Search results for: multi-core architectures

Authors: Nazmul Shahadat, Anthony S. Maida

Abstract:

In recent years, hypercomplex inspired neural networks improved deep CNN architectures due to their ability to share weights across input channels and thus improve cohesiveness of representations within the layers. The work described herein studies the effect of replacing existing layers in an Axial Attention ResNet with their quaternion variants that use cross-channel weight sharing to assess the effect on image classification. We expect the quaternion enhancements to produce improved feature maps with more interlinked representations. We experiment with the stem of the network, the bottleneck layer, and the fully connected backend by replacing them with quaternion versions. These modifications lead to novel architectures which yield improved accuracy performance on the ImageNet300k classification dataset. Our baseline networks for comparison were the original real-valued ResNet, the original quaternion-valued ResNet, and the Axial Attention ResNet. Since improvement was observed regardless of which part of the network was modified, there is a promise that this technique may be generally useful in improving classification accuracy for a large class of networks.

Keywords: axial attention, representational networks, weight sharing, cross-channel correlations, quaternion-enhanced axial attention, deep networks

Procedia PDF Downloads 45

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs –Sigmoid, ReLU, and Tanh–have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment with multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLUReLU) combination. Our results show that using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: activation function, universal approximation function, neural networks, convergence

Procedia PDF Downloads 126

Authors: Parisa Golbayani, Dan Wang, Ionut¸ Florescu

Abstract:

In this work we implement machine learning techniques to financial statement reports in order to asses company’s credit rating. Specifically, the work analyzes the performance of four neural network architectures (MLP, CNN, CNN2D, LSTM) in predicting corporate credit rating as issued by Standard and Poor’s. The paper focuses on companies from the energy, financial, and healthcare sectors in the US. The goal of this analysis is to improve application of machine learning algorithms to credit assessment. To accomplish this, the study investigates three questions. First, we investigate if the algorithms perform better when using a selected subset of important features or whether better performance is obtained by allowing the algorithms to select features themselves. Second, we address the temporal aspect inherent in financial data and study whether it is important for the results obtained by a machine learning algorithm. Third, we aim to answer if one of the four particular neural network architectures considered consistently outperforms the others, and if so under which conditions. This work frames the problem as several case studies to answer these questions and analyze the results using ANOVA and multiple comparison testing procedures.

Keywords: convolutional neural network, long short term memory, multilayer perceptron, credit rating

Procedia PDF Downloads 207

Authors: Surupa Shaw, Debjyoti Banerjee

Abstract:

Enhancing heat transfer in compact volumes is a challenge when constrained by cost issues, especially those associated with requirements for minimizing pumping power consumption. This is particularly acute for electronic chip cooling applications. Technological advancements in microelectronics have led to development of chip architectures that involve increased power consumption. As a consequence packaging, technologies are saddled with needs for higher rates of power dissipation in smaller form factors. The increasing circuit density, higher heat flux values for dissipation and the significant decrease in the size of the electronic devices are posing thermal management challenges that need to be addressed with a better design of the cooling system. Maximizing surface area for heat exchanging surfaces (e.g., extended surfaces or “fins”) can enable dissipation of higher levels of heat flux. Fractal structures have been shown to maximize surface area in compact volumes. Self-replicating structures at multiple length scales are called “Fractals” (i.e., objects with fractional dimensions; unlike regular geometric objects, such as spheres or cubes whose volumes and surface area values scale as integer values of the length scale dimensions). Fractal structures are expected to provide an appropriate technology solution to meet these challenges for enhanced heat transfer in the microelectronic devices by maximizing surface area available for heat exchanging fluids within compact volumes. In this study, the effect of different fractal micro-channel architectures and flow structures on the enhancement of transport phenomena in heat exchangers is explored by parametric variation of fractal dimension. This study proposes a model that would enable cost-effective solutions for thermal-fluid transport for energy applications. The objective of this study is to ascertain the sensitivity of various parameters (such as heat flux and pressure gradient as well as pumping power) to variation in fractal dimension. The role of the fractal parameters will be instrumental in establishing the most effective design for the optimum cooling of microelectronic devices. This can help establish the requirement of minimal pumping power for enhancement of heat transfer during cooling. Results obtained in this study show that the proposed models for fractal architectures of microchannels significantly enhanced heat transfer due to augmentation of surface area in the branching networks of varying length-scales.

