Search results for: second language vocabulary learning
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 9192

Search results for: second language vocabulary learning

2022 A Data Science Pipeline for Algorithmic Trading: A Comparative Study in Applications to Finance and Cryptoeconomics

Authors: Luyao Zhang, Tianyu Wu, Jiayi Li, Carlos-Gustavo Salas-Flores, Saad Lahrichi

Abstract:

Recent advances in AI have made algorithmic trading a central role in finance. However, current research and applications are disconnected information islands. We propose a generally applicable pipeline for designing, programming, and evaluating algorithmic trading of stock and crypto tokens. Moreover, we provide comparative case studies for four conventional algorithms, including moving average crossover, volume-weighted average price, sentiment analysis, and statistical arbitrage. Our study offers a systematic way to program and compare different trading strategies. Moreover, we implement our algorithms by object-oriented programming in Python3, which serves as open-source software for future academic research and applications.

Keywords: algorithmic trading, AI for finance, fintech, machine learning, moving average crossover, volume weighted average price, sentiment analysis, statistical arbitrage, pair trading, object-oriented programming, python3

Procedia PDF Downloads 111
2021 A Study of Primary School Parents’ Interaction with Teachers’ in Malaysia

Authors: Shireen Simon

Abstract:

This study explores the interactions between primary school parents-teachers in Malaysia. Schools in the country are organized to promote participation between parents and teachers. Exchanges of dialogue are most valued between parents and teachers because teachers are in daily contact with pupils’ and the first line of communication with parents. Teachers are considered by parents as the most important connection to improve children learning and well-being. Without a good communication, interaction or involvement between parent-teacher might tarnish a pupils’ performance in school. This study tries to find out multiple emotions among primary school parents-teachers, either estranged or cordial, when they communicate in a multi-cultured society in Malaysia. Important issues related to parent-teacher interactions are discussed further. Parents’ involvement in an effort to boost better education in school is significantly more effective with parents’ involvement. Lastly, this article proposes some suggestions for parents and teachers to build a positive relationship with effective communication and establish more democratic open door policy.

Keywords: multi-cultured society, parental involvement, parent-teacher relationships, parents’ interaction

Procedia PDF Downloads 221
2020 A Dynamic Neural Network Model for Accurate Detection of Masked Faces

Authors: Oladapo Tolulope Ibitoye

Abstract:

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. This is a prominent area due to the coronavirus disease pandemic and the post-pandemic phases. Wearing a face mask in public slows the spread of the virus, according to experts’ submission. This calls for the development of a reliable and effective model for detecting face masks on people's faces during compliance checks. The existing neural network models for facemask detection are characterized by their black-box nature and large dataset requirement. The highlighted challenges have compromised the performance of the existing models. The proposed model utilized Faster R-CNN Model on Inception V3 backbone to reduce system complexity and dataset requirement. The model was trained and validated with very few datasets and evaluation results shows an overall accuracy of 96% regardless of skin tone.

Keywords: convolutional neural network, face detection, face mask, masked faces

Procedia PDF Downloads 44
2019 Perceptions of Senior Academics in Teacher Education Colleges Regarding the Integration of Digital Games during the Pandemic

Authors: Merav Hayakac, Orit Avidov-Ungarab

Abstract:

The current study adopted an interpretive-constructivist approach to examine how senior academics from a large sample of Israeli teacher education colleges serving general or religious populations perceived the integration of digital games into their teacher instruction and what their policy and vision were in this regard in the context of the COVID-19 pandemic. Half the participants expressed a desire to integrate digital games into their teaching and learning but acknowledged that this practice was uncommon. Only a small minority believed they had achieved successful integration, with doubt and skepticism expressed by some religious colleges. Most colleges had policies encouraging technology integration supported by ongoing funding. Although a considerable gap between policy and implementation remained, the COVID-19 pandemic was viewed as having accelerated the integration of digital games into pre-service teacher instruction. The findings suggest that discussions around technology-related vision and policy and their translation into practice should relate to the specific cultural needs and academic preparedness of the population(s) served by the college.

