Search results for: multimodal transformer autoencoder

Authors: Pingping Lin, Xudong Luo, Yifan Fan

Abstract:

Sentiment analysis is a very active research topic. Every day, Facebook, Twitter, Weibo, and other social media, as well as significant e-commerce websites, generate a massive amount of comments, which can be used to analyse peoples opinions or emotions. The existing methods for sentiment analysis are based mainly on sentiment dictionaries, machine learning, and deep learning. The first two kinds of methods rely on heavily sentiment dictionaries or large amounts of labelled data. The third one overcomes these two problems. So, in this paper, we focus on the third one. Specifically, we survey various sentiment analysis methods based on convolutional neural network, recurrent neural network, long short-term memory, deep neural network, deep belief network, and memory network. We compare their futures, advantages, and disadvantages. Also, we point out the main problems of these methods, which may be worthy of careful studies in the future. Finally, we also examine the application of deep learning in multimodal sentiment analysis and aspect-level sentiment analysis.

Keywords: document analysis, deep learning, multimodal sentiment analysis, natural language processing

Procedia PDF Downloads 131

Authors: N. Dunleavy, E. Lovemore, K. Siljeur, D. Jackson, M. Hendricks, M. Hoosain, N. Plastow, S. Marais

Abstract:

Background: The work requirements of sewing machine operators cause physical and emotional strain. Past ergonomic interventions have been provided to alleviate physical concerns; however, a holistic, multimodal intervention was needed to improve these factors. Aim: The study aimed to examine the effect of an occupational therapy programme on sewing machine operators’ pain, mental health, and productivity within a factory in the South African context. Methods: A pilot randomised control trial was conducted with 22 sewing machine operators within a single factory. Stratified randomisation was used to determine the experimental (EG) and control groups (CG), using measures for pain intensity, level of depression (mental health), and productivity rates as stratification variables. The EG received the multimodal intervention, incorporating education, seating adaptations, and mental health intervention. In three months, the CG will receive the same intervention. Pre- and post-intervention testing have occurred with upcoming three- and six-month follow-ups. Results: Immediate results indicate a statistically significant decrease in pain in both experimental and control groups; no change in productivity scores and depression between the two groups. This may be attributed to external factors. The values for depression further showed no statistical significance between the two groups and within pre-and post-test results. The Statistical Program for Social Sciences (SPSS) version-24 was used as the data analysis testing, where all the tests will be evaluated at a 5% significance level. Contribution of research: The research adds to the body of knowledge informing the Occupational Therapy role in work settings, providing evidence on the effectiveness of workplace-based multimodal interventions. Conclusion: The study provides initial data on the effectiveness of a pilot randomised control trial on pain and mental health in South Africa. Results indicated no quantitative change between the experimental and control groups; however, qualitative data suggest a clinical significance of the findings.

Keywords: ergonomics programme, occupational therapy, sewing machine operators, workplace-based multimodal interventions

Procedia PDF Downloads 51

Authors: Virender Singh, Mathew Rees, Simon Hampton, Sivaram Annadurai

Abstract:

Plant identification is a challenging task that aims to identify the family, genus, and species according to plant morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users narrow down the possibilities. However, numerous morphological similarities between and within species render correct classification difficult. In this paper, we tested custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88,000 provided by the Royal Horticultural Society (RHS) and a smaller dataset of 16,000 images from the PlantClef 2015 dataset for classifying plants at genus and species levels, respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420 and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. For classifying plants at the species level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success. In conclusion, these results could help end users, professionals and the general public alike in identifying plants quicker and with improved accuracy.

Keywords: plant identification, CNN, image processing, vision transformer, classification

Procedia PDF Downloads 62

Authors: Sijia Guo

Abstract:

The development of new technologies and the falling cost of high-speed Internet access have made it easier for institutes and language teachers to opt different ways to communicate with students at distance. The emergence of web-conferencing applications, which integrate text, chat, audio / video and graphic facilities, offers great opportunities for language learning to through the multimodal environment. This paper reports on data elicited from a Ph.D. study of using web-conferencing in the teaching of first-year Chinese class in order to promote learners’ collaborative learning. Firstly, a comparison of four desktop videoconferencing (DVC) tools was conducted to determine the pedagogical value of the videoconferencing tool-Blackboard Collaborate. Secondly, the evaluation of 14 campus-based Chinese learners who conducted five one-hour online sessions via the multimodal environment reveals the users’ choice of modes and their learning preference. The findings show that the tasks designed for the web-conferencing environment contributed to the learners’ collaborative learning and second language acquisition.

