Search results for: automatic recognition of speech

Authors: Akemi Nasu, Keiko Matsumoto

Abstract:

Rehabilitation for cancer requires setting up individual goals for each patient and an approach that properly fits the stage of cancer when putting into practice. In order to cope with the daily changes in the patients' condition, the establishment of a good cooperative relationship between the nurses and the physiotherapists, occupational therapists, and speech-language-hearing therapists (therapists) becomes essential. This study will focus on the present situation of the cooperation between nurses and therapists, especially the speech-language-hearing therapists, and aim to elucidate what develops there. A semi-structured interview was conducted targeted at a physical therapist having practical experience in working in collaboration with nurses. The contents of the interview were transcribed and converted to data, and the data was encoded and categorized with sequentially increasing degrees of abstraction to conduct a qualitative explorative factor analysis of the data. When providing ethical explanations, particular care was taken to ensure that participants would not be subjected to any disadvantages as a result of participating in the study. In addition, they were also informed that their privacy would be ensured and that they have the right to decline to participate in the study. In addition, they were also informed that the results of the study would be announced publicly at an applicable nursing academic conference. This study has been approved following application to the ethical committee of the university with which the researchers are affiliated. The survey participant is a female speech-language-hearing therapist in her forties. As a result of the analysis, 6 categories were extracted consisting of 'measures to address appetite and aspiration pneumonia prevention', 'limitation of the care a therapist alone could provide', 'the all-inclusive patient- supportive care provided by nurses', 'expand the beneficial cooperation with nurses', 'providing education for nurses on the swallowing function utilizing videofluoroscopic examination of swallowing', 'enhancement of communication including conferences'. In order to improve the team performance, and for the teamwork competency necessary for the provision of safer care, mutual support is essential. As for the cooperation between nurses and therapists, this survey indicates that the maturing of the cooperation between professionals in order to improve nursing professionals' knowledge and enhance communication will lead to an improvement in the quality of the rehabilitation for cancer.

Keywords: cancer rehabilitation, nurses, speech-language-hearing therapists, interprofessional work

Procedia PDF Downloads 133

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 269

Authors: Nami Takase

Abstract:

Computer-mediated-communication allows people to connect and interact with each other as if they were sharing the same space. The current study examined the effects of using video letters (VLs) on the development of second language speaking skills of Common European Framework of Reference for Languages (CEFR) A1 and CEFR B2 level learners of English as a foreign language. Two groups were formed to measure the impact of VLs. The experimental and control groups were given the same topic, and both groups worked with a native English-speaking university student from the United States of America. Students in the experimental group exchanged VLs, and students in the control group used video conferencing. Pre- and post-tests were conducted to examine the effects of each practice mode. The transcribed speech-text data showed that the VL group had improved speech accuracy scores, while the video conferencing group had increased sentence complexity scores. The use of VLs may be more effective for beginner-level learners because they are able to notice their own errors and replay videos to better understand the native speaker’s speech at their own pace. Both the VL and video conferencing groups provided positive feedback regarding their interactions with native speakers. The results showed how different types of computer-mediated communication impacts different areas of language learning and speaking practice and how each of these types of online communication tool is suited to different teaching objectives.

Keywords: computer-assisted-language-learning, computer-mediated-communication, english as a foreign language, speaking

Procedia PDF Downloads 99

Authors: Saad M. Darwish, Mohamed A. El-Iskandarani, Guitar M. Shawkat

Abstract:

Nowadays, the amount of available multimedia data is continuously on the rise. The need to find a required image for an ordinary user is a challenging task. Content based image retrieval (CBIR) computes relevance based on the visual similarity of low-level image features such as color, textures, etc. However, there is a gap between low-level visual features and semantic meanings required by applications. The typical method of bridging the semantic gap is through the automatic image annotation (AIA) that extracts semantic features using machine learning techniques. In this paper, a multi-label image annotation system guided by Firefly and Bayesian method is proposed. Firstly, images are segmented using the maximum variance intra cluster and Firefly algorithm, which is a swarm-based approach with high convergence speed, less computation rate and search for the optimal multiple threshold. Feature extraction techniques based on color features and region properties are applied to obtain the representative features. After that, the images are annotated using translation model based on the Net Bayes system, which is efficient for multi-label learning with high precision and less complexity. Experiments are performed using Corel Database. The results show that the proposed system is better than traditional ones for automatic image annotation and retrieval.

