Search results for: floating architectures

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 98

Authors: Tushar K. Routh

Abstract:

If inputs are engineered in certain manners, they can influence deep neural networks’ (DNN) performances by facilitating misclassifications, a phenomenon well-known as adversarial attacks that question networks’ vulnerability. Recent studies have unfolded the relationship between vulnerability of such networks with their complexity. In this paper, the distinctive influence of additional convolutional layers at the decision boundaries of several DNN architectures was investigated. Here, to engineer inputs from widely known image datasets like MNIST, Fashion MNIST, and Cifar 10, we have exercised One Step Spectral Attack (OSSA) and Fast Gradient Method (FGM) techniques. The aftermaths of adding layers to the robustness of the architectures have been analyzed. For reasoning, separation width from linear class partitions and local geometry (curvature) near the decision boundary have been examined. The result reveals that model complexity has significant roles in adjusting relative distances from margins, as well as the local features of decision boundaries, which impact robustness.

Keywords: DNN robustness, decision boundary, local curvature, network complexity

Procedia PDF Downloads 82

Authors: Calvin Ralph, Edward Archer, Alistair McIlhagger

Abstract:

3D woven textile composites continue to emerge as an advanced material for structural applications and composite manufacture due to their bespoke nature, through thickness reinforcement and near net shape capabilities. When 3D woven preforms are produced, they are in their optimal physical state. As 3D weaving is a dry preforming technology it relies on compression of the preform to achieve the desired composite thickness, fibre volume fraction (Vf) and consolidation. This compression of the preform during manufacture results in changes to its thickness and architecture which can often lead to under-performance or changes of the 3D woven composite. Unlike traditional 2D fabrics, the bespoke nature and variability of 3D woven architectures makes it difficult to know exactly how each 3D preform will behave during processing. Therefore, the focus of this study is to investigate the effect of compression on differing 3D woven architectures in terms of structure, crimp or fibre waviness and thickness as well as analysing the accuracy of available software to predict how 3D woven preforms behave under compression. To achieve this, 3D preforms are modelled and compression simulated in Wisetex with varying architectures of binder style, pick density, thickness and tow size. These architectures have then been woven with samples dry compression tested to determine the compressibility of the preforms under various pressures. Additional preform samples were manufactured using Resin Transfer Moulding (RTM) with varying compressive force. Composite samples were cross sectioned, polished and analysed using microscopy to investigate changes in architecture and crimp. Data from dry fabric compression and composite samples were then compared alongside the Wisetex models to determine accuracy of the prediction and identify architecture parameters that can affect the preform compressibility and stability. Results indicate that binder style/pick density, tow size and thickness have a significant effect on compressibility of 3D woven preforms with lower pick density allowing for greater compression and distortion of the architecture. It was further highlighted that binder style combined with pressure had a significant effect on changes to preform architecture where orthogonal binders experienced highest level of deformation, but highest overall stability, with compression while layer to layer indicated a reduction in fibre crimp of the binder. In general, simulations showed a relative comparison to experimental results; however, deviation is evident due to assumptions present within the modelled results.

Keywords: 3D woven composites, compression, preforms, textile composites

Procedia PDF Downloads 141

Authors: Namugenyi Ephrance Eunice, Julianne Sansa Otim, Marco Zennaro, Stephen D. Wolthusen

Abstract:

The Internet of Things (IoT) is a network of connected data processing devices, mechanical and digital machinery, items, animals, or people that may send data across a network without requiring human-to-human or human-to-computer interaction. Each component has sensors that can pick up on specific phenomena, as well as processing software and other technologies that can link to and communicate with other systems and/or devices over the Internet or other communication networks and exchange data with them. IoT is increasingly being used in fields other than consumer electronics, such as public safety, emergency response, industrial automation, autonomous vehicles, the Internet of Medical Things (IoMT), and general environmental monitoring. Consumer-based IoT applications, like smart home gadgets and wearables, are also becoming more prevalent. This paper presents the main IoT deployment areas for environmental monitoring in developing regions and the backhaul options suitable for them. A detailed review of each of the list of papers selected for the study is included in section III of this document. The study includes an overview of existing IoT deployments, the underlying communication architectures, protocols, and technologies that support them. This overview shows that Low Power Wireless Area Networks (LPWANs), as summarized in Table 1, are very well suited for monitoring environment architectures designed for remote locations. LoRa technology, particularly the LoRaWAN protocol, has an advantage over other technologies due to its low power consumption, adaptability, and suitable communication range. The prevailing challenges of the different architectures are discussed and summarized in Table 3 of the IV section, where the main problem is the obstruction of communication paths by buildings, trees, hills, etc.

