in various area of research especially in Music Emotion Classification (MEC). In order to classify selected song with certain mood or emotion, the algorithms of the machine learning must be intelligent enough to learn the data features as to match the features accordingly to the accurate emotion. Until now, there were only few studies on MEC that exploit audio timbre features from vocal part of the song incorporated with the instrumental part of a song. Timbre features is the quality of a musical features or sound that distinguishes different types of sound production in human voices and musical instruments such as string instruments, wind instruments and percussion instruments. Most of existing works in MEC are done by looking at audio, lyrics, social tags or combination of two or more classes. The question is does exploitation of both timbre features from both vocal and instrumental sound features helped in producing positive result in MEC? Thus, this research present works on detecting emotion features in Malay popular music using artificial neural network by extracting audio timbre features from both vocal and instrumental sound clips. The findings of this research will collectively improve MEC based on the manipulation of vocal and instrumental sound timbre features, as well as contributing towards the literature of music information retrieval, affective computing and psychology.

Facial expressions are becoming more and more important in today's computer systems with humanoid user interfaces. Avatars have become popular, however their facial communication is usually limited. This is partly due to the fact that many questions, especially on the dynamics of expressions, are still open. Moreover, the few commercial facial animation tools have limited facilities, and are not aimed at lightweight Web applications. In this article we discuss the empirical basis and a software tool to produce faces with emotional expressions and lip-sync. In order to elicit the characteristics of expressions on real human faces and to map them on synthetic, non-realistic ones, we analysed expressions on real and artist-drawn cartoon faces. We developed CharToon, a software tool that allows the construction of faces and to animate them from scratch or by re-using components of the facial feature and expression repertoire. CharToon faces can be animated real time. The list of applications includes 3D faces of avatars in a VRML environment.

In this paper the question of whether the Phrygian mode is always associated with perceived emotional responses of negative valence is looked into. To this end, we carried out a series of experiments. Music from two musical traditions where the Phrygian mode is very common, flamenco and Galician music, were chosen for listening tests. Our subjects were 124 children of age 4-7. Some subjects were complete unfamiliar with both traditions and some were familiar with the Galician tradition; none was familiar with flamenco music. Results showed that the perceived emotion was in all cases of positive valence, flamenco music having less valence than Galician music.

This paper proposes a dynamic Bayesian network (DBN) based MPEG-4 compliant 3D facial animation synthesis method driven by the (Evaluation, Activation) values in the continuous emotion space. For each emotion, a state synchronous DBN model (SS_DBN) is firstly trained using the Cohn-Kanade (CK) database with two streams of inputs: (i) the annotated (Evaluation, Activation) values, and (ii) the extracted Facial Action Parameters (FAPs) of the face image sequences. Then given an input (Evaluation, Activation) sequence, the optimal FAP sequence is estimated via the maximum likelihood estimation (MLE) criterion, and then used to construct the MPEG-4 compliant 3D facial animation. Compared with the state-of-the-art approaches where the mapping between the emotional space and the FAPs has been made empirically, in our approach the mapping is learned and optimized using DBN to fit the input (Evaluation, Activation) sequence. Emotion recognition results on the constructed facial animations, as well as subjective evaluations, show that the proposed method obtains natural facial animations representing well the dynamic process of the emotions from neutral to exaggerate. I.

BACKGROUND The automatic prediction of emotional content in music is nowadays a growing area of interest. Several algorithms have been developed to retrieve music features and computational models using these features are continuously being created in order to predict music emotional content.

The matters regarding speech signal processing and analyzing in terms of emotional states recognition were presented in this paper. An experiment was conducted to perform both objective and subjective emotional states recognition tests for Polish language.

Facial skin is skin that protects the inside of the face such as the eyes, nose, mouth, and others. Facial skin consists of several types, including normal skin, oily skin, dry skin, and combination skin. This is a problem for women because it is difficult to recognize and distinguish their skin types this is what causes some women to find it difficult to determine the right make-up and care products for their skin types. In this study, the Convolutional Neural Network (CNN) method is the right method for classifying women's skin types from the age of 20-30 years by following several stages using Python 3.5 programming with a depth of three layers and the results of this research using the CNN method get the results of the accuracy value good at 67%

Bu çalışmada, klasik makine öğrenme yöntemleri farklı kültürlere ait farklı türdeki müziklerden oluşmuş veri tabanları üzerinde duygu tanıması yapmak için kullanılmışlardır. Bu veri tabanlarında bulunan müziklerden öznitelik çıkarmak için çalışmalarda yaygın olarak kullanılan araçlar tercih edilmiştir. Çıkarılan bütün özniteliklere korelasyon tabanlı öznitelik seçme yöntemi uygulanmıştır. Makine öğrenmesi yöntemleri olarak Bayes Ağları, Sıralı Minimal Optimizasyon, Lojistik Regresyon ve Karar Ağaçları kullanılmıştır. Öznitelik seçim işlemi sonrasında kalan özniteliklere Bayes Ağları yöntemi uygulandığında, Türkçe Duygusal Müzik Veri Tabanı için %94,35, Bi-Modal Veri Tabanı için %79,62 ve Soundtrack Veri Tabanı için ise %75,45 tanıma oranı elde edilmiş ve karşılaştırılan sınıflandırıcılardan daha iyi sonuç alınmıştır. Daha sonra, araçlardan çıkarılan öznitelikler bir araya getirilmiş ve yine seçim işlemi yapılmıştır. Bu işlemden sonra ise, sırasıyla bu veritabanları için %95,96, %80,...