Keywords: fractals, microelectronics, constructal theory, heat transfer enhancement, pumping power enhancement

Procedia PDF Downloads 290

Authors: Pranav Gunhal

Abstract:

This paper presents an analysis of sentiment on Twitter towards the Karnataka elections held in 2023, utilizing transformer-based models specifically designed for sentiment analysis in Indic languages. Through an innovative data collection approach involving a combination of novel methods of data augmentation, online data preceding the election was analyzed. The study focuses on sentiment classification, effectively distinguishing between positive, negative, and neutral posts while specifically targeting the sentiment regarding the loss of the Bharatiya Janata Party (BJP) or the win of the Indian National Congress (INC). Leveraging high-performing transformer architectures, specifically IndicBERT, coupled with specifically fine-tuned hyperparameters, the AI models employed in this study achieved remarkable accuracy in predicting the INC’s victory in the election. The findings shed new light on the potential of cutting-edge transformer-based models in capturing and analyzing sentiment dynamics within the Indian political landscape. The implications of this research are far-reaching, providing invaluable insights to political parties for informed decision-making and strategic planning in preparation for the forthcoming 2024 Lok Sabha elections in the nation.

Keywords: sentiment analysis, twitter, Karnataka elections, congress, BJP, transformers, Indic languages, AI, novel architectures, IndicBERT, lok sabha elections

Procedia PDF Downloads 59

Authors: Oliver Bertram, Leonel Akoto Chama

Abstract:

In today's civil transport aircraft, the design of flight control systems is based on the experience gained from previous aircraft configurations with a clear distinction between primary and secondary flight control functions for controlling the aircraft altitude and trajectory. Significant system improvements are now seen particularly in multifunctional moveable concepts where the flight control functions are no longer considered separate but integral. This allows new functions to be implemented in order to improve the overall aircraft performance. However, the classical design process of flight controls is sequential and insufficiently interdisciplinary. In particular, the systems discipline is involved only rudimentarily in the early phase. In many cases, the task of systems design is limited to meeting the requirements of the upstream disciplines, which may lead to integration problems later. For this reason, approaching design with an incremental development is required to reduce the risk of a complete redesign. Although the potential and the path to multifunctional moveable concepts are shown, the complete re-engineering of aircraft concepts with less classic moveable concepts is associated with a considerable risk for the design due to the lack of design methods. This represents an obstacle to major leaps in technology. This gap in state of the art is even further increased if, in the future, unconventional aircraft configurations shall be considered, where no reference data or architectures are available. This means that the use of the above-mentioned experience-based approach used for conventional configurations is limited and not applicable to the next generation of aircraft. In particular, there is a need for methods and tools for a rapid trade-off between new multifunctional flight control systems architectures. To close this gap in the state of the art, an integrated system-driven design process for multifunctional flight control systems of non-classical aircraft configurations will be presented. The overall goal of the design process is to find optimal solutions for single or combined target criteria in a fast process from the very large solution space for the flight control system. In contrast to the state of the art, all disciplines are involved for a holistic design in an integrated rather than a sequential process. To emphasize the systems discipline, this paper focuses on the methodology for designing moveable actuation systems in the context of this integrated design process of multifunctional moveables. The methodology includes different approaches for creating system architectures, component design methods as well as the necessary process outputs to evaluate the systems. An application example of a reference configuration is used to demonstrate the process and validate the results. For this, new unconventional hydraulic and electrical flight control system architectures are calculated which result from the higher requirements for multifunctional moveable concept. In addition to typical key performance indicators such as mass and required power requirements, the results regarding the feasibility and wing integration aspects of the system components are examined and discussed here. This is intended to show how the systems design can influence and drive the wing and overall aircraft design.

