Search results for: logistics network optimization

Authors: Peter Fedichev

Abstract:

We studied fundamental aspects of aging to develop a mathematical model of gene regulatory network. We show that aging manifests itself as an inherent instability of gene network leading to exponential accumulation of regulatory errors with age. To validate our approach we studied age-dependent omic data such as transcriptomes, metabolomes etc. of different model organisms and humans. We build a computational platform based on our model to identify the targets and biomarkers of aging to design new drugs against aging and age-related diseases. As biomarkers of aging, we choose the rate of aging and the biological age since they completely determine the state of the organism. Since rate of aging rapidly changes in response to an external stress, this kind of biomarker can be useful as a tool for quantitative efficacy assessment of drugs, their combinations, dose optimization, chronic toxicity estimate, personalized therapies selection, clinical endpoints achievement (within clinical research), and death risk assessments. According to our model, we propose a method for targets identification for further interventions against aging and age-related diseases. Being a biotech company, we offer a complete pipeline to develop an anti-aging drug-candidate.

Keywords: aging, longevity, biomarkers, senescence

Procedia PDF Downloads 274

Authors: Earleen Jane Fuentes, Regeene Melarese Lim, Franklin Benjamin Tapia, Alexis Pantola

Abstract:

Mobile Ad-hoc Network (MANET) is an infrastructure-less network of mobile devices, also known as nodes. These nodes heavily rely on each other’s resources such as memory, computing power, and energy. Thus, some nodes may become selective in forwarding packets so as to conserve their resources. These nodes are called misleading nodes. Several reputation-based techniques (e.g. CORE, CONFIDANT, LARS, SORI, OCEAN) and acknowledgment-based techniques (e.g. TWOACK, S-TWOACK, EAACK) have been proposed to detect such nodes. These techniques do not appropriately punish misleading nodes. Hence, this paper addresses the limitations of these techniques using a system called MINDRA.

Keywords: acknowledgment-based techniques, mobile ad-hoc network, selfish nodes, reputation-based techniques

Procedia PDF Downloads 385

Authors: Yang Xiong, Hua Cheng

Abstract:

In this paper, for the basic problem of wireless sensor network topology control and deployment, the Roesser model in rectangular grid sensor networks is presented. In addition, a general constructive realization procedure will be proposed. The procedure enables a distributed implementation of linear systems on a sensor network. A non-trivial example is illustrated.

Keywords: grid sensor networks, Roesser model, state-space realization, multidimensional systems

Procedia PDF Downloads 655

Authors: Li Dan, Zhao Junsuo, Zhang Wenjun

Abstract:

Aiming at the shortcomings of the Quantum Genetic Algorithm such as the multimodal function optimization problems easily falling into the local optimum, and vulnerable to premature convergence due to no closely relationship between individuals, the paper presents an Improved Many Worlds Quantum Genetic Algorithm (IMWQGA). The paper using the concept of Many Worlds; using the derivative way of parallel worlds’ parallel evolution; putting forward the thought which updating the population according to the main body; adopting the transition methods such as parallel transition, backtracking, travel forth. In addition, the algorithm in the paper also proposes the quantum training operator and the combinatorial optimization operator as new operators of quantum genetic algorithm.

Keywords: quantum genetic algorithm, many worlds, quantum training operator, combinatorial optimization operator

Procedia PDF Downloads 745

Authors: Frederic Jumelle, Kelvin So, Didan Deng

Abstract:

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

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

Procedia PDF Downloads 125

Authors: Hang Yang, Jichao Li, Kewei Yang, Tianyang Lei

Abstract:

