Search results for: automatic speech recognition

Authors: Mohd Iz'aan Paiz Bin Zamri, Anis Salwa Mohd Khairuddin, Norrima Mokhtar, Rubiyah Yusof

Abstract:

Effective statistical feature extraction and classification are important in image-based automatic inspection and analysis. An automatic wood species recognition system is designed to perform wood inspection at custom checkpoints to avoid mislabeling of timber which will results to loss of income to the timber industry. The system focuses on analyzing the statistical pores properties of the wood images. This paper proposed a fuzzy-based feature extractor which mimics the experts’ knowledge on wood texture to extract the properties of pores distribution from the wood surface texture. The proposed feature extractor consists of two steps namely pores extraction and fuzzy pores management. The total number of statistical features extracted from each wood image is 38 features. Then, a backpropagation neural network is used to classify the wood species based on the statistical features. A comprehensive set of experiments on a database composed of 5200 macroscopic images from 52 tropical wood species was used to evaluate the performance of the proposed feature extractor. The advantage of the proposed feature extraction technique is that it mimics the experts’ interpretation on wood texture which allows human involvement when analyzing the wood texture. Experimental results show the efficiency of the proposed method.

Keywords: classification, feature extraction, fuzzy, inspection system, image analysis, macroscopic images

Procedia PDF Downloads 395

Authors: Ziyad Motala

Abstract:

It is often proclaimed by leasers in Muslim majority countries that Islamic Law does not permit dissent against a ruler. This paper will evaluate and discuss freedom of speech and dissent as found in concrete prophetic examples during the time of the Prophet Muhammad. It will further look at the examples and practices during the time of the four Noble Caliphs, the immediate successors to the Prophet Muhammad. It will argue that the positivist position of absolute obedience to a ruler is inconsistent with the prophetic tradition. The examples of the Prophet and his immediate four successors (whose lessons Sunni Islam considers to be a source of Islamic Law) demonstrates among the earliest example of freedom of speech and dissent in human history. That tradition frowned upon an inert and uninvolved citizenry. It will conclude with lessons for modern day Muslim majority countries arguing with empirical evidence that freedom of speech, dissent and the right to be governed by consensus versus coercion are fundamental requisites of Islamic law.

Keywords: islamic law, demoracy, freedom of speech, right to dissent

Procedia PDF Downloads 48

Authors: Komal Ghafoor, Tauqir Ahmad, Murtaza Hanif, Hira Zaheer

Abstract:

Assistive technology has been developed to support visually impaired people in their social interactions. Conversation assistive technology is designed to enhance communication skills, facilitate social interaction, and improve the quality of life of visually impaired individuals. This technology includes speech recognition, text-to-speech features, and other communication devices that enable users to communicate with others in real time. The technology uses natural language processing and machine learning algorithms to analyze spoken language and provide appropriate responses. It also includes features such as voice commands and audio feedback to provide users with a more immersive experience. These technologies have been shown to increase the confidence and independence of visually impaired individuals in social situations and have the potential to improve their social skills and relationships with others. Overall, conversation-assistive technology is a promising tool for empowering visually impaired people and improving their social interactions. One of the key benefits of conversation-assistive technology is that it allows visually impaired individuals to overcome communication barriers that they may face in social situations. It can help them to communicate more effectively with friends, family, and colleagues, as well as strangers in public spaces. By providing a more seamless and natural way to communicate, this technology can help to reduce feelings of isolation and improve overall quality of life. The main objective of this research is to give blind users the capability to move around in unfamiliar environments through a user-friendly device by face, object, and activity recognition system. This model evaluates the accuracy of activity recognition. This device captures the front view of the blind, detects the objects, recognizes the activities, and answers the blind query. It is implemented using the front view of the camera. The local dataset is collected that includes different 1st-person human activities. The results obtained are the identification of the activities that the VGG-16 model was trained on, where Hugging, Shaking Hands, Talking, Walking, Waving video, etc.

