Search results for: handwritten word recognition

Authors: Shaode Yu, Jiajian Meng, Bing Zhu, Hang Yu, Qiurui Sun

Abstract:

Speech emotion recognition (SER) is for recognizing human subjective emotions through audio data in-depth analysis. From speech audios, how to comprehensively extract emotional information and how to effectively fuse extracted features remain challenging. This paper presents a dual-stream SER framework that embraces both full training and transfer learning of different networks for thorough feature encoding. Besides, a plug-and-play cross-attention fusion (CAF) module is implemented for the valid integration of the dual-stream encoder output. The effectiveness of the proposed CAF module is compared to the other three fusion modules (feature summation, feature concatenation, and feature-wise linear modulation) on two databases (RAVDESS and IEMO-CAP) using different dual-stream encoders (full training network, DPCNN or TextRCNN; transfer learning network, HuBERT or Wav2Vec2). Experimental results suggest that the CAF module can effectively reconcile conflicts between features from different encoders and outperform the other three feature fusion modules on the SER task. In the future, the plug-and-play CAF module can be extended for multi-branch feature fusion, and the dual-stream SER framework can be widened for multi-stream data representation to improve the recognition performance and generalization capacity.

Keywords: speech emotion recognition, cross-attention fusion, dual-stream, pre-trained

Procedia PDF Downloads 79

Authors: Carmel Sofer, Dan Vilenchik, Ron Dotsch, Galia Avidan

Abstract:

Studies investigating emotional facial expressions typically reveal consensus among observes regarding the meaning of basic expressions, whose number ranges between 6 to 15 emotional states. Given this limited number of discrete expressions, how is it that the human vocabulary of emotional states is so rich? The present study argues that perceivers use sequences of these discrete expressions as the basis for a much richer vocabulary of emotional states. Such mechanisms, in which a relatively small number of basic components is expanded to a much larger number of possible combinations of meanings, exist in other human communications modalities, such as spoken language and music. In these modalities, letters and notes, which serve as basic components of spoken language and music respectively, are temporally linked, resulting in the richness of expressions. In the current study, in each trial participants were presented with sequences of two images containing facial expression in different combinations sampled out of the eight static basic expressions (total 64; 8X8). In each trial, using single word participants were required to judge the 'state of mind' portrayed by the person whose face was presented. Utilizing word embedding methods (Global Vectors for Word Representation), employed in the field of Natural Language Processing, and relying on machine learning computational methods, it was found that the perceived meanings of the sequences of facial expressions were a weighted average of the single expressions comprising them, resulting in 22 new emotional states, in addition to the eight, classic basic expressions. An interaction between the first and the second expression in each sequence indicated that every single facial expression modulated the effect of the other facial expression thus leading to a different interpretation ascribed to the sequence as a whole. These findings suggest that the vocabulary of emotional states conveyed by facial expressions is not restricted to the (small) number of discrete facial expressions. Rather, the vocabulary is rich, as it results from combinations of these expressions. In addition, present research suggests that using word embedding in social perception studies, can be a powerful, accurate and efficient tool, to capture explicit and implicit perceptions and intentions. Acknowledgment: The study was supported by a grant from the Ministry of Defense in Israel to GA and CS. CS is also supported by the ABC initiative in Ben-Gurion University of the Negev.

Keywords: Glove, face perception, facial expression perception. , facial expression production, machine learning, word embedding, word2vec

Procedia PDF Downloads 176

Authors: Beier Zhu, Rui Zhang, Qi Song

Abstract:

Text contained within fixed-layout documents can be of great semantic value and so requires a high localization accuracy, such as ID cards, invoices, cheques, and passports. Recently, algorithms based on deep convolutional networks achieve high performance on text detection tasks. However, for text localization in fixed-layout documents, such algorithms detect word bounding boxes individually, which ignores the layout information. This paper presents a novel architecture built on convolutional neural networks (CNNs). A global text localization network and a regional bounding-box regression network are introduced to tackle the problem in a coarse-to-fine manner. The text localization network simultaneously locates word bounding points, which takes the layout information into account. The bounding-box regression network inputs the features pooled from arbitrarily sized RoIs and refine the localizations. These two networks share their convolutional features and are trained jointly. A typical type of fixed-layout documents: ID cards, is selected to evaluate the effectiveness of the proposed system. These networks are trained on data cropped from nature scene images, and synthetic data produced by a synthetic text generation engine. Experiments show that our approach locates high accuracy word bounding boxes and achieves state-of-the-art performance.

Keywords: bounding box regression, convolutional networks, fixed-layout documents, text localization

Procedia PDF Downloads 198

Authors: Esther Chiramal, Kelvin Soh Boon Kai

Abstract:

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human-interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other hand, however, it also opens the door to locating possible vulnerabilities in an AI model. Traditional adversarial text attack uses word substitution, data augmentation techniques, and gradient-based attacks on powerful pre-trained Bidirectional Encoder Representations from Transformers (BERT) variants to generate adversarial sentences. These attacks are generally white-box in nature and not practical as they can be easily detected by humans e.g., Changing the word from “Poor” to “Rich”. We proposed a simple yet effective Grey-box cum Black-box approach that does not require the knowledge of the model while using a set of surrogate Transformer/BERT models to perform the attack using Explainable AI techniques. As Transformers are the current state-of-the-art models for almost all Natural Language Processing (NLP) tasks, an attack generated from BERT1 is transferable to BERT2. This transferability is made possible due to the attention mechanism in the transformer that allows the model to capture long-range dependencies in a sequence. Using the power of BERT generalisation via attention, we attempt to exploit how transformers learn by attacking a few surrogate transformer variants which are all based on a different architecture. We demonstrate that this approach is highly effective to generate semantically good sentences by changing as little as one word that is not detectable by humans while still fooling other BERT models.