Multivariate time series anomaly detection is a significant research topic in the field of data mining, encompassing a wide range of applications across various industrial sectors such as traffic roads, financial logistics, and corporate production. The inherent spatial dependencies and temporal characteristics present in multivariate time series introduce challenges to the anomaly detection task. Previous studies have typically been based on the assumption that all variables belong to the same spatial hierarchy, neglecting the multi-level spatial relationships. To address this challenge, this paper proposes a multi-scale spatial and unified temporal feature fusion network, denoted as MSUT-Net, for multivariate time series anomaly detection. The proposed model employs a multi-level modeling approach, incorporating both temporal and spatial modules. The spatial module is designed to capture the spatial characteristics of multivariate time series data, utilizing an adaptive graph structure learning model to identify the multi-level spatial relationships between data variables and their attributes. The temporal module consists of a unified temporal processing module, which is tasked with capturing the temporal features of multivariate time series. This module is capable of simultaneously identifying temporal dependencies among different variables. Extensive testing on multiple publicly available datasets confirms that MSUT-Net achieves superior performance on the majority of datasets. Our method is able to model and accurately detect systems data with multi-level spatial relationships from a spatial-temporal perspective, providing a novel perspective for anomaly detection analysis.

Keywords: data mining, industrial system, multivariate time series, anomaly detection

Procedia PDF Downloads 15

Authors: Oumaima Khlifati, Khadija Baba

Abstract:

Pavement distress is the main factor responsible for the deterioration of road structure durability, damage vehicles, and driver comfort. Transportation agencies spend a high proportion of their funds on pavement monitoring and maintenance. The auscultation of pavement distress was based on the manual survey, which was extremely time consuming, labor intensive, and required domain expertise. Therefore, the automatic distress detection is needed to reduce the cost of manual inspection and avoid more serious damage by implementing the appropriate remediation actions at the right time. Inspired by recent deep learning applications, this paper proposes an algorithm for automatic road distress detection and classification using on the Deep Convolutional Neural Network (DCNN). In this study, the types of pavement distress are classified as transverse or longitudinal cracking, alligator, pothole, and intact pavement. The dataset used in this work is composed of public asphalt pavement images. In order to learn the structure of the different type of distress, the DCNN models are trained and tested as a multi-label classification task. In addition, to get the highest accuracy for our model, we adjust the structural optimization hyper parameters such as the number of convolutions and max pooling, filers, size of filters, loss functions, activation functions, and optimizer and fine-tuning hyper parameters that conclude batch size and learning rate. The optimization of the model is executed by checking all feasible combinations and selecting the best performing one. The model, after being optimized, performance metrics is calculated, which describe the training and validation accuracies, precision, recall, and F1 score.

Keywords: distress pavement, hyperparameters, automatic classification, deep learning

Procedia PDF Downloads 93

Authors: Han Bing, Yin Zhenjie

Abstract:

In order to analyze the status of a diesel engine, as well as conduct fault prediction, a new prediction model based on a gray system is proposed in this paper, which takes advantage of the neural network and the genetic algorithm. The proposed GBPGA prediction model builds on the GM (1.5) model and uses a neural network, which is optimized by a genetic algorithm to construct the error compensator. We verify our proposed model on the diesel faulty simulation data and the experimental results show that GBPGA has the potential to employ fault prediction on diesel.

Keywords: fault prediction, neural network, GM(1, 5) genetic algorithm, GBPGA

Procedia PDF Downloads 304

Authors: Madia Safdar, G. Amjad Hussain, Mashhood Ahmad

Abstract:

One of the major challenges of today’s era is peak demand which causes stress on the transmission lines and also raises the cost of energy generation and ultimately higher electricity bills to the end users, and it was used to be managed by the supply side management. However, nowadays this has been withdrawn because of existence of potential in the demand side management (DSM) having its economic and- environmental advantages. DSM in domestic load can play a vital role in reducing the peak load demand on the network provides a significant cost saving. In this paper the potential of demand response (DR) in reducing the peak load demands and electricity bills to the electric users is elaborated. For this purpose the domestic appliances are modeled in MATLAB Simulink and controlled by a module called energy management controller. The devices are categorized into controllable and uncontrollable loads and are operated according to real-time tariff pricing pattern instead of fixed time pricing or variable pricing. Energy management controller decides the switching instants of the controllable appliances based on the results from optimization algorithms. In GAMS software, the MILP (mixed integer linear programming) algorithm is used for optimization. In different cases, different constraints are used for optimization, considering the comforts, needs and priorities of the end users. Results are compared and the savings in electricity bills are discussed in this paper considering real time pricing and fixed tariff pricing, which exhibits the existence of potential to reduce electricity bills and peak loads in demand side management. It is seen that using real time pricing tariff instead of fixed tariff pricing helps to save in the electricity bills. Moreover the simulation results of the proposed energy management system show that the gained power savings lie in high range. It is anticipated that the result of this research will prove to be highly effective to the utility companies as well as in the improvement of domestic DR.

