Search results for: distributed network

Authors: Zhihao Zheng, Zhilin Wang, Linxin Liu

Abstract:

In the research of automated knowledge question-answering systems, accuracy and efficiency are critical challenges. This paper proposes a knowledge graph-enhanced Retrieval-Augmented Generation (RAG) method, combined with a Graph Neural Network (GNN) structure, to automatically determine the correctness of knowledge competition questions. First, a domain-specific knowledge graph was constructed from a large corpus of academic journal literature, with key entities and relationships extracted using Natural Language Processing (NLP) techniques. Then, the RAG method's retrieval module was expanded to simultaneously query both text databases and the knowledge graph, leveraging the GNN to further extract structured information from the knowledge graph. During answer generation, contextual information provided by the knowledge graph and GNN is incorporated to improve the accuracy and consistency of the answers. Experimental results demonstrate that the knowledge graph and GNN-enhanced RAG method perform excellently in determining the correctness of questions, achieving an accuracy rate of 95%. Particularly in cases involving ambiguity or requiring contextual information, the structured knowledge provided by the knowledge graph and GNN significantly enhances the RAG method's performance. This approach not only demonstrates significant advantages in improving the accuracy and efficiency of automated knowledge question-answering systems but also offers new directions and ideas for future research and practical applications.

Keywords: knowledge graph, graph neural network, retrieval-augmented generation, NLP

Procedia PDF Downloads 39

Authors: Farnaz Fotovvatikhah, Javad Akbari

Abstract:

Test time of a test architecture is an important factor which depends on the architecture's delay and test patterns. Here a new architecture to store the test results based on network on chip is presented. In addition, simple analytical model is proposed to calculate link test time for built in self-tester (BIST) and external tester (Ext) in multiprocessor systems. The results extracted from the model are verified using FPGA implementation and experimental measurements. Systems consisting 16, 25, and 36 processors are implemented and simulated and test time is calculated. In addition, BIST and Ext are compared in terms of test time at different conditions such as at different number of test patterns and nodes. Using the model the maximum frequency of testing could be calculated and the test structure could be optimized for high speed testing.

Keywords: test, nano on-chip network, JTAG, modelling

Procedia PDF Downloads 488

Authors: Hussain Sajid, Jung-Hun Shin, Kum-Won Cho

Abstract:

Image super-resolution is the most common computer vision problem with many important applications. Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory requirements of GAN-based SR (mainly generators) lead to performance degradation and increased energy consumption, making it difficult to implement it onto resource-constricted devices. To relieve such a problem, In this paper, we introduce an optimized and highly efficient architecture for SR-GAN (generator) model by utilizing model compression techniques such as Knowledge Distillation and pruning, which work together to reduce the storage requirement of the model also increase in their performance. Our method begins with distilling the knowledge from a large pre-trained model to a lightweight model using different loss functions. Then, iterative weight pruning is applied to the distilled model to remove less significant weights based on their magnitude, resulting in a sparser network. Knowledge Distillation reduces the model size by 40%; pruning then reduces it further by 18%. To accelerate the learning process, we employ the Horovod framework for distributed training on a cluster of 2 nodes, each with 8 GPUs, resulting in improved training performance and faster convergence. Experimental results on various benchmarks demonstrate that the proposed compressed model significantly outperforms state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and image quality for x4 super-resolution tasks.

Keywords: single-image super-resolution, generative adversarial networks, knowledge distillation, pruning

Procedia PDF Downloads 96

Authors: Adebowale Olukayode Efunnowo

Abstract:

This study was carried out to assess the awareness and utilization of Social Network Tools (SNTs) among agricultural science students in Colleges of Education in Ogun State, Nigeria. Simple random sampling techniques were used to select 280 respondents from the study area. Descriptive statistics was used to describe the objectives while Pearson Product Moment Correlation was used to test the hypothesis. The result showed that the majority (71.8%) of the respondents were single, with a mean age of 20 years. Almost all (95.7%) the respondents were aware of Facebook and 2go as a Social Network Tools (SNTs) while 85.0% of the respondents were not aware of Blackplanet, LinkedIn, MyHeritage and Bebo. Many (41.1%) of the respondents had views that using SNTs can enhance extensive literature survey, increase internet browsing potential, promote teaching proficiency, and update on outcomes of researches. However, 51.4% of the respondents perceived that SNTs usage as what is meant for the lecturers/adults only while 16.1% considered it as mainly used by internet fraudsters. Findings revealed that about 50.0% of the respondents browsed Facebook and 2go daily while more than 80% of the respondents used Blackplanet, MyHeritage, Skyrock, Bebo, LinkedIn and My YearBook as the need arise. Major constraints to the awareness and utilization of SNTs were high cost and poor quality of ICTs facilities (77.1%), epileptic power supply (75.0%), inadequate telecommunication infrastructure (71.1%), low technical know-how (62.9%) and inadequate computer knowledge (61.1%). The result of PPMC analysis showed that there was an inverse relationship between constraints and utilization of SNTs at p < 0.05. It can be concluded that constraints affect efficient and effective utilization of SNTs in the study area. It is hereby recommended that management of colleges of education and agricultural institutes should provide good internet connectivity, computer facilities, and alternative power supply in order to increase the awareness and utilization of SNTs among students.