Keywords: BERT, explainable AI, Grey-box text attack, transformer

Procedia PDF Downloads 138

Authors: Anderson Rocha, Pedro Miguel de Figueiredo Dinis Oliveira Gaspar

Abstract:

Machine vision has been widely used in recent years in agriculture, as a tool to promote the automation of processes and increase the levels of productivity. The aim of this work is the development of a path recognition algorithm based on image processing to guide a terrestrial robot in-between tree rows. The proposed algorithm was developed using the software MATLAB, and it uses several image processing operations, such as threshold detection, morphological erosion, histogram equalization and the Hough transform, to find edge lines along tree rows on an image and to create a path to be followed by a mobile robot. To develop the algorithm, a set of images of different types of orchards was used, which made possible the construction of a method capable of identifying paths between trees of different heights and aspects. The algorithm was evaluated using several images with different characteristics of quality and the results showed that the proposed method can successfully detect a path in different types of environments.

Keywords: agricultural mobile robot, image processing, path recognition, hough transform

Procedia PDF Downloads 147

Authors: Aiza Dalman

Abstract:

Words are powerful when these are used wisely and strategically. In this study, twelve (12) campaign speeches of President Donald J. Trump were analyzed as to frequently used words and ethos, pathos and logos being employed. The speeches were read thoroughly, analyzed and interpreted. With the use of Word Counter Tool and Text Analyzer software accessible online, it was found out that the word ‘will’ has the highest frequency of 121, followed by Hillary (58), American (38), going (35), plan and Clinton (32), illegal (30), government (28), corruption (26) and criminal (24). When the speeches were analyzed as to ethos, pathos and logos, on the other hand, it revealed that these were all employed in his speeches. The statements under these pointed out against Hillary or in his favor. The unique strategy of President Donald J. Trump as to frequently used words and ethos, pathos and logos in persuading people perhaps lead the way to his victory.

Keywords: campaign speeches, corpus analysis, ethos, logos and pathos, power of words

Procedia PDF Downloads 281

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 250

Authors: Hami-Ziniman Revital, Ashwall Rachelly

Abstract:

The conflict resolution realm has developed tremendously during the last half-decade. Three main approaches should be mentioned: an Alternative Dispute Resolution (ADR) suggesting processes such as Arbitration or Interests-based Negotiation was developed as an answer to obligations and rights-based conflicts. The Pragmatic mediation approach focuses on the gap between interests and needs of disputants. The Transformative mediation approach focusses on relations and suits identity-based conflicts. In the current study, we examine the conflictual relations between religious and non-religious Jews in Israel and the impact of three transformative mechanisms: Inter-group recognition, In-group empowerment and Value-based reframing on the relations between the participants. The research was conducted during four facilitated joint mediation classes. A unique finding was found. Using both transformative mechanisms and the Contact Hypothesis criteria, we identify transformation in participants’ relations and a considerable change from anger, alienation, and suspiciousness to an increased understanding, affection and interpersonal concern towards the out-group members. Intergroup Recognition, In-group empowerment, and Values-based reframing were the skills discovered as the main enablers of the change in the relations and the research participants’ fostered mutual recognition of the out-group values and identity-based issues. We conclude this transformation was possible due to a constant intergroup contact, based on the Contact Hypothesis criteria. In addition, as Interests-based mediation uses “Reframing” as a skill to acknowledge both mutual and opposite needs of the disputants, we suggest the use of “Value-based Reframing” in intergroup identity-based conflicts, as a skill contributes to the empowerment and the recognition of both mutual and different out-group values. We offer to implement those insights and skills to assist conflict resolution facilitators in various intergroup identity-based conflicts resolution efforts and to establish further research and knowledge.

Keywords: empowerment, identity-based conflict, intergroup recognition, intergroup relations, mediation skills, multi-cultural society, reframing, value-based recognition

Procedia PDF Downloads 343

Authors: Duong Thuy Nguyen, Giulia Bencini

Abstract:

The present study examined structural and prosodic factors on the computation of antecedent-reflexive relationships and sentence comprehension in native English (L1) and Vietnamese-English bilinguals (L2). Participants read sentences presented on the computer screen in one of three presentation formats aimed at manipulating prosodic parsing: word-by-word (RSVP), phrase-segment (self-paced), or whole-sentence (self-paced), then completed a grammaticality rating and a comprehension task (following Pratt & Fernandez, 2016). The design crossed three factors: syntactic structure (simple; complex), grammaticality (target-match; target-mismatch) and presentation format. An example item is provided in (1): (1) The actress that (Mary/John) interviewed at the awards ceremony (about two years ago/organized outside the theater) described (herself/himself) as an extreme workaholic). Results showed that overall, both L1 and L2 speakers made use of a good-enough processing strategy at the expense of more detailed syntactic analyses. L1 and L2 speakers’ comprehension and grammaticality judgements were negatively affected by the most prosodically disrupting condition (word-by-word). However, the two groups demonstrated differences in their performance in the other two reading conditions. For L1 speakers, the whole-sentence and the phrase-segment formats were both facilitative in the grammaticality rating and comprehension tasks; for L2, compared with the whole-sentence condition, the phrase-segment paradigm did not significantly improve accuracy or comprehension. These findings are consistent with the findings of Pratt & Fernandez (2016), who found a similar pattern of results in the processing of subject-verb agreement relations using the same experimental paradigm and prosodic manipulation with English L1 and L2 English-Spanish speakers. The results provide further support for a Good-Enough cue model of sentence processing that integrates cue-based retrieval and implicit prosodic parsing (Pratt & Fernandez, 2016) and highlights similarities and differences between L1 and L2 sentence processing and comprehension.

Keywords: anaphora resolution, bilingualism, implicit prosody, sentence processing

Procedia PDF Downloads 152

Authors: Sebastião Pais, João Casal, Ricardo Ponciano, Sérgio Lorenço

Abstract:

The adaptation paradigm is a basic defining feature for pervasive computing systems. Adaptation systems must work efficiently in a smart environment while providing suitable information relevant to the user system interaction. The key objective is to deduce the information needed information changes. Therefore relying on fixed operational models would be inappropriate. This paper presents a study on developing an Intelligent Personal Assistant to assist the user in interacting with their Smart Environment. We propose an Unsupervised and Language-Independent Adaptation through Intelligent Speech Interface and a set of methods of Acquiring Knowledge, namely Semantic Similarity and Unsupervised Learning.

Keywords: intelligent personal assistants, intelligent speech interface, unsupervised learning, language-independent, knowledge acquisition, association measures, symmetric word similarities, attributional word similarities

Procedia PDF Downloads 564

Authors: Samuel Mwangi, Josephine K. Mule

Abstract:

Access control as a security technique regulates who or what can access resources. It is a fundamental concept in security that minimizes risks to the institutions that use access control. Regulating access to institutions of higher learning is key to ensure only authorized personnel and students are allowed into the institutions. The use of biometrics has been criticized due to the setup and maintenance costs, hygiene concerns, and trepidations regarding data privacy, among other apprehensions. Facial recognition is arguably a fast and accurate way of validating identity in order to guard protected areas. It guarantees that only authorized individuals gain access to secure locations while requiring far less personal information whilst providing an additional layer of security beyond keys, fobs, or identity cards. This exploratory study sought to investigate the use of facial recognition in controlling access in institutions of higher learning in Kenya. The sample population was drawn from both private and public higher learning institutions. The data is based on responses from staff and students. Questionnaires were used for data collection and follow up interviews conducted to understand responses from the questionnaires. 80% of the sampled population indicated that there were many security breaches by unauthorized people, with some resulting in terror attacks. These security breaches were attributed to stolen identity cases, where staff or student identity cards were stolen and used by criminals to access the institutions. These unauthorized accesses have resulted in losses to the institutions, including reputational damages. The findings indicate that security breaches are a major problem in institutions of higher learning in Kenya. Consequently, access control would be beneficial if employed to curb security breaches. We suggest the use of facial recognition technology, given its uniqueness in identifying users and its non-repudiation capabilities.

Keywords: facial recognition, access control, technology, learning

Procedia PDF Downloads 127

Authors: Sebastião Pais, João Casal, Ricardo Ponciano, Sérgio Lourenço

Abstract:

The adaptation paradigm is a basic defining feature for pervasive computing systems. Adaptation systems must work efficiently in smart environment while providing suitable information relevant to the user system interaction. The key objective is to deduce the information needed information changes. Therefore, relying on fixed operational models would be inappropriate. This paper presents a study on developing a Intelligent Personal Assistant to assist the user in interacting with their Smart Environment. We propose a Unsupervised and Language-Independent Adaptation through Intelligent Speech Interface and a set of methods of Acquiring Knowledge, namely Semantic Similarity and Unsupervised Learning.

Keywords: intelligent personal assistants, intelligent speech interface, unsupervised learning, language-independent, knowledge acquisition, association measures, symmetric word similarities, attributional word similarities

Procedia PDF Downloads 645

Authors: Shweta Pinjarkar, Shrutika Yawale, Mayuri Patil, Reshma Adagale

Abstract:

Face recognition is the technique which can be applied to the wide variety of problems like image and film processing, human computer interaction, criminal identification etc. This has motivated researchers to develop computational models to identify the faces, which are easy and simple to implement. In this, demonstrates the face recognition system in android device using eigenface. The system can be used as the base for the development of the recognition of human identity. Test images and training images are taken directly with the camera in android device.The test results showed that the system produces high accuracy. The goal is to implement model for particular face and distinguish it with large number of stored faces. face recognition system detects the faces in picture taken by web camera or digital camera and these images then checked with training images dataset based on descriptive features. Further this algorithm can be extended to recognize the facial expressions of a person.recognition could be carried out under widely varying conditions like frontal view,scaled frontal view subjects with spectacles. The algorithm models the real time varying lightning conditions. The implemented system is able to perform real-time face detection, face recognition and can give feedback giving a window with the subject's info from database and sending an e-mail notification to interested institutions using android application. Face recognition is the technique which can be applied to the wide variety of problems like image and film processing, human computer interaction, criminal identification etc. This has motivated researchers to develop computational models to identify the faces, which are easy and simple to implement. In this , demonstrates the face recognition system in android device using eigenface. The system can be used as the base for the development of the recognition of human identity. Test images and training images are taken directly with the camera in android device.The test results showed that the system produces high accuracy. The goal is to implement model for particular face and distinguish it with large number of stored faces. face recognition system detects the faces in picture taken by web camera or digital camera and these images then checked with training images dataset based on descriptive features. Further this algorithm can be extended to recognize the facial expressions of a person.recognition could be carried out under widely varying conditions like frontal view,scaled frontal view subjects with spectacles. The algorithm models the real time varying lightning conditions. The implemented system is able to perform real-time face detection, face recognition and can give feedback giving a window with the subject's info from database and sending an e-mail notification to interested institutions using android application.

Keywords: face detection, face recognition, eigen faces, algorithm

Procedia PDF Downloads 361

Authors: Jennifer De Paola

Abstract:

Objectives: The literature is saturated with figures and hard data on happiness and its rates, causes and effects at a large scale, whereas very little is known about the way specific groups of people within societies understand and talk about happiness in their everyday life. The present study contributes to fill this gap in the happiness research by analyzing social representations of happiness among young women through the theoretical frame provided by Moscovici’s Social Representation Theory. Methods: Participants were (N= 351) female students (16-18 year olds) from Finnish, Swedish and English speaking high schools in the Helsinki region, Finland. Main source of data collection were word associations using the stimulus word ‘happiness’ and word associations using as stimulus the term that in the participants’ opinion represents the opposite of happiness. The allowed number of associations was five per stimulus word (10 associations per participant). In total, the 351 participants produced 6973 associations with the two stimulus words given: 3500 (50,19%) associations with ‘happiness’ and 3473 (49,81%) associations with ‘opposite of happiness’. The associations produced were analyzed qualitatively to identify associations with similar meaning and then coded combining similar associations in larger categories. Results: In total, 33 categories were identified respectively for the stimulus word ‘happiness’ and for the stimulus word ‘opposite of happiness’. In general terms, the 33 categories identified for ‘happiness’ included associations regarding relationships with key people considered important, such as ‘family’, abstract concepts such as meaningful life, success and moral values as well as more mundane and hedonic elements like food, pleasure and fun. Similarly, the 33 categories emerged for ‘opposite of happiness’ included relationship problems and arguments, negative feelings such as sadness, depression, stress as well as more concrete issues such as financial problems. Participants were also asked to rate their own level of happiness on a scale from 1 to 10. Results indicated the mean of the self-rated level of happiness was 7,93 (the range varied from 1 to 10; SD = 1, 50). Participants’ responses were further divided into three different groups according to the self-rated level of happiness: group 1 (level 10-9), group 2 (level 8-6), and group 3 (level 5 and lower) in order to investigate the way the categories mentioned above were distributed among the different groups. Preliminary results show that the category ‘family’ is associated with higher level of happiness, whereas its presence gradually decreases among the participants with a lower level of happiness. Moreover, the category ‘depression’ seems to be mainly present among participants in group 3, whereas the category ‘sadness’ is mainly present among participants with higher level of happiness. Conclusion: In conclusion, this study indicates the prevalent ways of thinking about happiness and its opposite among young female students, suggesting that representations varied to some extent depending on the happiness level of the participants. This study contributes to bringing new knowledge as it considers happiness as a holistic state, thus going beyond the literature that so far has too often viewed happiness as a mere unidimensional spectrum.

Keywords: female, happiness, social representations, unhappiness

Procedia PDF Downloads 227

Authors: El Sayed A. Sharara, A. Tsuji, K. Terada

Abstract:

Call centers have been expanding and they have influence on activation in various markets increasingly. A call center’s work is known as one of the most demanding and stressful jobs. In this paper, we propose the fatigue detection system in order to detect burnout of call center agents in the case of a neck pain and upper back pain. Our proposed system is based on the computer vision technique combined skin color detection with the Viola-Jones object detector. To recognize the gesture of hand poses caused by stress sign, the YCbCr color space is used to detect the skin color region including face and hand poses around the area related to neck ache and upper back pain. A cascade of clarifiers by Viola-Jones is used for face recognition to extract from the skin color region. The detection of hand poses is given by the evaluation of neck pain and upper back pain by using skin color detection and face recognition method. The system performance is evaluated using two groups of dataset created in the laboratory to simulate call center environment. Our call center agent burnout detection system has been implemented by using a web camera and has been processed by MATLAB. From the experimental results, our system achieved 96.3% for upper back pain detection and 94.2% for neck pain detection.