Keywords: communication technologies, environmental monitoring, Internet of Things, IoT deployment challenges

Procedia PDF Downloads 91

Authors: Ryan Kelvin Ford

Abstract:

For individuals and organizations, significant potential benefits were assured by sharing the data in a secure, trusted, and standardized environment. Technical trust and standards help each participant to use data space securely to share and access data. Sharing data in a safe environment helps acquire new business opportunities. Data sovereignty, interoperability, and trust were considered key factors to evaluate data spaces. Businesses and policymakers assure a fair data economy by integrating data space in organizations. A collaborative environment was needed to facilitate data sharing among organizations, satisfied with the implementation of different architectures using data spaces such as Eclipse Data Space Components (EDC), International Data Space Association (IDSA), Gaia-X, and Gaia-X Federation Services (GXFS). The last 15 years of application were reviewed and compared based on the architectures and implementations of different data spaces such as IDSA, EDC, Gaia-X and GXFS, EDC framework, IDSA, GXFS, data connector, data space architecture, characteristics of data space connectors, federated data spaces initiatives, data spaces overview, eclipse data space connector, designing data spaces, building data spaces based on technical overview, European future digital ecosystem based on Gaia-Vision and strategy of Gaia-Architecture. Empirical research based on an organized view was conducted. The current discussion elaborates on the systematic review of the impact of data space technology from various perspectives. The systematic review uses multiple databases such as IEEE Explore, Taylor & Francis, Science Direct, and Google Scholar to pursue publications on the impact of Data space from January 2019 to December 2024. The search results showcased a comparative review of 150 articles, out of which 20 were related to the IDSA, Gaia‑X, and EDC architecture and implementation.

Keywords: IDSA, Gaia-X, Gaia-X architecture, EDC, EDC architecture, GXFS architecture, IDSA, data space connector

Procedia PDF Downloads 9

Authors: Muhanad Al-Jubouri

Abstract:

A local scour is the most important of the several scours impacting bridge performance and security. Even though scour is widespread in bridges, especially during flood seasons, the experimental tests could not be applied to many standard highway bridges. A computational fluid dynamics numerical model was used to solve the problem of calculating local scouring and deposition for non-cohesive silt and clear water conditions near single and double cylindrical piers with the effect of floating debris. When FLOW-3D software is employed with the Rang turbulence model, the Nilsson bed-load transfer equation and fine mesh size are considered. The numerical findings of single cylindrical piers correspond pretty well with the physical model's results. Furthermore, after parameter effectiveness investigates the range of outcomes based on predicted user inputs such as the bed-load equation, mesh cell size, and turbulence model, the final numerical predictions are compared to experimental data. When the findings are compared, the error rate for the deepest point of the scour is equivalent to 3.8% for the single pier example.

Keywords: local scouring, non-cohesive, clear water, computational fluid dynamics, turbulence model, bed-load equation, debris

Procedia PDF Downloads 73

Authors: Andrew Hardman, Alistair T. McIlhagger, Edward Archer

Abstract:

A degree of research has been undertaken in the determination of 3D textile preforms behaviour to compression with direct comparison to 2D counterparts. Multiscale simulations have been developed to try and accurately analyse the behaviour of varying architectures post-consolidation. However, further understanding is required to experimentally identify the mechanisms and deformations that exist upon conforming to a complex contour. Due to the complexity of 3D textile preforms, determination of yarn behaviour to a complex contour is assessed through consolidation by means of vacuum assisted resin transfer moulding (VARTM), and the resulting mechanisms are investigated by micrograph analysis. Varying architectures; with known areal densities, pic density and thicknesses are assessed for a cohesive study. The resulting performance of each is assessed qualitatively as well as quantitatively from the perspective of material in terms of the change in representative unit cell (RVE) across the curved beam contour, in crimp percentage, tow angle, resin rich areas and binder distortion. A novel textile is developed from the resulting analysis to overcome the observed deformations.