Keywords: COVID-19, digital games, pedagogy, teacher education colleges

Procedia PDF Downloads 70
2018 Artificial Intelligence and Distributed System Computing: Application and Practice in Real Life

Authors: Lai Junzhe, Wang Lihao, Burra Venkata Durga Kumar

Abstract:

In recent years, due to today's global technological advances, big data and artificial intelligence technologies have been widely used in various industries and fields, playing an important role in reducing costs and increasing efficiency. Among them, artificial intelligence has derived another branch in its own continuous progress and the continuous development of computer personnel, namely distributed artificial intelligence computing systems. Distributed AI is a method for solving complex learning, decision-making, and planning problems, characterized by the ability to take advantage of large-scale computation and the spatial distribution of resources, and accordingly, it can handle problems with large data sets. Nowadays, distributed AI is widely used in military, medical, and human daily life and brings great convenience and efficient operation to life. In this paper, we will discuss three areas of distributed AI computing systems in vision processing, blockchain, and smart home to introduce the performance of distributed systems and the role of AI in distributed systems.

Keywords: distributed system, artificial intelligence, blockchain, IoT, visual information processing, smart home

Procedia PDF Downloads 83
2017 Investigations of Protein Aggregation Using Sequence and Structure Based Features

Authors: M. Michael Gromiha, A. Mary Thangakani, Sandeep Kumar, D. Velmurugan

Abstract:

The main cause of several neurodegenerative diseases such as Alzhemier, Parkinson, and spongiform encephalopathies is formation of amyloid fibrils and plaques in proteins. We have analyzed different sets of proteins and peptides to understand the influence of sequence-based features on protein aggregation process. The comparison of 373 pairs of homologous mesophilic and thermophilic proteins showed that aggregation-prone regions (APRs) are present in both. But, the thermophilic protein monomers show greater ability to ‘stow away’ the APRs in their hydrophobic cores and protect them from solvent exposure. The comparison of amyloid forming and amorphous b-aggregating hexapeptides suggested distinct preferences for specific residues at the six positions as well as all possible combinations of nine residue pairs. The compositions of residues at different positions and residue pairs have been converted into energy potentials and utilized for distinguishing between amyloid forming and amorphous b-aggregating peptides. Our method could correctly identify the amyloid forming peptides at an accuracy of 95-100% in different datasets of peptides.

Keywords: aggregation, amyloids, thermophilic proteins, amino acid residues, machine learning techniques

Procedia PDF Downloads 583
2016 Multi-Modal Visualization of Working Instructions for Assembly Operations

Authors: Josef Wolfartsberger, Michael Heiml, Georg Schwarz, Sabrina Egger

Abstract:

Growing individualization and higher numbers of variants in industrial assembly products raise the complexity of manufacturing processes. Technical assistance systems considering both procedural and human factors allow for an increase in product quality and a decrease in required learning times by supporting workers with precise working instructions. Due to varying needs of workers, the presentation of working instructions leads to several challenges. This paper presents an approach for a multi-modal visualization application to support assembly work of complex parts. Our approach is integrated within an interconnected assistance system network and supports the presentation of cloud-streamed textual instructions, images, videos, 3D animations and audio files along with multi-modal user interaction, customizable UI, multi-platform support (e.g. tablet-PC, TV screen, smartphone or Augmented Reality devices), automated text translation and speech synthesis. The worker benefits from more accessible and up-to-date instructions presented in an easy-to-read way.

Keywords: assembly, assistive technologies, augmented reality, manufacturing, visualization

Procedia PDF Downloads 143
2015 Lecturer’s Perception of the Role of Information and Communication Technology in Office Technology and Management Programme in Polytechnics in Nigeria

Authors: Felicia Kikelomo Oluwalola

Abstract:

This study examined lecturers’ perception of the roles of Information and Communication Technology (ICT) in Office Technology and Management (OTM) programme in polytechnics, in South-West, Nigeria. Descriptive survey design was adopted in this study. Purposive sampling technique was used to select all OTM lecturers in the nine (9) Polytechnics in the South-West, Nigeria. A 4-rating scale was adopted questionnaire titled ‘Lecturers’ Perception of the Roles of ICT in OTM Programme in Polytechnics’ with a reliability index of 0.93 was used. Two research questions were answered, and one null hypothesis was tested for the study. Data collected was analysed using descriptive statistics, independent t-test and one way Analysis of Variance (ANOVA) at 0.05 level of significance. The study revealed that lecturers have right perception of the roles of ICT in OTM programme in polytechnics. Also, the study revealed no significant difference between the mean perception of male and female lecturers in office technology and management. Based on the findings, the study recommended among others that recruitment of professionals in the field of ICT is necessary for effective teaching learning to be established and OTM curriculum should be constantly reviewed to enhance some ICT package that is acceptable globally.

