Brain emotional learning based intelligent controller Research Papers

Melomaniac : Emotion Based Music Recommendation System

2025, International Journal of Advance Research and Innovative Ideas in Education

An innovative approach that generates a playlist for the user according to his /her mood. In today's modern world music has become an integral and crucial part of human life and advanced technologies. Hard part of listening a song... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by Kavin Kumar

2025, International Journal for Research in Applied Science and Engineering Technology

We propose a new approach for playing music automatically using facial emotion. Most of the existing approaches involve playing music manually, using wearable computing devices, or classifying based on audio features. Instead, we propose... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by Dhruv Parikh

2025, International Journal for Research in Applied Science and Engineering Technology

We propose a new approach for playing music automatically using facial emotion. Most of the existing approaches involve playing music manually, using wearable computing devices, or classifying based on audio features. Instead, we propose... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by tushar bhakte

2024, International Journal of Research Publication and Reviews

The increasing volume of digital music content has led to a growing demand for personalized music recommendation systems that can understand and cater to individual preferences. This paper proposes an emotion-based music recommendation... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by Basavaraj Neelgar

2024, International Journal of Research Publication and Reviews

The increasing volume of digital music content has led to a growing demand for personalized music recommendation systems that can understand and cater to individual preferences. This paper proposes an emotion-based music recommendation... more

descriptionView Paper arrow_downwardDownload

Lie Detection Using Facial Analysis, Electrodermal Activity, Pulse and Temperature

by Amey Kadam

2024

The paper describes a system based on lie detection named “Lie Detection Using Facial Analysis, Electrodermal Activity, Pulse and Temperature”. Detecting lies plays a vital role in many areas, such as airport security, police... more

descriptionView Paper arrow_downwardDownload

Rational Emotive Behavioural Therapy, Fear of Failure and Examination Malpractice Behaviour among Secondary School Students in Calabar Municipality

by Dr. Blessing Agbo Ntamu

2024, Journal of Education and Practice

Examination malpractice is a behavior in the educational system that is destructive and needs modification in order for the gains of education to be maximized. Fear of failure has been identified as one of the key causes of examination... more

The research design employed in this study is the pretest/posttest control group experimental design. Two groups were used for this study, one experimental group and one control group. The experimental group was pretested, treated and then post tested. The control group was pretested, post tested and given a placebo treatment consisting of a summary of the treatment after the post test.

REBT has a positive effect on fear of failure as can be gleaned from table 1. At pretest students in the experimental group had a more intense fear of failure. This more intense fear of failure before treatment is indicated by higher pretest scores of 343 as compared to 229 in the posttest, and a mean of 17.15 at pretest and 11.45 at posttest. Descriptive statistics of fear of failure scores of students What i is the effect of REBT on fear of failure scores of students?

There is no significant difference between the experimental and the control group on the effect of REBT on scores of fear of failure.

df =39, Sig. at 0.05 level, P value =0.003 The assumptions for Analysis of Co-Variance (ANCOVA) were met, particularly the homogeneity for regression effects was evident for the covariate. A one - way ANCOVA was carried out to test for a significant mean difference between the experimental and the control group for fear of failure scores at the posttest. Holm’s sequential Bonferroni procedure was used to control for type 1 error across the pairwise comparisons. The ANCOVA was significant at F (2, 38) = 10.328, p = .003. P is less than .05. Hence we reject the null hvpothesis. There is a significant mean difference between the expnerimental and the control group at the end of

descriptionView Paper arrow_downwardDownload

Rational Emotive Behavioural Therapy, Fear of Failure and Examination Malpractice Behaviour among Secondary School Students in Calabar Municipality

by Dr. Blessing Agbo Ntamu

2024, Journal of Education and Practice

Examination malpractice is a behavior in the educational system that is destructive and needs modification in order for the gains of education to be maximized. Fear of failure has been identified as one of the key causes of examination... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by shaik aziz

2024, International Journal for Research in Applied Science and Engineering Technology

Music has a powerful impact on people and is extensively utilised for relaxation, mood control, stress relief, and illness prevention, as well as to sustain mental and physical work. Music has been nowadays acting as an stress-buster for... more

descriptionView Paper arrow_downwardDownload

Hypothesis of Stele and Collision Effects in a Narcissistic Teaching Model; and Psychophysiological Record in Students, Provided by Emotional Learning Method (ELM)

by Dr. Carlos González Bravo

2024

Efecto Estela - parte III (Stele Effect - part III)El análisis estadístico de 907 encuestas realizadas a alumnos de Arquitectura y sus profesores por medio de la denominada Encuesta Empática, con el objetivo de analizar las divergencias... more

descriptionView Paper arrow_downwardDownload

Object Detection Using Correlation Technique

by Pragati Upadhyay

2024

This paper describes an object detection using correlation and template matching technique. This paper contains how we can use simple correlation technique for detection of object by using matlab software and image processing. This... more

The first two terms can be computed efficiently using integral images of the original image and the squared image. To speed up the numerator computation, we can decomposed the template into box basis function so that, Normalized cross correlation is a well-liked method for finding 2D patterns in images. An (2h +1) x (2w+1) template T is correlated in opposition to an image X. At the image location (u, v), the normalized cross correlation is computed as Normalized cross correlation

Use direct command ‘imcrop(image)’ or use “imtool (Image)’ command ang select object which want to crop. ‘imread (main image)’

Step 3: Save the cropped image as template for detecting same object from main image.