Keywords: computer-mediated communication (CMC), CALL evaluation, TBLT, web-conferencing, online Chinese teaching

Procedia PDF Downloads 282

Authors: Rahul Ganpat Mapari, D. G. Wakde

Abstract:

In this paper, a proposed approach to improve the power factor of single-phase rectifiers and to regulate the output voltage against the change in grid voltage and load is presented. This converter topology is evaluated on the basis of performance and its salient features like simplicity, low cost and high performance are discussed to analyze its applicability. The proposed control strategy is bridgeless, transformer-less and output current sensor-less and consists of only two Bi-directional IGBTs and two diodes. The voltage regulation is achieved by a simple voltage divider to communicate to a controller to control the duty cycles of PWM. A control technique and operational procedure are also developed, both theoretically and experimentally. The experimental results clearly verify the theoretical analysis from the prototype connected to grid unity.

Keywords: Active Rectifier (AC-DC), power factor, single phase, voltage regulation

Procedia PDF Downloads 552

Authors: Shomaila Sadaf, Margarethe Olbertz-Siitonen

Abstract:

This study looks at identity and othering in discourses around sensitive issues in social media. More specifically, the study explores the multimodal resources and narratives through which the other is formed, and identities are ascribed in online spaces. As an integral part of social life, media spaces have become an important site for negotiating and ascribing identities. In line with recent research, identity is seen hereas constructions of belonging which go hand in hand with processes of in- and out-group formations that in some cases may lead to othering. Previous findings underline that identities are neither fixed nor limited but rather contextual, intersectional, and interactively achieved. The goal of this study is to explore and develop an understanding of how people co-construct the ‘other’ and ascribe certain identities in social media using multiple modes. In the beginning of the year 2018, the British government decided to include relationships, sexual orientation, and sex education into the curriculum of state funded primary schools. However, the addition of information related to LGBTQ+in the curriculum has been met with resistance, particularly from religious parents.For example, the British Muslim community has voiced their concerns and protested against the actions taken by the British government. YouTube has been used by news companies to air video stories covering the protest and narratives of the protestors along with the position ofschool officials. The analysis centers on a YouTube video dealing with the protest ofa local group of parents against the addition of information about LGBTQ+ in the curriculum in the UK. The video was posted in 2019. By the time of this study, the videos had approximately 169,000 views andaround 6000 comments. In deference to multimodal nature of YouTube videos, this study utilizes multimodal discourse analysis as a method of choice. The study is still ongoing and therefore has not yet yielded any final results. However, the initial analysis indicates a hierarchy of ascribing identities in the data. Drawing on multimodal resources, the media works with social categorizations throughout the documentary, presenting and classifying involved conflicting parties in the light of their own visible and audible identifications. The protesters can be seen to construct a strong group identity as Muslim parents (e.g., clothing and reference to shared values). While the video appears to be designed as a documentary that puts forward facts, the media does not seem to succeed in taking a neutral position consistently throughout the video. At times, the use of images, soundsand language contributes to the formation of “us” vs. “them”, where the audience is implicitly encouraged to pick a side. Only towards the end of the documentary this problematic opposition is addressed and critically reflected through an expert interview that is – interestingly – visually located outside the previously presented ‘battlefield’. This study contributes to the growing understanding of the discursive construction of the ‘other’ in social media. Videos available online are a rich source for examining how the different social actors ascribe multiple identities and form the other.

Keywords: identity, multimodal discourse analysis, othering, youtube

Procedia PDF Downloads 87

Authors: Jinan Fiaidhi, Hashmath Shaik

Abstract:

Breaking the barrier for practicing evidence-based medicine relies on effective methods for rapidly identifying relevant evidence from the body of biomedical literature. An important challenge confronted by medical practitioners is the long time needed to browse, filter, summarize and compile information from different medical resources. Deep learning can help in solving this based on automatic question answering (Q&A) and transformers. However, Q&A and transformer technologies are not trained to answer clinical queries that can be used for evidence-based practice, nor can they respond to structured clinical questioning protocols like PICO (Patient/Problem, Intervention, Comparison and Outcome). This article describes the use of deep learning techniques for Q&A that are based on transformer models like BERT and GPT to answer PICO clinical questions that can be used for evidence-based practice extracted from sound medical research resources like PubMed. We are reporting acceptable clinical answers that are supported by findings from PubMed. Our transformer methods are reaching an acceptable state-of-the-art performance based on two staged bootstrapping processes involving filtering relevant articles followed by identifying articles that support the requested outcome expressed by the PICO question. Moreover, we are also reporting experimentations to empower our bootstrapping techniques with patch attention to the most important keywords in the clinical case and the PICO questions. Our bootstrapped patched with attention is showing relevancy of the evidence collected based on entropy metrics.