Keywords: feature extraction, feature selection, image annotation, classification

Procedia PDF Downloads 586

Authors: Dasom Kim, Chen Liu, Myungsu Lim, Su-Hyeon Jeon, ByeoungKug Jeon, Kee-Young Kwahk, Namgyu Kim

Abstract:

Recently, numerous documents including unstructured data and text have been created due to the rapid increase in the usage of social media and the Internet. Each document is usually provided with a specific category for the convenience of the users. In the past, the categorization was performed manually. However, in the case of manual categorization, not only can the accuracy of the categorization be not guaranteed but the categorization also requires a large amount of time and huge costs. Many studies have been conducted towards the automatic creation of categories to solve the limitations of manual categorization. Unfortunately, most of these methods cannot be applied to categorizing complex documents with multiple topics because the methods work by assuming that one document can be categorized into one category only. In order to overcome this limitation, some studies have attempted to categorize each document into multiple categories. However, they are also limited in that their learning process involves training using a multi-categorized document set. These methods therefore cannot be applied to multi-categorization of most documents unless multi-categorized training sets are provided. To overcome the limitation of the requirement of a multi-categorized training set by traditional multi-categorization algorithms, we previously proposed a new methodology that can extend a category of a single-categorized document to multiple categorizes by analyzing relationships among categories, topics, and documents. In this paper, we design a survey-based verification scenario for estimating the accuracy of our automatic categorization methodology.

Keywords: big data analysis, document classification, multi-category, text mining, topic analysis

Procedia PDF Downloads 272

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 153

Authors: Premvadee Na Nakornpanom

Abstract:

Language mixing in spontaneous speech has been widely discussed, but not in virtual situations; especially in context of the third language learning students. Thus, this study was an attempt to explore the characteristics of the mixing of Japanese, English and Thai in a mobile chat room by students with their background of Japanese, English, and Thai. The result found that Insertion of Thai and English content words was a very common linguistic phenomenon embedded in the utterances. As chatting is to be ‘relational’ or ‘interactional’, it affected the style of lexical choices to be speech-like, more personal and emotional-related. A Japanese sentence-final question particle“か”(ka) was added to the end of the sentence based on Thai grammar rule. Moreover, some unique characteristics were created. The non-verbal cues were represented in personal, Thai styles by inserting textual representations of images or feelings available on the websites into streams of conversations.

Keywords: code-mixing, Japanese, English, Thai, line chat

Procedia PDF Downloads 652

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 119

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: 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

Authors: Uswah Khairuddin, Rubiyah Yusof, Nenny Ruthfalydia Rosli

Abstract:

This paper presents a comparative study between k-Nearest Neighbour (k-NN) and Multi-Layer Perceptron Neural Network (MLP-NN) classifier using Genetic Algorithm (GA) as feature selector for wood recognition system. The features have been extracted from the images using Grey Level Co-Occurrence Matrix (GLCM). The use of GA based feature selection is mainly to ensure that the database used for training the features for the wood species pattern classifier consists of only optimized features. The feature selection process is aimed at selecting only the most discriminating features of the wood species to reduce the confusion for the pattern classifier. This feature selection approach maintains the ‘good’ features that minimizes the inter-class distance and maximizes the intra-class distance. Wrapper GA is used with k-NN classifier as fitness evaluator (GA-kNN). The results shows that k-NN is the best choice of classifier because it uses a very simple distance calculation algorithm and classification tasks can be done in a short time with good classification accuracy.

Keywords: feature selection, genetic algorithm, optimization, wood recognition system

Procedia PDF Downloads 545

Authors: Mafunda Esther

Abstract:

The paper seeks to find out and document the impact of culture and religion on disability, specifically language impairment and health care seeking practices of the Shona people. Its main objectives are to explore the cultural and religious beliefs that affect the utilization of rehabilitation services in a rural community in Zimbabwe. The other objective of the paper is to describe how language impairment is presented and understood by people living in a Zimbabwean rural area. The research is qualitative interpretive phenomenological research, and it utilizes the case study approach using semi structured interviews and focus group discussions. Results from the research established that religious and cultural beliefs determine how the Shona people view disability, and this guides their health care seeking practices. The research is important since communication disorders occur in populations worldwide though they are not always recognized as such. The lack of recognition of and the attitudes toward speech and languages disorders, as well as the beliefs about the causes of such disorders, affect people's attitudes toward the treatment of the disorders.