Keywords: controllable and uncontrollable domestic loads, demand response, demand side management, optimization, MILP (mixed integer linear programming)

Procedia PDF Downloads 302

Authors: Atcharawan Phenwansuk

Abstract:

The product design is important to the development of SME towards the global, because it made to the quality product to react the needs of consumers and could reduces cost in the production, making it more profitable. As a results, the business are competition advantage for more marketing. It also enhance image of product and firms to build its own brand products to be acceptable. The product was designed should be shape, size, colorful, and direct of target consumers. This is method to add value products to get popular and effective, because the beauty is first satisfaction which come from main shape and color of the design product, but the product was designed need to hold data and law combination of shape and color between artistic theory and satisfaction of consumers together. The design must consider the safety of life and asset of consumers the most important. From to use of designed products should be to consider the cost savings, convenient distance, transportation, routes (land, water or air) of living space on transport (capacity, volume, width, length of the car, truck and container, etc). The packaging must be can to prevent not damage of the products. If products is more large , maybe to design new packaging, which can easily disassembled for make smaller package such as designing the assembly. Products must be packed in the container for size standard for save costs, as well as the buyer can make transport and assembly of products to fit easily on your own.

Keywords: logistics process , pineapple’s leaves product, product design, satisfaction of consumers

Procedia PDF Downloads 397

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 161

Authors: Jinwooung Kim, Jae-Hwan Jung, Seong-Jun Kim, Sung-Ah Kim

Abstract:

Because the building envelope has a significant impact on the operation and maintenance stage of the building, designing the facade considering the performance can improve the performance of the building and lower the maintenance cost of the building. In general, however, optimizing two or more performance factors confronts the limits of time and computational tools. The optimization phase typically repeats infinitely until a series of processes that generate alternatives and analyze the generated alternatives achieve the desired performance. In particular, as complex geometry or precision increases, computational resources and time are prohibitive to find the required performance, so an optimization methodology is needed to deal with this. Instead of directly analyzing all the alternatives in the optimization process, applying experimental techniques (heuristic method) learned through experimentation and experience can reduce resource waste. This study proposes and verifies a method to optimize the double envelope of a building composed of a perforated panel using machine learning to the design geometry and quantitative performance. The proposed method is to achieve the required performance with fewer resources by supplementing the existing method which cannot calculate the complex shape of the perforated panel.

Keywords: building envelope, machine learning, perforated metal, multi-factor optimization, façade

Procedia PDF Downloads 224

Authors: Mahdi Mottahedi, Peter Zahn, Armin Lechler, Alexander Verl

Abstract:

Optimal topology of components leads to the maximum stiffness with the minimum material use. For the generation of these topologies, normally algorithms are employed, which tackle manufacturing limitations, at the cost of the optimal result. The global optimum result with penalty factor one, however, cannot be fabricated with conventional methods. In this article, an additive manufacturing method is introduced, in order to enable the production of global topology optimization results. For a benchmark, topology optimization with higher and lower penalty factors are performed. Different algorithms are employed in order to interpret the results of topology optimization with lower factors in many microstructure layers. These layers are then joined to form the final geometry. The algorithms’ benefits are then compared experimentally and numerically for the best interpretation. The findings demonstrate that by implementation of the selected algorithm, the stiffness of the components produced with this method is higher than what could have been produced by conventional techniques.

Keywords: topology optimization, additive manufacturing, 3D-printer, laminated object manufacturing

Procedia PDF Downloads 339

Authors: H. Nikzad, S. Yoshitomi

Abstract:

This study investigates and develops the structural optimization method. The effect of size constraints on practical solution of reinforced concrete (RC) building structure with shear wall is proposed. Cross-sections of beam and column, and thickness of shear wall are considered as design variables. The objective function to be minimized is total cost of the structure by using a simple and efficient automated MATLAB platform structural optimization methodology. With modification of mathematical formulations, the result is compared with optimal solution without size constraints. The most suitable combination of section sizes is selected as for the final design application based on linear static analysis. The findings of this study show that defining higher value of upper bound of sectional sizes significantly affects optimal solution, and defining of size constraints play a vital role in finding of global and practical solution during optimization procedures. The result and effectiveness of proposed method confirm the ability and efficiency of optimal solutions for 3D RC shear wall-frame structure.