Keywords: actuation systems, flight control surfaces, multi-functional movables, wing design process

Procedia PDF Downloads 108

Authors: Azadeh Rezafar

Abstract:

Iran is one of the oldest countries with traditional culture in the world. All over the history Iranians had traditional architectural designs, which were at the same time sustainable, ecological, functional and environmental consistent. These human scale architectures were built for maximum use, comfort, climate adaptation with available resources and techniques. Climate variability of the country caused developing of variety design methods. More of these methods such as windcatchers in Yazd City or Panam (Insulation) were scientific solutions at the same time. Renewable energy resources were used in these methods that featured in them. While climate and ecological issues were dominant parts of these traditional designs, aesthetic and beauty issues were not ignored. Conformity with the community’s culture caused more compact designs that the visual aesthetics of them can be seen inside of them. Different organizations of space were used for these visual aesthetic issues inside the houses as well as historical urban designs. For example dry and hot climates in central parts of the country designed with centralized organization. Most central parts of these designs functioned as a courtyard for temperate the air in the summer. This paper will give summary descriptive information about traditional Iranian architectural style by figures all around the country with different climate conditions, while focus of the paper is traditional architectural design of the central part of the country, with dry and hot climate condition. This information may be useful for contemporary architectural designs, which are designed without noticing to the vernacular condition and caused cities look like each other.

Keywords: architectural design, traditional design, Iran, sustainability

Procedia PDF Downloads 190

Authors: Sebastian Hiergeist

Abstract:

It is a common view that Unmanned Aerial Vehicles (UAV) tend to migrate into the civil airspace. This trend is challenging UAV manufacturer in plenty ways, as there come up a lot of new requirements and functional aspects. On the higher application levels, this might be collision detection and avoidance and similar features, whereas all these functions only act as input for the flight control components of the aircraft. The flight control computer (FCC) is the central component when it comes up to ensure a continuous safe flight and landing. As these systems are flight critical, they have to be built up redundantly to be able to provide a Fail-Operational behavior. Recent architectural approaches of FCCs used in UAV systems are often based on very simple microprocessors in combination with proprietary Application-Specific Integrated Circuit (ASIC) or Field Programmable Gate Array (FPGA) extensions implementing the whole redundancy functionality. In the future, such simple microprocessors may not be available anymore as they are more and more replaced by higher sophisticated System on Chip (SoC). As the avionic industry cannot provide enough market power to significantly influence the development of new semiconductor products, the use of solutions from foreign markets is almost inevitable. Products stemming from the industrial market developed according to IEC 61508, or automotive SoCs, according to ISO 26262, can be seen as candidates as they have been developed for similar environments. Current available SoC from the industrial or automotive sector provides quite a broad selection of interfaces like, i.e., Ethernet, SPI or FlexRay, that might come into account for the implementation of a redundancy network. In this context, possible network architectures shall be investigated which could be established by using the interfaces stated above. Of importance here is the avoidance of any single point of failures, as well as a proper segregation in distinct fault containment regions. The performed analysis is supported by the use of guidelines, published by the aviation authorities (FAA and EASA), on the reliability of data networks. The main focus clearly lies on the reachable level of safety, but also other aspects like performance and determinism play an important role and are considered in the research. Due to the further increase in design complexity of recent and future SoCs, also the risk of design errors, which might lead to common mode faults, increases. Thus in the context of this work also the aspect of dissimilarity will be considered to limit the effect of design errors. To achieve this, the work is limited to broadly available interfaces available in products from the most common silicon manufacturer. The resulting work shall support the design of future UAV FCCs by giving a guideline on building up a redundancy network between SoCs, solely using on board interfaces. Therefore the author will provide a detailed usability analysis on available interfaces provided by recent SoC solutions, suggestions on possible redundancy architectures based on these interfaces and an assessment of the most relevant characteristics of the suggested network architectures, like e.g. safety or performance.