Keywords: comformability, compression, binder architecture, 3D weaving, textile preform

Procedia PDF Downloads 170

Authors: Albert Bou, Sebastian Dittert, Gianni de Fabritiis

Abstract:

Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popular RL libraries advocate for highly modular agent composability, which facilitates experimentation and development. To solve challenging environments within reasonable time frames, scaling RL to large sampling and computing resources has proved a successful strategy. However, this capability has been so far difficult to combine with modularity. In this work, we explore design choices to allow agent composability both at a local and distributed level of execution. We propose a versatile approach that allows the definition of RL agents at different scales through independent, reusable components. We demonstrate experimentally that our design choices allow us to reproduce classical benchmarks, explore multiple distributed architectures, and solve novel and complex environments while giving full control to the user in the agent definition and training scheme definition. We believe this work can provide useful insights to the next generation of RL libraries.

Keywords: deep reinforcement learning, Python, PyTorch, distributed training, modularity, library

Procedia PDF Downloads 85

Authors: Rohit T. P., Sahil Athrij, Sasi Gopalan

Abstract:

Currently, the content entertainment industry is dominated by mobile devices. As the trends slowly shift towards Augmented/Virtual Reality applications the computational demands on these devices are increasing exponentially and we are already reaching the limits of hardware optimizations. This paper proposes a software solution to this problem. By leveraging the capabilities of cloud computing we can offload the work from mobile devices to dedicated rendering servers that are way more powerful. But this introduces the problem of latency. This paper introduces a protocol that can achieve high-performance low latency Augmented/Virtual Reality experience. There are two parts to the protocol, 1) In-flight compression The main cause of latency in the system is the time required to transmit the camera frame from client to server. The round trip time is directly proportional to the amount of data transmitted. This can therefore be reduced by compressing the frames before sending. Using some standard compression algorithms like JPEG can result in minor size reduction only. Since the images to be compressed are consecutive camera frames there won't be a lot of changes between two consecutive images. So inter-frame compression is preferred. Inter-frame compression can be implemented efficiently using WebGL but the implementation of WebGL limits the precision of floating point numbers to 16bit in most devices. This can introduce noise to the image due to rounding errors, which will add up eventually. This can be solved using an improved interframe compression algorithm. The algorithm detects changes between frames and reuses unchanged pixels from the previous frame. This eliminates the need for floating point subtraction thereby cutting down on noise. The change detection is also improved drastically by taking the weighted average difference of pixels instead of the absolute difference. The kernel weights for this comparison can be fine-tuned to match the type of image to be compressed. 2) Dynamic Load distribution Conventional cloud computing architectures work by offloading as much work as possible to the servers, but this approach can cause a hit on bandwidth and server costs. The most optimal solution is obtained when the device utilizes 100% of its resources and the rest is done by the server. The protocol balances the load between the server and the client by doing a fraction of the computing on the device depending on the power of the device and network conditions. The protocol will be responsible for dynamically partitioning the tasks. Special flags will be used to communicate the workload fraction between the client and the server and will be updated in a constant interval of time ( or frames ). The whole of the protocol is designed so that it can be client agnostic. Flags are available to the client for resetting the frame, indicating latency, switching mode, etc. The server can react to client-side changes on the fly and adapt accordingly by switching to different pipelines. The server is designed to effectively spread the load and thereby scale horizontally. This is achieved by isolating client connections into different processes.

Keywords: 2D kernelling, augmented reality, cloud computing, dynamic load distribution, immersive experience, mobile computing, motion tracking, protocols, real-time systems, web-based augmented reality application

Procedia PDF Downloads 78

Authors: Mariem Saied, Jens Gustedt, Gilles Muller

Abstract:

We present Dido, a source-to-source auto-generation and optimization framework for multi-dimensional stencil computations. It enables a large programmer community to easily and safely implement stencil codes on distributed-memory parallel architectures with Ordered Read-Write Locks (ORWL) as an execution and communication back-end. ORWL provides inter-task synchronization for data-oriented parallel and distributed computations. It has been proven to guarantee equity, liveness, and efficiency for a wide range of applications, particularly for iterative computations. Dido consists mainly of an implicitly parallel domain-specific language (DSL) implemented as a source-level transformer. It captures domain semantics at a high level of abstraction and generates parallel stencil code that leverages all ORWL features. The generated code is well-structured and lends itself to different possible optimizations. In this paper, we enhance Dido to handle both Jacobi and Gauss-Seidel grid traversals. We integrate temporal blocking to the Dido code generator in order to reduce the communication overhead and minimize data transfers. To increase data locality and improve intra-node data reuse, we coupled the code generation technique with the polyhedral parallelizer Pluto. The accuracy and portability of the generated code are guaranteed thanks to a parametrized solution. The combination of ORWL features, the code generation pattern and the suggested optimizations, make of Dido a powerful code generation framework for stencil computations in general, and for distributed-memory architectures in particular. We present a wide range of experiments over a number of stencil benchmarks.