Keywords: communication, information, perception, technology

Procedia PDF Downloads 426
2014 Indigenous Storytelling: Transformation for Health, Emotions and Spirituality

Authors: Annabelle Nelson

Abstract:

This literature review documents indigenous storytelling as it functions to help humans face adversity and find emotional strength by aligning with nature. Archetypes in stories can transform the inner world from a Jungian perspective. Joseph Campbell’s hero-heroine cycle depicts the structure of stories to include a call to adventure, tests, helpers, and a return as the transformed person can help him or herself and even help their communities. By showcasing certain character traits, such as bravery or perseverance or humility, stories give maps for humans to face adversity. The main characters or archetypes in stories, as Carl Jung posited, provide a vehicle that can open consciousness if a listener identifies with the character. As documented in the review, this has many benefits. First, it can open consciousness to the collective unconscious for insight and intuitive clarity, as well as healing and release emotional trauma. The resultant spacious quality of consciousness allows the spiritual self to present insights to conscious awareness. Research in applied youth development programs demonstrates the utility of storytelling to prompt healthy choices and transform difficult life experience into success.

Keywords: archetypes, learning, storytelling, transformation

Procedia PDF Downloads 142
2013 Influence of Radio Frequency Identification Technology at Cost of Supply Chain as a Driver for the Generation of Competitive Advantage

Authors: Mona Baniahmadi, Saied Haghanifar

Abstract:

Radio Frequency Identification (RFID) is regarded as a promising technology for the optimization of supply chain processes since it improves manufacturing and retail operations from forecasting demand for planning, managing inventory, and distribution. This study precisely aims at learning to know the RFID technology and at explaining how it can concretely be used for supply chain management and how it can help improving it in the case of Hejrat Company which is located in Iran and works on the distribution of medical drugs and cosmetics. This study uses some statistical analysis to calculate the expected benefits of an integrated RFID system on supply chain obtained through competitive advantages increases with decreasing cost factor. The study investigates how the cost of storage process, labor cost, the cost of missing goods, inventory management optimization, on-time delivery, order cost, lost sales and supply process optimization affect the performance of the integrated RFID supply chain regarding cost factors and provides a competitive advantage.

Keywords: cost, competitive advantage, radio frequency identification, supply chain

Procedia PDF Downloads 246
2012 Results of Longitudinal Assessments of Very Low Birth Weight and Extremely Low Birth Weight Infants

Authors: Anett Nagy, Anna Maria Beke, Rozsa Graf, Magda Kalmar

Abstract:

Premature birth involves developmental risks – the earlier the baby is born and the lower its birth weight, the higher the risks. The developmental outcomes for immature, low birth weight infants are hard to predict. Our aim is to identify the factors influencing infant and preschool-age development in very low birth weight (VLBW) and extremely low birth weight (ELBW) preterms. Sixty-one subjects participated in our longitudinal study, which consisted of thirty VLBW and thirty-one ELBW children. The psychomotor development of the infants was assessed using the Brunet-Lezine Developmental Scale at the corrected ages of one and two years; then at three years of age, they were tested with the WPPSI-IV IQ test. Birth weight, gestational age, perinatal complications, gender, and maternal education, were added to the data analysis as independent variables. According to our assessments, our subjects as a group scored in the average range in each subscale of the Brunet-Lezine Developmental Scale. The scores were the lowest in language at both measurement points. The children’s performances improved between one and two years of age, particularly in the domain of coordination. At three years of age the mean IQ test results, although still in the average range, were near the low end of it in each index. The ELBW preterms performed significantly poorer in Perceptual Reasoning Index. The developmental level at two years better predicted the IQ than that at one year. None of the measures distinguished the genders.

Keywords: preterm, extremely low birth-weight, perinatal complication, psychomotor development, intelligence, follow-up

Procedia PDF Downloads 217
2011 Challenges in Promoting Software Usability and Applying Principles of Usage-Centred Design in Saudi Arabia

Authors: Kholod J. Alotaibi, Andrew M. Gravell

Abstract:

A study was conducted in which 212 software developers in higher education institutions in Saudi Arabia were surveyed to gather an indication of their understanding of the concept of usability, their acceptance of its importance, and to see how well its principles are applied. Interviews were then held with 20 of these developers, and a demonstration of Usage-Centred Design was attempted, a highly usability focused software development methodology, at one select institution for its redesign of an e-learning exam system interface during the requirements gathering phase. The study confirms the need to raise awareness of usability and its importance, and for Usage-Centred Design to be applied in its entirety, also need to encourage greater consultation with potential end-users of software and collaborative practices. The demonstration of Usage-Centred Design confirmed its ability to capture usability requirements more completely and precisely than would otherwise be the case, and hence its usefulness for developers concerned with improving software usability. The concluding discussion delves on the challenges for promoting usability and Usage-Centred Design in light of the research results and findings and recommendations are made for the same.