Keywords: automatic question answering, PICO questions, evidence-based medicine, generative models, LLM transformers

Procedia PDF Downloads 6

Authors: Shweta Singh, Sudaman Katti

Abstract:

The most well-known sequence models make use of complex recurrent neural networks in an encoder-decoder configuration. The model used in this research makes use of a transformer, which is based purely on a self-attention mechanism, without relying on recurrence at all. More specifically, encoders and decoders which make use of self-attention and operate based on a memory, are used. In this research work, results for various 3D visual and non-visual reinforcement learning tasks designed in Unity software were obtained. Convolutional neural networks, more specifically, nature CNN architecture, are used for input processing in visual tasks, and comparison with standard long short-term memory (LSTM) architecture is performed for both visual tasks based on CNNs and non-visual tasks based on coordinate inputs. This research work combines the transformer architecture with the proximal policy optimization technique used popularly in reinforcement learning for stability and better policy updates while training, especially for continuous action spaces, which are used in this research work. Certain tasks in this paper are long horizon tasks that carry on for a longer duration and require extensive use of memory-based functionalities like storage of experiences and choosing appropriate actions based on recall. The transformer, which makes use of memory and self-attention mechanism in an encoder-decoder configuration proved to have better performance when compared to LSTM in terms of exploration and rewards achieved. Such memory based architectures can be used extensively in the field of cognitive robotics and reinforcement learning.

Keywords: convolutional neural networks, reinforcement learning, self-attention, transformers, unity

Procedia PDF Downloads 97

Authors: Nissa Phloimontri

Abstract:

This research explores the current physical conditions of motorcycle taxi stands located near the BTS stations in the central business district (CBD) and the comfort conditions of motorcycle taxi drivers. The criteria set up for physical stand survey and assessment are the integration of multimodal access design guidelines. After the survey, stands that share similar characteristics are classified into a series of typologies. Based on the environmental comfort model, questionnaires and in-depth interviews are conducted to evaluate the comfort levels of drivers including physical, functional, and psychological comfort. The results indicate that there are a number of motorcycle taxi stands that are not up to standard and are not conducive to the work-related activities of drivers. The study concludes by recommending public policy for integrated paratransit stops that support the multimodal transportation and seamless mobility concepts within the specific context of Bangkok as well as promote the quality of work life of motorcycle taxi drivers.

Keywords: motorcycle taxi, paratransit stops, environmental comfort, quality of work life

Procedia PDF Downloads 72

Authors: Khizar Z. Choudhrya, Richard Coles, Salman Qureshi, Robert Ashford, Salim Khan, Rabia R. Mir

Abstract:

Abstract: The majority of existing landscape research has been derived by conducting heuristic evaluations, without having empirical insight of real participant visual response. In this research, a modern multimodal measurement approach (using narratives and eye tracking) was applied to investigate visual behaviour in perceiving naturalistic and urban environments. This research is unique in exploring gaze behaviour on environmental images possessing different levels of saliency. Eye behaviour is predominantly attracted by salient locations. The concept of methodology of this research on naturalistic and urban environments is drawn from the approaches in market research. Borrowing methodologies from market research that examine visual responses and qualities provided a critical and hitherto unexplored approach. This research has been conducted by using mixed methodological quantitative and qualitative approaches. On the whole, the results of this research corroborated existing landscape research findings, but they also identified potential refinements. The research contributes both methodologically and empirically to human-environment interaction (HEI). This study focused on initial impressions of environmental images with the help of eye tracking. Taking under consideration the importance of the image, this study explored the factors that influence initial fixations in relation to expectations and preferences. In terms of key findings of this research it is noticed that each participant has his own unique navigation style while surfing through different elements of landscape images. This individual navigation style is given the name of ‘visual signature’. This study adds the necessary clarity that would complete the picture and bring an insight for future landscape researchers.

Keywords: human-environment interaction (HEI), multimodal measurement, narratives, eye tracking

Procedia PDF Downloads 315

Authors: Saeed Khandan Siar, Stefan Tenbohlen, Christian Breuer, Raphael Lebreton

Abstract:

The goal of this article is to investigate the detailed temperature distribution and the fluid flow of an oil cooled winding of a power transformer by means of computational fluid dynamics (CFD). The experimental setup consists of three passes of a zig-zag cooled disc type winding, in which losses are modeled by heating cartridges in each winding segment. A precise temperature sensor measures the temperature of each turn. The laboratory setup allows the exact control of the boundary conditions, e.g. the oil flow rate and the inlet temperature. Furthermore, a simulation model is solved using the open source computational fluid dynamics solver OpenFOAM and validated with the experimental results. The model utilizes the laminar and turbulent flow for the different mass flow rate of the oil. The good agreement of the simulation results with experimental measurements validates the model.

Keywords: CFD, conjugated heat transfer, power transformers, temperature distribution

Procedia PDF Downloads 390

Authors: Helena M. Wilhelm, Paulo O. Fernandes, Laís P. Dill, Kethlyn G. Moscon

Abstract:

The use of vegetable oil (or natural ester) as an insulating fluid in electrical transformers is a trend that aims to contribute to environmental preservation since it is biodegradable and non-toxic. Besides, vegetable oil has high flash and combustion points, being considered a fire safety fluid. However, vegetable oil is usually less stable towards oxidation than mineral oil. Both insulating fluids, mineral and vegetable oils, need to be tested periodically according to specific standards. Oxidation stability can be determined by the induction period measured by conductivity method (Rancimat) by monitoring the effectivity of oil’s antioxidant additives, a methodology already developed for food application and biodiesel but still not standardized for insulating fluids. Besides adequate oxidation stability, fluids must be compatible with transformer's construction materials under normal operating conditions to ensure that damage to the oil and parts of the transformer does not occur. ASTM standard and Brazilian normative differ in parameters evaluated, which reveals the need to regulate tests for each oil type. The aim of this study was to assess oxidation stability and compatibility of vegetable oils to suggest the best way to assure a viable performance of vegetable oil as transformer insulating fluid. The determination of the induction period for several vegetable insulating oils from the local market by using Rancimat was carried out according to BS EN 14112 standard, at different temperatures (110, 120, and 130 °C). Also, the compatibility of vegetable oil was assessed according to ASTM and ABNT NBR standards. The main results showed that the best temperature for use in the Rancimat test is 130 °C, which allows a better observation of conductivity change. The compatibility test results presented differences between vegetable and mineral oil standards that should be taken into account in oil testing since materials compatibility and oxidation stability are essential for equipment reliability.

Keywords: compatibility, Rancimat, natural ester, vegetable oil

Procedia PDF Downloads 173

Authors: Grzegorz Sierpiński, Ireneusz Celiński, Marcin Staniek

Abstract:

The article discusses multi modal mobility in contemporary societies as a main planning and organization issue in the functioning of administrative bodies, a problem which really exists in the space of contemporary cities in terms of shaping modern transport systems. The article presents classification of available resources and initiatives undertaken for developing multi modal mobility. Solutions can be divided into three groups of measures–physical measures in the form of changes of the transport network infrastructure, organizational ones (including transport policy) and information measures. The latter ones include in particular direct support for people travelling in the transport network by providing information about ways of using available means of transport. A special measure contributing to this end is a trip planner. The article compares several selected planners. It includes a short description of the Green Travelling Project, which aims at developing a planner supporting environmentally friendly solutions in terms of transport network operation. The article summarizes preliminary findings of the project.

Keywords: mobility, modal split, multimodal trip, multimodal platforms, sustainable transport

Procedia PDF Downloads 380

Authors: Laheeb M. Ibrahim, Ibrahim A. Salih

Abstract:

Biometrics is a technology that has been widely used in many official and commercial identification applications. The increased concerns in security during recent years (especially during the last decades) have essentially resulted in more attention being given to biometric-based verification techniques. Here, a novel fusion approach of palmprint, dental traits has been suggested. These traits which are authentication techniques have been employed in a range of biometric applications that can identify any postmortem PM person and antemortem AM. Besides improving the accuracy, the fusion of biometrics has several advantages such as increasing, deterring spoofing activities and reducing enrolment failure. In this paper, a first unimodel biometric system has been made by using (palmprint and dental) traits, for each one classification applying an artificial neural network and a hybrid technique that combines swarm intelligence and neural network together, then attempt has been made to combine palmprint and dental biometrics. Principally, the fusion of palmprint and dental biometrics and their potential application has been explored as biometric identifiers. To address this issue, investigations have been carried out about the relative performance of several statistical data fusion techniques for integrating the information in both unimodal and multimodal biometrics. Also the results of the multimodal approach have been compared with each one of these two traits authentication approaches. This paper studies the features and decision fusion levels in multimodal biometrics. To determine the accuracy of GAR to parallel system decision-fusion including (AND, OR, Majority fating) has been used. The backpropagation method has been used for classification and has come out with result (92%, 99%, 97%) respectively for GAR, while the GAR) for this algorithm using hybrid technique for classification (95%, 99%, 98%) respectively. To determine the accuracy of the multibiometric system for feature level fusion has been used, while the same preceding methods have been used for classification. The results have been (98%, 99%) respectively while to determine the GAR of feature level different methods have been used and have come out with (98%).

Keywords: back propagation neural network BP ANN, multibiometric system, parallel system decision-fusion, practical swarm intelligent PSO

Procedia PDF Downloads 510

Authors: Yi Meng, YunGao

Abstract:

Having been studied and worked in North America and Europe, we, two Chinese art educators, have been enormously influenced by eastern and western cultures. Thus, we aim to enhance students’ learning experiences by exploring and amalgamating both cultures for art creating. This text draws on our action research study of students’ visual literacy practices in a foundation sketching course in a major Chinese university, exploring art forms by cross-utilizing various cultural aspects. Instead of relying on the predominant western observational drawing skills in our classroom, we taught students about ancient Chinese art in the provincial museum, using Fu Hao owl-shaped vessel, a Shang Dynasty national treasure, as the final sketch project of this course. We took up multimodal literacy, which emphasized students’ critical use of creativity to exploit the semiotic potentials of communicative modes to address diverse cultural issues through their multimodal design. We used the Hong Kong-based artist Tik Ka’s artworks to demonstrate the cultural amalgamation of Chinese traditions and western pop cultures. Collectively, these approaches create a dialogical space for students to experience, analyze, and negotiate with complex modes and potentially transform their understanding of both cultures by redesigning Fu Hao.