Keywords: stencil computations, ordered read-write locks, domain-specific language, polyhedral model, experiments

Procedia PDF Downloads 132

Authors: Gourida Siham

Abstract:

Chinese society has witnessed a continuing trend of nationwide rural to urban migration since the 1970's. Before that age, under restricted hukou systems, peasants were kept still and fixed in the farm land. The year 1978 and later years saw the control of migration in China was relaxed gradually, freeing peasants to start their own businesses and reach out to work also in urban areas. Since then the “floating population” (migrants without local hukou) took great momentum and drew great attention from both the media and academia. The scale of such internal migration is enormous –the floating population has reached to a number of 79 million in 2000, and as of 2010, the number of migrant workers from rural China amounts to over 221 million and according to the annual survey results projections by National Bureau of Statistics; the total migrant workers in china in 2012 amounted to 262.61 million, which refers to an increase of 9.83 million compared with the previous year with increase percentage by 3.9%. Using China’s Jiangxi Province as a case, this paper examines patterns of internal migration as a response of emigrations in the context of high emigration communities. Our findings suggest that emigration of individuals initially deterred both inter-provincial and intra- provincial migration of other family members, and yet, overtime they had an increasing propensity to migrate internally at both scales.

Keywords: internal migration, jiangxi, nanchang, remittances

Procedia PDF Downloads 410

Authors: Wojcieh Drożdż, Artur R. Stefankiewicz

Abstract:

Ambidentate ligands can be described as organic structures possessing two different types of coordination units within a single molecule. These features enable the coordination of two different metal ions, which can directly affect the properties of obtained complexes as well as further application. In the current research, we focused on a β-diketone ligand containing terminally located pyridine units in order to assemble cage-like architectures. This will be possible due to the peculiar geometry of the proposed ligands, called "banana-shape", widely used in the synthesis of sophisticated metallosupramolecular architectures. Each of the coordination units plays an important role in cage assembly. Pyridine units enable the coordination of square-planar metal ions (Pd²⁺, Pt²⁺), forming a positively charged cage. On the other hand, the β-diketone group provides the possibility of post-modification, including the introduction of additional functional groups with specific properties (sensing, catalytic, etc.). Such obtained cages are of great interest due to their application potential, including storage or transport of guest molecules, selective detection/separation of analytes as well as efficient catalytic processes.

Keywords: metalloligands, coordination cages, nanoreactors, β-diketonate complexes

Procedia PDF Downloads 77

Authors: Yunpeng Xia, Jiajia Zha, Haoxin Huang, Hau Ping Chan, Chaoliang Tan

Abstract:

Although the crystal phase of two-dimensional (2D) transition metal dichalcogenides (TMDs) has been proven to play an essential role in fabricating high-performance electronic devices in the past decade, its effect on the performance of 2D material-based flash memory devices still remains unclear. Here, we report the exploration of the effect of MoTe₂ in different phases as the charge trapping layer on the performance of 2D van der Waals (vdW) heterostructure-based flash memory devices, where the metallic 1T′-MoTe₂ or semiconducting 2H-MoTe₂ nanoflake is used as the floating gate. By conducting comprehensive measurements on the two kinds of vdW heterostructure-based devices, the memory device based on MoS2/h-BN/1T′-MoTe₂ presents much better performance, including a larger memory window, faster switching speed (100 ns) and higher extinction ratio (107), than that of the device based on MoS₂/h-BN/2H-MoTe₂ heterostructure. Moreover, the device based on MoS₂/h-BN/1T′-MoTe₂ heterostructure also shows a long cycle (>1200 cycles) and retention (>3000 s) stability. Our study clearly demonstrates that the crystal phase of 2D TMDs has a significant impact on the performance of nonvolatile flash memory devices based on 2D vdW heterostructures, which paves the way for the fabrication of future high-performance memory devices based on 2D materials.