Keywords: culture, religion, disability, language impairment

Procedia PDF Downloads 98

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction

Procedia PDF Downloads 340

Authors: Awais Ahmad Khan, Emad Abouel Nasr, H. M. A. Hussein, Abdulrahman Al-Ahmari

Abstract:

Sheet-metal parts have been widely applied in electronics, communication and mechanical industries in recent decades; but the advancement in sheet-metal part design and manufacturing is still behind in comparison with the increasing importance of sheet-metal parts in modern industry. This paper presents a methodology for automatic extraction of some common 2D internal sheet metal features. The features used in this study are taken from Unipunch ™ catalogue. The extraction process starts with the data extraction from STEP file using an object oriented approach and with the application of suitable algorithms and rules, all features contained in the catalogue are automatically extracted. Since the extracted features include geometry and engineering information, they will be effective for downstream application such as feature rebuilding and process planning.

Keywords: feature extraction, internal features, punch shapes, sheet metal

Procedia PDF Downloads 616

Authors: Hadeer R. M. Tawfik, Rania A. K. Birry, Amani A. Saad

Abstract:

Eyes are considered to be the most sensitive and important organ for human being. Thus, any eye disorder will affect the patient in all aspects of life. Cataract is one of those eye disorders that lead to blindness if not treated correctly and quickly. This paper demonstrates a model for automatic detection, classification, and grading of cataracts based on image processing techniques and artificial intelligence. The proposed system is developed to ease the cataract diagnosis process for both ophthalmologists and patients. The wavelet transform combined with 2D Log Gabor Wavelet transform was used as feature extraction techniques for a dataset of 120 eye images followed by a classification process that classified the image set into three classes; normal, early, and advanced stage. A comparison between the two used classifiers, the support vector machine SVM and the artificial neural network ANN were done for the same dataset of 120 eye images. It was concluded that SVM gave better results than ANN. SVM success rate result was 96.8% accuracy where ANN success rate result was 92.3% accuracy.

Keywords: cataract, classification, detection, feature extraction, grading, log-gabor, neural networks, support vector machines, wavelet

Procedia PDF Downloads 332

Authors: Sean W. T. Bayly, Daniel Glover, Don Horrell, Simon Horrocks, Barnes Callum, Stuart Gibson, Mac Misuira

Abstract:

We assess suitability of recent, ∼7B parameter, instruction-tuned Language Models Mistral-v0.3, Llama-3, and Phi-3, for Generative Named Entity Recognition (GNER). Our proposed Multi-Level Information Retrieval method achieves notable improvements over finetuned entity-level and sentence-level methods. We consider recent developments at the cross roads of prompt engineering and Retrieval Augmented Generation (RAG), such as EmotionPrompt. We conclude that language models directed toward this task are highly capable when distinguishing between positive classes (precision). However, smaller models seem to struggle to find all entities (recall). Poorly defined classes such as ”Miscellaneous” exhibit substantial declines in performance, likely due to the ambiguity it introduces to the prompt. This is partially resolved through a self verification method using engineered prompts containing knowledge of the stricter class definitions, particularly in areas where their boundaries are in danger of overlapping, such as the conflation between the location ”Britain” and the nationality ”British”. Finally, we explore correlations between model performance on the GNER task with performance on relevant academic benchmarks.

Keywords: generative named entity recognition, information retrieval, lightweight artificial intelligence, prompt engineering, personal information identification, retrieval augmented generation, self verification

Procedia PDF Downloads 46

Authors: Payel Datta, Abhishek Das, Abhishek Roychoudhury, Dhiman Chattopadhyay, Tanushyam Chattopadhyay

Abstract:

Machine learning (ML) and deep learning (DL) is most predominantly used in image/video processing, natural language processing (NLP), audio and speech recognition but not that much used in system performance evaluation. In this paper, authors are going to describe the architecture of an abstraction layer constructed using ML/DL to detect the system failure. This proposed system is used to detect the system failure by evaluating the performance metrics of an IoT service deployment under constrained infrastructure environment. This system has been tested on the manually annotated data set containing different metrics of the system, like number of threads, throughput, average response time, CPU usage, memory usage, network input/output captured in different hardware environments like edge (atom based gateway) and cloud (AWS EC2). The main challenge of developing such system is that the accuracy of classification should be 100% as the error in the system has an impact on the degradation of the service performance and thus consequently affect the reliability and high availability which is mandatory for an IoT system. Proposed ML/DL classifiers work with 100% accuracy for the data set of nearly 4,000 samples captured within the organization.