The ubiquity of digital music consumption has made it possible to extract information about modern music that allows us to perform large scale analysis of stylistic change over time. In order to uncover underlying patterns in cultural evolution, we examine the relationship between the established characteristics of different genres and styles, and the introduction of novel ideas that fuel this ongoing creative evolution. To understand how this dynamic plays out and shapes the cultural ecosystem, we compare musical artifacts to their contemporaries to identify novel artifacts, study the relationship between novelty and commercial success, and connect this to the changes in musical content that we can observe over time. Using Music Information Retrieval (MIR) data and lyrics from Billboard Hot 100 songs between 1974-2013, we calculate a novelty score for each song's aural attributes and lyrics. Comparing both scores to the popularity of the song following its release, we uncover key patterns in the relationship between novelty and audience reception. Additionally, we look at the link between novelty and the likelihood that a song was influential given where its MIR and lyrical features fit within the larger trends we observed.

A modern development in technology is Speech Emotion Recognition (SER). SER in partnership with Humane-Machine interaction (HMI) has advanced machine intelligence. An emotion precise HMI is designed by integrating speech processing and machine learning algorithm which is sculpted to formulate an automated smart and secure application for detecting emotions in a household as well as in commercial application. This project presents a study of distinguishing emotions by acoustic speech recognition (ASR) using K-means nearest neighbor (K-NN), a machine learning (ML) technique. The most significant paralinguistic information obtained from spectral features is presented by ASR i.e. by using Mel frequency cepstrum coefficient (MFCC). The most important processing techniques methods include feature extraction, feature selection, and classification of emotions. A customized dataset consisting of speech corpus, simulated emotion samples in the Sanskrit language is used to classify emotions in different emotional classes i.e. happy, sad, excitement, fear, anger and disgust. The emotions are classified using a K-NN algorithm over 2 separate models, based on the soft and high pitch voice. Model 1 and 2 achieved about 72.95% and 76.96% recognition

Music appears to deeply affect emotional, cerebral and physiological states, and its effect on stress and anxiety has been established using a variety of self-report, physiological, and observational means. Yet, the relationship between specific musical parameters and emotional responses is still not clear. One issue is that precise, replicable and independent control of musical parameters is often difficult to obtain from human performers. However, it is now possible to generate expressive musical material such as pitch, velocity, articulation, tempo, scale, mode, harmony and timbre using synthetic music systems. In this study, we use a synthetic music system called the SMuSe, to generate a set of wellcontrolled musical stimuli, and analyze the influence of musical structure, performance variations and timbre on emotional responses.The subjective emotional responses we obtained from a group of 13 participants on the scale of valence, arousal and dominance were similar to previous studies that used human-produced musical excerpts. This validates the use of a synthetic music system to evoke and study emotional responses in a controlled manner.

Günümüzde bilgisayar kullanımı yaygınlaştıkça insan-bilgisayar etkileşimi üzerine yenilikçi çalışmalar hız kazanmıştır. Bu yeniliklerden biri, insanların duygusal durumlarının bilgisayarlı sistemler tarafından belirlenmesidir. Bu çalışmada, literatürden farklı öğrenme algoritmaları dışında bir yöntem geliştirilmesi amaçlanmıştır. Bu çalışmada sırasıyla; insan yüzü tespiti, yüz işaretçilerinin tespiti, niteliklerin yaratılmasına dayalı yüz işaretçileri, çeşitli hesaplamalar üzerine nitelikler yapılmıştır. Bu çalışma Raspberry Pi 3 donanımı ve Python yazılım dili kullanılarak geliştirilmiştir. Önerilen yöntem, 27 farklı birey (15 kadın, 12 erkek) içeren orijinal veri setinde test edilmiş ve sistemin performansı % 96.3 olarak belirlenmiştir.

This paper presents the principal phase of extraction and recognition of the basic emotions in the Arabic speech applied to five emotional states were taken into effect; neutral, sadness, fear, anger and happiness. Emotional speech database REGIM_TES was created and evaluated to provide all practical experiences of extraction. The database described in section 3 has been recorded and processed in this vein. The selected descriptors in our study are; Pitch of voice, Energy, MFCCs, Formant, LPC and the spectrogram. Descriptors showed the importance of the Arabic language on the physiological events and the influence of culture on emotional behavior. Results performed in this work showed that pooling together features extracted at different sites indeed improved classification performance. A comparative study between the kernel functions has enabled us to promote the RBF kernel SVMs multiclass classifier performing the classification phase.

Depression is the most prevalent mood disorder and a leading cause of disability worldwide. Automated video-based analyses may afford objective measures to support clinical judgments. In the present paper, categorical depression assessment is addressed by proposing a novel variant of the Motion History Image (MHI) which considers Gabor-inhibited filtered data instead of the original image. Classification results obtained with this method on the AVEC'14 dataset are compared to those derived using (a) an earlier MHI variant, the Landmark Motion History Image (LMHI), and (b) the original MHI. The different motion representations were tested in several combinations of appearance-based descriptors, as well as with the use of convolutional neural networks. The F1 score of 87.4% achieved in the proposed work outperformed previously reported approaches.