Keywords: awareness, utilization, social network tools, constraints, students

Procedia PDF Downloads 352

Authors: Sofia Stoica

Abstract:

In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.

Keywords: finance, machine learning, opening price, stock market

Procedia PDF Downloads 189

Authors: David P. Tantua, Abdulkader Helwan

Abstract:

Biometrics has been recently used for the human identification systems using the biological traits such as the fingerprints and iris scanning. Identification systems based biometrics show great efficiency and accuracy in such human identification applications. However, these types of systems are so far based on some image processing techniques only, which may decrease the efficiency of such applications. Thus, this paper aims to develop a human palmprint identification system using multi-layer perceptron neural network which has the capability to learn using a backpropagation learning algorithms. The developed system uses images obtained from a public database available on the internet (CASIA). The processing system is as follows: image filtering using median filter, image adjustment, image skeletonizing, edge detection using canny operator to extract features, clear unwanted components of the image. The second phase is to feed those processed images into a neural network classifier which will adaptively learn and create a class for each different image. 100 different images are used for training the system. Since this is an identification system, it should be tested with the same images. Therefore, the same 100 images are used for testing it, and any image out of the training set should be unrecognized. The experimental results shows that this developed system has a great accuracy 100% and it can be implemented in real life applications.

Keywords: biometrics, biological traits, multi-layer perceptron neural network, image skeletonizing, edge detection using canny operator

Procedia PDF Downloads 371

Authors: Aleksei Samarin, Artyom Nazarenko, Valentin Malykh

Abstract:

Image enhancement is becoming more and more popular, especially on mobile devices. Nowadays, it is a common approach to enhance an image using a convolutional neural network (CNN). Such a network should be of significant size; otherwise, a possibility for the artifacts to occur is overgrowing. The existing large CNNs are computationally expensive, which could be crucial for mobile devices. Another important flaw of such models is they are poorly interpretable. There is another approach to image enhancement, namely, the usage of predefined filters in combination with the prediction of their applicability. We present an approach following this paradigm, which outperforms both existing CNN-based and filter-based approaches in the image enhancement task. It is easily adaptable for mobile devices since it has only 47 thousand parameters. It shows the best SSIM 0.919 on RANDOM250 (MIT Adobe FiveK) among small models and is thrice faster than previous models.

Keywords: universal filter, image enhancement, neural networks, computer vision

Procedia PDF Downloads 101

Authors: Katharina Eberhardt, Florian Klaus Kaiser, Frank Schultmann

Abstract:

Last-mile distribution is one of the most critical parts of a disaster relief operation. Various uncertainties, such as infrastructure conditions, resource availability, and fluctuating beneficiary demand, render last-mile distribution challenging in disaster relief operations. The need to balance critical performance criteria like response time, meeting demand and cost-effectiveness further complicates the task. The occurrence of disasters cannot be controlled, and the magnitude is often challenging to assess. In summary, these uncertainties create a need for additional flexibility, agility, and preparedness in logistics operations. As a result, strategic planning and efficient network design are critical for an effective and efficient response. Furthermore, the increasing frequency of disasters and the rising cost of logistical operations amplify the need to provide robust and resilient solutions in this area. Therefore, we formulate a scenario-based bi-objective optimization model that integrates pre-positioning, allocation, and distribution of relief supplies extending the general form of a covering location problem. The proposed model aims to minimize underlying logistics costs while maximizing demand coverage. Using a set of disruption scenarios, the model allows decision-makers to identify optimal network solutions to address the risk of disruptions. We provide an empirical case study of the public authorities’ emergency food storage strategy in Germany to illustrate the potential applicability of the model and provide implications for decision-makers in a real-world setting. Also, we conduct a sensitivity analysis focusing on the impact of varying stockpile capacities, single-site outages, and limited transportation capacities on the objective value. The results show that the stockpiling strategy needs to be consistent with the optimal number of depots and inventory based on minimizing costs and maximizing demand satisfaction. The strategy has the potential for optimization, as network coverage is insufficient and relies on very high transportation and personnel capacity levels. As such, the model provides decision support for public authorities to determine an efficient stockpiling strategy and distribution network and provides recommendations for increased resilience. However, certain factors have yet to be considered in this study and should be addressed in future works, such as additional network constraints and heuristic algorithms.