. We can get this position at the time of cropping image by right clicking on top middle portion of rectangle on image. Step 2: Calculate the normalized cross-correlation of two sub images and display it as a surface plot. We are using this function for finding highest matched peak value from both sub images. The peak of the cross-correlation matrix occurs where the sub images are best correlated.

‘he total offset or translation between images depends on the location of the peak in the cross-correlation matrix, and nn the size and position of the sub images. shading flat: The shading function controls the color shading of surface and patch graphics objects .Each mesh line segment and face has a constant color determined by the color value at the endpoint of the segment or the corner of the face that has the smallest index or indices.

Step 6: check extracted object is matching with original template or not with respect to size and value.

| blackout complete main image then overlap extracted image one that to get following output

Figure 9 : recovered object with background view

descriptionView Paper arrow_downwardDownload

Review Paper on Music Genre Classification and Play Songs Using Facial Emotion

by rahul raut

2023, JETIR

Human facial expression recognition is one of the foremost powerful and difficult tasks in social communication yet plays very important role in communicating the emotions and intensions of human beings. Generally, facial expressions are... more

descriptionView Paper arrow_downwardDownload

Language Experience Activities

by Andrew Johnson

2023

Language experience activities are an effective strategy to use with beginning-level readers. Here students dictate an experience or story to the teacher. The teacher then records what students say. I strongly recommended that you use... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by KAVIN KUMAR K

2023, International Journal for Research in Applied Science and Engineering Technology

We propose a new approach for playing music automatically using facial emotion. Most of the existing approaches involve playing music manually, using wearable computing devices, or classifying based on audio features. Instead, we propose... more

descriptionView Paper arrow_downwardDownload

Evolutionary-Based BEL Controller Applied to a Magneto-Rheological Structural System

by Joao Paulo Coelho

2023, Actuators

This work addresses the problem of finding the best controller parameters in order to improve the response of a single degree-of-freedom structural system under earthquake excitation. The control paradigm considered is based on brain... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by Pratham Shinde

2023, International Journal for Research in Applied Science and Engineering Technology

We propose a new approach for playing music automatically using facial emotion. Most of the existing approaches involve playing music manually, using wearable computing devices, or classifying based on audio features. Instead, we propose... more

descriptionView Paper arrow_downwardDownload

Aproximación a una Metodología de Aprendizaje Emocional (MAE) en las enseñanzas de Arquitectura

by Carlos Carlos González Bravo

2023, Arbor

descriptionView Paper arrow_downwardDownload

Music Recommendation based on Facial Emotion Detection

by Sonika Malik

2023, International Journal of Computer Applications

Human face expressions directly express what's going on inside a person. Detecting someone's emotions is not a difficult task for a human but for a machine it can be difficult. Also when it comes to sear a song according to our mood, is... more

The data consists of 48x48 pixel gray scale images of faces. The task is to categorize each face based on the emotion shown in the facial expression of the person into one of these seven categories (O=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral). This dataset was prepared by Pierre- Luc Carrier and Aaron Courville, for an ongoing research project [15].

value are selected for further verification. At this stage, the face symmetry is measured and the existence of the different facial features is verified for each face candidate. Emotion Detection

WAV files contain a sequence of bits representing the raw audio data, as well as headers with metadata in RIFF (Resource Interchange File Format) format. For CD recordings, the industry standard is to store each audio sample (an individual audio data point relating to air pressure) as a 16-bit value, at 44100 samples per second. To reduce file size, it may be sufficient to store some recordings (for example of human speech) at a lower sampling rate, such as 8000 samples per second, although this does mean that higher sound frequencies may not be as accurately represented. A few of the libraries discussed in this tutorial play and record bytes’ objects, With machine learning, in particular, we often see metrics being used to make decisions, not because they ‘re reliable, but simply because they can be measured. This is a technology that excels at finding connections, and this can lead to all sorts of spurious analyses: from scanning babysitters ‘social media posts to detect their attitude to analyzing corporate transcripts of earnings calls to try to predict stock prices. Often, the very mention of AI gives an undeserved veneer of credibility. If emotion recognition becomes common, there’s a danger that we will simply accept it and change our behavior to accommodate its failings. In the same way that people now act in the knowledge that what they do online will be interpreted by various algorithms (e.g., choosing to not like certain pictures on Instagram because it affects your ads), we might end up performing exaggerated facial expressions because we know how they will be interpreted by machines. That wouldn’t be too different from signaling to other humans. Barrett says that perhaps the most important takeaway from the review is that we need to think about emotions in a more complex fashion. The expressions of emotions are varied, complex, and situational. She compares the needed change in thinking to Charles Darwin’s work on the nature of species and how his research overturned a simplistic view of the animal kingdom. Darwin recognized that the biological category of a species does not have an essence, it’s a category of highly variable individuals, says Barrett. Exactly the same thing is true of emotional categories.