Keywords: call center agents, fatigue, skin color detection, face recognition

Procedia PDF Downloads 295

Authors: James Rigor Camacho, Wansu Lim

Abstract:

Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.

Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors

Procedia PDF Downloads 107

Authors: Jonathan A. Mikhail, Arsenio Paez

Abstract:

It is not uncommon for a viral infection to cause hearing loss. Many viral infections are associated with sudden-onset, often unilateral, idiopathic sensorineural hearing loss. We conducted an exploratory study with thirty patients with pre-existing hearing loss between 50 and 64 to evaluate if COVID-19 was associated with exacerbated hearing loss. We hypothesized that hearing loss would be exacerbated by COVID-19 infection in patients with pre-existing hearing loss. A statistically significant paired T-test between pure tone averages (PTAs) at the patient’s original diagnosis and a current, updated audiometric assessment indicated a regression in hearing (p-value < .001) sensitivity following the contraction of COVID-19. Speech reception thresholds (SRTs) and word recognition scores (WRSs) were also considered, as well as the participants' gender. SRTs between each ear exhibited a statistically significant change (p-value of .002 and p-value < .001). WRSs did not show statistically significant differences (p-value of .290 and p-value of .098). A non-statistically significant Two-Way ANOVA was performed to evaluate gender’s potential role in exacerbated hearing loss and proved to be statistically insignificant (p-value of .214). This study discusses practical implications for clinical and educational pursuits in understanding COVID-19's effect on the auditory system and the need to evaluate the deadly virus further.

Keywords: audiology, COVID-19, sensorineural hearing loss, otology, auditory research

Procedia PDF Downloads 80

Authors: Biraj Puri, Bikram Puri

Abstract:

Arbitration is one of the prompt and efficient methods of alternative dispute resolution, especially of a commercial nature, by a neutral arbitrator outside the formal court structure. Due to the globalization of trade, privatization, and global investment, recognition and enforcement of foreign arbitral awards attract prime concern. Arbitral awards are generally based on arguments and evidence presented by disputing parties. The foreign investor wants to secure the investment by appropriate legal measures and an amicable way of dispute settlement if it arises. Now, arbitration as a mechanism of commercial dispute settlement has gained international recognition. It can take place in any State, in any language and with arbitrators of any nationality. There are various international institutions to conduct arbitral proceedings and render awards. Once an arbitral award is delivered, it can be enforced as a court judgment. However, it is really challenging to execute foreign arbitral awards in Nepal. Any party willing to execute an award made in a foreign country in Nepal should submit an application to the High Court along with essential documents prescribed by domestic law (The Arbitration Act 1999). Arbitrarily and public policy are also the requirements regarding the recognition and enforcement of foreign arbitral awards in Nepal. Nepal is a signatory State to the New York Convention on Recognition and Enforcement of Foreign Arbitral Awards, 1958. It is crucial to acknowledge that Nepal has liberalized its economy as well as opened the door for a liberal and market-oriented economy through the Constitution of Nepal, 2015. Nepal is trying to expand business from local to global level. Commercial trade is expanding day by day. So in this context, acceptance of arbitration as an alternative means to solve commercial disputes is a matter of prime importance. India ratified the New York Convention, and also being a neighborhood country of Nepal, in practice, does not enforce arbitral awards provided by Nepal in the name of reservation. India has published a gazette notice in which it lists the countries in which the award will be recognized in India, but it does not include Nepal. As the largest trade partner of Nepal, India should rethink this in order to make trade smooth.

Keywords: commercial arbitration, foreign arbitral awards, recognition and enforcement of foreign arbitral awards, requirements

Procedia PDF Downloads 5

Authors: Amin Pashaye Amiri

Abstract:

Freedom of information, according to which the public has a right to have access to government-held information, is largely considered as a tool for improving transparency and accountability in governments, and as a requirement of self-governance and good governance. So far, more than ninety countries have recognized citizens’ right to have access to public information. This recognition often took place through the adoption of an act referred to as “freedom of information act”, “access to public records act”, and so on. A freedom of information act typically imposes a positive obligation on a government to initially and regularly release certain public information, and also obliges it to provide individuals with information they request. Such an act usually allows governmental bodies to withhold information only when it falls within a limited number of exemptions enumerated in the act such as exemptions for protecting privacy of individuals and protecting national security. Some steps have been taken at the national and international level towards the recognition of freedom of information as a human right. Freedom of information was recognized in a few countries as a part of freedom of expression, and therefore, as a human right. Freedom of information was also recognized by some international bodies as a human right. The Inter-American Court of Human Rights ruled in 2006 that Article 13 of the American Convention on Human Rights, which concerns the human right to freedom of expression, protects the right of all people to request access to government information. The European Court of Human Rights has recently taken a considerable step towards recognizing freedom of information as a human right. However, in spite of the measures that have been taken, public access to government information is not yet widely accepted as an international human right. The paper will consider the degree to which freedom of information has been recognized as a human right, and study the possibility of widespread recognition of such a human right in the future. It will also examine the possible benefits of such recognition for the development of the human right to free expression.