Keywords: machine learning, system performance, performance metrics, IoT, edge

Procedia PDF Downloads 195

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 79

Authors: Megan Weisbart

Abstract:

Background/Significance: The Intensive Care Unit (ICU) environment contributes to nurse burnout. Burnout costs include decreased employee compassion, missed workdays, worse patient outcomes, diminished job performance, high turnover, and higher organizational cost. Meaningful recognition, nurturing of interpersonal connections, and mindfulness-based interventions are associated with decreased burnout. The purpose of this quality improvement project was to decrease Neonatal ICU (NICU) nurse burnout using a Wellness Bundle that fosters meaningful recognition, interpersonal connections and includes mindfulness-based interventions. Methods: The Professional Quality of Life Scale Version 5 (ProQOL5) was used to measure burnout before Wellness Bundle implementation, after six months, and will be given yearly for three years. Meaningful recognition bundle items include Online submission and posting of staff shoutouts, recognition events, Nurses Week and Unit Practice Council member gifts, and an employee recognition program. Fostering of interpersonal connections bundle items include: Monthly staff games with prizes, social events, raffle fundraisers, unit blog, unit wellness basket, and a wellness resource sheet. Quick coherence techniques were implemented at staff meetings and huddles as a mindfulness-based intervention. Findings: The mean baseline burnout score of 14 NICU nurses was 20.71 (low burnout). The baseline range was 13-28, with 11 nurses experiencing low burnout, three nurses experiencing moderate burnout, and zero nurses experiencing high burnout. After six months of the Wellness Bundle Implementation, the mean burnout score of 39 NICU nurses was 22.28 (low burnout). The range was 14-31, with 22 nurses experiencing low burnout, 17 nurses experiencing moderate burnout, and zero nurses experiencing high burnout. Conclusion: A NICU Wellness Bundle that incorporated meaningful recognition, fostering of interpersonal connections, and mindfulness-based activities was implemented to improve work environments and decrease nurse burnout. Participation bias and low baseline response rate may have affected the reliability of the data and necessitate another comparative measure of burnout in one year.

Keywords: burnout, NICU, nurse, wellness

Procedia PDF Downloads 87

Authors: Mairo Musa Galadima, Phoebe Mshelia

Abstract:

In Nigeria, the national policy of education stipulates that the kindergarten primary schools and the legislature are to use the three popular Nigerian Languages namely: Hausa, Igbo and Yoruba. However, the English language seems to be preferred and this calls for this paper. Attempts were made to draw out the challenges faced by learners in understanding English speech sounds and using them to communicate effectively in English; using 5(five) selected secondary school in Bauchi. It was discover that challenges abound in the wrong use of stress and intonation, transfer of phonetic features from their first language. Others are inadequate qualified teachers and relevant materials including text-books. It is recommended that teachers of English should lay more emphasis on the teaching of supra-segmental features and should be encouraged to go for further studies, seminars and refresher courses.

Keywords: kindergarten, stress, phonetic and intonation, Nigeria

Procedia PDF Downloads 300

Authors: Umair Rashid

Abstract:

Normally softmax loss is used as the supervision signal in face recognition (FR) system, and it boosts the separability of features. In the last two years, a number of techniques have been proposed by reformulating the original softmax loss to enhance the discriminating power of Deep Convolutional Neural Networks (DCNNs) for FR system. To learn angularly discriminative features Cosine-Margin based softmax has been adjusted as monotonically decreasing angular function, that is the main challenge for angular based softmax. On that issue, we propose monotonically decreasing element for Cosine-Margin based softmax and also, we discussed the effect of different monotonically decreasing parameters on angular Margin softmax for FR system. We train the model on publicly available dataset CASIA- WebFace via our proposed monotonically decreasing parameters for cosine function and the tests on YouTube Faces (YTF, Labeled Face in the Wild (LFW), VGGFace1 and VGGFace2 attain the state-of-the-art performance.