Fig. 6: Flowchart of the Working Model Model & Outcome For emotion detection we have used CNN and tried to achieve the best accuracy that we could. We have therefore used the 7 Layered CNN-ANN network.

International Journal of Computer Applications (0975 — 8887) Volume 185 — No. 1, April 2023

And therefore, it has over 1 Million parameters which are being trained under 25 epochs with batch size of 897.

descriptionView Paper arrow_downwardDownload

Hypothesis of Stele and Collision Effects in a Narcissistic Teaching Model; and Psychophysiological Record in Students, Provided by Emotional Learning Method (ELM)

by Carlos Carlos González Bravo

2023

Efecto Estela - parte III (Stele Effect - part III)El análisis estadístico de 907 encuestas realizadas a alumnos de Arquitectura y sus profesores por medio de la denominada Encuesta Empática, con el objetivo de analizar las divergencias... more

descriptionView Paper arrow_downwardDownload

Sentiment Analysis: A Novel Approach for Prediction of Satisfaction Level from Facial Expressions

by Prashant Kanade

2023

Digital Image Processing is one of the evolving technologies in today's world. There is a myriad of applications which are developed on the basis of this like remote sensing, color sensing, pattern recognition, video processing, etc.... more

Methodology: Following figure represents the overall setup of the system where the camera is a major equipment to capture facial expressions. After capturing various expressions in a group, features and expressions will be identified and will be compared with a knowledgebase to have exact analysis of expressions and emotions of a person. The various tasks involved in this system are as mentioned below.

After running the code the camera opens up and we can see the video starts now as soon as the face is detected depending upon the expressions the relevant emotion or satisfaction category is displayed and depending upon the emotions at each instance the emotion keeps on changing. Implementation:

In our system we also have the capacity to detect more than one human face so here is an instance where it determines the emotion of multiple people at a time; it changes according to the situation and time.

descriptionView Paper arrow_downwardDownload

Song Recommendation System Based on Real-Time Facial Expressions

by IJRASET Publication

2022, International Journal for Research in Applied Science and Engineering Technology (IJRASET)

Traditional methods of playing music according to a person's mood required human interaction. Migrating to computer vision technology will enable the automation of the such system. This article describes the implementation details of a... more

descriptionView Paper arrow_downwardDownload

Melomaniac : Emotion Based Music Recommendation System

by Vedant Shirpurkar

2022, International Journal of Advance Research and Innovative Ideas in Education

An innovative approach that generates a playlist for the user according to his /her mood. In today's modern world music has become an integral and crucial part of human life and advanced technologies. Hard part of listening a song... more

descriptionView Paper arrow_downwardDownload

EMOFY: Emotional Data Acquisition within a con- trolled stimulus environment

by Ayan Chakraborty

2022

Human being can be authenticated using three parameters, i.e., physical entities, behavioral and cognitive nature, and social associations. As we consider the finger print (or finger impressions) to authenticate a human being physically,... more

descriptionView Paper arrow_downwardDownload

Verification of intelligent control of a launch vehicle with HILS

by Ali Sedigh

2022, Journal of Mechanical Science and Technology

The reliability of an intelligent self tuning controller called the brain emotional learning based intelligent controller (BELBIC) to attitude control of a nonlinear launch vehicle (LV) simulation with hardware-in-the loop simulation... more

descriptionView Paper arrow_downwardDownload

Improving Student Learning Awareness Using Rational Emotive Behavior Therapy Techniques at Vocational School of Darul Anwar, Banyuwangi Regency City East Java Indonesia

by agus mursidi

2022

Low is due to low self-awareness of students. On the one hand, low self-awareness is caused because students have irrational thoughts about lessons and how they learn. Thinking that learning is very boring, not fun, studying or studying... more

descriptionView Paper arrow_downwardDownload

Smart Surveillance System Using Artificial Intelligence

by Puneshkumar Tembhare

2022, Journal of emerging technologies and innovative research

Recognition of the face is one of the biometric techniques used to recognize any facial image. Since birth, faces have played a crucial role in any individual's social interaction that gives the individual a distinctive identity. Face... more

We are only interested in selected few features from the large number of features computed in part I which would enable us to detect the face with great precision. To this, we use the Adaboost Algorithm to pick the key features and to train classifiers that will use them. The purpose of this algorithm is to construct a strong classifier from a linear weak classification combination. Adaboost is an effective boosting algorithm combining simple statistical learners thus significantly reducing both the training error and the more elusive generalization error. A concept called Adaboost which selects the best features and then trains the classifiers which is used. This algorithm creates a sturdy classifier using a linear combination of weighted simple weak classifiers.

FIGURE 2: Flow chart of Cascade Classifier Finally, in the recognition module the fundamental components of the face from the new video are extracted. Then those features get compared with the list of elements stored during training and the ones with the best match is found and name of the person recognized is displayed. This monitoring system fulfills the basic needs of face detection and recognition system, also takes the cost into consideration to ensure the pervasive mode as economical as possible. Furthermore, it can also be combined with real-time analvsis algorithms.