Keywords: structural optimization, linear static analysis, ETABS, MATLAB, RC shear wall-frame structures

Procedia PDF Downloads 375

Authors: Emery A. Coppola Jr., Suna Cinar, Ferenc Szidarovszky

Abstract:

Over-pumping of groundwater resources is a serious problem world-wide. In addition to depleting this valuable resource, hydraulically connected sensitive ecological resources like wetlands and surface water bodies are often impacted and even destroyed by over-pumping. Effectively managing groundwater in a way that satisfy human demand while preserving natural resources is a daunting challenge that will only worsen with growing human populations and climate change. As presented in this paper, a numerical flow model developed for a hypothetical but realistic groundwater/surface water system was combined with formal optimization. Response coefficients were used in an optimization management model to maximize groundwater pumping in a complex, multi-layered aquifer system while protecting against groundwater over-draft, streamflow depletion, and wetland impacts. Pumping optimization was performed for different constraint sets that reflect different resource protection preferences, yielding significantly different optimal pumping solutions. A sensitivity analysis on the optimal solutions was performed on select response coefficients to identify differences between wet and dry periods. Stochastic optimization was also performed, where uncertainty associated with changing irrigation demand due to changing weather conditions are accounted for. One of the strengths of this optimization approach is that it can efficiently and accurately identify superior management strategies that minimize risk and adverse environmental impacts associated with groundwater pumping under different hydrologic conditions.

Keywords: numerical groundwater flow modeling, water management optimization, groundwater overdraft, streamflow depletion

Procedia PDF Downloads 233

Authors: Bokkasam Sasidhar, Ibrahim Aljasser

Abstract:

The problem of finding optimal schedules for each equipment in a production process is considered, which consists of a single stage of manufacturing and which can handle different types of products, where changeover for handling one type of product to the other type incurs certain costs. The machine capacity is determined by the upper limit for the quantity that can be processed for each of the products in a set up. The changeover costs increase with the number of set ups and hence to minimize the costs associated with the product changeover, the planning should be such that similar types of products should be processed successively so that the total number of changeovers and in turn the associated set up costs are minimized. The problem of cost minimization is equivalent to the problem of minimizing the number of set ups or equivalently maximizing the capacity utilization in between every set up or maximizing the total capacity utilization. Further, the production is usually planned against customers’ orders, and generally different customers’ orders are assigned one of the two priorities – “normal” or “priority” order. The problem of production planning in such a situation can be formulated into a Multiple Arc Network (MAN) model and can be solved sequentially using the algorithm for maximizing flow along a MAN and the algorithm for maximizing flow along a MAN with priority arcs. The model aims to provide optimal production schedule with an objective of maximizing capacity utilization, so that the customer-wise delivery schedules are fulfilled, keeping in view the customer priorities. Algorithms have been presented for solving the MAN formulation of the production planning with customer priorities. The application of the model is demonstrated through numerical examples.

Keywords: scheduling, maximal flow problem, multiple arc network model, optimization

Procedia PDF Downloads 402

Authors: Xiaocong Liu, Huazhen Wang, Ting He, Xiaozheng Li, Weihan Zhang, Jian Chen

Abstract:

The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluate the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.

Keywords: convolutional neural network, electronic medical record, feature representation, lexical semantics, semantic decision

Procedia PDF Downloads 126

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 273

Authors: Muhammad Azam, Micheal Olaolu Arowolo, Fei He, Mihail Popescu, Dong Xu

Abstract:

The number of biological papers is growing quickly, which means that the number of biological pathway figures in those papers is also increasing quickly. Each pathway figure shows extensive biological information, like the names of genes and how the genes are related. However, manually annotating pathway figures takes a lot of time and work. Even though using advanced image understanding models could speed up the process of curation, these models still need to be made more accurate. To improve gene name recognition from pathway figures, we applied a Siamese network to map image segments to a library of pictures containing known genes in a similar way to person recognition from photos in many photo applications. We used a triple loss function and a triplet spatial pyramid pooling network by combining the triplet convolution neural network and the spatial pyramid pooling (TSPP-Net). We compared VGG19 and VGG16 as the Siamese network model. VGG16 achieved better performance with an accuracy of 93%, which is much higher than OCR results.