Keywords: Chinese traditions, western pop cultures, Fu Hao, arts education, design sketch

Procedia PDF Downloads 69

Authors: Murad Almadani, Khalil Abu-Hantash, Xinyu Wang, Herbert Jelinek, Kinda Khalaf

Abstract:

Gait analysis is used by healthcare professionals as a tool to gain a better understanding of the movement impairment and track progress. In most circumstances, monitoring patients in their real-life environments with low-cost equipment such as cameras and wearable sensors is more important. Inertial sensors, on the other hand, cannot provide enough information on angular dynamics. This research offers a method for tracking 2D joint coordinates using cutting-edge vision algorithms and a single RGB camera. We provide an end-to-end comprehensive deep learning pipeline for marker-less gait parameter estimation, which, to our knowledge, has never been done before. To make our pipeline function in real-time for real-world applications, we leverage the AlphaPose human posture prediction model and a deep learning transformer. We tested our approach on the well-known GPJATK dataset, which produces promising results.

Keywords: gait analysis, human pose estimation, deep learning, real time gait estimation, AlphaPose, transformer

Procedia PDF Downloads 83

Authors: Sean Paulsen, Michael Casey

Abstract:

In this work we present a self-supervised pretraining framework for transformers on functional Magnetic Resonance Imaging (fMRI) data. First, we pretrain our architecture on two self-supervised tasks simultaneously to teach the model a general understanding of the temporal and spatial dynamics of human auditory cortex during music listening. Our pretraining results are the first to suggest a synergistic effect of multitask training on fMRI data. Second, we finetune the pretrained models and train additional fresh models on a supervised fMRI classification task. We observe significantly improved accuracy on held-out runs with the finetuned models, which demonstrates the ability of our pretraining tasks to facilitate transfer learning. This work contributes to the growing body of literature on transformer architectures for pretraining and transfer learning with fMRI data, and serves as a proof of concept for our pretraining tasks and multitask pretraining on fMRI data.

Keywords: transfer learning, fMRI, self-supervised, brain decoding, transformer, multitask training

Procedia PDF Downloads 60

Authors: Yasunori Kobori, Li Quan, Shu Wu, Nizam Mohyar, Zachary Nosker, Nobukazu Tsukiji, Nobukazu Takai, Haruo Kobayashi

Abstract:

This paper proposes an electrolytic capacitor-less transformer-less AC-DC LED driver with a current ripple canceller. The proposed LED driver includes a diode bridge, a buck-boost converter, a negative feedback controller and a current ripple cancellation circuit. The current ripple canceller works as a bi-directional current converter using a sub-inductor, a sub-capacitor and two switches for controlling current flow. LED voltage is controlled in order to regulate LED current by the negative feedback controller using a current sense resistor. There are two capacitors which capacitance of 5 uF. We describe circuit topologies, operation principles and simulation results for our proposed circuit. In addition, we show the line regulation for input voltage variation from 85V to 130V. The output voltage ripple is 2V and the LED current ripple is 65 mA which is less than 20% of the typical current of 350 mA. We are now making the proposed circuit on a universal board in order to measure the experimental characteristics.

Keywords: LED driver, electrolytic, capacitor-less, AC-DC converter, buck-boost converter, current ripple canceller

Procedia PDF Downloads 441

Authors: Thomas Bryan, Veton Kepuska, Ivica Kostanic

Abstract:

Speaker recognition is performed in high Additive White Gaussian Noise (AWGN) environments using principals of Computational Auditory Scene Analysis (CASA). CASA methods often classify sounds from images in the time-frequency (T-F) plane using spectrograms or cochleargrams as the image. In this paper atomic decomposition implemented by matching pursuit performs a transform from time series speech signals to the T-F plane. The atomic decomposition creates a sparsely populated T-F vector in “weight space” where each populated T-F position contains an amplitude weight. The weight space vector along with the atomic dictionary represents a denoised, compressed version of the original signal. The arraignment or of the atomic indices in the T-F vector are used for classification. Unsupervised feature learning implemented by a sparse autoencoder learns a single dictionary of basis features from a collection of envelope samples from all speakers. The approach is demonstrated using pairs of speakers from the TIMIT data set. Pairs of speakers are selected randomly from a single district. Each speak has 10 sentences. Two are used for training and 8 for testing. Atomic index probabilities are created for each training sentence and also for each test sentence. Classification is performed by finding the lowest Euclidean distance between then probabilities from the training sentences and the test sentences. Training is done at a 30dB Signal-to-Noise Ratio (SNR). Testing is performed at SNR’s of 0 dB, 5 dB, 10 dB and 30dB. The algorithm has a baseline classification accuracy of ~93% averaged over 10 pairs of speakers from the TIMIT data set. The baseline accuracy is attributable to short sequences of training and test data as well as the overall simplicity of the classification algorithm. The accuracy is not affected by AWGN and produces ~93% accuracy at 0dB SNR.