Keywords: redundancy, System-on-Chip, UAV, flight control computer (FCC)

Procedia PDF Downloads 185

Authors: Imen Amari, Kaouther Gasmi, Asma Rebaya, Salem Hasnaoui

Abstract:

The problem of scheduling and mapping data flow applications on multi-core architectures is notoriously difficult. This difficulty is related to the rapid evaluation of Telecommunication and multimedia systems accompanied by a rapid increase of user requirements in terms of latency, execution time, consumption, energy, etc. Having an optimal scheduling on multi-cores DSP (Digital signal Processors) platforms is a challenging task. In this context, we present a novel technic and algorithm in order to find a valid schedule that optimizes the key performance metrics particularly the Latency. Our contribution is based on Satisfiability Modulo Theories (SMT) solving technologies which is strongly driven by the industrial applications and needs. This paper, describe a scheduling module integrated in our proposed Workflow which is advised to be a successful approach for programming the applications based on NoC-DSP platforms. This workflow transform automatically a Simulink model to a synchronous dataflow (SDF) model. The automatic transformation followed by SMT solver scheduling aim to minimize the final latency and other software/hardware metrics in terms of an optimal schedule. Also, finding the optimal numbers of cores to be used. In fact, our proposed workflow taking as entry point a Simulink file (.mdl or .slx) derived from embedded Matlab functions. We use an approach which is based on the synchronous and hierarchical behavior of both Simulink and SDF. Whence, results of running the scheduler which exist in the Workflow mentioned above using our proposed SMT solver algorithm refinements produce the best possible scheduling in terms of latency and numbers of cores.

Keywords: multi-cores DSP, scheduling, SMT solver, workflow

Procedia PDF Downloads 253

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

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

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

Procedia PDF Downloads 103

Authors: Elisavet Anastasiadou

Abstract:

Global citizenship refers to an economic, social, political, and cultural interconnectedness, and it is inextricably intertwined with social justice, respect for human rights, peace, and a sense of responsibility to act on a local and global level. It aims to be transformative, enhance critical thinking and participation with pedagogical approaches based on social justice and democracy. The purpose of this study is to explore how Global Citizenship Education (GCE) is presented and implemented in two educational contexts, specifically in the curricula and pedagogical practices of primary education in Finland and Scotland. The impact of GCE is recognized as means for further development by institution such as and Finnish and Scottish curricula acknowledge the significance of GCE, emphasizing the student's ability to act and succeed in diverse and global communities. This comparative study should provide a good basis for further developing teaching practices based on informed understanding of how GCE is constrained or enabled from two different perspectives, extend the methodological applications of Practice Architectures and provide critical insights into GCE as a theoretical notion adopted by national and international educational policy. The study is directly connected with global citizenship aiming at future and societal change. The empirical work employs a multiple case study approach, including interviews and analysis of existing documents (textbook, curriculum). The data consists of the Finnish and Scottish curriculum. A systematic analysis of the curriculum in relation to GCE will offer insights into how the aims of GCE are presented and framed within the two contexts. This will be achieved using the theory of Practice Architectures. Curricula are official policy documentations (texts) that frame and envisage pedagogical practices. Practices, according to the theory of practice architectures, consist of sayings, doings, and relatings. Hence, even if the text analysis includes the semantic space (sayings) that are prefigured by the cultural-discursive arrangements and the relating prefigured by the socio-political arrangements, they will inevitably reveal information on the (doings) prefigured by the material-economic arrangements, as they hang together in practices. The results will assist educators in making changes to their teaching and enhance their self-conscious understanding of the history-making significance of their practices. It will also have a potential reform and focus on educationally relevant to such issues. Thus, the study will be able to open the ground for interventions and further research while it will consider the societal demands of a world in change.

Keywords: citizenhsip, curriculum, democracy, practices

Procedia PDF Downloads 177

Authors: Ananya Ananya, Karthik Rao

Abstract:

Accurate segmentation of knee cartilage in 3-D magnetic resonance (MR) images for quantitative assessment of volume is crucial for studying and diagnosing osteoarthritis (OA) of the knee, one of the major causes of disability in elderly people. Radiologists generally perform this task in slice-by-slice manner taking 15-20 minutes per 3D image, and lead to high inter and intra observer variability. Hence automatic methods for knee cartilage segmentation are desirable and are an active field of research. This paper presents design and experimental evaluation of 2D convolutional neural networks based fully automated methods for knee cartilage segmentation in 3D MRI. The architectures are validated based on 40 test images and 60 training images from SKI10 dataset. The proposed methods segment 2D slices one by one, which are then combined to give segmentation for whole 3D images. Proposed methods are modified versions of U-net and dilated convolutions, consisting of a single step that segments the given image to 5 labels: background, femoral cartilage, tibia cartilage, femoral bone and tibia bone; cartilages being the primary components of interest. U-net consists of a contracting path and an expanding path, to capture context and localization respectively. Dilated convolutions lead to an exponential expansion of receptive field with only a linear increase in a number of parameters. A combination of modified U-net and dilated convolutions has also been explored. These architectures segment one 3D image in 8 – 10 seconds giving average volumetric Dice Score Coefficients (DSC) of 0.950 - 0.962 for femoral cartilage and 0.951 - 0.966 for tibia cartilage, reference being the manual segmentation.