Keywords: dataset, visually impaired person, natural language process, human activity recognition

Procedia PDF Downloads 25

Authors: Phawin Sangsuvan, Chutimet Srinilta

Abstract:

This Paper presents the applications of Particle Swarm Optimization (PSO) Method for Thai optical character recognition (OCR). OCR consists of the pre-processing, character recognition and post-processing. Before enter into recognition process. The Character must be “Prepped” by pre-processing process. The PSO is an optimization method that belongs to the swarm intelligence family based on the imitation of social behavior patterns of animals. Route of each particle is determined by an individual data among neighborhood particles. The interaction of the particles with neighbors is the advantage of Particle Swarm to determine the best solution. So PSO is interested by a lot of researchers in many difficult problems including character recognition. As the previous this research used a Projection Histogram to extract printed digits features and defined the simple Fitness Function for PSO. The results reveal that PSO gives 67.73% for testing dataset. So in the future there can be explored enhancement the better performance of PSO with improve the Fitness Function.

Keywords: character recognition, histogram projection, particle swarm optimization, pattern recognition techniques

Procedia PDF Downloads 438

Authors: Zehai Yu, Hui Zhu, Linglong Lin, Huawei Liang, Biao Yu, Weixin Huang

Abstract:

With the development of intelligent vehicle systems, a high-precision road map is increasingly needed in many aspects. The automatic lane lines extraction and modeling are the most essential steps for the generation of a precise lane-level road map. In this paper, an automatic lane-level road map generation system is proposed. To extract the road markings on the ground, the multi-region Otsu thresholding method is applied, which calculates the intensity value of laser data that maximizes the variance between background and road markings. The extracted road marking points are then projected to the raster image and clustered using a two-stage clustering algorithm. Lane lines are subsequently recognized from these clusters by the shape features of their minimum bounding rectangle. To ensure the storage efficiency of the map, the lane lines are approximated to cubic polynomial curves using a Bayesian estimation approach. The proposed lane-level road map generation system has been tested on urban and expressway conditions in Hefei, China. The experimental results on the datasets show that our method can achieve excellent extraction and clustering effect, and the fitted lines can reach a high position accuracy with an error of less than 10 cm.

Keywords: curve fitting, lane-level road map, line recognition, multi-thresholding, two-stage clustering

Procedia PDF Downloads 103

Authors: Benjawan Rangsikamol, Chutimet Srinilta

Abstract:

This research paper deals with extraction of Thai character features using the proposed histogram projection so as to improve the recognition performance. The process starts with transformation of image files into binary files before thinning. After character thinning, the skeletons are entered into the proposed extraction using histogram projection (horizontal and vertical) to extract unique features which are inputs of the subsequent recognition step. The recognition rate with the proposed extraction technique is as high as 97 percent since the technique works very well with the idiosyncrasies of Thai characters.

Keywords: character recognition, histogram projection, multilayer perceptron, Thai character features extraction

Procedia PDF Downloads 431

Authors: Nestor A. Garcia Fragoso, Tetyana Baydyk, Ernst Kussul

Abstract:

This article contains information from our investigation in the field of voice recognition. For this purpose, we created a voice database that contains different phrases in two languages, English and Spanish, for men and women. As a classifier, the LIRA (Limited Receptive Area) grayscale neural classifier was selected. The LIRA grayscale neural classifier was developed for image recognition tasks and demonstrated good results. Therefore, we decided to develop a recognition system using this classifier for voice recognition. From a specific set of speakers, we can recognize the speaker’s voice. For this purpose, the system uses spectrograms of the voice signals as input to the system, extracts the characteristics and identifies the speaker. The results are described and analyzed in this article. The classifier can be used for speaker identification in security system or smart buildings for different types of intelligent devices.