Keywords: time-frequency plane, atomic decomposition, envelope sampling, Gabor atoms, matching pursuit, sparse dictionary learning, sparse autoencoder

Procedia PDF Downloads 261

Authors: Yuntao Liu, Lei Wang, Haoran Xia

Abstract:

Machine learning has shown extensive applications in the development of classification models for autism spectrum disorder (ASD) using neural image data. This paper proposes a fusion multi-modal classification network based on a graph neural network. First, the brain is segmented into 116 regions of interest using a medical segmentation template (AAL, Anatomical Automatic Labeling). The image features of sMRI and the signal features of fMRI are extracted, which build the node and edge embedding representations of the brain map. Then, we construct a dynamically updated brain map neural network and propose a method based on a dynamic brain map adjacency matrix update mechanism and learnable graph to further improve the accuracy of autism diagnosis and recognition results. Based on the Autism Brain Imaging Data Exchange I dataset(ABIDE I), we reached a prediction accuracy of 74% between ASD and TD subjects. Besides, to study the biomarkers that can help doctors analyze diseases and interpretability, we used the features by extracting the top five maximum and minimum ROI weights. This work provides a meaningful way for brain disorder identification.

Keywords: autism spectrum disorder, brain map, supervised machine learning, graph network, multimodal data, model interpretability

Procedia PDF Downloads 22

Authors: Antonis Constantinides, Christos Yiallouras, Christakis Damianou

Abstract:

The coaxial transformer-coupled push-pull circuitry has been used widely in HF and VHF amplifiers for many decades without significant changes in the topology of the transformers. Basic changes over the years concerned the construction and turns ratio of the transformers as has been imposed upon the newer technologies active devices demands. The balun transmission line transformers applied in push-pull amplifiers enable input/output impedance transformation, but are mainly used to convert the balanced output into unbalanced and the input unbalanced into balanced. A simple and affordable alternative solution over the traditional coaxial transformer is the coreless planar balun. A key advantage over the traditional approach lies in the high specifications repeatability; simplifying the amplifier construction requirements as the planar balun constitutes an integrated part of the PCB copper layout. This paper presents the performance analysis of a planar LDMOS MRFE6VP5600 Push-Pull amplifier that enables robust operation in Band III, DVB-T, DVB-T2 standards but functions equally well in Band II, for DRM+ new generation transmitters.

Keywords: amplifier, balun, complex impedance, LDMOS, planar-transformers

Procedia PDF Downloads 413

Authors: Arvind Dhingra, Tejinder Singh Saggu

Abstract:

As the energy demands rise and the pollution levels grow, it becomes imperative for us to save energy in all the fields in which it is used. The industrial sector is the major commercial energy consuming sector in India, where electrical energy is the most common and widely used type of energy. As the demand and price of energy are increasing day by day, therefore, the subject of energy conservation is a concern for most energy users particularly industry. Judicious use of energy becomes imperative for third world developing country being presence of energy crisis. This paper provides some measure for energy saving that can be commonly recommended for a rolling unit of steel industry. A case of hot rolling unit in JSL Stainless Ltd., Hisar for energy conservation is given. Overall improvement in energy consumption in light of the stated recommendation is illustrated along with the proposed utilization of the techniques and their applications. Energy conservation in conventional motor with replacement or use of star delta star converter, reduction in cable losses, replacement of filament of LED lamps, replacement of conventional transformer with cast resin dry type transformer and provision of energy management system for energy conservation and per unit production cost reduction are elaborated in this paper.

Keywords: energy audit, energy conservation, energy efficient motors

Procedia PDF Downloads 494

Authors: Atuhurra Jesse, N'guessan Yves-Roland Douha, Pabitra Lenka

Abstract:

The detection of diseases within plants has attracted a lot of attention from computer vision enthusiasts. Despite the progress made to detect diseases in many plants, there remains a research gap to train image classifiers to detect the cacao swollen shoot virus disease or CSSVD for short, pertinent to cacao plants. This gap has mainly been due to the unavailability of high quality labeled training data. Moreover, institutions have been hesitant to share their data related to CSSVD. To fill these gaps, image classifiers to detect CSSVD-infected cacao plants are presented in this study. The classifiers are based on VGG16, ResNet50 and Vision Transformer (ViT). The image classifiers are evaluated on a recently released and publicly accessible KaraAgroAI Cocoa dataset. The best performing image classifier, based on ResNet50, achieves 95.39\% precision, 93.75\% recall, 94.34\% F1-score and 94\% accuracy on only 20 epochs. There is a +9.75\% improvement in recall when compared to previous works. These results indicate that the image classifiers learn to identify cacao plants infected with CSSVD.