Keywords: convolutional neural networks, dilated convolutions, 3 dimensional, fully automated, knee cartilage, MRI, segmentation, U-net

Procedia PDF Downloads 231

Authors: John Lamb, Robert Epstein, Vasundhara L. Bhupathi, Sanjeev Kumar Marimekala

Abstract:

In this paper, we focus on the importance of scalable architecture for data centers and buildings in general to help an enterprise achieve environmental sustainability. The scalable architecture helps in many ways, such as adaptability to the business and user requirements, promotes high availability and disaster recovery solutions that are cost effective and low maintenance. The scalable architecture also plays a vital role in three core areas of sustainability: economy, environment, and social, which are also known as the 3 pillars of a sustainability model. If the architecture is scalable, it has many advantages. A few examples are that scalable architecture helps businesses and industries to adapt to changing technology, drive innovation, promote platform independence, and build resilience against natural disasters. Most importantly, having a scalable architecture helps industries bring in cost-effective measures for energy consumption, reduce wastage, increase productivity, and enable a robust environment. It also helps in the reduction of carbon emissions with advanced monitoring and metering capabilities. Scalable architectures help in reducing waste by optimizing the designs to utilize materials efficiently, minimize resources, decrease carbon footprints by using low-impact materials that are environmentally friendly. In this paper we also emphasize the importance of cultural shift towards the reuse and recycling of natural resources for a balanced ecosystem and maintain a circular economy. Also, since all of us are involved in the use of computers, much of the scalable architecture we have studied is related to data centers.

Keywords: scalable architectures, sustainability, application design, disruptive technology, machine learning and natural language processing, AI, social media platform, cloud computing, advanced networking and storage devices, advanced monitoring and metering infrastructure, climate change

Procedia PDF Downloads 47

Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle

Abstract:

Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.

Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3

Procedia PDF Downloads 23

Authors: P. Bauer, K. Mougin, V. Vignal, A. Buch, P. Ponthiaux, D. Faye

Abstract:

Nowadays, noble metallic nanostructures with unique morphology are widely used as new sensors due to their fascinating optical, electronic and catalytic properties. Among various shapes, dendritic nanostructures have attracted much attention because of their large surface-to-volume ratio, high sensitivity and special texture with sharp tips and nanoscale junctions. Several methods have been developed to fabricate those specific structures such as electrodeposition, photochemical way, seed-mediated growth or wet chemical method. The present study deals with a novel approach for a controlled growth pattern-directed organisation of Au flower-like crystals (NFs) deposited onto stainless steel plates to achieve large-scale functional surfaces. This technique consists in the deposition of a soft nanoporous template on which Au NFs are grown by electroplating and seed-mediated method. Size, morphology, and interstructure distance have been controlled by a site selective nucleation process. Dendritic Au nanostructures have appeared as excellent Raman-active candidates due to the presence of very sharp tips of multi-branched Au nanoparticles that leads to a large local field enhancement and a good SERS sensitivity. In addition, these structures have also been used as electrochemical sensors to detect traces of molecules present in a solution. A correlation of the number of active sites on the surface and the current charge by both colorimetric method and cyclic voltammetry of gold structures have allowed a calibration of the system. This device represents a first step for the fabrication of MEMs platform that could ultimately be integrated into a lab-on-chip system. It also opens pathways to several technologically large-scale nanomaterials fabrication such as hierarchically ordered crystal architectures for sensor applications.