Keywords: extreme learning, LIRA neural classifier, speaker identification, voice recognition

Procedia PDF Downloads 141

Authors: Avitus A. Agbor

Abstract:

Numerous incidents, ranging from trivial to catastrophic, do come to mind when one reflects on hate. The victims of these belong to specific identifiable groups within communities. These experiences evoke discussions on Islamophobia, xenophobia, homophobia, anti-Semitism, racism, ethnic hatred, atheism, and other brutal forms of bigotry. Common to all these is an invisible but portent force that drives all of them: hatred. Such hatred is usually fueled by a profound degree of intolerance (to diversity) and the zeal to impose on others their beliefs and practices which they consider to be the conventional norm. More importantly, the perpetuation of these hateful acts is the unfortunate outcome of an overplay of invectives and hate speech which, to a greater extent, cannot be divorced from hate. From a legal perspective, acknowledging the existence of an undeniable link between hate speech and hate is quite easy. However, both within and without legal scholarship, the notion of “hate speech” remains a conundrum: a phrase that is quite easily explained through experiences than propounding a watertight definition that captures the entire essence and nature of what it is. The problem is further compounded by a few factors: first, within the international human rights framework, the notion of hate speech is not used. In limiting the right to freedom of expression, the ICCPR simply excludes specific kinds of speeches (but does not refer to them as hate speech). Regional human rights instruments are not so different, except for the subsequent developments that took place in the European Union in which the notion has been carefully delineated, and now a much clearer picture of what constitutes hate speech is provided. The legal architecture in domestic legal systems clearly shows differences in approaches and regulation: making it more difficult. In short, what may be hate speech in one legal system may very well be acceptable legal speech in another legal system. Lastly, the cornucopia of academic voices on the issue of hate speech exude the divergence thereon. Yet, in the absence of a well-formulated and universally acceptable definition, it is important to consider how hate speech can be defined. Taking an evidence-based approach, this research looks into the issue of defining hate speech in legal scholarship and how and why such a formulation is of critical importance in the prohibition and prosecution of hate speech.

Keywords: hate speech, international human rights law, international criminal law, freedom of expression

Procedia PDF Downloads 38

Authors: U. Ravi Babu, Mohd Mastan

Abstract:

The present paper proposes a novel approach for handwritten digit recognition system. The present paper extract digit image features based on distance measure and derives an algorithm to classify the digit images. The distance measure can be performing on the thinned image. Thinning is the one of the preprocessing technique in image processing. The present paper mainly concentrated on an extraction of features from digit image for effective recognition of the numeral. To find the effectiveness of the proposed method tested on MNIST database, CENPARMI, CEDAR, and newly collected data. The proposed method is implemented on more than one lakh digit images and it gets good comparative recognition results. The percentage of the recognition is achieved about 97.32%.

Keywords: handwritten digit recognition, distance measure, MNIST database, image features

Procedia PDF Downloads 432

Authors: Toshinori Nawata

Abstract:

In this paper a nonlinear feedback control called augmented automatic choosing control (AACC) for a class of nonlinear systems with constrained input is presented. When designing the control, a constant term which arises from linearization of a given nonlinear system is treated as a coefficient of a stable zero dynamics. Parameters of the control are suboptimally selected by maximizing the stable region in the sense of Lyapunov with the aid of a genetic algorithm. This approach is applied to a field excitation control problem of power system to demonstrate the splendidness of the AACC. Simulation results show that the new controller can improve performance remarkably well.

Keywords: augmented automatic choosing control, nonlinear control, genetic algorithm, zero dynamics

Procedia PDF Downloads 446

Authors: Faizan Tariq, Moayid Ali Zaidi

Abstract:

Facial emotion recognition algorithms are expanding rapidly now a day. People are using different algorithms with different combinations to generate best results. There are six basic emotions which are being studied in this area. Author tried to recognize the facial expressions using object detector algorithms instead of traditional algorithms. Two object detection algorithms were chosen which are Faster R-CNN and YOLO. For pre-processing we used image rotation and batch normalization. The dataset I have chosen for the experiments is Static Facial Expression in Wild (SFEW). Our approach worked well but there is still a lot of room to improve it, which will be a future direction.