Keywords: humanitarian logistics, bi-objective optimization, pre-positioning, last mile distribution, decision support, disaster relief networks

Procedia PDF Downloads 79

Authors: Mahsa Oroojeni Mohammad Javad

Abstract:

Globalization of economic activity and rapid growth of information technology has resulted in shorter product lifecycles, reduced transport capacity, dynamic and changing customer behaviors, and an increased focus on supply chain design in recent years. The design of the supply chain network is one of the most important supply chain management decisions. These decisions will have a long-term impact on the efficacy and efficiency of the supply chain. In this paper, a two-objective mixed-integer linear programming (MILP) model is developed for designing and optimizing a closed-loop green supply chain network that, to the greatest extent possible, includes all real-world assumptions such as multi-level supply chain, the multiplicity of production technologies, and multiple modes of transportation, with the goals of minimizing the total cost of the chain (first objective) and minimizing total emissions of emissions (second objective). The ε-constraint and CPLEX Solver have been used to solve the problem as a single-objective problem and validate the problem. Finally, the sensitivity analysis is applied to study the effect of the real-world parameters’ changes on the objective function. The optimal management suggestions and policies are presented.

Keywords: closed-loop supply chain, multi-level green supply chain, mixed-integer programming, transportation modes

Procedia PDF Downloads 78

Authors: Lea Lenhardt, Ivana Zeković, Tatjana Dramićanin, Miroslav D. Dramićanin

Abstract:

Fluorescence spectroscopy coupled with parallel factor analysis (PARAFAC) and artificial neural networks (ANN) were used for characterization and classification of honey. Excitation emission spectra were obtained for 95 honey samples of different botanical origin (acacia, sunflower, linden, meadow, and fake honey) by recording emission from 270 to 640 nm with excitation in the range of 240-500 nm. Fluorescence spectra were described with a six-component PARAFAC model, and PARAFAC scores were further processed with two types of ANN’s (feed-forward network and self-organizing maps) to obtain algorithms for classification of honey on the basis of their botanical origin. Both ANN’s detected fake honey samples with 100% sensitivity and specificity.

Keywords: honey, fluorescence, PARAFAC, artificial neural networks

Procedia PDF Downloads 954

Authors: Djamel–Eddine Yassine Boutiba

Abstract:

In this present memory, we present the various impacts deflectometer leading to the sizing by strengthening of existing roadways. It reminds that the road network in Algeria plays a major role with regard to drainage in major strategic areas and especially in the fringe northern Algeria. Heavy traffic passing through the northern fringe (between 25% and 30% heavy vehicles) causes substantial degradations at both the surface layer and base layer. The work on site by means within the laboratory CTTP such as deflectographe Lacroix, allowed us to record a large number of deflection localized bending on RN19A (Carrefour CW73-Ain- Merane), whose analysis of the results led us to opt for a building throughout the band's project . By the recorder against HWD (Heavy Weight déflectometer) allowed us to learn about the behavior of the pavement on the banks. In addition, the Software Alize III has been essential in the verification of the increase in the thickness dimensioned.

Keywords: capacity, deflection, deflectograph lacroix, degradation, hwd

Procedia PDF Downloads 285

Authors: Nurudeen Afolami Ayeni, Kasali Bello

Abstract:

Methylolmelamine with increasing degree of methylol substitution and the phosphates derivatives were used to resinate cotton fabric (CF). The resination was carried out at different curing time and curing temperature. Generally, the results show a reduction in the flame propagation rate of the treated fabrics compared to the untreated cotton fabric (CF). While the flame retardancy of methylolmelamine-treated fibre could be attributed to the degree of crosslinking of fibre-resin network which promotes stability, the methylolmelamine phosphate-treated fabrics show better retardancy due to the intumescences action of the phosphate resin upon decomposition in the resin – fabric network.