Keywords: CSSVD, image classification, ResNet50, vision transformer, KaraAgroAI cocoa dataset

Procedia PDF Downloads 66

Authors: Nashwa Elyamany

Abstract:

In visual cultures, namely that of the United States, media representations are such influential and pervasive reflections of societal norms and expectations to the extent that they impact the manner in which both genders view themselves. Health and fitness magazines fall within the realm of visual culture. Since the main goal of communication is to ensure proper dissemination of information in order for the target audience to grasp the intended messages, it becomes imperative that magazine publishers, editors, advertisers and image producers use different modes of communication within their reach to convey messages to their readers and viewers. A rapid waxing flow of multimodality floods popular discourse, particularly health and fitness magazine cover pages. The use of well-crafted cover lines and visual images is imbued with agendas, consumerist ideologies and properties capable of effectively conveying implicit and explicit meaning to potential readers and viewers. In essence, the primary goal of this thesis is to interrogate the multi-semiotic operations and manifestations of hegemonic masculinity and femininity in male and female body culture, particularly on the cover pages of the twin American magazines Men's Health and Women's Health using corpora that spanned from 2011 to the mid of 2016. The researcher explores the semiotic resources that contribute to shaping and legitimizing a new form of postmodern, consumerist, gendered discourse that positions the reader-viewer ideologically. Methodologically, the researcher carries out analysis on the macro and micro levels. On the macro level, the researcher takes on a critical stance to illuminate the ideological nature of the multimodal ensemble of the cover pages, and, on the micro level, seeks to put forward new theoretical and methodological routes through which the semiotic choices well invested on the media texts can be more objectively scrutinized. On the macro level, a 'themes' analysis is initially conducted to isolate the overarching themes that dominate the fitness discourse on the cover pages under study. It is argued that variation in terms of frequencies of such themes is indicative, broadly speaking, of which facets of hegemonic masculinity and femininity are infused in the fitness discourse on the cover pages. On the micro level, this research work encompasses three sub-levels of analysis. The researcher follows an SF-MMDA approach, drawing on a trio of analytical frameworks: Halliday's SFG for the verbal analysis; Kress & van Leeuween's VG for the visual analysis; and CMT in relation to Sperber & Wilson's RT for the pragma-cognitive analysis of multimodal metaphors and metonymies. The data is presented in terms of detailed descriptions in conjunction with frequency tables, ANOVA with alpha=0.05 and MANOVA in the multiple phases of analysis. Insights and findings from this multi-faceted, social-semiotic analysis are interpreted in light of Cultivation Theory, Self-objectification Theory and the literature to date. Implications for future research include the implementation of a multi-dimensional approach whereby linguistic and visual analytical models are deployed with special regards to cultural variation.

Keywords: gender, hegemony, magazine cover page, multimodal discourse analysis, multimodal metaphor, multimodal metonymy, systemic functional grammar, visual grammar

Procedia PDF Downloads 314

Authors: Tingwei Shu, Dong Zhou, Chengjun Guo

Abstract:

Semantic communication is an emerging form of communication that realize intelligent communication by extracting semantic information of data at the source and transmitting it, and recovering the data at the receiving end. It can effectively solve the problem of data transmission under the situation of large data volume, low SNR and restricted bandwidth. With the development of Deep Learning, semantic communication further matures and is gradually applied in the fields of the Internet of Things, Uumanned Air Vehicle cluster communication, remote sensing scenarios, etc. We propose an improved semantic communication system for the situation where the data volume is huge and the spectrum resources are limited during the transmission of remote sensing images. At the transmitting, we need to extract the semantic information of remote sensing images, but there are some problems. The traditional semantic communication system based on Convolutional Neural Network cannot take into account the global semantic information and local semantic information of the image, which results in less-than-ideal image recovery at the receiving end. Therefore, we adopt the improved vision-Transformer-based structure as the semantic encoder instead of the mainstream one using CNN to extract the image semantic features. In this paper, we first perform pre-processing operations on remote sensing images to improve the resolution of the images in order to obtain images with more semantic information. We use wavelet transform to decompose the image into high-frequency and low-frequency components, perform bilinear interpolation on the high-frequency components and bicubic interpolation on the low-frequency components, and finally perform wavelet inverse transform to obtain the preprocessed image. We adopt the improved Vision-Transformer structure as the semantic coder to extract and transmit the semantic information of remote sensing images. The Vision-Transformer structure can better train the huge data volume and extract better image semantic features, and adopt the multi-layer self-attention mechanism to better capture the correlation between semantic features and reduce redundant features. Secondly, to improve the coding efficiency, we reduce the quadratic complexity of the self-attentive mechanism itself to linear so as to improve the image data processing speed of the model. We conducted experimental simulations on the RSOD dataset and compared the designed system with a semantic communication system based on CNN and image coding methods such as BGP and JPEG to verify that the method can effectively alleviate the problem of excessive data volume and improve the performance of image data communication.