Keywords: deep convolutional neural networks, cosine margin face recognition, softmax loss, monotonically decreasing parameter

Procedia PDF Downloads 101

Authors: Subir Gupta, Subhas Ganguly

Abstract:

In this paper, we demonstrate the new area of application of image processing in metallurgical images to develop the more opportunity for structure-property correlation based approaches of alloy design. The present exercise focuses on the development of image processing tools suitable for phrase segmentation, grain boundary detection and recognition of micro-constituents in SEM micrographs of ferrite and pearlite steels. A comprehensive data of micrographs have been experimentally developed encompassing the variation of ferrite and pearlite volume fractions and taking images at different magnification (500X, 1000X, 15000X, 2000X, 3000X and 5000X) under scanning electron microscope. The variation in the volume fraction has been achieved using four different plain carbon steel containing 0.1, 0.22, 0.35 and 0.48 wt% C heat treated under annealing and normalizing treatments. The obtained data pool of micrographs arbitrarily divided into two parts to developing training and testing sets of micrographs. The statistical recognition features for ferrite and pearlite constituents have been developed by learning from training set of micrographs. The obtained features for microstructure pattern recognition are applied to test set of micrographs. The analysis of the result shows that the developed strategy can successfully detect the micro constitutes across the wide range of magnification and variation of volume fractions of the constituents in the structure with an accuracy of about +/- 5%.

Keywords: SEM micrograph, metallurgical image processing, ferrite pearlite steel, microstructure

Procedia PDF Downloads 199

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 132

Authors: Hailang Yang

Abstract:

To ensure the confidentiality and integrity of speech signals in communication transmission, this paper proposes a voice signal encryption scheme based on chaotic theory. Firstly, the scheme utilizes chaotic mapping to generate a key stream and then employs the key stream to perform bitwise exclusive OR (XOR) operations for encrypting the speech signal. Additionally, the scheme utilizes a chaotic hash function to generate a Message Authentication Code (MAC), which is appended to the encrypted data to verify the integrity of the data. Subsequently, we analyze the security performance and encryption efficiency of the scheme, comparing and optimizing it against existing solutions. Finally, experimental results demonstrate that the proposed scheme can resist common attacks, achieving high-quality encryption and speed.

Keywords: chaotic theory, XOR encryption, chaotic hash function, Message Authentication Code (MAC)

Procedia PDF Downloads 51

Authors: Hae-Yeoun Lee

Abstract:

Quantification of cardiac function is performed by calculating blood volume and ejection fraction in routine clinical practice. However, these works have been performed by manual contouring,which requires computational costs and varies on the observer. In this paper, an automatic left ventricle segmentation algorithm on cardiac magnetic resonance images (MRI) is presented. Using knowledge on cardiac MRI, a K-mean clustering technique is applied to segment blood region on a coil-sensitivity corrected image. Then, a graph searching technique is used to correct segmentation errors from coil distortion and noises. Finally, blood volume and ejection fraction are calculated. Using cardiac MRI from 15 subjects, the presented algorithm is tested and compared with manual contouring by experts to show outstanding performance.

Keywords: cardiac MRI, graph searching, left ventricle segmentation, K-means clustering

Procedia PDF Downloads 399

Authors: Fahad Suleiman

Abstract:

Queuing, in medical system is the process of moving patients in a specific sequence to a specific service according to the patients’ nature of illness. The term scheduling stands for the process of computing a schedule. This may be done by a queuing based scheduler. This paper focuses on the medical consultancy system, the different queuing algorithms that are used in healthcare system to serve the patients, and the average waiting time. The aim of this paper is to build automatic queuing system for organizing the medical queuing system that can analyses the queue status and take decision which patient to serve. The new queuing architecture model can switch between different scheduling algorithms according to the testing results and the factor of the average waiting time. The main innovation of this work concerns the modeling of the average waiting time is taken into processing, in addition with the process of switching to the scheduling algorithm that gives the best average waiting time.