Keywords: face recognition, emotion recognition, deep learning, CNN

Procedia PDF Downloads 156

Authors: Qiu Chen, Koji Kotani, Feifei Lee, Tadahiro Ohmi

Abstract:

In this paper, we propose an improved face recognition algorithm using histogram-based features in spatial and frequency domains. For adding spatial information of the face to improve recognition performance, a region-division (RD) method is utilized. The facial area is firstly divided into several regions, then feature vectors of each facial part are generated by Binary Vector Quantization (BVQ) histogram using DCT coefficients in low frequency domains, as well as Local Binary Pattern (LBP) histogram in spatial domain. Recognition results with different regions are first obtained separately and then fused by weighted averaging. Publicly available ORL database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using RD method can achieve much higher recognition rate.

Keywords: binary vector quantization (BVQ), DCT coefficients, face recognition, local binary patterns (LBP)

Procedia PDF Downloads 313

Authors: Xingxing Peng

Abstract:

With the development of society, there are more and more online communication scenarios such as teleconference and online education. In the process of conference communication, the quality of voice communication is a very important part, and noise may cause the communication effect of participants to be greatly reduced. Therefore, voice noise reduction has an important impact on scenarios such as voice calls. This research focuses on the key technologies of the sound transmission process. The purpose is to maintain the audio quality to the maximum so that the listener can hear clearer and smoother sound. Firstly, to solve the problem that the traditional speech enhancement algorithm is not ideal when dealing with non-stationary noise, an adaptive speech noise reduction algorithm is studied in this paper. Traditional noise estimation methods are mainly used to deal with stationary noise. In this chapter, we study the spectral characteristics of different noise types, especially the characteristics of non-stationary Burst noise, and design a noise estimator module to deal with non-stationary noise. Noise features are extracted from non-speech segments, and the noise estimation module is adjusted in real time according to different noise characteristics. This adaptive algorithm can enhance speech according to different noise characteristics, improve the performance of traditional algorithms to deal with non-stationary noise, so as to achieve better enhancement effect. The experimental results show that the algorithm proposed in this chapter is effective and can better adapt to different types of noise, so as to obtain better speech enhancement effect.

Keywords: speech noise reduction, speech enhancement, self-adaptation, Wiener filter algorithm

Procedia PDF Downloads 20

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. Accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER, benefiting from deep learning, especially CNN and VGG16. First, the data is pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning

Procedia PDF Downloads 60

Authors: Zouhair Haddi, Stephane Delliaux, Jean-Francois Pons, Ismail Kechaf, Jean-Claude De Haro, Mustapha Ouladsine

Abstract:

Atrial fibrillation (AF) has been considered as the most common cardiac arrhythmia, and a major public health burden associated with significant morbidity and mortality. Nowadays, telemedical approaches targeting cardiac outpatients situate AF among the most challenged medical issues. The automatic, early, and fast AF detection is still a major concern for the healthcare professional. Several algorithms based on univariate analysis have been developed to detect atrial fibrillation. However, the published results do not show satisfactory classification accuracy. This work was aimed at resolving this shortcoming by proposing multivariate data analysis methods for automatic AF detection. Four publicly-accessible sets of clinical data (AF Termination Challenge Database, MIT-BIH AF, Normal Sinus Rhythm RR Interval Database, and MIT-BIH Normal Sinus Rhythm Databases) were used for assessment. All time series were segmented in 1 min RR intervals window and then four specific features were calculated. Two pattern recognition methods, i.e., Principal Component Analysis (PCA) and Learning Vector Quantization (LVQ) neural network were used to develop classification models. PCA, as a feature reduction method, was employed to find important features to discriminate between AF and Normal Sinus Rhythm. Despite its very simple structure, the results show that the LVQ model performs better on the analyzed databases than do existing algorithms, with high sensitivity and specificity (99.19% and 99.39%, respectively). The proposed AF detection holds several interesting properties, and can be implemented with just a few arithmetical operations which make it a suitable choice for telecare applications.