This device is capable of identifying the faces of the image taken from HD Video to analyze and identify the faces. Fron Section IV above, face detection determines where a face is located in an image, and is achieved by scanning the different imag scales and extracting the exact patterns to identify the face. The Prototype is designed from OpenCV with the Haar-Like feature Face detection for hair classifiers is used to create a search window t hat slides through an image and tests whether or not a certail region of an image looks like face. To identify a certain picture as face or non-face, hair-like features and a large set of very weal classifier use one single feature. That function is defined by the prototype and its coordinate relative to the search window that i the origin of the feature's size. The search window scans the first c assifier on the cascade quickly if the classifier returns fals then the calculation on that window also ends and no detected facial (positive) occurs. In addition, if the classifier returns true then the window will be moved in the cascade to the next classifi window return true, the result will also return true for the detection o er to do the exact same thing. When all classifiers for tha f certain window face.

Figure 4: Grey Scale Image We use gray scale image for image related operation because, gray scale image is a one-layer image from 0-255 whereas the ylored image has three different layer also color increases the complexity of the model. II.2 Gray-Scale Image

After the face detection step, human-face patches are removed from images via feature extraction phase. If we use these patches for face recognition directly, it may have some limitations; first, each patch usually holds over 1000 pixels, which are too enormous to build a robust recognition. Second, face patches may be taken under different illumination, with different face expressions, and with different camera alignment, and may suffer from occlusion and cluttering background. To overcome these drawbacks, we perform feature extractions to do dimensionality reduction, information packing, salience extraction, and noise cleaning. After this step, we transformed face patch into a vector with fixed dimension or a set of fiducial points and their corresponding locations. We can include feature extraction either in face detection or face recognition as per survey form some literatures.

Simply put, model training is the process of taking several face representation belonging to the same person, and creating a classifier that can recognize more instances of face portrayal from the same person. The most favored approach is to use a linear SVM.

In this step we will use Local Binary Pattern Histogram (LBPH) to consider the face structure and to evaluate patterns. We'll isolate and generalize the details so it can know what face belongs to somebody. FIGURE 7: Training Model

After formulating each face patch in the above steps, the last step is to recognize the identities of these faces. For face recognition, a face database is required to build. [4]For each individual, some images are taken and their features are removed and stored in the database. Whenever an input image came, we perform face detection and face extraction and after this we compare features of each face with stored database. Xt7. -eer...)vhlUuluY a gg eR Re ee ey ee

The table above shows the accuracy of the proposed model, and also shows the amount of correct and incorrect face-detected images given as the sample data collection.As, if we have all data models as correctly observed images, we can see it gives the highest precision. Whenever we send the suspected face to the device, it upgrades its data model with the provided face and tries to identify other faces matching the provided face so that it can automatically improve its models leading to correct facial recognition and automated facial identification takes place in live streaming videos or uploaded photographs.

FIGURE 9: Image showing Detection and Recognition of face

descriptionView Paper arrow_downwardDownload

Emotion Based Music Player - XBeats

by Manish krishnan (PGDM 17-19)

2022, International Journal of Advanced Engineering Research and Science

This paper showcases the development of an Android platform based application named XBeats which acts as a Music Player working on Image Processing fundamentals to capture, analyze and present music as per the emotion or mood of the user... more

descriptionView Paper arrow_downwardDownload

Face Mask Detection System using ML

by Nitish Kesarwani

2022

According to the World Health Organization, the corona virus COVID-19 pandemic is producing a worldwide health catastrophe, and the most effective protective technique is wearing a face mask in public places (WHO). The COVID-19 epidemic... more

TensorFlow is a free and open-source software framework for dataflow and differentiable programming that may be used to solve a variety of problems. It's a symbolic math library that's also utilised in neural networks and other machine learning applications. TensorFlow is Google Brain's second-generation system, which is used for both research and production.

PyTorch is an open source machine learning framework based on the Torch library that is used for applications such as computer vision and natural language processing. It was created largely by Facebook's AI Research team (FAIR).

Offices : The approach described might help maintain safety standards and prevent the spread of Covid-19 or any other airborne infection. If an employee is not wearing a mask, a reminder message may be sent to them. When choosing a system, the best performance must be taken into account. As a consequence, the aforementioned performance indicator: may be taken into account while designing the best system that can be implemented on a large scale..

. The dataset is partitioned into training and testing sets by preserving a reasonable proportion of different classes. The dataset contains a total of 1915 samples, with 80% of them being utilised in the training phase and 20% in the testing phase. There are 1532 and 383 pictures in the training and testing datasets, respectively. Because more training leads in overfitting on the training data, the resulting architecture is trained for 100 epochs. When a model learns the undesirable patterns of the training data, this is known as overfitting. As a result, training accuracy improves but test accuracy declines.

descriptionView Paper arrow_downwardDownload

Mood Based Music Playlist Generator Using Convolutional Neural Network

by IJRASET Publication

2022, International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Music is used in one's everyday life to modulate, enhance, and plummet undesirable emotional states like stress, fatigue, or anxiety. Even though in today's modern world, with the ever-increasing advancement in the area of multimedia... more

B. Model Training and Hyperparameter Tuning D. MLOUEL LIGULIS GG LTYPeCrPalarieler £ UPLLILS After getting the data and performing resizing and rescaling we went ahead and separated the data into training, testing, and validation sets. The dataset consisted of around 35 thousand images split into 6 different moods, Happy, Sad, Fear, Anger, Neutral, and Surprise. 80% of the data was set aside for training, 10% for validation, and 10% for testing. The first CNN architecture was with 6 Convolutional layers along with a Maxpooling layer and finally the flatten and dense layers. We used ‘relu’ as the activation function and for the dense layer, ‘softmax’ was used. The model was trained for 100 epochs and achieved an accuracy of 51.83% Keras Tuner [19] is a library that helps you pick the optimal set of hyperparameters for your TensorFlow program. Upon using the Keras tuner we trained the model with the best model as given by the Keras tuner. An accuracy of 56.19 % was achieved, around 5% more than the first model.