Keywords: cotton fabric, flame retardant, methylolmelamine, crosslinking, resination

Procedia PDF Downloads 385

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 170

Authors: Daham Owaid Matrood, Naqaa Hussein Raheem

Abstract:

Evolutionary algorithms and Artificial neural networks (ANN) are two relatively young research areas that were subject to a steadily growing interest during the past years. This paper examines the use of Particle Swarm Optimization (PSO) to train a multi-layer feed forward neural network for demand forecasting. We use in this paper weekly demand data for packed cement and towels, which have been outfitted by the Northern General Company for Cement and General Company of prepared clothes respectively. The results showed superiority of trained neural networks using particle swarm optimization on neural networks trained using error back propagation because their ability to escape from local optima.

Keywords: artificial neural network, demand forecasting, particle swarm optimization, weight optimization

Procedia PDF Downloads 452

Authors: Amr Sadek, Abdelrahaman Al-Qahtany, Turkey Salem Al-Qahtany

Abstract:

In this study, a backpropagation artificial neural network (ANN) model has been used to predict the cooling and heating capacities of air conditioners (AC) under different conditions. Sufficiently large measurement results were obtained from the national energy-efficiency laboratories in Saudi Arabia and were used for the learning process of the ANN model. The parameters affecting the performance of the AC, including temperature, humidity level, specific heat enthalpy indoors and outdoors, and the air volume flow rate of indoor units, have been considered. These parameters were used as inputs for the ANN model, while the cooling and heating capacity values were set as the targets. A backpropagation ANN model with two hidden layers and one output layer could successfully correlate the input parameters with the targets. The characteristics of the ANN model including the input-processing, transfer, neurons-distance, topology, and training functions have been discussed. The performance of the ANN model was monitored over the training epochs and assessed using the mean squared error function. The model was then used to predict the performance of the AC under conditions that were not included in the measurement results. The optimum performance of the AC was also predicted under the different environmental conditions in Saudi Arabia. The uncertainty of the ANN model predictions has been evaluated taking into account the randomness of the data and lack of learning.

Keywords: artificial neural network, uncertainty of model predictions, efficiency of air conditioners, cooling and heating capacities

Procedia PDF Downloads 74

Authors: Ibrahim Ozkan

Abstract:

In this study, a cross-layer design which combines adaptive modulation and coding (AMC) and hybrid automatic repeat request (HARQ) techniques for a cooperative wireless network is investigated analytically. Previous analyses of such systems in the literature are confined to the case where the fading channel is independent at each retransmission, which can be unrealistic unless the channel is varying very fast. On the other hand, temporal channel correlation can have a significant impact on the performance of HARQ systems. In this study, utilizing a Markov channel model which accounts for the temporal correlation, the performance of non-cooperative and cooperative networks are investigated in terms of packet loss rate and throughput metrics for Chase combining HARQ strategy.

Keywords: cooperative network, adaptive modulation and coding, hybrid ARQ, correlated fading

Procedia PDF Downloads 144

Authors: Ajai Singh

Abstract:

Simulation of hydrological processes at the watershed outlet through modelling approach is essential for proper planning and implementation of appropriate soil conservation measures in Damodar Barakar catchment, Hazaribagh, India where soil erosion is a dominant problem. This study quantifies the parametric uncertainty involved in simulation of stream flow using Soil and Water Assessment Tool (SWAT), a watershed scale model and Radial Basis Neural Network (RBNN), an artificial neural network model. Both the models were calibrated and validated based on measured stream flow and quantification of the uncertainty in SWAT model output was assessed using ‘‘Sequential Uncertainty Fitting Algorithm’’ (SUFI-2). Though both the model predicted satisfactorily, but RBNN model performed better than SWAT with R2 and NSE values of 0.92 and 0.92 during training, and 0.71 and 0.70 during validation period, respectively. Comparison of the results of the two models also indicates a wider prediction interval for the results of the SWAT model. The values of P-factor related to each model shows that the percentage of observed stream flow values bracketed by the 95PPU in the RBNN model as 91% is higher than the P-factor in SWAT as 87%. In other words the RBNN model estimates the stream flow values more accurately and with less uncertainty. It could be stated that RBNN model based on simple input could be used for estimation of monthly stream flow, missing data, and testing the accuracy and performance of other models.