Keywords: atrial fibrillation, multivariate data analysis, automatic detection, telemedicine

Procedia PDF Downloads 237

Authors: Monica Sharma, Harjit Pal Singh, Jasbinder Singh, Manju Bala

Abstract:

In Voice over Internet Protocol (VoIP) system, the speech signal is degraded when passed through the network layers. The speech signal is processed through the best effort policy based IP network, which leads to the network degradations including delay, packet loss and jitter. The packet loss is the major issue of the degradation in the VoIP signal quality; even a single lost packet may generate audible distortion in the decoded speech signal. In addition to these network degradations, the quality of the speech signal is also affected by the environmental noises and coder distortions. The signal quality of the VoIP system is improved through the interleaving technique. The performance of the system is evaluated for various types of noises at different network conditions. The performance of the enhanced VoIP signal is evaluated using perceptual evaluation of speech quality (PESQ) measurement for narrow band signal.

Keywords: VoIP, interleaving, packet loss, packet size, background noise

Procedia PDF Downloads 450

Authors: Imen Ben Abda

Abstract:

Languages have been classified into different rhythm classes. 'Stress-timed' languages are exemplified by English, 'syllable-timed' languages by French and 'mora-timed' languages by Japanese. However, to our best knowledge, acoustic studies have not been unanimous in strictly establishing which rhythm category a given language belongs to and failed to show empirical evidence for isochrony. Perception seems to be a good approach to categorize languages into different rhythm classes. This study, within the scope of experimental phonetics, includes an account of different perceptual experiments using cues from natural and inverted speech, as well as pitch extracted from speech data. It is an attempt to categorize speech rhythm over a large set of Arabic (Tunisian, Algerian, Lebanese and Moroccan) and English dialects (Welsh, Irish, Scottish and Texan) as well as other languages such as Chinese, Japanese, French, and German. Listeners managed to classify the different languages and dialects into different rhythm classes using suprasegmental cues mainly rhythm and pitch (F0). They also perceived rhythmic differences even among languages and dialects belonging to the same rhythm class. This may show that there are different subclasses within very broad rhythmic typologies.

Keywords: F0, inverted speech, mora-timing, rhythm variation, stress-timing, syllable-timing

Procedia PDF Downloads 478

Authors: Wan-Lin Tsai

Abstract:

Speech act of requests is an important issue in the field of language learning and teaching because we cannot avoid making requesting in our daily life. This study examined whether or not the subjects who were freshmen and majored in German at Wenzao University of Languages were able to use the linguistic forms which they had learned from their course book Schritte International to make appropriate requests through dialogue completed tasks (DCT). The results revealed that the majority of the subjects were unable to use the forms to make appropriate requests in German due to the lack of explicit instructions. Furthermore, Chinese interference was observed in students' productions. Explicit instructions in speech acts are strongly recommended.

Keywords: Chinese interference, German pragmatics, German teaching, make appropriate requests in German, speech act of requesting

Procedia PDF Downloads 431

Authors: Sirajdin Olagoke Adeshina, Haidi Ibrahim, Akeem Salawu

Abstract:

large lecture theatres cannot be covered by a single camera but rather by a multicamera setup because of their size, shape, and seating arrangements. Although, classroom capture is achievable through a single camera. Therefore, a design and implementation of a multicamera setup for a large lecture hall were considered. Researchers have shown emphasis on the impact of class attendance taken on the academic performance of students. However, the traditional method of carrying out this exercise is below standard, especially for large lecture theatres, because of the student population, the time required, sophistication, exhaustiveness, and manipulative influence. An automated large classroom attendance system is, therefore, imperative. The common approach in this system is face detection and recognition, where known student faces are captured and stored for recognition purposes. This approach will require constant face database updates due to constant changes in the facial features. Alternatively, face counting can be performed by cropping the localized faces on the video or image into a folder and then count them. This research aims to develop a face localization-based approach to detect student faces in classroom images captured using a multicamera setup. A selected Haar-like feature cascade face detector trained with an asymmetric goal to minimize the False Rejection Rate (FRR) relative to the False Acceptance Rate (FAR) was applied on Raspberry Pi 4B. A relationship between the two factors (FRR and FAR) was established using a constant (λ) as a trade-off between the two factors for automatic adjustment during training. An evaluation of the proposed approach and the conventional AdaBoost on classroom datasets shows an improvement of 8% TPR (output result of low FRR) and 7% minimization of the FRR. The average learning speed of the proposed approach was improved with 1.19s execution time per image compared to 2.38s of the improved AdaBoost. Consequently, the proposed approach achieved 97% TPR with an overhead constraint time of 22.9s compared to 46.7s of the improved Adaboost when evaluated on images obtained from a large lecture hall (DK5) USM.

Keywords: automatic attendance, face detection, haar-like cascade, manual attendance

Procedia PDF Downloads 46

Authors: Elad Vashdi

Abstract:

It is common to find speech deficit among children diagnosed with Autism. It can be found in the clinical field and recently in research. One of the DSM-V criteria suggests a speech delay (Delay in, or total lack of, the development of spoken language), but doesn't explain the cause of it. A common perception among professionals and families is that the inability to talk results from the autism. Autism is a name for a syndrome which just describes a phenomenon and is defined behaviorally. Since it is not based yet on a physiological gold standard, one can not conclude the nature of a deficit based on the name of the syndrome. A wide retrospective research (n=270) which included children with motor speech difficulties was conducted in Israel. The study analyzed entry evaluations in a private clinic during the years 2006-2013. The data was extracted from the reports. High percentage of children diagnosed with Autism (60%) was found. This result demonstrates the high relationship between Autism and motor speech problem. It also supports recent findings in research of Childhood apraxia of speech (CAS) occurrence among children with ASD. Only small percentage of the participants in this research (10%) were diagnosed with CAS even though their verbal deficits well fitted the guidelines for CAS diagnosis set by ASHA in 2007. This fact raises questions regarding the diagnostic procedure in Israel. The understanding that CAS might highly exist within Autism and can have a remarkable influence on the course of early development should be a guiding tool within the diagnosis procedure. CAS can explain the nature of the speech problem among some of the autistic children and guide the treatment in a more accurate way. Calculating the prevalence of CAS which includes the comorbidity with ASD reveals new numbers and suggests treating differently the CAS population.

Keywords: childhood apraxia of speech, Autism, treatment, speech

Procedia PDF Downloads 248

Authors: Ashutosh Mishra, Nikhil Goyal

Abstract:

A 3D facial emotion recognition model based on deep learning is proposed in this paper. Two convolution layers and a pooling layer are employed in the deep learning architecture. After the convolution process, the pooling is finished. The probabilities for various classes of human faces are calculated using the sigmoid activation function. To verify the efficiency of deep learning-based systems, a set of faces. The Kaggle dataset is used to verify the accuracy of a deep learning-based face recognition model. The model's accuracy is about 65 percent, which is lower than that of other facial expression recognition techniques. Despite significant gains in representation precision due to the nonlinearity of profound image representations.