Keywords: dendritic, electroplating, gold, template

Procedia PDF Downloads 162

Authors: Robin Ferguson

Abstract:

The context which this paper explores is the provision of Technical Vocational Education and Training (TVET) of southern African workers at sea on local and foreign vessels using a blended learning approach. The pedagogical challenge of providing quality education in this context is that multiple African and foreign languages and cultural norms are found amongst the all-male crew; and there are widely differing levels of education, low levels of digital literacy and limited connectivity. The methodology used is a nested case study. The study describes the mechanisms used to provide ongoing, real-time workplace TVET on two foreign vessels. Some training was done in person when the vessels came into port, however, the majority of the TVET was achieved from shore to ship using a combination of commonly available Google and Microsoft Apps and WhatsApp. Voice, video and text in multiple languages were used to accommodate different learning styles. The learning was supported by the development of learning networks using social media. This paper also reflects on the shore-based organisational change processes required to support sea learning. The conceptual framework used is the Theory of Practice Architectures (TPA) as is provides a site-ontological perspective of the sayings/thinkings, doings and relatings of this workplace training which is multiplanar as it plays out at sea and ashore, in-person and on-line. Using TPA, the overarching practice architectures and supporting structures which confound or enable these learning practices are revealed. The contribution which this paper makes is an insight into an innovative vocational pedagogy which promotes ICT-mediated learning amongst workers who suffer from low levels of literacies and limited ICT-access and who work and live in remote places. It is a pedagogy of possibility which crosses the digital divide.

Keywords: theory of practice architecture, microsoft, google, whatsapp, vocational pedagogy, mariners, distributed workplaces

Procedia PDF Downloads 38

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 67

Authors: M. K. Benhaoua, A. E. H. Benyamina, T. Djeradi, P. Boulet

Abstract:

In this paper, we propose adaptive routing that considers the routing of communications in order to optimize the overall performance. The routing technique uses a newly proposed Algorithm to route communications between the tasks. The routing we propose of the communications leads to a better optimization of several performance metrics (time and energy consumption). Experimental results show that the proposed routing approach provides significant performance improvements when compared to those using static routing.

Keywords: multi-processor systems-on-chip (mpsocs), network-on-chip (noc), heterogeneous architectures, adaptive routin

Procedia PDF Downloads 347

Authors: Rajaa Filali, Mohamed Bouhdadi

Abstract:

This paper presents an incremental formal development of the Wireless Transaction Protocol (WTP) in Event-B. WTP is part of the Wireless Application Protocol (WAP) architectures and provides a reliable request-response service. To model and verify the protocol, we use the formal technique Event-B which provides an accessible and rigorous development method. This interaction between modelling and proving reduces the complexity and helps to eliminate misunderstandings, inconsistencies, and specification gaps. As result, verification of WTP allows us to find some deficiencies in the current specification.

Keywords: event-B, wireless transaction protocol, proof obligation, refinement, Rodin, ProB

Procedia PDF Downloads 290

Authors: Marina Vicario, Amadeo Argüelles, Pilar Gómez, Carlos Hernández

Abstract:

In this paper, the Computer Research Network of the National Polytechnic Institute of Mexico proposes a paradigmatic model for the inference of cognitive patterns in digital learning systems. This model leads to metadata architecture useful for analysis and prediction in online learning systems; especially on MOOc's architectures. The model is in the design phase and expects to be tested through an institutional of courses project which is going to develop for the MOOc.

Keywords: cognitive footprints, learning analytics, predictive learning, digital learning, educational computing, educational informatics

Procedia PDF Downloads 439

Authors: Massimiliano Nastri

Abstract:

The study examines the façade systems according to the constitutive and typological characters, as well as the functional and applicative requirements such as the expressive, constructive, and interactive criteria towards the environmental, perceptive, and energy conditions. The envelope systems are understood as instruments of mediation, interchange, and dynamic interaction between environmental conditions. The façades are observed for the sustainable concept of eco-efficient envelopes, selective and multi-purpose filters, adaptable and adjustable according to the environmental performance.

Keywords: typologies of façades, environmental and energy sustainability, interaction and perceptive mediation, technical skins

Procedia PDF Downloads 108

Authors: M. K. Benhaoua, A. K. Singh, A. E. H. Benyamina

Abstract:

In this paper, we propose heuristic for dynamic communications mapping that considers the placement of communications in order to optimize the overall performance. The mapping technique uses a newly proposed Algorithm to place communications between the tasks. The placement we propose of the communications leads to a better optimization of several performance metrics (time and energy consumption). Experimental results show that the proposed mapping approach provides significant performance improvements when compared to those using static routing.