Keywords: crystal Phase, 2D van der Waals heretostructure, flash memory device, floating gate

Procedia PDF Downloads 61

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: distillation, machine learning, neural networks, quantization

Procedia PDF Downloads 332

Authors: Anton Hristozov, Eric Matson, Eric Dietz, Marcus Rogers

Abstract:

Components are heavily used in many software systems, including robotics systems. The growth of sophistication and diversity of new capabilities for robotic systems presents new challenges to their architectures. Their complexity is growing exponentially with the advent of AI, smart sensors, and the complex tasks they have to accomplish. Such complexity requires a more rigorous approach to the creation, use, and interoperability of software components. The issue is exacerbated because robotic systems are becoming more and more reliant on third-party components for certain functions. In order to achieve this kind of interoperability, including dynamic component replacement, we need a way to standardize their interfaces. A formal approach is desperately needed to specify what an interface of a robotic software component should contain. This study performs an analysis of the issue and presents a universal and generic approach to standardizing component interfaces for robotic systems. Our approach is inspired by well-established robotic architectures such as ROS, PX4, and Ardupilot. The study is also applicable to other software systems that share similar characteristics with robotic systems. We consider the use of JSON or Domain Specific Languages (DSL) development with tools such as Antlr and automatic code and configuration file generation for frameworks such as ROS and PX4. A case study with ROS2 is presented as a proof of concept for the proposed methodology.

Keywords: CPS, robots, software architecture, interface, ROS, autopilot

Procedia PDF Downloads 96

Authors: Mustafa Elfituri, Jonathan Cook

Abstract:

Recently, graph-based computations have become more important in large-scale scientific computing as they can provide a methodology to model many types of relations between independent objects. They are being actively used in fields as varied as biology, social networks, cybersecurity, and computer networks. At the same time, graph problems have some properties such as irregularity and poor locality that make their performance different than regular applications performance. Therefore, parallelizing graph algorithms is a hard and challenging task. Initial evidence is that standard computer architectures do not perform very well on graph algorithms. Little is known exactly what causes this. The Graph500 benchmark is a representative application for parallel graph-based computations, which have highly irregular data access and are driven more by traversing connected data than by computation. In this paper, we present results from analyzing the performance of various example implementations of Graph500, including a shared memory (OpenMP) version, a distributed (MPI) version, and a hybrid version. We measured and analyzed all the factors that affect its performance in order to identify possible changes that would improve its performance. Results are discussed in relation to what factors contribute to performance degradation.

Keywords: graph computation, graph500 benchmark, parallel architectures, parallel programming, workload characterization.

Procedia PDF Downloads 153

Authors: Vinay Kumar Vanjakula, Frank Adam, Nils Goseberg

Abstract:

Wind power is one of the leading renewable energy generation methods. Due to abundant higher wind speeds far away from shore, the construction of offshore wind turbines began in the last decades. However, installation of offshore foundation-based (monopiles) wind turbines in deep waters are often associated with technical and financial challenges. To overcome such challenges, the concept of floating wind turbines is expanded as the basis from the oil and gas industry. The unfolding of Universal heavyweight gravity anchor (UGA) for floating based foundation for floating Tension Leg Platform (TLP) sub-structures is developed in this research work. It is funded by the German Federal Ministry of Education and Research) for a three-year (2019-2022) research program called “Offshore Wind Solutions Plus (OWSplus) - Floating Offshore Wind Solutions Mecklenburg-Vorpommern.” It’s a group consists of German institutions (Universities, laboratories, and consulting companies). The part of the project is focused on the numerical modeling of gravity anchor that involves to analyze and solve fluid flow problems. Compared to gravity-based torpedo anchors, these UGA will be towed and lowered via controlled machines (tug boats) at lower speeds. This kind of installation of UGA are new to the offshore wind industry, particularly for TLP, and very few research works have been carried out in recent years. Conventional methods for transporting the anchor requires a large transportation crane vessel which involves a greater cost. This conceptual UGA anchors consists of ballasting chambers which utilizes the concept of buoyancy forces; the inside chambers are filled with the required amount of water in a way that they can float on the water for towing. After reaching the installation site, those chambers are ballasted with water for lowering. After it’s lifetime, these UGA can be unballasted (for erection or replacement) results in self-rising to the sea surface; buoyancy chambers give an advantage for using an UGA without the need of heavy machinery. However, while lowering/rising the UGA towards/away from the seabed, it experiences difficult, harsh marine environments due to the interaction of waves and currents. This leads to drifting of the anchor from the desired installation position and damage to the lowering machines. To overcome such harsh environments problems, a numerical model is built to investigate the influences of different outer contours and other fluid governing shapes that can be installed on the UGA to overcome the turbulence and drifting. The presentation will highlight the importance of the Computational Fluid Dynamics (CFD) numerical model in OpenFOAM, which is open-source programming software.