Keywords: queuing systems, queuing system models, scheduling algorithms, patients

Procedia PDF Downloads 354

Authors: Bharati Mehta, Manish Parakh, Bharti Bhandari, Sneha Ambwani

Abstract:

Speech and language delay (SLD) is seen commonly as a co-morbidity in children having severe resistant focal and generalized, syndromic and symptomatic epilepsies. It is however not clear whether epilepsy contributes to or is a mere association in the pathogenesis of SLD. Also, it is acknowledged that Auditory Brainstem Evoked Responses (ABER), besides used for evaluating hearing threshold, also aid in prognostication of neurological disorders and abnormalities in the hearing pathway in the brainstem. There is no circumscribed or surrogate neurophysiologic laboratory marker to adjudge the extent of SLD. The current study was designed to evaluate the abnormalities in Electroencephalography (EEG) and ABER in children with SLD who do not have an overt hearing deficit or autism. 94 children of age group 2-8 years with predominant SLD and without any gross motor developmental delay, head injury, gross hearing disorder, cleft lip/palate and autism were selected. Standard video Electroencephalography using the 10:20 international system and ABER after click stimulus with intensities 110 db until 40 db was performed in all children. EEG was abnormal in 47.9% (n= 45; 36 boys and 9 girls) children. In the children with abnormal EEG, 64.5% (n=29) had an abnormal background, 57.8% (n=27) had presence of generalized interictal epileptiform discharges (IEDs), 20% (n=9) had focal epileptiform discharges exclusively from left side and 33.3% (n=15) had multifocal IEDs occurring both in isolation or associated with generalised abnormalities. In ABER, surprisingly, the peak latencies for waves I, III & V, inter-peak latencies I-III & I-V, III-V and wave amplitude ratio V/I, were found within normal limits in both ears of all the children. Thus in the current study it is certain that presence of generalized IEDs in EEG are seen in higher frequency with SLD and focal IEDs are seen exclusively in left hemisphere in these children. It may be possible that even with generalized EEG abnormalities present in these children, left hemispheric abnormalities as a part of this generalized dysfunction may be responsible for the speech and language dysfunction. The current study also emphasizes that ABER may not be routinely recommended as diagnostic or prognostic tool in children with SLD without frank hearing deficit or autism, thus reducing the burden on electro physiologists, laboratories and saving time and financial resources.

Keywords: ABER, EEG, speech, language delay

Procedia PDF Downloads 536

Authors: Mohammad Rahim Rahnama

Abstract:

Market-transaction price for housing is the main criteria for determining municipality taxes and is determined and announced on an annual basis. Of course, there is a discrepancy between the actual value of transactions in the Bureau of Finance (P for short) or municipality (P´ for short) and the real price on the market (P˝). The present research aims to determine the real price of housing in the metropolis of Mashhad and to pinpoint the price gap with those of the aforementioned apparatuses and identify the factors affecting it. In order to reach this practical objective, Automatic Linear Modeling, which calls for an explanatory research, was utilized. The population of the research consisted of all the residential units in Mashhad, from which 317 residential units were randomly selected. Through cluster sampling, out of the 170 income blocks defined by the municipality, three blocks form high-income (Kosar), middle-income (Elahieh), and low-income (Seyyedi) strata were surveyed using questionnaires during February and March of 2015 and the information regarding the price and specifications of residential units were gathered. In order to estimate the effect of various factors on the price, the relationship between independent variables (8 variables) and the dependent variable of the housing price was calculated using Automatic Linear Modeling in SPSS. The results revealed that the average for housing price index is 788$ per square meter, compared to the Bureau of Finance’s prices which is 10$ and that of municipality’s which is 378$. Correlation coefficient among dependent and independent variables was calculated to be R²=0.81. Out of the eight initial variables, three were omitted. The most influential factor affecting the housing prices is the quality of Quality of construction (Ordinary, Full, Luxury). The least important factor influencing the housing prices is the variable of number of sides. The price gap between low-income (Seyyedi) and middle-income (Elahieh) districts was not confirmed via One-Way ANOVA but their gap with the high-income district (Kosar) was confirmed. It is suggested that city be divided into two low-income and high-income sections, as opposed three, in terms of housing prices.

Keywords: automatic linear modeling, housing prices, Mashhad, Iran

Procedia PDF Downloads 255

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 562

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 643