Keywords: Multi-Processor Systems-on-Chip (MPSoCs), Network-on-Chip (NoC), heterogeneous architectures, dynamic mapping heuristics

Procedia PDF Downloads 503

Authors: Thilina Ranaweera, Enes Makalic, John L. Hopper, Adrian Bickerstaffe

Abstract:

Data are the primary asset of biomedical researchers, and the engine for both discovery and research translation. As the volume and complexity of research datasets increase, especially with new technologies such as large single nucleotide polymorphism (SNP) chips, so too does the requirement for software to manage, process and analyze the data. Researchers often need to execute complicated queries and conduct complex analyzes of large-scale datasets. Existing tools to analyze such data, and other types of high-dimensional data, unfortunately suffer from one or more major problems. They typically require a high level of computing expertise, are too simplistic (i.e., do not fit realistic models that allow for complex interactions), are limited by computing power, do not exploit the computing power of large-scale parallel architectures (e.g. supercomputers, GPU clusters etc.), or are limited in the types of analysis available, compounded by the fact that integrating new analysis methods is not straightforward. Solutions to these problems, such as those developed and implemented on parallel architectures, are currently available to only a relatively small portion of medical researchers with access and know-how. The past decade has seen a rapid expansion of data management systems for the medical domain. Much attention has been given to systems that manage phenotype datasets generated by medical studies. The introduction of heterogeneous genomic data for research subjects that reside in these systems has highlighted the need for substantial improvements in software architecture. To address this problem, we have developed SPARK, an enabling and translational system for medical research, leveraging existing high performance computing resources, and analysis techniques currently available or being developed. It builds these into The Ark, an open-source web-based system designed to manage medical data. SPARK provides a next-generation biomedical data management solution that is based upon a novel Micro-Service architecture and Big Data technologies. The system serves to demonstrate the applicability of Micro-Service architectures for the development of high performance computing applications. When applied to high-dimensional medical datasets such as genomic data, relational data management approaches with normalized data structures suffer from unfeasibly high execution times for basic operations such as insert (i.e. importing a GWAS dataset) and the queries that are typical of the genomics research domain. SPARK resolves these problems by incorporating non-relational NoSQL databases that have been driven by the emergence of Big Data. SPARK provides researchers across the world with user-friendly access to state-of-the-art data management and analysis tools while eliminating the need for high-level informatics and programming skills. The system will benefit health and medical research by eliminating the burden of large-scale data management, querying, cleaning, and analysis. SPARK represents a major advancement in genome research technologies, vastly reducing the burden of working with genomic datasets, and enabling cutting edge analysis approaches that have previously been out of reach for many medical researchers.

Keywords: biomedical research, genomics, information systems, software

Procedia PDF Downloads 237

Authors: Ahmed Madian, Muaz Aljarhi

Abstract:

Coordinate Rotation Digital Computer (CORDIC) is a unique digital computing unit intended for the computation of mathematical operations and functions. This paper presents a multi-CORDIC processor that integrates different CORDIC architectures on a single FPGA chip and allows the user to select the CORDIC architecture to proceed with based on what he wants to calculate and his/her needs. Synthesis show that radix 2 CORDIC has the lowest clock delay, radix 8 CORDIC has the highest LUT usage and lowest register usage while Hybrid Radix 4 CORDIC had the highest clock delay.

Keywords: multi, CORDIC, FPGA, processor

Procedia PDF Downloads 440

Authors: Tesfaye Alamirew Dessie

Abstract:

Our study focuses on developing a Model Predictive Controller (MPC) and evaluating it against a traditional PID for a pasteurization process. Utilizing system identification from the experimental data, the dynamics of the pasteurization process were calculated. Using best fit with data validation, residual, and stability analysis, the quality of several model architectures was evaluated. The validation data fit the auto-regressive with exogenous input (ARX322) model of the pasteurization process by roughly 80.37 percent. The ARX322 model structure was used to create MPC and PID control techniques. After comparing controller performance based on settling time, overshoot percentage, and stability analysis, it was found that MPC controllers outperform PID for those parameters.