Keywords: freedom of information, freedom of expression, human rights, government information

Procedia PDF Downloads 550

Authors: Sang-Keun Moon, Hong-Rok Lim, Jin-O Kim

Abstract:

This paper presents a Power Quality (PQ) modeling and filtering processes for the distribution system disturbances using recognition learning methods. Typical PQ waveforms with mathematical applications and gathered field data are applied to the proposed models. The objective of this paper is analyzing PQ data with respect to monitoring, discriminating, and evaluating the waveform of power disturbances to ensure the system preventative system failure protections and complex system problem estimations. Examined signal filtering techniques are used for the field waveform noises and feature extractions. Using extraction and learning classification techniques, the efficiency was verified for the recognition of the PQ disturbances with focusing on interactive modeling methods in this paper. The waveform of selected 8 disturbances is modeled with randomized parameters of IEEE 1159 PQ ranges. The range, parameters, and weights are updated regarding field waveform obtained. Along with voltages, currents have same process to obtain the waveform features as the voltage apart from some of ratings and filters. Changing loads are causing the distortion in the voltage waveform due to the drawing of the different patterns of current variation. In the conclusion, PQ disturbances in the voltage and current waveforms indicate different types of patterns of variations and disturbance, and a modified technique based on the symmetrical components in time domain was proposed in this paper for the PQ disturbances detection and then classification. Our method is based on the fact that obtained waveforms from suggested trigger conditions contain potential information for abnormality detections. The extracted features are sequentially applied to estimation and recognition learning modules for further studies.

Keywords: power quality recognition, PQ modeling, waveform feature extraction, disturbance trigger condition, PQ signal filtering

Procedia PDF Downloads 188

Authors: Ons Slimene, Aroua Taamallah, Maha Khemaja

Abstract:

In recent years, human activity recognition (HAR) has been a key area of research due to its diverse applications. It has garnered increasing attention in the field of computer vision. HAR plays an important role in people’s daily lives as it has the ability to learn advanced knowledge about human activities from data. In HAR, activities are usually represented by exploiting different types of sensors, such as embedded sensors or visual sensors. However, these sensors have limitations, such as local obstacles, image-related obstacles, sensor unreliability, and consumer concerns. Recently, several deep learning-based approaches have been proposed for HAR and these approaches are classified into two categories based on the type of data used: vision-based approaches and sensor-based approaches. This research paper highlights the importance of multimodal data fusion from skeleton data obtained from videos and data generated by embedded sensors using deep neural networks for achieving HAR. We propose a deep multimodal fusion network based on a twostream architecture. These two streams use the Convolutional Neural Network combined with the Bidirectional LSTM (CNN BILSTM) to process skeleton data and data generated by embedded sensors and the fusion at the feature level is considered. The proposed model was evaluated on a public OPPORTUNITY++ dataset and produced a accuracy of 96.77%.

Keywords: human activity recognition, action recognition, sensors, vision, human-centric sensing, deep learning, context-awareness

Procedia PDF Downloads 102

Authors: Fadhl Qutaish

Abstract:

This paper examines the pharyngealization spread in one of the Yemeni Arabic dialects, namely, Ibbi Arabic (IA). It investigates how pharyngealized sounds spread their acoustic features onto the neighboring vowels and change their default features. This feature has been investigated quietly well in MSA but still has to be deeply studied in the different dialect of Arabic which will bring about a clearer picture of the similarities and the differences among these dialects and help in mapping them based on the way this feature is utilized. Though the studies are numerous, no one of them has illustrated how far in the multi-syllabic word the spread can be and whether it takes a steady or gradient manner. This study tries to fill this gap and give a satisfactory explanation of the pharyngealization spread in Ibbi Dialect. This study is the first step towards a larger investigation of the different dialects of Yemeni Arabic in the future. The data recorded are represented in minimal pairs in which the trigger (pharyngealized or the non-pharyngealized sound) is in the initial or final position of monosyllabic and multisyllabic words. A group of 24 words were divided into four groups and repeated three times by three subjects which will yield 216 tokens that are tested and analyzed. The subjects are three male speakers aged between 28 and 31 with no history of neurological, speaking or hearing problems. All of them are bilingual speakers of Arabic and English and native speakers of Ibbi-Dialect. Recordings were done in a sound-proof room and praat software was used for the analysis and coding of the trajectories of F1 and F2 for the low vowel /a/ to see the effect of pharyngealization on the formant trajectory within the same syllable and in other syllables of the same word by comparing the F1 and F2 formants to the non-pharyngealized environment. The results show that pharyngealization spread is gradient (progressively and regressively). The spread is reflected in the gradual raising of F1 as we move closer towards the trigger and the gradual lowering of F2 as well. The results of the F1 mean values in tri-syllabic words when the trigger is word initially show that there is a raise of 37.9 HZ in the first syllable, 26.8HZ in the second syllable and 14.2HZ in the third syllable. F2 mean values undergo a lowering of 239 HZ in the first syllable, 211.7 HZ in the second syllable and 176.5 in the third syllable. This gradual decrease in the difference of F2 values in the non-pharyngealized and pharyngealized context illustrates that the spread is gradient. A similar result was found when the trigger is word-final which proves that the spread is gradient (progressively and regressively.