Real time user independent facial expression recognition is important for virtual agents but challenging. However, since in real time recognition users are not necessarily presenting all the emotions, some proposed methods are not applicable. In this paper, we present a new approach that instead of using the traditional base face normalization on whole face shapes, performs normalization on the point cloud of each landmark. The result shows that our method outperforms the other two when the user input does not contain all six universal emotions.

Hampir setiap orang akan memperhatikan impresi busana yang dipakai, termasuk busana dengan motif batik. Namun, perpaduan berbagai motif dan warna batik memberikan impresi yang beragam. Sehingga, penentuan impresi dari satu kain batik menjadi sulit. Untuk membantu seseorang dalam menentukan impresi dari busana batik yang dipilih, dibutuhkan sistem yang mampu mengklasifikasikan impresi citra kain batik secara otomatis. Akan tetapi, pembuatan sistem klasifikasi label jamak merupakan memiliki tantangan tersendiri. Penelitian sebelumnya membuktikan bahwa metode klasifikasi ansambel label jamak dengan pencarian threshold mampu menjawab tantangan tersebut dengan kehandalannya dalam menangani himpunan data label jamak. Studi ini bertujuan untuk mengembangkan sistem yang menerapkan metode klasifikasi ansambel label jamak untuk menentukan impresi citra kain batik. Sistem ini memanfaatkan fitur tekstur dan warna yang dihasilkan dari Histogram Perbedaan Warna. Hasil uji coba metode ini memberikan performa yang baik dalam evaluasi label jamak. Nilai evaluasi tersebut antara lain Hamming Loss sebesar 0,173 dan Average Precision 0,866.

In recent decades computer technology has considerable developed in use of intelligent systems for classification. The development of HCI systems is highly depended on accurate understanding of emotions. However, facial expressions are difficult to classify by a mathematical models because of natural quality. In this paper, quantitative analysis is used in order to find the most effective features movements between the selected facial feature points. Therefore, the features are extracted not only based on the psychological studies, but also based on the quantitative methods to arise the accuracy of recognitions. Also in this model, fuzzy logic and genetic algorithm are used to classify facial expressions. Genetic algorithm is an exclusive attribute of proposed model which is used for tuning membership functions and increasing the accuracy.

Beyin fonksiyonları ile ilgili olarak EEG işaretleri birçok bilgi içermektedir. EEG işaretlerinin dalga biçimleri diğer beyin işaretleri ile benzerlik göstermektedir. Bu çalışmada sunulan yöntemde, önce EEG işaretlerine öz bağlanımlı (Auto-Regressive) yöntem uygulanarak güç spektrumu elde edilmiştir. AR-Burg analizinden elde edilen veriler Destek Vektör Makineleri(DVM) yöntemi ile sınıflandırılmıştır. DVM'de kullanılan bazı çekirdek fonksiyonları için sınıflandırma başarıları araştırılmıştır. Sınıflandırma başarısını artıran ayarlama ve çekirdek parametreleri günümüzde önemi artarak devam eden Parçacık Sürü Optimizasyonu(PSO) algoritması ile hesaplanmıştır. Böylece sınıflandırmayı etkileyen parametrelerin seçiminde en uygun değerler araştırılarak en yüksek sonuç elde edilmeye çalışılmıştır. Bu çalıma neticesinde epilepsi hastalığı teşhisi için yeni bir algoritmik yaklaşım sergilenmiştir.

• MUAP (Motor Unit Action Potential) clustering with hybrid structure • Use of multiple attribute vectors • Classification of neuromuscular diseases by artificial intelligence methods In this study, a classification structure consisting of five processing stages was organized for the diagnosis of ALS and Myopathic diseases, the most common types of neuromuscular diseases (Figure A). Figure A. Structure used to classify EMG data Purpose: To design a system that classifies EMG signals with or without neuromuscular disorder and to establish the infrastructure and preliminary preparation of a real-time software that can be integrated into the prototype EMG device which is designed in in BAL-LAB