Keywords: SWAT, RBNN, SUFI 2, bootstrap technique, stream flow, simulation

Procedia PDF Downloads 370

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti

Abstract:

Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 123

Authors: Pierre-Andre Mudry, Jean Decaix, Jeremy Schmid, Cesar Papilloud, Cecile Munch-Alligne

Abstract:

In most of the Swiss Alpine regions, the availability of water resources is usually adequate even in times of drought, as evidenced by the 2003 and 2018 summers. Indeed, important natural stocks are for the moment available in the form of snow and ice, but the situation is likely to change in the future due to global and regional climate change. In addition, alpine mountain regions are areas where climate change will be felt very rapidly and with high intensity. For instance, the ice regime of these regions has already been affected in recent years with a modification of the monthly availability and extreme events of precipitations. The current research, focusing on the municipality of Val de Bagnes, located in the canton of Valais, Switzerland, is part of a project led by the Altis company and achieved in collaboration with WSL, BlueArk Entremont, and HES-SO Valais-Wallis. In this region, water occupies a key position notably for winter and summer tourism. Thus, multiple actors want to apprehend the future needs and availabilities of water, on both the 2050 and 2100 horizons, in order to plan the modifications to the water supply and distribution networks. For those changes to be salient and efficient, a good knowledge of the current water distribution networks is of most importance. In the current case, the water drinking network is well documented, but this is not the case for the irrigation one. Since the water consumption for irrigation is ten times higher than for drinking water, data acquisition on the irrigation network is a major point to determine future scenarios. This paper first presents the instrumentation and simulation of the irrigation network using custom-designed IoT devices, which are coupled with a digital clone simulated to reduce the number of measuring locations. The developed IoT ad-hoc devices are energy-autonomous and can measure flows and pressures using industrial sensors such as calorimetric water flow meters. Measurements are periodically transmitted using the LoRaWAN protocol over a dedicated infrastructure deployed in the municipality. The gathered values can then be visualized in real-time on a dashboard, which also provides historical data for analysis. In a second phase, a digital clone of the irrigation network was modeled using EPANET, a software for water distribution systems that performs extended-period simulations of flows and pressures in pressurized networks composed of reservoirs, pipes, junctions, and sinks. As a preliminary work, only a part of the irrigation network was modelled and validated by comparisons with the measurements. The simulations are carried out by imposing the consumption of water at several locations. The validation is performed by comparing the simulated pressures are different nodes with the measured ones. An accuracy of +/- 15% is observed on most of the nodes, which is acceptable for the operator of the network and demonstrates the validity of the approach. Future steps will focus on the deployment of the measurement devices on the whole network and the complete modelling of the network. Then, scenarios of future consumption will be investigated. Acknowledgment— The authors would like to thank the Swiss Federal Office for Environment (FOEN), the Swiss Federal Office for Agriculture (OFAG) for their financial supports, and ALTIS for the technical support, this project being part of the Swiss Pilot program 'Adaptation aux changements climatiques'.

Keywords: hydraulic digital clone, IoT water monitoring, LoRaWAN water measurements, EPANET, irrigation network

Procedia PDF Downloads 145

Authors: Zekang Lan, Yan Xu, Yingkun Huang, Dian Huang, Shengzhong Feng

Abstract:

Jobs on high-performance computing (HPC) clusters can suffer significant performance degradation due to inter-job network interference. Topology-aware job allocation problem (TJAP) is such a problem that decides how to dedicate nodes to specific applications to mitigate inter-job network interference. In this paper, we study the window-based TJAP on a fat-tree network aiming at minimizing the cost of communication hop, a defined inter-job interference metric. The window-based approach for scheduling repeats periodically, taking the jobs in the queue and solving an assignment problem that maps jobs to the available nodes. Two special allocation strategies are considered, i.e., static continuity assignment strategy (SCAS) and dynamic continuity assignment strategy (DCAS). For the SCAS, a 0-1 integer programming is developed. For the DCAS, an approach called neural simulated algorithm (NSA), which is an extension to simulated algorithm (SA) that learns a repair operator and employs them in a guided heuristic search, is proposed. The efficacy of NSA is demonstrated with a computational study against SA and SCIP. The results of numerical experiments indicate that both the model and algorithm proposed in this paper are effective.