Keywords: anchor lowering, towing, waves, currrents, computational fluid dynamics

Procedia PDF Downloads 170

Authors: Nickolay Jelev, Andy Keane, Carren Holden, András Sóbester

Abstract:

In aircraft design, the jump from the conceptual to preliminary design stage introduces a level of complexity which cannot be realistically handled by a single optimiser, be that a human (chief engineer) or an algorithm. The design process is often partitioned along disciplinary lines, with each discipline given a level of autonomy. This introduces a number of challenges including, but not limited to: coupling of design variables; coordinating disciplinary teams; handling of large amounts of analysis data; reaching an acceptable design within time constraints. A number of classical Multidisciplinary Design Optimisation (MDO) architectures exist in academia specifically designed to address these challenges. Their limited use in the industrial aircraft design process has inspired the authors of this paper to develop an alternative strategy based on well established ideas from Decision Support Systems. The proposed rule based architecture sacrifices possibly elusive guarantees of convergence for an attractive return in simplicity. The method is demonstrated on analytical and aircraft design test cases and its performance is compared to a number of classical distributed MDO architectures.

Keywords: Multidisciplinary Design Optimisation, Rule Based Architecture, Aircraft Design, Decision Support System

Procedia PDF Downloads 358

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 90

Authors: Carlos Roberto De Rolt, Julio da Silva Dias, Rafael Tezza, Luca Foschini, Matteo Mura

Abstract:

The seasonal population fluctuation presents a challenge to touristic cities since the number of inhabitants can double according to the season. The aim of this work is to develop a model that correlates the waste collected with the population of the city and also allow cooperation between the inhabitants and the local government. The model allows public managers to evaluate the impact of the seasonal population fluctuation on waste generation and also to improve planning resource utilization throughout the year. The study uses data from the company that collects the garbage in Florianópolis, a Brazilian city that presents the profile of a city that attracts tourists due to numerous beaches and warm weather. The fluctuations are caused by the number of people that come to the city throughout the year for holidays, summer time vacations or business events. Crowdsensing will be accomplished through smartphones with access to an app for data collection, with voluntary participation of the population. Crowdsensing participants can access information collected in waves for this portal. Crowdsensing represents an innovative and participatory approach which involves the population in gathering information to improve the quality of life. The management of crowdsensing solutions plays an essential role given the complexity to foster collaboration, establish available sensors and collect and process the collected data. Practical implications of this tool described in this paper refer, for example, to the management of seasonal tourism in a large municipality, whose public services are impacted by the floating of the population. Crowdsensing and big data support managers in predicting the arrival, permanence, and movement of people in a given urban area. Also, by linking crowdsourced data to databases from other public service providers - e.g., water, garbage collection, electricity, public transport, telecommunications - it is possible to estimate the floating of the population of an urban area affected by seasonal tourism. This approach supports the municipality in increasing the effectiveness of resource allocation while, at the same time, increasing the quality of the service as perceived by citizens and tourists.

Keywords: big data, dashboards, floating population, smart city, urban management solutions

Procedia PDF Downloads 294

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 162

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 240

Authors: Nishita Jaiswal, Apoorv Mohan Satpute

Abstract:

The increasing demand for efficient, cost-effective motor control systems in the automotive industry has driven the need for advanced, highly optimized control algorithms. Field-Oriented Control (FOC) has established itself as the leading approach for motor control, offering precise and dynamic regulation of torque, speed, and position. However, as energy efficiency becomes more critical in modern applications, implementing FOC on low-power, cost-sensitive microcontrollers pose significant challenges due to the limited availability of computational and hardware resources. Currently, most solutions rely on high-performance 32-bit microcontrollers or Application-Specific Integrated Circuits (ASICs) equipped with Floating Point Units (FPUs) and Hardware Accelerated Units (HAUs). These advanced platforms enable rapid computation and simplify the execution of complex control algorithms like FOC. However, these benefits come at the expense of higher costs, increased power consumption, and added system complexity. These drawbacks limit their suitability for embedded systems with strict power and budget constraints, where achieving energy and execution efficiency without compromising performance is essential. In this paper, we present an alternative approach that utilizes optimized data representation and computation techniques on a 16-bit microcontroller without FPUs or HAUs. By carefully optimizing data point formats and employing fixed-point arithmetic, we demonstrate how the precision and computational efficiency required for FOC can be maintained in resource-constrained environments. This approach eliminates the overhead performance associated with floating-point operations and hardware acceleration, providing a more practical solution in terms of cost, scalability and improved execution time efficiency, allowing faster response in motor control applications. Furthermore, it enhances system design flexibility, making it particularly well-suited for applications that demand stringent control over power consumption and costs.

Keywords: field-oriented control, fixed-point arithmetic, floating point unit, hardware accelerator unit, motor control systems

Procedia PDF Downloads 26

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 321

Authors: Pooja Verma, Sumana Ghosh

Abstract:

There is a growing need for alternative way of power generation worldwide. The reason can be attributed to limited resources of fossil fuels, environmental pollution, increasing cost of conventional fuels, and lower efficiency of conversion of energy in existing systems. In this context, one of the potential alternatives for power generation is wave energy. However, it is difficult to estimate the amount of electrical energy generation in an irregular sea condition by experiment and or analytical methods. Therefore in this work, a numerical wave tank is developed using the computational fluid dynamics software Open FOAM. In this software a specific utility known as waves2Foam utility is being used to carry out the simulation work. The computational domain is a tank of dimension: 5m*1.5m*1m with a floating object of dimension: 0.5m*0.2m*0.2m. Regular waves are generated at the inlet of the wave tank according to Stokes second order theory. The main objective of the present study is to validate the numerical model against existing experimental data. It shows a good matching with the existing experimental data of floater displacement. Later the model is exploited to estimate energy extraction due to the movement of such a point absorber in real sea conditions. Scale down the wave properties like wave height, wave length, etc. are used as input parameters. Seasonal variations are also considered.

Keywords: OpenFOAM, numerical wave tank, regular waves, floating object, point absorber

Procedia PDF Downloads 356

Authors: Salim Yusif

Abstract:

Fiber optic technology has revolutionized telecommunications and data transmission, providing unmatched speed, bandwidth, and reliability. This paper presents the latest advancements in fiber optic technology, focusing on innovations in fiber materials, transmission techniques, and network architectures that enhance the performance of high-speed data transmission systems. Key advancements include the development of ultra-low-loss optical fibers, multi-core fibers, advanced modulation formats, and the integration of fiber optics into next-generation network architectures such as Software-Defined Networking (SDN) and Network Function Virtualization (NFV). Additionally, recent developments in fiber optic sensors are discussed, extending the utility of optical fibers beyond data transmission. Through comprehensive analysis and experimental validation, this research offers valuable insights into the future directions of fiber optic technology, highlighting its potential to drive innovation across various industries.

Keywords: fiber optics, high-speed data transmission, ultra-low-loss optical fibers, multi-core fibers, modulation formats, coherent detection, software-defined networking, network function virtualization, fiber optic sensors

Procedia PDF Downloads 66

Authors: Jinsong Zhao, Lin Zhao

Abstract:

Shenzhen, one of the fastest growing cities in the world, has been building a global ocean central city since 2017, facing many challenges, especially how to innovate new legal regimes to meet the future demands of the development of global shipping. First, the current legal regime of bills of lading as a document of title was established by English law in the 18th century but limited to the period of marine transportation from port of loading to port of discharge (namely, port to port). The e-commerce era is asking for such a function to be extended from port to port to door to door. Secondly, the function of the port has also been upgraded from the traditional loading and unloading of goods to a much wider area, such as being custody of warehousing goods for its mortgage bank, and therefore its legal status is changing, so it is necessary to amend the law of ports and harbours and innovate the rights and responsibilities of the port under its new role as the custody. Thirdly, the development of new marine energy has made more and more offshore floating wind power and floating photovoltaic devices face new legal issues such as legal status, nationality and ownership registration, mortgage, maritime lien, and possessory lien. Fourthly, the jurisdiction of the above issues, as well as conflicts of law and the applicable law, are also questions pending answers. This paper will discuss these issues of private international law, especially the innovation of new legal regimes with an aim to solve the above problems.