Music has grown into an important part of people's daily lives. As we move further into the digital age in which a large collection of music is being created daily and becomes easily accessible renders people to spend more time on activities that involve music. Consequently, the form of music retrieval is changed from catalogue based searches to searches made based on emotion tags in order for easy and effective musical information access. In this study, it is aimed to generate a model for automatic recognition of the perceived emotion of songs with the help of their lyrics and machine learning algorithms. For this purpose, first 300 songs are selected and annotated by human taggers with respect to their perceived emotions. Thereafter, Unigram, Bigram and Trigram word features are extracted from song lyrics after performing text preprocessing where stemming of the Turkish words is an essential part. Then, term by document matrices are created where term frequencies and tf-idf scores are considered as representations for the indices. Five different classification algorithms are fed with these matrices in order to find the best combination that achieves the highest accuracy results where recall and precision values are used as comparison metrics. As a result, best accuracy results are obtained by using Multinomial Naïve Bayes classifier where Unigram features are used to create the term by document matrix. In this setting, Unigram features are stemmed by Zemberek Long stemming method, and the index representation is chosen as term frequency. For this combination, obtained recall and precision values are 43.7 and 46.9, respectively. Müzik insanlık tarihinde önemli bir yere sahiptir. Özellikle dijital çağda kişiler tarafından her gün yaratılan ve ulaşılan müzik koleksiyonlarının büyüklüğü ile müziğin önemi daha da artmış ve insanlar müzik içeren aktivitelere daha fazla zaman ayırmaya başlamışlardır. Bununla birlikte, müziğe bilgi geri getirim sürecini kolay ve etkin hale getirmek için yapılan katalog bazlı aramalar duygu tabanlı etiketlere göre aramalara dönüşmüştür. Bu araştırmada amacımız şarkı sözlerine göre bir şarkıdan algılanan duygunun otomatik olarak çıkarıldığı bir model geliştirmektir. Model metin bazlı sınıflandırma için kullanılan makina öğrenmesi algoritmaları ile oluşturulmuştur. Bu amaçla araştırmada 300 şarkı seçilmiş ve bu şarkılar kişiler tarafından hissedilen duygularına göre etiketlenmiştir. Devamında metin ön analizi ile şarkı sözleri Türkçe köklerine ayrıştırılarak Unigram, Bigram ve Trigram kelime özellikleri çıkartılmıştır. Ardından endeksleri terim sıklığı ve tf-idf değerleri olan doküman bazında terim matrisleri yaratılmıştır. Bu matris değerleri 5 farklı sınıflandırma algoritmasına girdi olarak verilerek en yüksek doğruluk sonuçları, hatırlama ve kesinlik metrikleri üzerinden araştırılmıştır. Araştırmanın sonucunda en yüksek kesinlik değeri Zemberek Uzun Kök Ayıştırma Metodu ile Unigram kelime özelliklerine göre ayrıştırılmış ve endeksi terim sıklığına göre belirlenmiş terim bazlı doküman matrisinin Katlıterim Naïve Bayes kümeleyicisinde verdiği görülmüştür. Bu kombinasyonda hatırlama metriği değeri 43.7 iken kesinlik metriği değeri 46.9'dur.

Music has grown into an important part of people's daily lives. As we move further into the digital age in which a large collection of music is being created daily and becomes easily accessible renders people to spend more time on activities that involve music. Consequently, the form of music retrieval is changed from catalogue based searches to searches made based on emotion tags in order for easy and effective musical information access. In this study, it is aimed to generate a model for automatic recognition of the perceived emotion of songs with the help of their lyrics and machine learning algorithms. For this purpose, first 300 songs are selected and annotated by human taggers with respect to their perceived emotions. Thereafter, Unigram, Bigram and Trigram word features are extracted from song lyrics after performing text preprocessing where stemming of the Turkish words is an essential part. Then, term by document matrices are created where term frequencies and tf-idf scores are considered as representations for the indices. Five different classification algorithms are fed with these matrices in order to find the best combination that achieves the highest accuracy results where recall and precision values are used as comparison metrics. As a result, best accuracy results are obtained by using Multinomial Naïve Bayes classifier where Unigram features are used to create the term by document matrix. In this setting, Unigram features are stemmed by Zemberek Long stemming method, and the index representation is chosen as term frequency. For this combination, obtained recall and precision values are 43.7 and 46.9, respectively. Müzik insanlık tarihinde önemli bir yere sahiptir. Özellikle dijital çağda kişiler tarafından her gün yaratılan ve ulaşılan müzik koleksiyonlarının büyüklüğü ile müziğin önemi daha da artmış ve insanlar müzik içeren aktivitelere daha fazla zaman ayırmaya başlamışlardır. Bununla birlikte, müziğe bilgi geri getirim sürecini kolay ve etkin hale getirmek için yapılan katalog bazlı aramalar duygu tabanlı etiketlere göre aramalara dönüşmüştür. Bu araştırmada amacımız şarkı sözlerine göre bir şarkıdan algılanan duygunun otomatik olarak çıkarıldığı bir model geliştirmektir. Model metin bazlı sınıflandırma için kullanılan makina öğrenmesi algoritmaları ile oluşturulmuştur. Bu amaçla araştırmada 300 şarkı seçilmiş ve bu şarkılar kişiler tarafından hissedilen duygularına göre etiketlenmiştir. Devamında metin ön analizi ile şarkı sözleri Türkçe köklerine ayrıştırılarak Unigram, Bigram ve Trigram kelime özellikleri çıkartılmıştır. Ardından endeksleri terim sıklığı ve tf-idf değerleri olan doküman bazında terim matrisleri yaratılmıştır. Bu matris değerleri 5 farklı sınıflandırma algoritmasına girdi olarak verilerek en yüksek doğruluk sonuçları, hatırlama ve kesinlik metrikleri üzerinden araştırılmıştır. Araştırmanın sonucunda en yüksek kesinlik değeri Zemberek Uzun Kök Ayıştırma Metodu ile Unigram kelime özelliklerine göre ayrıştırılmış ve endeksi terim sıklığına göre belirlenmiş terim bazlı doküman matrisinin Katlıterim Naïve Bayes kümeleyicisinde verdiği görülmüştür. Bu kombinasyonda hatırlama metriği değeri 43.7 iken kesinlik metriği değeri 46.9'dur.