Keywords: high-performance computing, job allocation, neural simulated annealing, topology-aware

Procedia PDF Downloads 116

Authors: Aditya Purohit, Neha Bansal

Abstract:

Unplanned urbanization and multidirectional sprawl of the cities have resulted in increased motorization and deteriorating transport conditions like traffic congestion, longer commuting, pollution, increased carbon footprint, and above all increased fatalities. In order to overcome these problems, various practices have been adopted including– promoting and implementing mass transport; traffic junction channelization; smart transport etc. However, these methods are found to be primarily focusing on vehicular mobility rather than people accessibility. With this research gap, this paper tries to resolve the mobility issues for Ahmedabad city in India, which being the economic capital Gujarat state has a huge commuter and visitor inflow. This research aims to resolve the traffic congestion and urban mobility issues focusing on Gujarat State Regional Transport Corporation (GSRTC) for the city of Ahmadabad by analyzing the existing operations and network structure of GSRTC followed by finding possibilities of integrating it with other modes of urban transport. The network restructuring (NR) methodology is used with appropriate variations, based on commuter demand and growth pattern of the city. To do these ‘scenarios’ based on priority issues (using 12 parameters) and their best possible solution, are established after route network analysis for 2700 population sample of 20 traffic junctions/nodes across the city. Approximately 5% sample (of passenger inflow) at each node is considered using random stratified sampling technique two scenarios are – Scenario 1: Resolving mobility issues by use of Special Purpose Vehicle (SPV) in joint venture to GSRTC and Private Operators for establishing feeder service, which shall provide a transfer service for passenger for movement from inner city area to identified peripheral terminals; and Scenario 2: Augmenting existing mass transport services such as BRTS and AMTS for using them as feeder service to the identified peripheral terminals. Each of these has now been analyzed for the best suitability/feasibility in network restructuring. A desire-line diagram is constructed using this analysis which indicated that on an average 62% of designated GSRTC routes are overlapping with mass transportation service routes of BRTS and AMTS in the city. This has resulted in duplication of bus services causing traffic congestion especially in the Central Bus Station (CBS). Terminating GSRTC services on the periphery of the city is found to be the best restructuring network proposal. This limits the GSRTC buses at city fringe area and prevents them from entering into the city core areas. These end-terminals of GSRTC are integrated with BRTS and AMTS services which help in segregating intra-state and inter-state bus services. The research concludes that absence of integrated multimodal transport network resulted in complexity of transport access to the commuters. As a further scope of research comparing and understanding of value of access time in total travel time and its implication on generalized cost on trip and how it varies city wise may be taken up.

Keywords: mass transportation, multi-modal integration, network restructuring, travel behavior, urban transport

Procedia PDF Downloads 197

Authors: Jeaha Yang, Ahmed Khan, Donna L. Rodela, Mohammed A. Qaudeer

Abstract:

Traditional supply chain silos still exist today due to the difficulty of establishing trust between various partners and technological barriers across industries. Companies lose opportunities and revenue and inadvertently make poor business decisions resulting in further challenges. Blockchain technology can bring a new level of transparency through sharing information with a distributed ledger in a decentralized manner that creates a basis of trust for business. Blockchain is a loosely coupled, hub-style communication network in which trading partners can work indirectly with each other for simpler integration, but they work together through the orchestration of their supply chain operations under a coherent process that is developed jointly. A Blockchain increases efficiencies, lowers costs, and improves interoperability to strengthen and automate the supply chain management process while all partners share the risk. Blockchain ledger is built to track inventory lifecycle for supply chain transparency and keeps a journal of inventory movement for real-time reconciliation. State design patterns are used to capture the life cycle (behavior) of inventory management as a state machine for a common, transparent and coherent process which creates an opportunity for trading partners to become more responsive in terms of changes or improvements in process, reconcile discrepancies, and comply with internal governance and external regulations. It enables end-to-end, inter-company visibility at the unit level for more accurate demand planning with better insight into order fulfillment and replenishment.

Keywords: supply chain management, inventory trace-ability, perpetual inventory system, inventory lifecycle, blockchain, inventory consignment, supply chain transparency, digital thread, demand planning, hyper ledger fabric

Procedia PDF Downloads 90

Authors: Ahmad Saadiq, Neeraj Sahu

Abstract:

Sediment, which comprises of solid particles of mineral and organic material are transported by water. In river systems, the amount of sediment transported is controlled by both the transport capacity of the flow and the supply of sediment. The transport of sediment in rivers is important with respect to pollution, channel navigability, reservoir ageing, hydroelectric equipment longevity, fish habitat, river aesthetics and scientific interests. The sediment load transported in a river is a very complex hydrological phenomenon. Hence, sediment transport has attracted the attention of engineers from various aspects, and different methods have been used for its estimation. So, several experimental equations have been submitted by experts. Though the results of these methods have considerable differences with each other and with experimental observations, because the sediment measures have some limits, these equations can be used in estimating sediment load. In this present study, two black box models namely, an SRC (Sediment Rating Curve) and ANN (Artificial Neural Network) are used in the simulation of the suspended sediment load. The study is carried out for Seonath subbasin. Seonath is the biggest tributary of Mahanadi river, and it carries a vast amount of sediment. The data is collected for Jondhra hydrological observation station from India-WRIS (Water Resources Information System) and IMD (Indian Meteorological Department). These data include the discharge, sediment concentration and rainfall for 10 years. In this study, sediment load is estimated from the input parameters (discharge, rainfall, and past sediment) in various combination of simulations. A sediment rating curve used the water discharge to estimate the sediment concentration. This estimated sediment concentration is converted to sediment load. Likewise, for the application of these data in ANN, they are normalised first and then fed in various combinations to yield the sediment load. RMSE (root mean square error) and R² (coefficient of determination) between the observed load and the estimated load are used as evaluating criteria. For an ideal model, RMSE is zero and R² is 1. However, as the models used in this study are black box models, they don’t carry the exact representation of the factors which causes sedimentation. Hence, a model which gives the lowest RMSE and highest R² is the best model in this study. The lowest values of RMSE (based on normalised data) for sediment rating curve, feed forward back propagation, cascade forward back propagation and neural network fitting are 0.043425, 0.00679781, 0.0050089 and 0.0043727 respectively. The corresponding values of R² are 0.8258, 0.9941, 0.9968 and 0.9976. This implies that a neural network fitting model is superior to the other models used in this study. However, a drawback of neural network fitting is that it produces few negative estimates, which is not at all tolerable in the field of estimation of sediment load, and hence this model can’t be crowned as the best model among others, based on this study. A cascade forward back propagation produces results much closer to a neural network model and hence this model is the best model based on the present study.

Keywords: artificial neural network, Root mean squared error, sediment, sediment rating curve

Procedia PDF Downloads 325

Authors: Habib Gorine, Rabia Saleh

Abstract:

Mobile Ad-Hoc Networks are the special type of wireless networks which share common security requirements with other networks such as confidentiality, integrity, authentication, and availability, which need to be addressed in order to secure data transfer through the network. Their routing protocols are vulnerable to various malicious attacks which could have a devastating consequence on data security. In this paper, three types of attacks such as selfish, gray hole, and black hole attacks have been applied to the two most important routing protocols in MANET named dynamic source routing and ad-hoc on demand distance vector in order to analyse and compare the impact of these attacks on the Network performance in terms of throughput, average delay, packet loss, and consumption of energy using NS2 simulator.

Keywords: MANET, wireless networks, routing protocols, malicious attacks, wireless networks simulation

Procedia PDF Downloads 320

Authors: Sathapath Kilaso

Abstract:

Thailand has a large range of geographic diversity. Thailand can be divided into 5 regions which are North Region, East Region, West Region, South Region and North-East Region which each region has a different geographic and climate. Especially in North Region, the geographic is mountain and intermontane plateau which will be a reason that the roads in the North Region have a lot of bends. So the driver in the North Region road will have to have a very high skill of driving. If the accident is occurred, the emergency rescue will have a hard time to reach the accident area and rescue the victim of the accident as the long distance and steep road. This article will apply the concept of the wireless sensor network with the micro-controller to alert the driver when the driver reaches the very dangerous bend.

Keywords: wireless sensor network, motion sensor, smart alert, dangerous bend

Procedia PDF Downloads 276

Authors: Mohamed Gouda

Abstract:

Antibacterial wound dressings based on cellulose nanofibers containing different metal nanoparticles (CMC-MNPs) were synthesized using an electrospinning technique. First, the composite of carboxymethyl cellulose containing different metal nanoparticles (CMC/MNPs), such as copper nanoparticles (CuNPs), iron nanoparticles (FeNPs), zinc nanoparticles (ZnNPs), cadmium nanoparticles (CdNPs) and cobalt nanoparticles (CoNPs) were synthesized, and finally, these composites were transferred to the electrospinning process. Synthesized CMC-MNPs were characterized using scanning electron microscopy (SEM) coupled with high-energy dispersive X-ray (EDX) and UV-visible spectroscopy used to confirm nanoparticle formation. The SEM images clearly showed regular flat shapes with semi-porous surfaces. All MNPs were well distributed inside the backbone of the cellulose without aggregation. The average particle diameters were 29-39 nm for ZnNPs, 29-33 nm for CdNPs, 25-33 nm for CoNPs, 23-27 nm for CuNPs and 22-26 nm for FeNPs. Surface morphology, water uptake and release of MNPs from the nanofibers in water and antimicrobial efficacy were studied. SEM images revealed that electrospun CMC-MNPs nanofibers are smooth and uniformly distributed without bead formation with average fiber diameters in the range of 300 to 450 nm. Fiber diameters were not affected by the presence of MNPs. TEM images showed that MNPs are present in/on the electrospun CMC-MNPs nanofibers. The diameter of the electrospun nanofibers containing MNPs was in the range of 300–450 nm. The MNPs were observed to be spherical in shape. The CMC-MNPs nanofibers showed good hydrophilic properties and had excellent antibacterial activity against the Gram-negative bacteria Escherichia coli and the Gram-positive bacteria Staphylococcus aureus.