Keywords: usability, usage-centred, applying principles of usage-centred, Saudi Arabia

Procedia PDF Downloads 358
2010 A Neural Network Based Clustering Approach for Imputing Multivariate Values in Big Data

Authors: S. Nickolas, Shobha K.

Abstract:

The treatment of incomplete data is an important step in the data pre-processing. Missing values creates a noisy environment in all applications and it is an unavoidable problem in big data management and analysis. Numerous techniques likes discarding rows with missing values, mean imputation, expectation maximization, neural networks with evolutionary algorithms or optimized techniques and hot deck imputation have been introduced by researchers for handling missing data. Among these, imputation techniques plays a positive role in filling missing values when it is necessary to use all records in the data and not to discard records with missing values. In this paper we propose a novel artificial neural network based clustering algorithm, Adaptive Resonance Theory-2(ART2) for imputation of missing values in mixed attribute data sets. The process of ART2 can recognize learned models fast and be adapted to new objects rapidly. It carries out model-based clustering by using competitive learning and self-steady mechanism in dynamic environment without supervision. The proposed approach not only imputes the missing values but also provides information about handling the outliers.

Keywords: ART2, data imputation, clustering, missing data, neural network, pre-processing

Procedia PDF Downloads 248
2009 Investigation on Performance of Change Point Algorithm in Time Series Dynamical Regimes and Effect of Data Characteristics

Authors: Farhad Asadi, Mohammad Javad Mollakazemi

Abstract:

In this paper, Bayesian online inference in models of data series are constructed by change-points algorithm, which separated the observed time series into independent series and study the change and variation of the regime of the data with related statistical characteristics. variation of statistical characteristics of time series data often represent separated phenomena in the some dynamical system, like a change in state of brain dynamical reflected in EEG signal data measurement or a change in important regime of data in many dynamical system. In this paper, prediction algorithm for studying change point location in some time series data is simulated. It is verified that pattern of proposed distribution of data has important factor on simpler and smother fluctuation of hazard rate parameter and also for better identification of change point locations. Finally, the conditions of how the time series distribution effect on factors in this approach are explained and validated with different time series databases for some dynamical system.

Keywords: time series, fluctuation in statistical characteristics, optimal learning, change-point algorithm

Procedia PDF Downloads 398
2008 Developing Academic English through Interaction

Authors: John Bankier

Abstract:

Development of academic English occurs not only in communities of practice but also within wider social networks, referred to by Zappa-Hollman and Duff as individual networks of practice. Such networks may exist whether students are developing academic English in English-dominant contexts or in contexts in which English is not a majority language. As yet, little research has examined how newcomers to universities interact with a variety of social ties in such networks to receive academic and emotional support as they develop the academic English necessary to succeed in local and global academia. The one-year ethnographic study described in this presentation followed five Japanese university students enrolled on an academic English program in their home country. We graphically represent participants’ individual networks of practice related to academic English and display the role of interaction in these networks to socialization. Specific examples of academic practices will be linked to specific instances of social interaction. Interaction supportive of the development of academic practices often occurred during unplanned interactions outside the classroom and among small groups of close friends who were connected to each other in more than one way, such as those taking multiple classes together. These interactions occurred in study spaces, in hallways between class periods, at lunchtimes, and online. However, constraints such as differing accommodation arrangements, class scheduling and the hierarchical levelling of English classes by test scores discouraged some participants both from forming strong ties related to English and from interacting with existing ties. The presentation will briefly describe ways in which teachers in all contexts can maximise interaction outside the classroom.

Keywords: academic, english, practice, network

Procedia PDF Downloads 237
2007 Remittances, Unemployement and Demographic Changes between Tunisia and Europe

Authors: Hajer Habib, Ghazi Boulila

Abstract:

The objective of this paper is to present our contribution to the theoretical literature through a simple theoretical model dealing with the effect of transferring funds on the labor market of the countries of origin and on the other hand to test this relationship empirically in the case of Tunisia. The methodology used consists of estimating a panel of the nine main destinations of the Tunisian diaspora in Europe between 1994 and 2014 in order to better value the net effect of these migratory financial flows on unemployment through population growth. The empirical results show that the main factors explaining the decision to emigrate are the economic factors related mainly to the income differential, the demographic factors related to the differential age structure of the origin and host populations, and the cultural factors linked basically to the mastery of the language. Indeed, the stock of migrants is one of the main determinants of the transfer of migratory funds to Tunisia. But there are other variables that do not lack importance such as the economic conditions linked by the host countries. This shows that Tunisian migrants react more to economic conditions in European countries than in Tunisia. The economic situation of European countries dominates the numbers of emigrants as an explanatory factor for the amount of transfers from Tunisian emigrants to their country of origin. Similarly, it is clear that there is an indirect effect of transfers on unemployment in Tunisia. This suggests that the demographic transition conditions the effects of transferring funds on the level of unemployment.