Keywords: biological pathway, image understanding, gene name recognition, object detection, Siamese network, VGG

Procedia PDF Downloads 291

Authors: Henok Mezemr Besfat, Haftom Gebreslassie Gebregwergs

Abstract:

wireless network is one of the most important mediums of transmission of information from one device to another devices. Wireless communication has a broad range of applications, including mobile communications through cell phones and satellites, Internet of Things (IoT) connecting several devices, wireless sensor networks for traffic management and environmental monitoring, satellite communication for weather forecasting and TV without requiring any cable or wire or other electronic conductors, by using electromagnetic waves like IR, RF, satellite, etc. This paper summarizes different wireless network technologies, applications of different wireless technologies and different types of wireless networks. Generally, wireless technology will further enhance operations and experiences across sectors with continued innovation. This paper suggests different strategies that can improve wireless networks and technologies.

Keywords: wireless senser, wireless technology, wireless network, internet of things

Procedia PDF Downloads 53

Authors: Hninn Thiri Naing

Abstract:

In Myanmar, there are many regions that are far away from the national grid. For these areas, isolated regional micro-grids are one of the solutions. The study area in this paper is also operating in such way. The main difficulty in such regions is the high cost of electrical energy. This paper will be approached to cost-effective or cost-optimization by energy planning with renewable energy resources and natural gas. Micro-grid will be set up for performance in the Dawei region since it is economic zone in lower Myanmar and so far from national grids. The required metrological and geographical data collections are done. Currently, the status is electric unit rate is higher than the other. For microgrid planning and optimization, Homer Pro-software is employed in this research.

Keywords: energy planning, renewable energy, homer pro, cost of energy

Procedia PDF Downloads 129

Authors: Oluwaponmile David Alao

Abstract:

Misdiagnosis has been the major problem in health sector. Heart attack has been one of diseases that have high level of misdiagnosis recorded on the part of physicians. In this paper, an intelligent system has been developed for diagnosis of heart attack in the health sector. Dataset of heart attack obtained from UCI repository has been used. This dataset is made up of thirteen attributes which are very vital in diagnosis of heart disease. The system is developed on the multilayer perceptron trained with back propagation neural network then simulated with feed forward neural network and a recognition rate of 87% was obtained which is a good result for diagnosis of heart attack in medical field.

Keywords: heart attack, artificial neural network, diagnosis, intelligent system

Procedia PDF Downloads 655

Authors: İkbal Eski

Abstract:

This investigation is researched on design of robust neural network predictors for analyzing vibration effects on moving parts of a drilling machine. Moreover, the research is divided two parts; first part is experimental investigation, second part is simulation analysis with neural networks. Therefore, a real time the drilling machine is used to vibrations during working conditions. The measured real vibration parameters are analyzed with proposed neural network. As results: Simulation approaches show that Radial Basis Neural Network has good performance to adapt real time parameters of the drilling machine.

Keywords: artificial neural network, vibration analyses, drilling machine, robust

Procedia PDF Downloads 394

Authors: Safak Baykal

Abstract:

The purpose of this study is analyzing the relationship between self leadership and social capital of people with using Social Network Analysis. In this study, two aspects of social capital will be focused: bonding, homophilous social capital (BoSC) which implies better, strong, dense or closed network ties, and bridging, heterophilous social capital (BrSC) which implies weak ties, bridging the structural holes. The other concept of the study is Trust (Tr), namely interpersonal trust, willingness to ascribe good intentions to and have confidence in the words and actions of other people. In this study, the sample group, 61 people, was selected from a private firm from the defense industry. The relation between BoSC/BrSC and Tr is shown by using Social Network Analysis (SNA) and statistical analysis with Likert type-questionnaire. The results of the analysis show the Cronbach’s alpha value is 0.73 and social capital values (BoSC/BrSC) is highly correlated with Tr values of the people.