Keywords: pharyngealization, Yemeni Arabic, Ibbi dialect, pharyngealization spread

Procedia PDF Downloads 223

Authors: Tuiana A. Aiusheeva, Sergey S. Tamozhnikov, Alexander E. Saprygin, Arina A. Antonenko, Valentina V. Stepanova, Natalia N. Tolstykh, Alexander N. Savostyanov

Abstract:

Situation of choice is an important condition for the formation of essential character qualities of a child, such as being initiative, responsible, hard-working. We have studied the behavioral and EEG reactions in Russian schoolchildren during recognition of syntactic errors in emotionally colored sentences that describe the choice situation. Twenty healthy children (mean age 9,0±0,3 years, 12 boys, 8 girls) were examined. Forty sentences were selected for the experiment; the half of them contained a syntactic error. The experiment additionally had the hidden condition: 50% of the sentences described the children's own choice and were emotionally colored (positive or negative). The other 50% of the sentences described the forced-choice situation, also with positive or negative coloring. EEG were recorded during execution of error-recognition task. Reaction time and quality of syntactic error detection were chosen as behavioral measures. Event-related spectral perturbation (ERSP) was applied to characterize the oscillatory brain activity of children. There were two time-frequency intervals in EEG reactions: (1) 500-800 ms in the 3-7 Hz frequency range (theta synchronization) and (2) 500-1000 ms in the 8-12 Hz range (alpha desynchronization). We found out that behavioral and brain reactions in child brain during recognition of positive and negative sentences describing forced-choice situation did not have significant differences. Theta synchronization and alpha desynchronization were stronger during recognition of sentences with children's own choice, especially with negative coloring. Also, the quality and execution time of the task were higher for this types of sentences. The results of our study will be useful for improvement of teaching methods and diagnostics of children affective disorders.

Keywords: choice situation, electroencephalogram (EEG), emotionally colored sentences, schoolchildren

Procedia PDF Downloads 271

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 155

Authors: Xiaoxiao Li, Shuangcheng Jia, Qian Li

Abstract:

Keypoint detection has always been a challenge in the field of image recognition. This paper proposes a novelty keypoint detection method which is called Multi-Scale Feature Fusion Convolutional Network with Attention (MFFCNA). We verified that the multi-scale features with the attention mechanism module have better feature expression capability. The feature fusion between different scales makes the information that the network model can express more abundant, and the network is easier to converge. On our self-made street sign corner dataset, we validate the MFFCNA model with an accuracy of 97.8% and a recall of 81%, which are 5 and 8 percentage points higher than the HRNet network, respectively. On the COCO dataset, the AP is 71.9%, and the AR is 75.3%, which are 3 points and 2 points higher than HRNet, respectively. Extensive experiments show that our method has a remarkable improvement in the keypoint recognition tasks, and the recognition effect is better than the existing methods. Moreover, our method can be applied not only to keypoint detection but also to image classification and semantic segmentation with good generality.

Keywords: keypoint detection, feature fusion, attention, semantic segmentation

Procedia PDF Downloads 120

Authors: Khadijat T. Bamigbade, Olufade F. W. Onifade

Abstract:

The field of automatic facial expression analysis has been an active research area in the last two decades. Its vast applicability in various domains has drawn so much attention into developing techniques and dataset that mirror real life scenarios. Many techniques such as Local Binary Patterns and its variants (CLBP, LBP-TOP) and lately, deep learning techniques, have been used for facial expression recognition. However, the problem of occlusion has not been sufficiently handled, making their results not applicable in real life situations. This paper develops a simple, yet highly efficient method tagged Local Binary Pattern-Histogram of Gradient (LBP-HOG) with occlusion detection in face image, using a multi-class SVM for Action Unit and in turn expression recognition. Our method was evaluated on three publicly available datasets which are JAFFE, CK, SFEW. Experimental results showed that our approach performed considerably well when compared with state-of-the-art algorithms and gave insight to occlusion detection as a key step to handling expression in wild.

Keywords: automatic facial expression analysis, local binary pattern, LBP-HOG, occlusion detection

Procedia PDF Downloads 171

Authors: Nassib Abdallah, Pierre Chauvet, Abd El Salam Hajjar, Bassam Daya

Abstract:

In this paper, we propose an optimized brain computer interface (BCI) system for unspoken speech recognition, based on the fact that the constructions of unspoken words rely strongly on the Wernicke area, situated in the temporal lobe. Our BCI system has four modules: (i) the EEG Acquisition module based on a non-invasive headset with 14 electrodes; (ii) the Preprocessing module to remove noise and artifacts, using the Common Average Reference method; (iii) the Features Extraction module, using Wavelet Packet Transform (WPT); (iv) the Classification module based on a one-hidden layer artificial neural network. The present study consists of comparing the recognition accuracy of 5 Arabic words, when using all the headset electrodes or only the 4 electrodes situated near the Wernicke area, as well as the selection effect of the subbands produced by the WPT module. After applying the articial neural network on the produced database, we obtain, on the test dataset, an accuracy of 83.4% with all the electrodes and all the subbands of 8 levels of the WPT decomposition. However, by using only the 4 electrodes near Wernicke Area and the 6 middle subbands of the WPT, we obtain a high reduction of the dataset size, equal to approximately 19% of the total dataset, with 67.5% of accuracy rate. This reduction appears particularly important to improve the design of a low cost and simple to use BCI, trained for several words.