Keywords: demographic changes, international migration, labor market, remittances

Procedia PDF Downloads 122
2006 The Information-Seeking Behaviour of Kuwaiti Judges (KJs)

Authors: Essam Mansour

Abstract:

The key purpose of this study is to show information-seeking behaviour of Kuwaiti Judges (KJs). Being one of the few studies about the information needs and information-seeking behaviour conducted in Arab and developing countries, this study is a pioneer one among many studies conducted in information seeking, especially with this significant group of information users. The authors tried to investigate this seeking behavior in terms of KJs' thoughts, perceptions, motivations, techniques, preferences, tools and barriers met when seeking information. The authors employed a questionnaire, with a response rate 77.2 percent. This study showed that most of KJs were likely to be older, educated and with a work experience ranged from new to old experience. There is a statistically reliable significant difference between KJs' demographic characteristics and some sources of information, such as books, encyclopedias, references and mass media. KJs were using information moderately to make a decision, to be in line with current events, to collect statistics and to make a specific/general research. The office and home were the most frequent location KJs were accessing information from. KJs' efficiency level of the English language is described to be moderately good, and a little number of them confirmed that their efficiency level of French was not bad. The assistance provided by colleagues, followed by consultants, translators, sectaries and librarians were found to be most strong types of assistance needed when seeking information. Mobile apps, followed by PCs, information networks (the Internet) and information databases were the highest technology tool used by KJs. Printed materials, followed by non-printed and audiovisual materials were the most preferred information formats KJs use. The use of languages, the recency of information and the place of information, the deficit role of the library to deliver information were at least significant barriers to KJs when seeking information.

Keywords: information users, information-seeking behaviour, information needs, judges, Kuwait

Procedia PDF Downloads 278
2005 Using Speech Emotion Recognition as a Longitudinal Biomarker for Alzheimer’s Diseases

Authors: Yishu Gong, Liangliang Yang, Jianyu Zhang, Zhengyu Chen, Sihong He, Xusheng Zhang, Wei Zhang

Abstract:

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide and is characterized by cognitive decline and behavioral changes. People living with Alzheimer’s disease often find it hard to complete routine tasks. However, there are limited objective assessments that aim to quantify the difficulty of certain tasks for AD patients compared to non-AD people. In this study, we propose to use speech emotion recognition (SER), especially the frustration level, as a potential biomarker for quantifying the difficulty patients experience when describing a picture. We build an SER model using data from the IEMOCAP dataset and apply the model to the DementiaBank data to detect the AD/non-AD group difference and perform longitudinal analysis to track the AD disease progression. Our results show that the frustration level detected from the SER model can possibly be used as a cost-effective tool for objective tracking of AD progression in addition to the Mini-Mental State Examination (MMSE) score.

Keywords: Alzheimer’s disease, speech emotion recognition, longitudinal biomarker, machine learning

Procedia PDF Downloads 81
2004 Improving System Performance through User's Resource Access Patterns

Authors: K. C. Wong

Abstract:

This paper demonstrates a number of examples in the hope to shed some light on the possibility of designing future operating systems in a more adaptation-based manner. A modern operating system, we conceive, should possess the capability of 'learning' in such a way that it can dynamically adjust its services and behavior according to the current status of the environment in which it operates. In other words, a modern operating system should play a more proactive role during the session of providing system services to users. As such, a modern operating system is expected to create a computing environment, in which its users are provided with system services more matching their dynamically changing needs. The examples demonstrated in this paper show that user's resource access patterns 'learned' and determined during a session can be utilized to improve system performance and hence to provide users with a better and more effective computing environment. The paper also discusses how to use the frequency, the continuity, and the duration of resource accesses in a session to quantitatively measure and determine user's resource access patterns for the examples shown in the paper.