Fig. 4 CNN Architecture of Proposed Model

The reported measurement has been obtained in Kaggle on an NVIDIA TESLA P100 GPU. Fig. 6 Confusion Matrix for Training Data

Fig. 8 Confusion Matrix for Testing Data

Fig. 8 Training and Validation Accuracy curve

Fig. 9 Training and Validation Loss curve

Fig. 11 Mood Detected and Songs generated accordingly

From the table it can be seen that the difference in accuracy between the proposed model and few other models, the proposed mode has only 3332806 parameters. Fig. 10 Taking user’s image as Input

descriptionView Paper arrow_downwardDownload

A Review on Facial Expression Recognition System using Deep Learning

by nayan verma

2022

Human emotions are spontaneous and conscious mental states of feeling that are accompanied by physiological changes in the face muscles implying face expression. Some important emotions are happy, sad, anger, disgust, fear, surprise,... more

Figure 2. Facial Expression Recognition system Fig. 2 shows an overview of the FER system. A FER system comprises important phases like facial picture preprocessing, extraction & categorization of features.

(Source: https://stackabuse.com/deep-learning-in-keras- building-a-deep-learning-model)

Table 1: The table below provides key emotions FE

of facial expression recognition systems & differen investigations. These systems include face recognition extraction & classification of features. For good recognitiot rates, many approaches may be used. Higher recognition rat approaches are greater performance. These techniques provid practical solutions to the issue of recognition of face expressio1 & may work properly in restricted environments. Recognitiot Table 2: Comparative Study of Literature Survey

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by DHRUV PARIKH 18BEC1292

2022, International Journal for Research in Applied Science and Engineering Technology

Human emotion play a vital role in recent times.Emotion is based on human feelings which can be both expressed or not.Emotion expresses the human's individual behaviour which can be in different forms.Extraction of the emotion states... more

Fisher face with open CV mainly it mainly emphasis on the class specific transformation matric so, they don’t take illustrative images as the subject.and emotion is mainly concluded by the model that the value evaluated from the process can help us to deduce the mood of the user.by comparing the data sets that each emotion is compared with tens of stored images and scale gives the exact emotion so that it can play the music based on the recommendation made by the system by using the following steps and methods. And it does not depend on the other personal details like the other existing software's. lie wen nAlA AKIO ARe RS Ata Je th FBR ws ec ee eee ee Lk ee Lee: 6. l Ate eweeklincs wxenthaatkacx QU IKA te

he input images that is acquired is from the web camera and is used to capture real-time images. And here we are ur main emotions because it is very hard to define all the emotions and by using limited options it can help the ympilation time and the outcome is more sophisticated. it compares the values that are present as a threshold in the de. The values will be transferred to perform the web service. The song’s will be played from the detected notion. The emotions are assigned to every song. When the emotion is transferred the respective song and the notions are numbered are arranged and assigned to every song. however, we can use many kinds of models to commend because of their accuracy. and we are using a fisherface that contains the PCA and LDA algorithms so it ves the accuracy better than other algorithms.and for the sound mechanism we are using the win sound and with equency and duration it the commonly used python library for basic sound playing for the echanism.obtained are being compared the values that are present as a threshold. and there are other alternative tions other than the emotion-based system that queue mode and the random mode.in queue mode, we can make a aylist as the other usual music software’s and the last one is the random mode it is for random picking of songs rather an the order and other and it is also one of the therapies that can brighten up our moods. when the song is played on e basis of users' emotions at the same time it also represents emotions in the form of emoticons in four different notions. each emotion is assigned with a number and that implies to music and also emoticons that are detected spectively. When the face is detected successfully , a box will appear as and it overlay the image to extract the face and for the further analysis.in the next step The images that are extracted previously will processed using the function .The code will extract the facial spatial positions from the face image and it is based on the pixel’s intensity values that are indexed at each point and it uses boosting algorithm. It is performs the comparision between the input data and with stored one so it can predict the class that contain the emotion. If it contains one of the four emotions anger, sad,neutral or happy .and detection of the emotion as seems to be decreasing speed command and it will be executed so that it can reduce the speed of the wheelchair so,that we could prevent the user from endangerment.