Keywords: brain-computer interface, speech recognition, artificial neural network, electroencephalography, EEG, wernicke area

Procedia PDF Downloads 272

Authors: Youhang Zhou, Weimin Zeng, Qi Xie

Abstract:

Abstract: In order to solve the wear recognition problem of the machine tool guide surface, a new machine tool guide surface recognition method based on the radar-graph barycentre feature is presented in this paper. Firstly, the gray mean value, skewness, projection variance, flat degrees and kurtosis features of the guide surface image data are defined as primary characteristics. Secondly, data Visualization technology based on radar graph is used. The visual barycentre graphical feature is demonstrated based on the radar plot of multi-dimensional data. Thirdly, a classifier based on the support vector machine technology is used, the radar-graph barycentre feature and wear original feature are put into the classifier separately for classification and comparative analysis of classification and experiment results. The calculation and experimental results show that the method based on the radar-graph barycentre feature can detect the guide surface effectively.

Keywords: guide surface, wear defects, feature extraction, data visualization

Procedia PDF Downloads 519

Authors: Sara T. K. Li, Belinda H. J. Chung, Jeffery C. N. Yip, Janet H. Hsiao

Abstract:

Music notation and text reading both involve statistical learning of music or linguistic structures. However, it remains unclear how music reading expertise influences text reading behavior. The present study examined this issue through an eye-tracking study. Chinese-English bilingual musicians and non-musicians read English sentences, Chinese sentences, musical phrases, and sentences in Tibetan, a language novel to the participants, with their eye movement recorded. Each set of stimuli consisted of two conditions in terms of structural regularity: syntactically correct and syntactically incorrect musical phrases/sentences. They then completed a sentence comprehension (for syntactically correct sentences) or a musical segment/word recognition task afterwards to test their comprehension/recognition abilities. The results showed that in reading musical phrases, as compared with non-musicians, musicians had a higher accuracy in the recognition task, and had shorter reading time, fewer fixations, and shorter fixation duration when reading syntactically correct (i.e., in diatonic key) than incorrect (i.e., in non-diatonic key/atonal) musical phrases. This result reflects their expertise in music reading. Interestingly, in reading Tibetan sentences, which was novel to both participant groups, while non-musicians did not show any behavior differences between reading syntactically correct or incorrect Tibetan sentences, musicians showed a shorter reading time and had marginally fewer fixations when reading syntactically correct sentences than syntactically incorrect ones. However, none of the musicians reported discovering any structural regularities in the Tibetan stimuli after the experiment when being asked explicitly, suggesting that they may have implicitly acquired the structural regularities in Tibetan sentences. This group difference was not observed when they read English or Chinese sentences. This result suggests that music reading expertise facilities reading texts in a novel language (i.e., Tibetan), but not in languages that the readers are already familiar with (i.e., English and Chinese). This phenomenon may be due to the similarities between reading music notations and reading texts in a novel language, as in both cases the stimuli follow particular statistical structures but do not involve semantic or lexical processing. Thus, musicians may transfer their statistical learning skills stemmed from music notation reading experience to implicitly discover structures of sentences in a novel language. This speculation is consistent with a recent finding showing that music reading expertise modulates the processing of English nonwords (i.e., words that do not follow morphological or orthographic rules) but not pseudo- or real words. These results suggest that the modulation of music reading expertise on language processing depends on the similarities in the cognitive processes involved. It also has important implications for the benefits of music education on language and cognitive development.

Keywords: eye movement behavior, eye-tracking, music reading expertise, sentence reading, structural regularity, visual processing

Procedia PDF Downloads 383

Authors: Ria Ghosh, Soumendra Singh, Dipanjan Mukherjee, Susmita Mondal, Monojit Das, Uttam Pal, Aniruddha Adhikari, Aman Bhushan, Surajit Bose, Siddharth Sankar Bhattacharyya, Debasish Pal, Tanusri Saha-Dasgupta, Maitree Bhattacharyya, Debasis Bhattacharyya, Asim Kumar Mallick, Ranjan Das, Samir Kumar Pal

Abstract:

Drug delivery to a target without adverse effects is one of the major criteria for clinical use. Herein, we have made an attempt to explore the delivery efficacy of SDS surfactant in a monomer and micellar stage during the delivery of the model drug, Toluidine Blue (TB) from the micellar cavity to DNA. Molecular recognition of pre-micellar SDS encapsulated TB with DNA occurs at a rate constant of k1 ~652 s 1. However, no significant release of encapsulated TB at micellar concentration was observed within the experimental time frame. This originated from the higher binding affinity of TB towards the nano-cavity of SDS at micellar concentration which does not allow the delivery of TB from the nano-cavity of SDS micelles to DNA. Thus, molecular recognition controls the extent of DNA recognition by TB which in turn modulates the rate of delivery of TB from SDS in a concentration-dependent manner.

Keywords: DNA, drug delivery, micelle, pre-micelle, SDS, toluidine blue

Procedia PDF Downloads 113