Keywords: facial recognition, computational intelligence, convolutional neural network, depth map

Procedia PDF Downloads 195

Authors: R. N. Begum, Ambalika Sharma, G. K. Singh

Abstract:

Identity theft has serious ramifications beyond data and personal information loss. This necessitates the implementation of robust and efficient user identification systems. Therefore, automatic biometric recognition systems are the need of the hour, and ECG-based systems are unquestionably the best choice due to their appealing inherent characteristics. The CNNs are the recent state-of-the-art techniques for ECG-based user identification systems. However, the results obtained are significantly below standards, and the situation worsens as the number of users and types of heartbeats in the dataset grows. As a result, this study proposes a highly accurate and resilient ECG-based person identification system using CNN's dense learning framework. The proposed research explores explicitly the calibre of dense CNNs in the field of ECG-based human recognition. The study tests four different configurations of dense CNN which are trained on a dataset of recordings collected from eight popular ECG databases. With the highest FAR of 0.04 percent and the highest FRR of 5%, the best performing network achieved an identification accuracy of 99.94 percent. The best network is also tested with various train/test split ratios. The findings show that DenseNets are not only extremely reliable but also highly efficient. Thus, they might also be implemented in real-time ECG-based human recognition systems.

Keywords: Biometrics, Dense Networks, Identification Rate, Train/Test split ratio

Procedia PDF Downloads 131

Authors: Shunzuo Wu, Xudong Luo, Yuanxiu Liao

Abstract:

Recently, the rapid development of deep learning makes artificial intelligence (AI) penetrate into many fields, replacing manual work there. In particular, AI systems also become a research focus in the field of automatic office. To meet real needs in automatic officiating, in this paper we develop an automatic form filling system. Specifically, it uses two classical neural network models and several word embedding models to classify various relevant information elicited from the Internet. When training the neural network models, we use less noisy and balanced data for training. We conduct a series of experiments to test my systems and the results show that our system can achieve better classification results.

Keywords: artificial intelligence and office, NLP, deep learning, text classification

Procedia PDF Downloads 149

Authors: Aya Idriss, Esraa Othman, Lujain Malak

Abstract:

Artificial intelligence is the emulation of human intelligence processes by machines, particularly computer systems that act logically. Some of the specific applications of AI include natural language processing, speech recognition, and machine vision. Cortana is a virtual assistant and she’s an example of an AI Application. Microsoft made it possible for this app to be accessed not only on laptops and PCs but can be downloaded on mobile phones and used as a virtual assistant which was a huge success. Cortana can offer a lot apart from the basic orders such as setting alarms and marking the calendar. Its capabilities spread past that, for example, it provides us with listening to music and podcasts on the go, managing my to-do list and emails, connecting with my contacts hands-free by simply just telling the virtual assistant to call somebody, gives me instant answers and so on. A questionnaire was sent online to numerous friends and family members to perform the study, which is critical in evaluating Cortana's recognition capacity and the majority of the answers were in favor of Cortana’s capabilities. The results of the questionnaire assisted us in determining the level of Cortana's skills.

Keywords: artificial intelligence, Cortana, AI, abstract

Procedia PDF Downloads 153

Authors: Mohd Noah A. Rahman, Afzaal H. Seyal, Norhafilah Bara

Abstract:

Developing a software application using an interface with computers and peripheral devices using gestures of human body such as hand movements keeps growing in interest. A review on this hand gesture detection and recognition based on computer vision technique remains a very challenging task. This is to provide more natural, innovative and sophisticated way of non-verbal communication, such as sign language, in human computer interaction. Nevertheless, this paper explores hand detection and hand gesture recognition applying a vision based approach. The hand detection and recognition used skin color spaces such as HSV and YCrCb are applied. However, there are limitations that are needed to be considered. Almost all of skin color space models are sensitive to quickly changing or mixed lighting circumstances. There are certain restrictions in order for the hand recognition to give better results such as the distance of user’s hand to the webcam and the posture and size of the hand.

Keywords: hand detection, hand gesture, hand recognition, sign language

Procedia PDF Downloads 274

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 79

Authors: Rominkumar Busa, Shahira K. C., Lijiya A.