It is widely acknowledged that music can communicate and induce a wide range of emotions in the listener. However, music is a highly-complex audio signal composed of a wide range of complex time- and frequency-varying components. Additionally, music-induced emotions are known to differ greatly between listeners. Therefore, it is not immediately clear what emotions will be induced in a given individual by a piece of music. We attempt to predict the music-induced emotional response in a listener by measuring the activity in the listeners electroencephalogram (EEG). We combine these measures with acoustic descriptors of the music, an approach that allows us to consider music as a complex set of time-varying acoustic features, independently of any specific music theory. Regression models are found which allow us to predict the music-induced emotions of our participants with a correlation between the actual and predicted responses of up to r=0.234,p<0.001. This regression fit suggests...

Despite theoretical claims that emotions are primarily communicated through prototypic facial expressions, empirical evidence is surprisingly scarce. This study aimed to: (1) test whether children produced more components of a prototypic emotional facial expression during situations judged or self-reported to involve the corresponding emotion than situations involving other emotions (termed "intersituational specificity"), (2) test whether children produced more components of the prototypic expression corresponding to a situation's judged or self-reported emotion than components of other emotional expressions (termed "intrasituational specificity"), and (3) examine coherence between children's self-reported emotional experience and observers' judgments of children's emotions. One hundred and twenty children (ages 7-9) were videorecorded during a discussion with their mothers. Emotion ratings were obtained for children in 441 episodes. Children's nonverbal behaviors were judged by observers and coded by FACS-trained researchers. Children's self-reported emotion corresponded significantly to observers' judgments of joy, anger, fear, and sadness but not surprise. Multilevel modeling results revealed that children produced joy facial expressions more in joy episodes than non-joy episodes (supporting intersituational specificity for joy) and more joy and surprise expressions than other emotional expressions in joy and surprise episodes (supporting intrasituational specificity for joy and surprise). However, children produced anger, fear, and sadness expressions more in noncorresponding episodes and produced these expressions less than other expressions in corresponding episodes. Findings suggest that communication of negative emotion during social interactions-as indexed by agreement between self-report and observer judgments-may rely less on prototypic facial expressions than is often theoretically assumed.

Öz Son yıllarda doğadan esinlenen sürü tabanlı algoritmalar arasında yer alan Salp Sürü Algoritması oldukça popüler olmuştur. Bu çalışmada, Salp Sürü Algoritması kullanılarak farklı veri setleri üzerinde öznitelik seçimi yapılmış, farklı sınıflandırıcılar ile bazı performans metrikleri karşılaştırılmıştır. Deneysel sonuçların hesaplanması için UCI Makine Öğrenmesi Deposunda yer alan BreastCancer, Colon ve Ionosphere veri setleri kullanılmıştır. Sınıflandırıcı olarak k En Yakın Komşu Algoritması, Destek Vektör Makineleri ve Rastgele Orman Algoritması kullanılmıştır. Sayısal sonuçlar incelendiğinde, çalışma zamanı bakımından kNN algoritması ile yapılan testler genellikle en hızlı algoritma olmuştur. Seçilen öznitelik sayısı bakımından ise SVM ve RF algoritmaları daha iyi sonuç vermiştir.

Provision of a new dataset to this field to work on it.  Showing the effects of noise normalization and preprocessing on the classification accuracy.  Representation of texts in vector form in various ways to be able to work on them.  Comparison of the LSTM Network with several machine learning algorithms.

Öz: Endüstriyel ve akademik çalışmalarda objelerin ağırlıklarının ölçülmesi oldukça önemli bir yere sahiptir. Bu nedenle gerçekleştirilmiş olan bu çalışmada yapay sinir ağları (YSA) kullanılarak görüntü işlemeye dayalı uzaklıktan ve kamera açısından bağımsız ağırlık tahmini yapılması amaçlanmıştır. Yapay sinir ağı yapısı olarak ileri beslemeli çok katmanlı algılayıcı (multi-layer perceptron-MLP) ve radyal tabanlı fonksiyon (radial basis function-RBF) ağı kullanılmıştır. Ağırlığı tahmin edilecek obje olarak da portakal ve yumurta örnekleri belirlenmiştir. Bu örnekler ile sistemin eğitilmesi ve test edilmesi için; 4 farklı marka ve 4 farklı sınıf (çok büyükbüyük-orta-küçük) olacak şekilde 250 adet yumurta örneği ve farklı boyutlarda 150 adet portakal örneği seçilmiştir. Bu örnekler kullanılarak; yumurta için dik açı, pozitif açı ve negatif açı ile elde edilmiş 750 adet görüntü içeren, portakal için de dik açı, pozitif açı ve negatif açı ile elde edilmiş 450 adet görüntü içeren bir veri tabanı oluşturulmuştur. Oluşturulan bu ağırlık tahmin sistemi; bir adet kamera, yapay aydınlatma sistemi, yansıtıcılar ve referans görüntüden oluşmaktadır ve ayrıca ağırlık tahmin işlemi sırasında MATLAB programı ve araç kutuları kullanılmıştır. Bu çalışmada farklı öznitelik vektörleri, farklı açılardan çekilmiş görüntüler ve farklı YSA parametreleri test edilerek başarımı en yüksek olan sistemin kurulması hedeflenmiştir. Her bir değişiklik sonucu oluşturulan sistem beşer kez çalıştırılarak sonuçların aritmetik ortalaması alınmıştır. Ayrıca başarımı en yüksek olan denemenin, k-katlı çapraz doğrulama yöntemi ile de başarımı hesaplanmıştır. Hassas tartı ile yapılan ölçümlerde, Türk Gıda Kodeksi Yumurta Tebliği'ne göre belirlenmiş ve yumurta kutularının üzerinde yazan sınıflandırma değerlerine göre doğruluk oranı %47 iken, gerçekleştirilen bu çalışma sonucunda bu oran MLP'de %