Kernel Learning Algorithms(fisher face,harcasscade) for Face Recognition By Jun-Bao Li, Shu-Chuan Chu, Jeng- Shyang Pan — 2013

descriptionView Paper arrow_downwardDownload

Effect of Two Therapies and Gender on Reading Skills of Pupils with Learning Disabilities

by Udeme S Jacob and

2022, Universal Journal of Educational Research

Reading is a fundamental skill required for effective participation in academic tasks. This research investigated the significant main effects of phonics and neurological impress instructional methods on the reading skills of pupils with... more

Table 1. ANCOVA showing the main and interaction effects of Treatment Group, Gender and Learning Style on reading skills

Table 2. Estimated marginal means on treatment groups Table 3. Estimated marginal means on gender

This current finding is consistent with Sitthitikul's [52] claim that phonics instruction had a significant effect on the reading skills of struggling readers in the early grades but had no effect on older children with reading problems.

descriptionView Paper arrow_downwardDownload

The Effectiveness of Group Counseling Services Using Rational Emotive Behavior Therapy Approach to Overcome Anxiety of Senior High School Students in Padang Tualang North Sumatera

by hadi widodo

2022, World Journal of Educational Research

Guidance and counseling have techniques and approaches to overcome anxiety, one of which is the Rational Emotive Behavior Therapy approach (hereinafter referred to as REBT). This type of research is quantitative research with experimental... more

Figure 1. Results of Pretest and Posttest about Anxiety of Speaking in the Class

Table 1. Description of the Pretest and Posttest Differences of Speech Anxiety in Class Anxiety conditions Students talk in class through the results of the pretest and posttest can be seen from

Table 2. Wilcoxon’s Signed Ranks Test of Control and Experimental Groups This Table shows that Wilcoxon test on two clases has, Asymp. Sig. (2-tailed), 0,005 score lower than

descriptionView Paper arrow_downwardDownload

Cosmetics Application Using Computer Vision

by Akash Pal

2022

Computer vision is a new emerging field of artificial intelligence using which machines are trained to make sense out of digital images and videos. An end solution which is directly going to benefit the producer and consumer in the... more

Fig 5.1: Examples of past techniques situation every relapse work in the course proficiently appraises the shape from an underlying assessment and the powers of a scanty arrangement of pixels listed comparative with this underlying evaluation. Our work expands on the enormous measure of research throughout the most recent decade that has brought about critical advancement for face arrangement [5, 6]. In particular,we join into our educated relapse capacities two key components that are available in a few of the effective calculations referred to.

Pisure J.2 MIpul aha WUtpur Lda ses Different ways of detection of faces were tested during the initial implementation of the project. HaarCascade is one suc! classifier which successfully detects facial regions. Object Detection is an innovation identified with computer vision, pictur preparing and profound discovery that manages distinguishing occurrences of items in pictures and recordings. Haar Cascad classifiers are a powerful path for object identification. This strategy was suggested in a paper by Michael Jones and Paul Viol ‘Rapid Object Detection utilizing a Boosted Cascade of Simple Features’[11] .Haar Cascade is an AI based methodology where : ton of positive and negative pictures are utilized to prepare the classifier. Initially detection of faces were done using the same sai Haarcascade classifier. With the help of scipy’s interpolation function in 1D[10] the landmarks were interpolated to obtain all the points in between and thus helpful to make the contours.

Figure 5.4: All 68 Facial landmark’s coordinates

Figure 5.3: HaarCascade Classifier Output

The model is trained on 1000 images of the dataset[8]. Thus it is found to be less accurate than the model trained on all of the images. The comparison of the model’s accuracy with respect to the complete trained model is shown in table 6.1 The error which are observed are the Mean absolute error (MAE) which tell the absolute difference of the calculated landmarks points with respect to the original coordinates.

Table 6.2 Mean absolute Error on Training Data-| Thus the average error obtained on the training data is 17.23%.

descriptionView Paper arrow_downwardDownload

Emotion based Ambiance and Music Regulation using Deep Learning

by Shikhar Maheshwari

2022, 2020 International Conference on Communication and Signal Processing (ICCSP)

In today’s hyper active world full of stress and pressure, mental and emotional health is becoming important%factors in maintaining a persons well-being, but with the ever increasing work and social load, people don’t have enough time to... more

descriptionView Paper arrow_downwardDownload

Emotion Based Music Recommendation System

by IJRASET Publication

2022, IJRASET

Our world today is driven by machines of various complexities. From a basic one like a computer to a highly complex humanoid robot, everything is a product of human intelligence. A lot of industries are being benefited from such new... more

Facial expression is one of the most important features of human emotion recognition. Images are high-dimensional objects. Facial features over high dimensional spaces can be counter-intuitive. Words may not match emotions and the face can act as a window and reveal what someone is actually thinking and feeling. Facial expressions are the same regardless of race or culture all around the world. This is what stands out and makes it important for us to use it for our machine learning objectives.