Keywords: adaptation-based systems, operating systems, resource access patterns, system performance

Procedia PDF Downloads 111
2003 An Investigation of the Relationship Between Privacy Crisis, Public Discourse on Privacy, and Key Performance Indicators at Facebook (2004–2021)

Authors: Prajwal Eachempati, Laurent Muzellec, Ashish Kumar Jha

Abstract:

We use Facebook as a case study to investigate the complex relationship between the firm’s public discourse (and actions) surrounding data privacy and the performance of a business model based on monetizing user’s data. We do so by looking at the evolution of public discourse over time (2004–2021) and relate topics to revenue and stock market evolution Drawing from archival sources like Zuckerberg We use LDA topic modelling algorithm to reveal 19 topics regrouped in 6 major themes. We first show how, by using persuasive and convincing language that promises better protection of consumer data usage, but also emphasizes greater user control over their own data, the privacy issue is being reframed as one of greater user control and responsibility. Second, we aim to understand and put a value on the extent to which privacy disclosures have a potential impact on the financial performance of social media firms. There we found significant relationship between the topics pertaining to privacy and social media/technology, sentiment score and stock market prices. Revenue is found to be impacted by topics pertaining to politics and new product and service innovations while number of active users is not impacted by the topics unless moderated by external control variables like Return on Assets and Brand Equity.

Keywords: public discourses, data protection, social media, privacy, topic modeling, business models, financial performance

Procedia PDF Downloads 61
2002 Colors and Interiority - A Study on the Relationship of Colors and Interior Spaces

Authors: Mahwish Ghulam Rasool

Abstract:

The design of a space is a complex process that involves multiple stages, from conceptualization, identifying design problems to understanding the context, materiality, and functionality of the space. Out of all the design elements, color is one of the most dominant and expressive factors that affect the spatial dynamics of the interior space. Color affects aesthetic comfort in space and has a lasting impact on human perception and psychology. Using color as a tool for creating spatial experiences is a new paradigm. Color semantics in spaces are not only used for surface treatment or aesthetics, but it also has more powerful functional characteristics. As interior spaces are evolving and becoming experiential with each decade, designers are looking for new processes to enhance the spatial and experiential quality of interior spaces. The relationship between color and interior typologies is a relatively new paradigm. This paper discusses the role of colors in interior spaces from various perspectives, exploring their impact on the formation of interior typologies and the use of colors in space design. The paper analyzes interior typologies worldwide, from residential to commercial interior spaces, where color semantics plays a prominent role in the design. The paper also emphasizes the design process and the creation of design language, unveiling the possibilities of applying colors in interior spaces that can be in harmony with the building context, space functionality, or in opposition to the existing building envelope or environment. The paper aims to contribute to the field of interior design education and practices. By using experimental and various research methodologies for investigation, it aims to fill the gap in the literature regarding color semantics and the relationship between interior typologies.

Keywords: color psychology, color semantics, interior environments, interior typologies

Procedia PDF Downloads 42
2001 1D Convolutional Networks to Compute Mel-Spectrogram, Chromagram, and Cochleogram for Audio Networks

Authors: Elias Nemer, Greg Vines

Abstract:

Time-frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training networks on frequency features such as the Mel-Spectrogram or Cochleogram have been proven more effective and convenient than training on-time samples. In practical realizations, these features are created on a different processor and/or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with different features. In this paper, we provide a PyTorch framework for creating various spectral features as well as time-frequency transformation and time-domain filter-banks using the built-in trainable conv1d() layer. This allows computing these features on the fly as part of a larger network and enabling easier experimentation with various combinations and parameters. Our work extends the work in the literature developed for that end: First, by adding more of these features and also by allowing the possibility of either starting from initialized kernels or training them from random values. The code is written as a template of classes and scripts that users may integrate into their own PyTorch classes or simply use as is and add more layers for various applications.

Keywords: neural networks Mel-Spectrogram, chromagram, cochleogram, discrete Fourrier transform, PyTorch conv1d()

Procedia PDF Downloads 196
2000 Functional Neural Network for Decision Processing: A Racing Network of Programmable Neurons Where the Operating Model Is the Network Itself

Authors: Frederic Jumelle, Kelvin So, Didan Deng

Abstract:

In this paper, we are introducing a model of artificial general intelligence (AGI), the functional neural network (FNN), for modeling human decision-making processes. The FNN is composed of multiple artificial mirror neurons (AMN) racing in the network. Each AMN has a similar structure programmed independently by the users and composed of an intention wheel, a motor core, and a sensory core racing at a specific velocity. The mathematics of the node’s formulation and the racing mechanism of multiple nodes in the network will be discussed, and the group decision process with fuzzy logic and the transformation of these conceptual methods into practical methods of simulation and in operations will be developed. Eventually, we will describe some possible future research directions in the fields of finance, education, and medicine, including the opportunity to design an intelligent learning agent with application in AGI. We believe that FNN has a promising potential to transform the way we can compute decision-making and lead to a new generation of AI chips for seamless human-machine interactions (HMI).