Keywords: bonding social capital, bridging social capital, trust, social network analysis (SNA)

Procedia PDF Downloads 529

Authors: Bonchan Koo, Junhee Han, Dohyung Lee

Abstract:

The research attempts to evaluate the accuracy and efficiency of a design optimization procedure which combines wavelets-based solution algorithm and proper orthogonal decomposition (POD) database management technique. Aerodynamic design procedure calls for high fidelity computational fluid dynamic (CFD) simulations and the consideration of large number of flow conditions and design constraints. Even with significant computing power advancement, current level of integrated design process requires substantial computing time and resources. POD reduces the degree of freedom of full system through conducting singular value decomposition for various field simulations. For additional efficiency improvement of the procedure, adaptive wavelet technique is also being employed during POD training period. The proposed design procedure was applied to the optimization of wing aerodynamic performance. Throughout the research, it was confirmed that the POD/wavelets design procedure could significantly reduce the total design turnaround time and is also able to capture all detailed complex flow features as in full order analysis.

Keywords: POD (Proper Orthogonal Decomposition), wavelets, CFD, design optimization, ROM (Reduced Order Model)

Procedia PDF Downloads 467

Authors: R. Dariani, S. Schmidt, R. Kasper

Abstract:

Based on a non-linear single track model which describes the dynamics of vehicle, an optimal path planning strategy is developed. Real time optimization is used to generate reference control values to allow leading the vehicle alongside a calculated lane which is optimal for different objectives such as energy consumption, run time, safety or comfort characteristics. Strict mathematic formulation of the autonomous driving allows taking decision on undefined situation such as lane change or obstacle avoidance. Based on position of the vehicle, lane situation and obstacle position, the optimization problem is reformulated in real-time to avoid the obstacle and any car crash.

Keywords: autonomous driving, obstacle avoidance, optimal control, path planning

Procedia PDF Downloads 370

Authors: Shraddha Srivastava, N. K. Painuly, S. P. Mishra, Navin Singh, Muhsin Punchankandy, Kirti Srivastava, M. L. B. Bhatt

Abstract:

Various optimization methods used in interstitial brachytherapy are based on dwell positions and dwell weights alteration to produce dose distribution based on the implant geometry. Since these optimization schemes are not anatomy based, they could lead to deviations from the desired plan. This study was henceforth carried out to compare anatomy-based Inverse Planning Simulated Annealing (IPSA) optimization technique with graphical and geometrical optimization methods in interstitial high dose rate brachytherapy planning of cervical carcinoma. Six patients with 12 CT data sets of MUPIT implants in HDR brachytherapy of cervical cancer were prospectively studied. HR-CTV and organs at risk (OARs) were contoured in Oncentra treatment planning system (TPS) using GYN GEC-ESTRO guidelines on cervical carcinoma. Three sets of plans were generated for each fraction using IPSA, graphical optimization (GrOPT) and geometrical optimization (GOPT) methods. All patients were treated to a dose of 20 Gy in 2 fractions. The main objective was to cover at least 95% of HR-CTV with 100% of the prescribed dose (V100 ≥ 95% of HR-CTV). IPSA, GrOPT, and GOPT based plans were compared in terms of target coverage, OAR doses, homogeneity index (HI) and conformity index (COIN) using dose-volume histogram (DVH). Target volume coverage (mean V100) was found to be 93.980.87%, 91.341.02% and 85.052.84% for IPSA, GrOPT and GOPT plans respectively. Mean D90 (minimum dose received by 90% of HR-CTV) values for IPSA, GrOPT and GOPT plans were 10.19 ± 1.07 Gy, 10.17 ± 0.12 Gy and 7.99 ± 1.0 Gy respectively, while D100 (minimum dose received by 100% volume of HR-CTV) for IPSA, GrOPT and GOPT plans was 6.55 ± 0.85 Gy, 6.55 ± 0.65 Gy, 4.73 ± 0.14 Gy respectively. IPSA plans resulted in lower doses to the bladder (D₂