The Adam optimizer, which was presented by Diederik Kingma and Jimmy Ba in their 2015 ICLR work titled "Adam: A Method for Stochastic Optimization," is also employed. The Adam Optimizer combines a hybrid of two gradient descent algorithms: Gradient Descent with Momentum Algorithm (AdaGrad) and Root Mean Square Propagation Algorithm (RMSP). Adam Optimizer employs a new formula derived from the two approaches. The optimizer surpasses the previous two models and delivers better results at a lower cost. Lh. CUOCMVOLULLOTLGML LINEUP ILVOCLWOTK We employed a neural network to identify the emotion. A neural network learns from the examples that are fed into it. The weight: associated with the neurons are adjusted by the network. Consecutive adjustments tend to teach the model more and help it perforn better. Convolutional Neural Networks (CNN) are used in this case. Since, the image is a multi-dimensional array, Artificial Neura Networks (ANN) cannot be employed because ANN requires 1-dimensional vectors. Thus, increasing the number of trainins parameters massively and not providing an efficient result. CNN, on the other hand, is a feed-forward network that is used tc analyse and recognise picture input. The project detects emotions of 7 categories - fear, surprise, angry, happy, sad, disgust, neutral The dataset “Facial expression recognition dataset” is being used, available on Kaggle. It contains 48x48 pixel grayscale image: grouped according to emotions in 7 different folders.

We fit the training set into the model. Then the performance of the model is evaluated by using the accuracy metrics to determine the evaluation of the loss functions and the characteristics of the negation in heatmap.

one ——ee~. St cae eee ee This section describes how the user's picture is acquired and how the face is extracted from it. The user's image is captured using one of the Python's libraries, OpenCV. The command cv2.CascadeClassifier(file name) is used to read the xml file for “haarcascade- frontal-face-default’”’. The file contains the features for detecting a person’s face. The command cv2.videoCapture() is used to get the object from the device's camera. An infinite loop is created where the read command is used to get the frames of the createc object. After capturing the user’s picture in a frame with OpenCV, the following step is to detect the user’s face from a frame captured through the webcam. The frame holding the image of the user is converted to Grayscale as the face is more defined by the composition of the set of pixels and not by the colours. So, the whole dataset of images is converted to grayscale by using the command cv2.COLOR_BGR2GRAY (image is initially present in BGR format). The image is modified (blurred, sharpened, o1 masked as required). The image undergoes segmentation. The segmentation algorithm divides the image into a set of pixels by assigning each pixel a label. The pixels having the same labels fall under a category that helps identify the contours in any giver image. The Haar Cascades image detection method is used here. The algorithm returns the coordinates which make a rectangulai box around the face. The algorithm uses features as shown below. As an image is represented as a NumPy array, it is not hard to imagine the dark part of the rectangle as a group of pixels with value 1 and the other as pixels with value 0. Considering feature (a), it detects the features with a horizontal edge, having darker pixels towards the bottom and lighter pixels towards the top. Haar value is calculated by the formula -

Fig. 8 Highest accuracy achieved of 64.52%

Fig. 10 Playing songs through Pywhatkit library

After detecting the face, the next step is to detect the emotion. For doing that, we require the use of Convolutional Neural Networks (CNN). To visualize an image stored as an array, we use the Matplotlib library. The method imshow() is used to see an image. The dataset is split into training and test sets. Then a neural network model is created by using the Keras library from Tensorflow. The model is a multilayered neural network. The layers are added by using the “add” method to the model initialized. It contains a convolutional 2D layer with ReLU as the activation function. The numbers of filters are constantly increased after every layer. The filter size determining the dimensions of the kernel are taken as inputs. The input shape of the image is needed to be defined for the first layer which is (48, 48, 1) in this case. The layers are MaxPooled and are given a small pool size of (2, 2). To avoid overfitting the data, a dropout layer is also introduced. The neurons from the current layer are randomly disconnected in the following layer with a probability p, forcing the network to rely on the existing connections. The Adam optimizer is used to optimize gradient descent; it takes a learning rate as the input. Finally, the model is flattened to a 1 Dimensional array format. The features detected in the model are saved in a JSON file to avoid retraining the model every time to save the operation and time complexity to train and attain similar accuracy for proceeding to neural network training.

The Haar Features are successfully able to detect the face during real-time video with a good precision. The model gives an accuracy of 64.52% to detect the right emotion. Detecting emotions has always been tricky even for humans. Performing the same task with a better accuracy by the help of machines has always been the part where new innovations takes place. The emotions are detected by the model stored in JSON format and can a so be used as an API for other projects. This model then is reiterated to visualize the facial characteristic to depict the song playlist in correlation to the neural network and the emotional sentiment of the individual. We were able to effectively show an intriguing use of facial emotion detection. The model can be quite useful for people having a hectic lifestyle. Thus, the model accomplishes the goal of proving a stress-free atmosphere to the people who need it the mact

descriptionView Paper arrow_downwardDownload

AI Based Scrutiny Bot for E-interview Using Natural Language Processing and Emotion Recognition

by harsha pariyani

2021

The introduction of artificial intelligence has reshaped job application and selection practices. The use of the internet in the organization has efficiently revolutionized the way of recruitment in an efficient manner. We aim to optimize... more

The interview questions are displayed in text format on the right side and a small window on the left side shows the live video of the candidate giving interview captured by a camera. The candidate answers the questions using webcam and microphone. The voice input has been converted to text form with speech recognition library in python. Natural language processing is used on the text for checking whether the answers are relevant. The screenshots of candidates are captured for understanding facial expressions which will show how they react. The trained CNN model trained in Keras using dataset fer2013 predicts the facial expression from an input face. After combining all the results system generates output. There are 0 moduilec in the evetem: 4.1 Webcam: The webcam captures live screenshots of the candidates during the interview. The images are stored in the database and further processed using OpenCV for classification of the emotions. Webcam used here is normal PC webcam having the minimum quality of 4-5 megapixels. To attain more accuracy webcam should be used.