Keywords: neural computing, human machine interation, artificial general intelligence, decision processing

Procedia PDF Downloads 94
1999 Comprehensive Lifespan Support for Quality of Life

Authors: Joann Douziech

Abstract:

Individuals with intellectual and developmental disabilities (IDD) possess characteristics that present both challenges and gifts. Individuals with IDD require and are worthy of intentional, strategic, and specialized support throughout their lifespan to ensure optimum quality-of-life outcomes. The current global advocacy movement advancing the rights of individuals with IDD emphasizes a high degree of choice over life decisions. For some individuals, this degree of choice results in a variety of negative health and well-being outcomes. Improving the quality of life outcomes requires the combination of a commitment to the rights of the individual with a responsibility to provide support and choice commensurate with individual capacity. A belief that individuals with IDD are capable of learning and they are worthy of being taught provides the foundation for a holistic model of support throughout their lifespan. This model is based on three pillars of engineering the environment, promoting skill development and maintenance, and staff support. In an ever-changing world, supporting quality of life requires attention to moments, phases, and changes in stages throughout the lifespan. Balancing these complexities with strategic, responsive, and dynamic interventions enhances the quality of life of individuals with ID throughout their lifespan.

Keywords: achieving optimum quality of life, comprehensive support, lifespan approach, philosophy and pedagogy

Procedia PDF Downloads 43
1998 Effects of Screen Time on Children from a Systems Engineering Perspective

Authors: Misagh Faezipour

Abstract:

This paper explores the effects of screen time on children from a systems engineering perspective. We reviewed literature from several related works on the effects of screen time on children to explore all factors and interrelationships that would impact children that are subjected to using long screen times. Factors such as kids' age, parent attitudes, parent screen time influence, amount of time kids spend with technology, psychosocial and physical health outcomes, reduced mental imagery, problem-solving and adaptive thinking skills, obesity, unhealthy diet, depressive symptoms, health problems, disruption in sleep behavior, decrease in physical activities, problematic relationship with mothers, language, social, emotional delays, are examples of some factors that could be either a cause or effect of screen time. A systems engineering perspective is used to explore all the factors and factor relationships that were discovered through literature. A causal model is used to illustrate a graphical representation of these factors and their relationships. Through the causal model, the factors with the highest impacts can be realized. Future work would be to develop a system dynamics model to view the dynamic behavior of the relationships and observe the impact of changes in different factors in the model. The different changes on the input of the model, such as a healthier diet or obesity rate, would depict the effect of the screen time in the model and portray the effect on the children’s health and other factors that are important, which also works as a decision support tool.

Keywords: children, causal model, screen time, systems engineering, system dynamics

Procedia PDF Downloads 118
1997 The Impact of Technology on Sales Researches and Distribution

Authors: Nady Farag Faragalla Hanna

Abstract:

In the car dealership industry in Japan, the sales specialist is a key factor in the success of the company. I hypothesize that when a company understands the characteristics of sales professionals in its industry, it is easier to recruit and train salespeople effectively. Lean human resources management ensures the economic success and performance of companies, especially small and medium-sized companies.The purpose of the article is to determine the characteristics of sales specialists for small and medium-sized car dealerships using the chi-square test and the proximate variable model. Accordingly, the results show that career change experience, learning ability and product knowledge are important, while university education, career building through internal transfer, leadership experience and people development are not important for becoming a sales professional. I also show that the characteristics of sales specialists are perseverance, humility, improvisation and passion for business.

Keywords: electronics engineering, marketing, sales, E-commerce digitalization, interactive systems, sales process ARIMA models, sales demand forecasting, time series, R codetraits of sales professionals, variable precision rough sets theory, sales professional, sales professionals

Procedia PDF Downloads 17
1996 Knowledge Based Behaviour Modelling and Execution in Service Robotics

Authors: Suraj Nair, Aravindkumar Vijayalingam, Alexander Perzylo, Alois Knoll

Abstract:

In the last decade robotics research and development activities have grown rapidly, especially in the domain of service robotics. Integrating service robots into human occupied spaces such as homes, offices, hospitals, etc. has become increasingly worked upon. The primary motive is to ease daily lives of humans by taking over some of the household/office chores. However, several challenges remain in systematically integrating such systems in human shared work-spaces. In addition to sensing and indoor-navigation challenges, programmability of such systems is a major hurdle due to the fact that the potential user cannot be expected to have knowledge in robotics or similar mechatronic systems. In this paper, we propose a cognitive system for service robotics which allows non-expert users to easily model system behaviour in an underspecified manner through abstract tasks and objects associated with them. The system uses domain knowledge expressed in the form of an ontology along with logical reasoning mechanisms to infer all the missing pieces of information required for executing the tasks. Furthermore, the system is also capable of recovering from failed tasks arising due to on-line disturbances by using the knowledge base and inferring alternate methods to execute the same tasks. The system is demonstrated through a coffee fetching scenario in an office environment using a mobile robot equipped with sensors and software capabilities for autonomous navigation and human-interaction through natural language.