Abstract:

Text recognition is an important area in computer vision which deals with detecting and recognising text from an image. The Optical Character Recognition (OCR) is a saturated area these days and with very good text recognition accuracy. However the same OCR methods when applied on text with small font sizes like the text data of chart images, the recognition rate is less than 30%. In this work, aims to extract small text in images using the deep learning model, CRNN with CTC loss. The text recognition accuracy is found to improve by applying image enhancement by super resolution prior to CRNN model. We also observe the text recognition rate further increases by 18% by applying the proposed method, which involves super resolution and character segmentation followed by CRNN with CTC loss. The efficiency of the proposed method shows that further pre-processing on chart image text and other small text images will improve the accuracy further, thereby helping text extraction from chart images.

Keywords: small text extraction, OCR, scene text recognition, CRNN

Procedia PDF Downloads 94

Authors: Ana Cleide Vieira Gomes Guimbal de Aquino

Abstract:

Sound communication is present in most vertebrates, from fish, mainly in species that live in murky waters, to some species of reptiles, anuran amphibians, birds, and mammals, including primates. There are, in fact, relevant similarities between human language and animal sound communication, and among these similarities are the vocalizations called calls. The first specific call in human babies is crying, which has a characteristic prosodic contour and is motivated most of the time by the need for food and by affecting the puppy-caregiver interaction, with a view to communicating the necessities and food requests and guaranteeing the survival of the species. The present work aims to articulate speech processing in the motor context with aspects of the project entitled emotional states and vocalization: a comparative study of the prosodic contours of crying in human and non-human animals. First, concepts of speech motor processing and general aspects of speech evolution will be presented to relate these two approaches to animal sound communication.

Keywords: speech motor processing, animal communication, animal behaviour, language acquisition

Procedia PDF Downloads 54

Authors: Yuanqing Li, Changyi Lei, Zhaopeng Xue, Zhuo Zheng, Yanbo Long

Abstract:

In agricultural production and breeding, implementing automatic picking robot in orchard farming to reduce human labour and error is challenging. The core function of it is automatic identification based on machine vision. This paper focuses on apple detection and counting in orchards and implements several deep learning methods. Extensive datasets are used and a semi-automatic annotation method is proposed. The proposed deep learning models are in state-of-the-art YOLO family. In view of the essence of the models with various backbones, a multi-dimensional comparison in details is made in terms of counting accuracy, mAP and model memory, laying the foundation for realising automatic precision agriculture.

Keywords: agricultural object detection, deep learning, machine vision, YOLO family

Procedia PDF Downloads 162

Authors: B.Shukir, H.Woo, P.Barzo, D.Kis

Abstract:

Preoperative brain mapping in tumors involving the speech areas has an important role to reduce surgical risks. Functional magnetic resonance imaging (fMRI) is the gold standard method to localize cortical speech areas preoperatively, but its availability in clinical routine is difficult. Diffusion MRI based probabilistic tractography is available in head MRI. It’s used to segment cortical subregions by their structural connectivity. In our study, we used probabilistic tractography to localize the frontal and temporal cortical speech areas. 15 patients with left frontal tumor were enrolled to our study. Speech fMRI and diffusion MRI acquired preoperatively. The standard automated anatomical labelling atlas 3 (AAL3) cortical atlas used to define 76 left frontal and 118 left temporal potential speech areas. 4 types of tractography were run according to the structural connection of these regions to the left arcuate fascicle (FA) to localize those cortical areas which have speech functions: 1, frontal through FA; 2, frontal with FA; 3, temporal to FA; 4, temporal with FA connections were determined. Thresholds of 1%, 5%, 10% and 15% applied. At each level, the number of affected frontal and temporal regions by fMRI and tractography were defined, the sensitivity and specificity were calculated. At the level of 1% threshold showed the best results. Sensitivity was 61,631,4% and 67,1523,12%, specificity was 87,210,4% and 75,611,37% for frontal and temporal regions, respectively. From our study, we conclude that probabilistic tractography is a reliable preoperative technique to localize cortical speech areas. However, its results are not feasible that the neurosurgeon rely on during the operation.

Keywords: brain mapping, brain tumor, fMRI, probabilistic tractography

Procedia PDF Downloads 123