Gender recognition from unconstrained face images is a challenging task due to the high degree of misalignment, pose, expression, and illumination variation. In previous works, the recognition of gender from unconstrained face images is approached by utilizing image alignment, exploiting multiple samples per individual to improve the learning ability of the classifier, or learning gender based on prior knowledge about pose and demographic distributions of the dataset. However, image alignment increases the complexity and time of computation, while the use of multiple samples or having prior knowledge about data distribution is unrealistic in practical applications. This paper presents an approach for gender recognition from unconstrained face images. Our technique exploits the robustness of local feature descriptor to photometric variations to extract the shape description of the 2D face image using a single sample image per individual. The results obtained from experiments on Labeled Faces in the Wild (LFW) dataset describe the effectiveness of the proposed method. The essence of this study is to investigate the most suitable functions and parameter settings for recognizing gender from unconstrained face images.

Music can be used to express a wide range of human emotions, from basic (e.g., pleasantness or unpleasantness dichotomies) to more complex emotions (e.g., transcendence or nostalgia). These emotions can be quantified by examining different elements of music such as rhythm, timbre, tonality etc. Past studies have identified that certain audio features are more prevalent than others in evoking certain emotions and previous research shows that time-series analysis and the temporal nature of music is essential in building robust music emotion recognition systems. In this study, we use the MediaEval Database for Emotional Analysis in Music (DEAM) to identify key low-level features that contribute towards music emotion characterization. The DEAM dataset contains 1802 music excerpts and Valence-Arousal annotations which we classify based on the Circumplex Model of Affect, where the cognitive representation of emotion is encapsulated using eight affect concepts. Audio feature extraction is performed on the DEAM dataset to carry out tests using machine learning to identify features that contribute towards classification of music emotion.

Our lives are being significantly impacted by the rapid development of wireless technology and mobile gadgets on this day. The digital economy demands that services be developed almost instantly while also paying close attention to client feedback. It becomes difficult to manage and analyse the information gathered about products from customers. Successful businesses typically gather reasonable input on customer behaviour, comprehend their clients, and maintain ongoing contact with them. But it's not an easy task to keep a record of each and every customer' feedback on a daily basis. Also, everyone is not intended to provide clear feedback whether the product was satisfactory or not. It is a very difficult and time-consuming task to analyse the data collected manually. Companies need automation of customer feedback processing in order to quickly use the data that has been collected and analyse consumer feedback. To proceed with the problem and through much research we came across a solution, Emotica.AI, an emotion recognition system which can overcome this situation in real time. Emotion recognition plays an important role in building interpersonal relationships. Speaking, making facial expressions, gesturing, or writing are all ways that people directly or indirectly convey their feelings. Now that AI has mastered the power of learning, it is capable of treating anything just like a human would. The proposed model is built with Haar-Cascade Algorithm and classified with CNN and is able to recognise the emotions of multiple faces in a real time scenario. Accuracy of this model is around 76% is achieved for seven emotions on a real-time basis. Our goal is to develop a real time implementation of an emotion detection system with better accuracy and make it more reliable for businesses and other purposes.

Author identification is one of the application areas of text mining. It deals with the automatic prediction of the potential author of an electronic text among predefined author candidates by using author specific writing styles. In this study, we conducted an experiment for the identification of the author of a Turkish language text by using classical machine learning methods including Support Vector Machines (SVM), Gaussian Naive Bayes (GaussianNB), Multi Layer Perceptron (MLP), Logistic Regression (LR), Stochastic Gradient Descent (SGD) and ensemble learning methods including Extremely Randomized Trees (ExtraTrees), and eXtreme Gradient Boosting (XGBoost). The proposed method was applied on three different sizes of author groups including 10, 15 and 20 authors obtained from a new dataset of newspaper articles. Term frequency-inverse document frequency (TF-IDF) vectors were created by using 1-gram and 2-gram word tokens. Our results show that the most successful method is the SGD with a classification performance accuracy of 0.976% by using word unigrams and most successful method is the LR with a classification performance accuracy of 0.935% by using word bigrams.