Keywords: cervical cancer, HDR brachytherapy, IPSA, MUPIT

Procedia PDF Downloads 187

Authors: Hanjong Kim, Changwan Han, Seonghun Park

Abstract:

Heat exchanger manifolds in aircraft play an important role in evenly distributing the fluid entering through the inlet to the heat transfer unit. In order to achieve this requirement, the manifold should be designed to have a light weight by withstanding high internal pressure. Therefore, this study aims at minimizing the weight of the heat exchanger manifold through topology optimization. For topology optimization, the initial design space was created with the inner surface extracted from the currently used manifold model and with the outer surface having a dimension of 243.42 mm of X 74.09 mm X 65 mm. This design space solid model was transformed into a finite element model with a maximum tetrahedron mesh size of 2 mm using ANSYS Workbench. Then, topology optimization was performed under the boundary conditions of an internal pressure of 5.5 MPa and the fixed support for rectangular inlet boundaries by SIMULIA TOSCA. This topology optimization produced the minimized finial volume of the manifold (i.e., 7.3% of the initial volume) based on the given constraints (i.e., 6% of the initial volume) and the objective function (i.e., maximizing manifold stiffness). Weight of the optimized model was 6.7% lighter than the currently used manifold, but after smoothing the topology optimized model, this difference would be bigger. The current optimized model has uneven thickness and skeleton-shaped outer surface to reduce stress concentration. We are currently simplifying the optimized model shape with spline interpolations by reflecting the design characteristics in thickness and skeletal structures from the optimized model. This simplified model will be validated again by calculating both stress distributions and weight reduction and then the validated model will be manufactured using 3D printing processes.

Keywords: topology optimization, manifold, heat exchanger, 3D printing

Procedia PDF Downloads 248

Authors: Ghorab Sara, Meziani Lila, Rubin Harvey Stuart

Abstract:

The rapid growth of deep learning has led to intricate and resource-intensive deep neural networks widely used in computer vision tasks. However, their complexity results in high computational demands and memory usage, hindering real-time application. To address this, research focuses on model compression techniques. The paper provides an overview of recent advancements in compressing neural networks and categorizes the various methods into four main approaches: network pruning, quantization, network decomposition, and knowledge distillation. This paper aims to provide a comprehensive outline of both the advantages and limitations of each method.

Keywords: model compression, deep neural network, pruning, knowledge distillation, quantization, low-rank decomposition

Procedia PDF Downloads 43

Authors: Abdallah Al-ZoubI, Mamoun Dmour

Abstract:

The spectrum of IoT devices is becoming widely diversified, entering almost all possible fields and finding applications in industry, health, finance, logistics, education, to name a few. The IoT active endpoint sensors and devices exceeded the 12 billion mark in 2021 and are expected to reach 27 billion in 2025, with over $34 billion in total market value. This sheer rise in numbers and use of IoT devices bring with it considerable concerns regarding data storage, analysis, manipulation and protection. IoT Blockchain-based systems have recently been proposed as a decentralized solution for large-scale data storage and protection. COVID-19 has actually accelerated the desire to utilize IoT devices as it impacted both demand and supply and significantly affected several regions due to logistic reasons such as supply chain interruptions, shortage of shipping containers and port congestion. An IoT-blockchain system is proposed to handle big data generated by a distributed network of sensors and controllers in an interactive manner. The system is designed using the Ethereum platform, which utilizes smart contracts, programmed in solidity to execute and manage data generated by IoT sensors and devices. such as Raspberry Pi 4, Rasbpian, and add-on hardware security modules. The proposed system will run a number of applications hosted by a local machine used to validate transactions. It then sends data to the rest of the network through InterPlanetary File System (IPFS) and Ethereum Swarm, forming a closed IoT ecosystem run by blockchain where a number of distributed IoT devices can communicate and interact, thus forming a closed, controlled environment. A prototype has been deployed with three IoT handling units distributed over a wide geographical space in order to examine its feasibility, performance and costs. Initial results indicated that big IoT data retrieval and storage is feasible and interactivity is possible, provided that certain conditions of cost, speed and thorough put are met.

Keywords: IoT devices, blockchain, Ethereum, big data

Procedia PDF Downloads 150