Keywords: cognitive robotics, reasoning, service robotics, task based systems

Procedia PDF Downloads 209
1995 E-teaching Barriers: A Survey from Shanghai Primary School Teachers

Authors: Liu Dan

Abstract:

It was considered either unnecessary or impossible for primary school students to implement online teaching until last year. A large number of E-learning or E-teaching researches have been focused on adult-learners, andragogy and technology, however, primary school education, it is facing many problems that need to be solved. Therefore, this research is aimed at exploring barriers and influential factors on online teaching for K-12 students from teachers’ perspectives and discussing the E-pedagogy that is suitable for primary school students and teachers. Eight hundred and ninety-six teachers from 10 primary schools in Shanghai were invited to participate in a questionnaire survey. Data were analysed by hierarchical regression, and the results stress the significant three barriers by teachers with online teaching: the existing system is deficient in emotional interaction, teachers’ attitude towards the technology is negative and the present teacher training is lack of systematic E-pedagogy guidance. The barriers discovered by this study will help the software designers (E-lab) develop tools that allow for flexible and evolving pedagogical approaches whilst providing an easy entry point for cautious newcomers, so that help the teachers free to engage in E-teaching at pedagogical and disciplinary levels, to enhance their repertoire of teaching practices.

Keywords: online teaching barriers (OTB), e-teaching, primary school, teachers, technology

Procedia PDF Downloads 175
1994 Simulation of Flow through Dam Foundation by FEM and ANN Methods Case Study: Shahid Abbaspour Dam

Authors: Mehrdad Shahrbanozadeh, Gholam Abbas Barani, Saeed Shojaee

Abstract:

In this study, a finite element (Seep3D model) and an artificial neural network (ANN) model were developed to simulate flow through dam foundation. Seep3D model is capable of simulating three-dimensional flow through a heterogeneous and anisotropic, saturated and unsaturated porous media. Flow through the Shahid Abbaspour dam foundation has been used as a case study. The FEM with 24960 triangular elements and 28707 nodes applied to model flow through foundation of this dam. The FEM being made denser in the neighborhood of the curtain screen. The ANN model developed for Shahid Abbaspour dam is a feedforward four layer network employing the sigmoid function as an activator and the back-propagation algorithm for the network learning. The water level elevations of the upstream and downstream of the dam have been used as input variables and the piezometric heads as the target outputs in the ANN model. The two models are calibrated and verified using the Shahid Abbaspour’s dam piezometric data. Results of the models were compared with those measured by the piezometers which are in good agreement. The model results also revealed that the ANN model performed as good as and in some cases better than the FEM.

Keywords: seepage, dam foundation, finite element method, neural network, seep 3D model

Procedia PDF Downloads 445
1993 Reusing Assessments Tests by Generating Arborescent Test Groups Using a Genetic Algorithm

Authors: Ovidiu Domşa, Nicolae Bold

Abstract:

Using Information and Communication Technologies (ICT) notions in education and three basic processes of education (teaching, learning and assessment) can bring benefits to the pupils and the professional development of teachers. In this matter, we refer to these notions as concepts taken from the informatics area and apply them to the domain of education. These notions refer to genetic algorithms and arborescent structures, used in the specific process of assessment or evaluation. This paper uses these kinds of notions to generate subtrees from a main tree of tests related between them by their degree of difficulty. These subtrees must contain the highest number of connections between the nodes and the lowest number of missing edges (which are subtrees of the main tree) and, in the particular case of the non-existence of a subtree with no missing edges, the subtrees which have the lowest (minimal) number of missing edges between the nodes, where a node is a test and an edge is a direct connection between two tests which differs by one degree of difficulty. The subtrees are represented as sequences. The tests are the same (a number coding a test represents that test in every sequence) and they are reused for each sequence of tests.

Keywords: chromosome, genetic algorithm, subtree, test

Procedia PDF Downloads 296