This paper presents a novel age function modelling technique on the basis of the fusion of local features obtained by local texture descriptors. Initially, image normalization is performed and a feature extraction process is carried out. The age estimation performances of new texture descriptors Local Phase Quantization, Weber Local Descriptor and the familiar texture descriptor Local Binary Patterns, which are not examined thoroughly for age estimation modelling, are analysed in this paper. Then the feature fusion process is taken place for investigating the age estimation precisions of various concatenation of the local texture descriptors. By using PCA, dimensionality reduction is implemented for reducing the dimensions of the images. Extreme Learning Machine (ELM) classifier is applied to evaluate the output images for the corresponding input images. Because of the mild optimization restrictions, ELM can be simple for execution and normally attains the finer generalization performance. The outcomes display that, when compared with the earlier techniques, the age function modelling accuracy of the developed system is better.

Conditions of extreme neurological disability prevent any form of communication, even to show the emotional state. Brain Computer Interfaces (BCI) often use Electro-encephalography (EEG) measurements of the voluntary brain activity for driving a communication system. A BCI usage requires the activation of mental tasks. In the last few years, a new paradigm of activation has been used consisting in the autonomous brain activation through self-induced emotions, remembered on autobiographical basis. In the present paper, we describe the state of the art of an affective BCI system, a-BCI, based on self-induced emotions. It can be used by people with Severe Neurological Disorders (SND) for: alternative communication, emotion transmission.

Stress and anxiety act as psycho-physical factors that increase the risk of developing several chronic diseases. Since they appear as early indicators, it is very important to be able to perform their evaluation in a contactless and non-intrusive manner in order to avoid inducing artificial stress or anxiety to the individual in question. For these reasons, this paper analyses the methodologies for the extraction of respective facial signs from images or videos, their classification and techniques for coding these signs into appropriate psycho-physical statuses. A review of existing datasets for the assessment of the various methodologies for facial expression analysis is reported. Finally, a short summary of the most interesting findings in the various stages of the procedure are indicated with the aim of achieving new contactless methods for the promotion of an individual's well-being.

This work shows the development of a lexicon for a poorly resourced language, namely Kokborok. Kokborok is a regional language of North East India and offers an entirely new base for research in music information retrieval (MIR) field. We first create a sentimental word dictionary known as lexicons to develop a polarity classification system. It is a text analysis work involving two types of lyrical features that are: 'text stylistic feature', and the features were taken out from the newly developed dictionary. We have also shown the comparative analysis with a various subset of music database based on their accuracy rate. After the system development, the experimental/simulations were done, and the results have been computationally analyzed. We performed linear extrapolation of the data taken by both the feature set, thus developing a dictionary. Text stylistic (TS) features have been observed to converge, at 52 and 39 percent respectively for the number of songs tending to infinity. It has been found that at present, it might be better to increase the features from the dictionary since it gives better accuracy for low resource language Kokborok.

Depression is the most prevalent mood disorder and a leading cause of disability worldwide. Automated video-based analyses may afford objective measures to support clinical judgments. In the present paper, categorical depression assessment is addressed by proposing a novel variant of the Motion History Image (MHI) which considers Gabor-inhibited filtered data instead of the original image. Classification results obtained with this method on the AVEC'14 dataset are compared to those derived using (a) an earlier MHI variant, the Landmark Motion History Image (LMHI), and (b) the original MHI. The different motion representations were tested in several combinations of appearance-based descriptors, as well as with the use of convolutional neural networks. The F1 score of 87.4% achieved in the proposed work outperformed previously reported approaches.

Emotion classification is essential for understanding human interactions and hence is a vital component of behavioral studies. Although numerous algorithms have been developed, the emotion classification accuracy is still short of what is desired for the algorithms to be used in real systems. In this paper, we evaluate an approach where basic acoustic features are extracted from speech samples, and the One-Against-All (OAA) Support Vector Machine (SVM) learning algorithm is used. We use a novel hybrid kernel, where we choose the optimal kernel functions for the individual OAA classifiers. Outputs from the OAA classifiers are normalized and combined using a thresholding fusion mechanism to finally classify the emotion. Samples with low 'relative confidence' are left as 'unclassified' to further improve the classification accuracy. Results show that the decision-level recall of our approach for six-class emotion classification is 80.5%, outperforming a state-of-the-art approach that uses the same dataset.

The paper presents a study on music mood categorisation. First, a review of music mood models is presented. Then, the preparation of a set of music excerpts to be used in the experiments and music parametrisation is described. Next, some listening tasks performed to obtain mood descriptors are introduced. Finally, the correlation between mood descriptors and features extracted from parameters is discussed. The paper concludes with some observations derived from the analysis performed.

This study reports experimental results on whether the acoustic realization of vocal emotions differs between Mandarin and English. Prosodic cues, spectral cues and articulatory cues generated by electroglottograph (EGG) of five emotions (anger, fear, happiness, sadness and neutral) were compared within and across Mandarin and English through a production experiment. Results of within-language comparison demonstrated that each vocal emotion had specific acoustic patterns in each language. Moreover, normalized data were used in the across-language comparison analysis. Results indicated that Mandarin and English showed different mechanisms of utilizing pitch for encoding emotions. The differences in pitch variation between neutral and other emotions were significantly larger in English than in Mandarin. However, the variations of speech rate and certain phonation cues (e.g., CPP (Cepstral Peak Prominence) and CQ (Contact quotient)) were significantly greater in Mandarin than in Englis...