Keywords: electrospinning technique, metal nanoparticles, cellulosic nanofibers, wound dressing

Procedia PDF Downloads 329

Authors: Julian Wise

Abstract:

Newcrest Mining is one of the world’s top five gold and rare earth mining organizations by production, reserves and market capitalization in the world. This paper elaborates on the data acquisition processes employed by Newcrest in collaboration with Fortune 500 listed organization, Insight Enterprises, to standardize machine learning solutions which process data from over a hundred thousand distributed Internet of Things (IoT) devices located at mine sites globally. Through the utilization of software architecture cloud technologies and edge computing, the technological developments enable for standardized processes of machine learning applications to influence the strategic optimization of mineral processing. Target objectives of the machine learning optimizations include time savings on mineral processing, production efficiencies, risk identification, and increased production throughput. The data acquired and utilized for predictive modelling is processed through edge computing by resources collectively stored within a data lake. Being involved in the digital transformation has necessitated the standardization software architecture to manage the machine learning models submitted by vendors, to ensure effective automation and continuous improvements to the mineral process models. Operating at scale, the system processes hundreds of gigabytes of data per day from distributed mine sites across the globe, for the purposes of increased improved worker safety, and production efficiency through big data applications.

Keywords: mineral technology, big data, machine learning operations, data lake

Procedia PDF Downloads 112

Authors: Lina Dagilienė

Abstract:

The article explores the impact of normative institutional factors on the development of sustainability reporting. The vast majority of research in the scientific literature focuses on mandatory institutional factors, i.e. how public institutions and market regulators affect sustainability reporting. Meanwhile, there is lack of empirical data for the impact of normative institutional factors. The effect of normative factors in this paper is based on the role of non-governmental organizations (NGO) and institutional theory. The case of Global Compact Local Network in the developing country was examined. The research results revealed that in the absence of regulated factors, companies were not active with regard to social disclosures; they presented non-systemized social information of a descriptive nature. Only 10% of sustainability reports were prepared using the GRI methodology. None of the reports were assured by third parties.

Keywords: institutional theory, normative, sustainability reporting, Global Compact Local Network

Procedia PDF Downloads 382

Authors: Durga Prasad Sapkota, Madhu Sudan Kayastha, Koichi Wakita

Abstract:

In this paper, we have compared and analyzed the electron absorption properties between with and without excitonic effect bulk in high purity GaAs spatial light modulator for an optical fiber communication network. The electroabsorption properties such as absorption spectra, change in absorption spectra, change in refractive index and extinction ratio have been calculated. We have also compared the result of absorption spectra and change in absorption spectra with the experimental results and found close agreement with experimental results.

Keywords: exciton, refractive index change, extinction ratio, GaAs

Procedia PDF Downloads 575

Authors: Jaiden X. Schraut

Abstract:

Medical Imaging Segmentation of Chest X-rays is used for the purpose of identification and differentiation of lung cancer, pneumonia, COVID-19, and similar respiratory diseases. Widespread application of computer-supported perception methods into the diagnostic pipeline has been demonstrated to increase prognostic accuracy and aid doctors in efficiently treating patients. Modern models attempt the task of segmentation and classification separately and improve diagnostic efficiency; however, to further enhance this process, this paper proposes a multi-output network that follows a U-Net architecture for image segmentation output and features an additional CNN module for auxiliary classification output. The proposed model achieves a final Jaccard Index of .9634 for image segmentation and a final accuracy of .9600 for classification on the COVID-19 radiography database.

Keywords: chest X-ray, deep learning, image segmentation, image classification

Procedia PDF Downloads 144