Figure 6.2 Sentiment analysis using Textblob.

Some limitations of the system are that it requires a proper internet connection, camera, and microphones for functioning. Speech recognition is unable to record accurate answers in a noisy place. The camera needs proper light for capturing screenshots of faces.

descriptionView Paper arrow_downwardDownload

Three-Time Scale Singular Perturbation Control for a Radio-Control Helicopter on a Platform

by Sergio Esteban

2021, 2005 AIAA Atmospheric Flight Mechanics Conference and Exhibit

A three-time scale singular perturbation control is applied to a Radio/Control helicopter on a platform to regulate its vertical position. The proposed control law allows to achieve the desired altitude by either selecting a desired... more

descriptionView Paper arrow_downwardDownload

Las emociones en el aprendizaje online

by Rafael Garcia Perez

2021

This paper presents the results of an educational innovation in Higher Education, whose aim is to design and test a pedagogical model for e-learning. This paper has the main aim to identify and evaluate emotional factors related to... more

descriptionView Paper arrow_downwardDownload

Aerospace launch vehicle control: an intelligent adaptive approach

by Jafar Roshanian

2021, Aerospace Science and Technology

A theoretical analysis of on-line autonomous intelligent adaptive tracking controller based on emotional learning model in mammalians brain (BELBIC) for aerospace launch vehicle is presented. The control algorithm is provided with some... more

descriptionView Paper arrow_downwardDownload

Designing PID and BELBIC Controllers in Path Tracking Problem

by mohammad reza

2021

This paper proposes a new intelligent control approach for path tracking of a vehicle used in automated highway systems. Brain emotional learning based intelligent controller (BELBIC) is an intelligent controller based on the model of... more

descriptionView Paper arrow_downwardDownload

Designing PID and BELBIC Controllers in Path Tracking Problem

by mohammad reza

2021

This paper proposes a new intelligent control approach for path tracking of a vehicle used in automated highway systems. Brain emotional learning based intelligent controller (BELBIC) is an intelligent controller based on the model of... more

descriptionView Paper arrow_downwardDownload

The Effectiveness of Group Rational Emotive Behavior Therapy to Reduce Student Learning Burnout

by Daharnis Daharnis

2021, International Journal of Research in Counseling and Education

This study aims to examine the effectiveness of the Group Rational Emotive Behavior Therapy approach in reducing learning burnout experienced by students due to irrational thoughts. This research is a quantitative analysis that uses the... more

descriptionView Paper arrow_downwardDownload

Aproximación a una Metodología de Aprendizaje Emocional (MAE) en las enseñanzas de Arquitectura

by Dr. Carlos González Bravo

2021, Arbor

descriptionView Paper arrow_downwardDownload

Identification and real-time position control of a servo-hydraulic rotary actuator by means of a neurobiologically motivated algorithm

by Hadi Sazgar

2021, ISA transactions

This paper presents a new intelligent approach for adaptive control of a nonlinear dynamic system. A modified version of the brain emotional learning based intelligent controller (BELBIC), a bio-inspired algorithm based upon a... more

descriptionView Paper arrow_downwardDownload

Designing and evaluating a Steady State Visually Evoked Potentials based Brain Computer Interface system

by Mauro R O Sansana

2021

In this report I describe the Steady State Visually Evoked Potentials based Brain Computer Interface system that I built during my summer internship in the University of Twente, using the Emotiv © EPOC headset, the Psychophysics Toolbox... more

descriptionView Paper arrow_downwardDownload

Designing PID and BELBIC Controllers in Path Tracking Problem

by Mohammad reza Kbs

2021

This paper proposes a new intelligent control approach for path tracking of a vehicle used in automated highway systems. Brain emotional learning based intelligent controller (BELBIC) is an intelligent controller based on the model of... more

descriptionView Paper arrow_downwardDownload

Three-Time Scale Singular Perturbation Control for a Radio-Control Helicopter on a Platform

by Francisco Javier Sámano Gordillo

2021, 2005 AIAA Atmospheric Flight Mechanics Conference and Exhibit

A three-time scale singular perturbation control is applied to a Radio/Control helicopter on a platform to regulate its vertical position. The proposed control law allows to achieve the desired altitude by either selecting a desired... more

descriptionView Paper arrow_downwardDownload

Three-Time Scale Singular Perturbation Control for a Radio-Control Helicopter on a Platform

by Francisco Javier Sámano Gordillo

2021, 2005 AIAA Atmospheric Flight Mechanics Conference and Exhibit

A three-time scale singular perturbation control is applied to a Radio/Control helicopter on a platform to regulate its vertical position. The proposed control law allows to achieve the desired altitude by either selecting a desired... more

descriptionView Paper arrow_downwardDownload

Las emociones en el aprendizaje online

by Luisa Caro

2021

This paper presents the results of an educational innovation in Higher Education, whose aim is to design and test a pedagogical model for e-learning. This paper has the main aim to identify and evaluate emotional factors related to... more

descriptionView Paper arrow_downwardDownload

Brain emotional learning based intelligent controller

Related Topics