Depression is the most prevalent mood disorder and a leading cause of disability worldwide. Automated video-based analyses may afford objective measures to support clinical judgments. In the present paper, categorical depression assessment is addressed by proposing a novel variant of the Motion History Image (MHI) which considers Gabor-inhibited filtered data instead of the original image. Classification results obtained with this method on the AVEC'14 dataset are compared to those derived using (a) an earlier MHI variant, the Landmark Motion History Image (LMHI), and (b) the original MHI. The different motion representations were tested in several combinations of appearance-based descriptors, as well as with the use of convolutional neural networks. The F1 score of 87.4% achieved in the proposed work outperformed previously reported approaches.

In addition to classic motor signs and symptoms, individuals with Parkinson’s disease (PD) are characterized by emotional deficits. Ongoing brain activity can be recorded as electroencephalograph (EEG) to discover the links between emotional states and brain activity. This study utilized machine-learning algorithms to categorize emotional states in PD patients compared with healthy controls (HC) using EEG. Twenty non-demented PD patients and 20 healthy age-, gender-, and education level-matched controls viewed happiness, sadness, fear, anger, surprise, and disgust emotional stimuli while fourteen-channel EEG was being recorded. Multi-modal stimulus (combination of audio and visual) was used to evoke the emotions. To classify the EEG-based emotional states and visualize the changes of emotional states over time, this paper compares four kinds of EEG features for emotional state classification and proposes an approach to track the trajectory of emotion changes with manifold learning. ...

Öz Son yıllarda doğadan esinlenen sürü tabanlı algoritmalar arasında yer alan Salp Sürü Algoritması oldukça popüler olmuştur. Bu çalışmada, Salp Sürü Algoritması kullanılarak farklı veri setleri üzerinde öznitelik seçimi yapılmış, farklı sınıflandırıcılar ile bazı performans metrikleri karşılaştırılmıştır. Deneysel sonuçların hesaplanması için UCI Makine Öğrenmesi Deposunda yer alan BreastCancer, Colon ve Ionosphere veri setleri kullanılmıştır. Sınıflandırıcı olarak k En Yakın Komşu Algoritması, Destek Vektör Makineleri ve Rastgele Orman Algoritması kullanılmıştır. Sayısal sonuçlar incelendiğinde, çalışma zamanı bakımından kNN algoritması ile yapılan testler genellikle en hızlı algoritma olmuştur. Seçilen öznitelik sayısı bakımından ise SVM ve RF algoritmaları daha iyi sonuç vermiştir.

Günümüzde bilgisayar kullanımı yaygınlaştıkça insan-bilgisayar etkileşimi üzerine yenilikçi çalışmalar hız kazanmıştır. Bu yeniliklerden biri, insanların duygusal durumlarının bilgisayarlı sistemler tarafından belirlenmesidir. Bu çalışmada, literatürden farklı öğrenme algoritmaları dışında bir yöntem geliştirilmesi amaçlanmıştır. Bu çalışmada sırasıyla; insan yüzü tespiti, yüz işaretçilerinin tespiti, niteliklerin yaratılmasına dayalı yüz işaretçileri, çeşitli hesaplamalar üzerine nitelikler yapılmıştır. Bu çalışma Raspberry Pi 3 donanımı ve Python yazılım dili kullanılarak geliştirilmiştir. Önerilen yöntem, 27 farklı birey (15 kadın, 12 erkek) içeren orijinal veri setinde test edilmiş ve sistemin performansı % 96.3 olarak belirlenmiştir.

Depression is the most prevalent mood disorder and a leading cause of disability worldwide. Automated video-based analyses may afford objective measures to support clinical judgments. In the present paper, categorical depression assessment is addressed by proposing a novel variant of the Motion History Image (MHI) which considers Gabor-inhibited filtered data instead of the original image. Classification results obtained with this method on the AVEC'14 dataset are compared to those derived using (a) an earlier MHI variant, the Landmark Motion History Image (LMHI), and (b) the original MHI. The different motion representations were tested in several combinations of appearance-based descriptors, as well as with the use of convolutional neural networks. The F1 score of 87.4% achieved in the proposed work outperformed previously reported approaches.

Facial skin is skin that protects the inside of the face such as the eyes, nose, mouth, and others. Facial skin consists of several types, including normal skin, oily skin, dry skin, and combination skin. This is a problem for women because it is difficult to recognize and distinguish their skin types this is what causes some women to find it difficult to determine the right make-up and care products for their skin types. In this study, the Convolutional Neural Network (CNN) method is the right method for classifying women's skin types from the age of 20-30 years by following several stages using Python 3.5 programming with a depth of three layers and the results of this research using the CNN method get the results of the accuracy value good at 67%

Abstract. Expressions of emotion abound in user-generated content, whether it be in blogs, reviews, or on social media. Much work has been devoted to detecting and classifying these emotions, but little of it has acknowledged the fact that emotionally charged text may express multiple emotions at the same time. We describe a new dataset of user-generated movie reviews annotated for emotional expressions, and experimentally validate two algorithms that can detect multiple emotions in each sentence of these reviews.