Keywords: MPC, PID, ARX, pasteurization

Procedia PDF Downloads 123

Authors: Donatella R. Fiorino, Marzia Loddo

Abstract:

The practice of freeing monuments from subsequent additions crosses the entire history of conservation and it is traditionally connected to the aim of valorisation, both for cultural and educational purpose and recently even for touristic exploitation. Defence heritage has been widely interested by these cultural and technical moods from philological restoration to critic innovations. A renovated critical analysis of Italian episodes and in particular the Sardinian case of the area of San Pancrazio in Cagliari, constitute an important lesson about the limits of this practice and the uncertainty in terms of results, towards the definition of a sustainable good practice in the restoration of military architectures.

Keywords: defensive architecture, liberation, Valorisation for tourism, historical restoration

Procedia PDF Downloads 302

Authors: Soner Guler, Fuat Korkut

Abstract:

Recently, the using of lightweights concretes in construction sector is rapidly increasing all over the world. Faster construction, low density and thermal transmitting coefficient and high fire resistance are the remarkable characteristics of the lightweight concretes. Lightweight concrete can be described as a type of concrete which enhance the volume of the mixture while giving additional advantages such as to reduce the dead weight of the structures. It is lighter than the conventional concrete. The use of lightweight concrete has been widely spread across countries such as USA, United Kingdom, and Sweden. In this study, the necessity of the using of lightweights concretes in the construction sector is emphasized and evaluated briefly for the architectures and civil engineers.

Keywords: lightweights concretes, low density, low thermal coefficient, construction sector

Procedia PDF Downloads 486

Authors: C. Jameke

Abstract:

During the cognitivist era in cognitive psychology, a theory of internal rules and symbolic representations was posited as an account of human cognition. This type of cognitive architecture had its heyday during the 1970s and 80s, but it has now been largely abandoned in favour of subsymbolic architectures (e.g. connectionism), non-representational frameworks (e.g. dynamical systems theory), and statistical approaches such as Bayesian theory. In this presentation I describe this changing landscape of research, and comment on the increasing influence of neuroscience on cognitive psychology. I then briefly review a few recent developments in connectionism, and neurocomputation relevant to cognitive psychology, and critically discuss the assumption made by some researchers in these frameworks that higher-level aspects of human cognition are simply emergent properties of massively large distributed neural networks

Keywords: connectionism, emergentism, postocgnitivist, representations, subsymbolic archiitecture

Procedia PDF Downloads 541

Authors: Daniel P. Clayton, Edward A. Ball

Abstract:

This paper describes an investigation into the isolation characteristics and bandwidth performance of RF combiners that are used as part of Chireix PA architectures, designed for use in the X-Band range of frequencies. Combiner designs investigated are the typical Chireix and Wilkinson configurations which also include simulation of the Wilkinson using manufacturer’s data for the isolation resistor. Another simulation was the less common approach of using a Branchline coupler to form the combiner, as well as simulation results from adding an additional stage. This paper presents the findings of this investigation and compares the bandwidth performance and isolation characteristics to determine suitability.

Keywords: bandwidth, Chireix, couplers, outphasing, power amplifiers, Wilkinson, X-Band

Procedia PDF Downloads 226

Authors: Yiwei Li, Mingyu Gao

Abstract:

Integrating hybrid memories with heterogeneous processors could leverage heterogeneity in both compute and memory domains for better system efficiency. To ensure performance isolation, we introduce Hydrogen, a hardware architecture to optimize the allocation of hybrid memory resources to heterogeneous CPU-GPU systems. Hydrogen supports efficient capacity and bandwidth partitioning between CPUs and GPUs in both memory tiers. We propose decoupled memory channel mapping and token-based data migration throttling to enable flexible partitioning. We also support epoch-based online search for optimized configurations and lightweight reconfiguration with reduced data movements. Hydrogen significantly outperforms existing designs by 1.21x on average and up to 1.31x.

Keywords: hybrid memory, heterogeneous systems, dram cache, graphics processing units

Procedia PDF Downloads 23