Keywords: semantic communication, transformer, wavelet transform, data processing

Procedia PDF Downloads 47

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 98

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, student engagement

Procedia PDF Downloads 67

Authors: Ozge Nilay Yalcin

Abstract:

Dialogue has been proposed to be the natural basis for the human-computer interaction, which is behaviorally rich and includes different modalities such as gestures, posture changes, gaze, para-linguistic parameters and linguistic context. However, equipping the system with these capabilities might have consequences on the usability of the system. One issue is to be able to find a good balance between rich behavior and fluent behavior, as planning and generating these behaviors is computationally expensive. In this work, we propose a multi-modal dialogue management system that automates the conversational flow from text-based dialogue examples and uses synchronized verbal and non-verbal conversational cues to achieve a fluent interaction. Our system is integrated with Smartbody behavior realizer to provide real-time interaction with embodied agent. The nonverbal behaviors are used according to turn-taking behavior, emotions, and personality of the user and linguistic analysis of the dialogue. The verbal behaviors are responsive to the emotional value of the utterance and the feedback from the user. Our system is aimed for online planning of these affective multi-modal components, in order to achieve enhanced user experience with richer and more natural interaction.

Keywords: affect, embodied conversational agents, human-agent interaction, multimodal interaction, natural interfaces

Procedia PDF Downloads 146

Authors: Teodora Vukovic, Christoph Hottiger, Noah Bubenhofer

Abstract:

The development of VIAN-DH aims at bridging two linguistic approaches: conversation analysis/interactional linguistics (IL), so far a dominantly qualitative field, and computational/corpus linguistics and its quantitative and automated methods. Contemporary IL investigates the systematic organization of conversations and interactions composed of speech, gaze, gestures, and body positioning, among others. These highly integrated multimodal behaviour is analysed based on video data aimed at uncovering so called “multimodal gestalts”, patterns of linguistic and embodied conduct that reoccur in specific sequential positions employed for specific purposes. Multimodal analyses (and other disciplines using videos) are so far dependent on time and resource intensive processes of manual transcription of each component from video materials. Automating these tasks requires advanced programming skills, which is often not in the scope of IL. Moreover, the use of different tools makes the integration and analysis of different formats challenging. Consequently, IL research often deals with relatively small samples of annotated data which are suitable for qualitative analysis but not enough for making generalized empirical claims derived quantitatively. VIAN-DH aims to create a workspace where many annotation layers required for the multimodal analysis of videos can be created, processed, and correlated in one platform. VIAN-DH will provide a graphical interface that operates state-of-the-art tools for automating parts of the data processing. The integration of tools that already exist in computational linguistics and computer vision, facilitates data processing for researchers lacking programming skills, speeds up the overall research process, and enables the processing of large amounts of data. The main features to be introduced are automatic speech recognition for the transcription of language, automatic image recognition for extraction of gestures and other visual cues, as well as grammatical annotation for adding morphological and syntactic information to the verbal content. In the ongoing instance of VIAN-DH, we focus on gesture extraction (pointing gestures, in particular), making use of existing models created for sign language and adapting them for this specific purpose. In order to view and search the data, VIAN-DH will provide a unified format and enable the import of the main existing formats of annotated video data and the export to other formats used in the field, while integrating different data source formats in a way that they can be combined in research. VIAN-DH will adapt querying methods from corpus linguistics to enable parallel search of many annotation levels, combining token-level and chronological search for various types of data. VIAN-DH strives to bring crucial and potentially revolutionary innovation to the field of IL, (that can also extend to other fields using video materials). It will allow the processing of large amounts of data automatically and, the implementation of quantitative analyses, combining it with the qualitative approach. It will facilitate the investigation of correlations between linguistic patterns (lexical or grammatical) with conversational aspects (turn-taking or gestures). Users will be able to automatically transcribe and annotate visual, spoken and grammatical information from videos, and to correlate those different levels and perform queries and analyses.

Keywords: multimodal analysis, corpus linguistics, computational linguistics, image recognition, speech recognition

Procedia PDF Downloads 75

Authors: Ling Qi, Matloob Khushi, Josiah Poon

Abstract:

This paper introduces a pre-trained Masked Candlestick Model (MCM) for trading time-series data. The pre-trained model is based on three core designs. First, we convert trading price data at each data point as a set of normalized elements and produce embeddings of each element. Second, we generate a masked sequence of such embedded elements as inputs for self-supervised learning. Third, we use the encoder mechanism from the transformer to train the inputs. The masked model learns the contextual relations among the sequence of embedded elements, which can aid downstream classification tasks. To evaluate the performance of the pre-trained model, we fine-tune MCM for three different downstream classification tasks to predict future price trends. The fine-tuned models achieved better accuracy rates for all three tasks than the baseline models. To better analyze the effectiveness of MCM, we test the same architecture for three currency pairs, namely EUR/GBP, AUD/USD, and EUR/JPY. The experimentation results demonstrate MCM’s effectiveness on all three currency pairs and indicate the MCM’s capability for signal extraction from trading data.

Keywords: masked language model, transformer, time series prediction, trading prediction, embedding, transfer learning, self-supervised learning

Procedia PDF Downloads 91