Keywords: maritime law, bills of lading, e-commerce, port law, marine clean energy

Procedia PDF Downloads 46

Authors: Sarra Zaied, Arthur Bonpain, Pierre Yves Fravallo

Abstract:

The permanent supply of marine litter implies their accumulation in the oceans, which causes the presence of more compact wastes layers. Their Spatio-temporal distribution is never homogeneous and depends mainly on the hydrodynamic characteristics of the environment and the size and location of the wastes. As part of optimizing collect of marine plastic wastes, it is important to measure and monitor their evolution over time. For this, many research studies have been dedicated to describing the wastes behavior in order to identify their accumulation in oceans areas. Several models are therefore developed to understand the mechanisms that allow the accumulation and the displacements of marine litter. These models are able to accurately simulate the drift of wastes to study their behavior and stranding. However, these works aim to study the wastes behavior over a long period of time and not at the time of waste collection. This work investigates the transport of floating marine litter (FML) to provide basic information that can help in optimizing wastes collection by proposing a model for predicting their behavior during collection. The proposed study is based on a Lagrangian modeling approach that uses the main factors influencing the dynamics of the waste. The performance of the proposed method was assessed on real data collected from the Copernicus Marine Environment Monitoring Service (CMEMS). Evaluation results in the Java Sea (Indonesia) prove that the proposed model can effectively predict the position and the velocity of marine wastes during collection.

Keywords: floating marine litter, lagrangian transport, particle-tracking model, wastes drift

Procedia PDF Downloads 197

Authors: Jianshu Yang, Delphine Sordes, Marek Kolmer, Christian Joachim

Abstract:

Nanoelectronics, for example the calculating circuits integrating at molecule scale logic gates, atomic scale circuits, has been constructed and investigated recently. A major challenge is their functional properties characterization because of the connecting problem from atomic scale to micrometer scale. New experimental instruments and new processes have been proposed therefore. To satisfy a precisely measurement at atomic scale and then connecting micrometer scale electrical integration controller, the technique improvement is kept on going. Our new machine, a low temperature high vacuum four scanning tunneling microscope, as a customer required instrument constructed by Omicron GmbH, is expected to be scaling down to atomic scale characterization. Here, we will present our first testified results about the performance of this new instrument. The sample we selected is Au(111) surface. The measurements have been taken at 4.2 K. The atomic resolution surface structure was observed with each of four scanners with noise level better than 3 pm. With a tip-sample distance calibration by I-z spectra, the sample conductance has been derived from its atomic locally I-V spectra. Furthermore, the surface conductance measurement has been performed using two methods, (1) by landing two STM tips on the surface with sample floating; and (2) by sample floating and one of the landed tips turned to be grounding. In addition, single atom manipulation has been achieved with a modified tip design, which is comparable to a conventional LT-STM.

Keywords: low temperature ultra-high vacuum four scanning tunneling microscope, nanoelectronics, point contact, single atom manipulation, tunneling resistance

Procedia PDF Downloads 281

Authors: A. Sreedevi, G. Anantaramu

Abstract:

The present space research organizations are striving towards the development of lighter, smaller, more efficient, low cost, and highly reliable power supply. Switch mode power supplies (SMPS) overcome the demerits of linear power supplies such as low efficiency, difficulties in thermal management, and in boosting the output voltage. Space applications require a constant DC voltage to supply its load. As the load varies, the battery terminal voltage tends to vary accordingly. To avoid this variation in the load terminal voltage, a DC-DC regulator is required. The conventional regulator for space applications is isolated boost topology. The proposed topology uses an interleaved push-pull converter with a current doubler secondary to reduce the EMI issues and increase efficiency. The proposed topology uses a floating technique where the converter derives power from the battery and generates only the voltage that is required to fill the gap between the bus and the battery voltage. The direct voltage sense and current loop provide tight regulation of output and better stability. Converter is designed with 50 kHz switching frequency using UC 1825 PWM controller employing both voltage and peak current mode control. Experimental tests have been carried out on the converter under different input and load conditions to validate the design. The experimental results showed that the efficiency was greater than 91%. Stability analysis is done using venable stability analyzer.

Keywords: push pull converter, current doubler, converter, PWM control

Procedia PDF Downloads 107