Search results for: MobileNetV2 neural network

Authors: Sreto Boljevic

Abstract:

In the absence of considerable investment in electricity generation, transmission and distribution network (DN) capacity, the demand for electrical energy will quickly strain the capacity of the existing electrical power network. With anticipated growth and proliferation of Electric vehicles (EVs) and Heat pump (HPs) identified the likelihood that the additional load from EV changing and the HPs operation will require capital investment in the DN. While an area-wide implementation of EVs and HPs will contribute to the decarbonization of the energy system, they represent new challenges for the existing low-voltage (LV) network. Distributed energy resources (DER), operating both as part of the DN and in the off-network mode, have been offered as a means to meet growing electricity demand while maintaining and ever-improving DN reliability, resiliency and power quality. DN planning has traditionally been done by forecasting future growth in demand and estimating peak load that the network should meet. However, new problems are arising. These problems are associated with a high degree of proliferation of EVs and HPs as load imposes on DN. In addition to that, the promotion of electricity generation from renewable energy sources (RES). High distributed generation (DG) penetration and a large increase in load proliferation at low-voltage DNs may have numerous impacts on DNs that create issues that include energy losses, voltage control, fault levels, reliability, resiliency and power quality. To mitigate negative impacts and at a same time enhance positive impacts regarding the new operational state of DN, CHP system integration can be seen as best action to postpone/reduce capital investment needed to facilitate promotion and maximize benefits of EVs, HPs and RES integration in low-voltage DN. The aim of this paper is to generate an algorithm by using an analytical approach. Algorithm implementation will provide a way for optimal placement of the CHP system in the DN in order to maximize the integration of RES and increase in proliferation of EVs and HPs.

Keywords: combined heat & power (CHP), distribution networks, EVs, HPs, RES

Procedia PDF Downloads 206

Authors: Belayneh Matebie, Michael Melese

Abstract:

The study focuses on addressing the challenges in classifying and ensuring the quality of Eragrostis Teff, a small and round grain that is the smallest cereal grain. Employing a traditional classification method is challenging because of its small size and the similarity of its environmental characteristics. To overcome this, this study employs a machine learning approach to develop a source and quality classification system for Teff cereal. Data is collected from various production areas in the Amhara regions, considering two types of cereal (high and low quality) across eight classes. A total of 5,920 images are collected, with 740 images for each class. Image enhancement techniques, including scaling, data augmentation, histogram equalization, and noise removal, are applied to preprocess the data. Convolutional Neural Network (CNN) is then used to extract relevant features and reduce dimensionality. The dataset is split into 80% for training and 20% for testing. Different classifiers, including FVGG16, FINCV3, QSCTC, EMQSCTC, SVM, and RF, are employed for classification, achieving accuracy rates ranging from 86.91% to 97.72%. The ensemble of FVGG16, FINCV3, and QSCTC using the Max-Voting approach outperforms individual algorithms.

Keywords: Teff, ensemble learning, max-voting, CNN, SVM, RF

Procedia PDF Downloads 59

Authors: Teklu Urgessa, Wookjae Maeng, Joong Seek Lee

Abstract:

Application of five implementations of three data mining classification techniques was experimented for extracting important insights from tourism data. The aim was to find out the best performing algorithm among the compared ones for tourism knowledge discovery. Knowledge discovery process from data was used as a process model. 10-fold cross validation method is used for testing purpose. Various data preprocessing activities were performed to get the final dataset for model building. Classification models of the selected algorithms were built with different scenarios on the preprocessed dataset. The outperformed algorithm tourism dataset was Random Forest (76%) before applying information gain based attribute selection and J48 (C4.5) (75%) after selection of top relevant attributes to the class (target) attribute. In terms of time for model building, attribute selection improves the efficiency of all algorithms. Artificial Neural Network (multilayer perceptron) showed the highest improvement (90%). The rules extracted from the decision tree model are presented, which showed intricate, non-trivial knowledge/insight that would otherwise not be discovered by simple statistical analysis with mediocre accuracy of the machine using classification algorithms.

Keywords: classification algorithms, data mining, knowledge discovery, tourism

Procedia PDF Downloads 300

Authors: Tolulope Aremu

Abstract:

This paper is based on the idea of using deep learning methodology for optimizing production yield by tuning a few key process parameters in a manufacturing environment. The study was explicitly on how to maximize production yield and minimize operational costs by utilizing advanced neural network models, specifically Long Short-Term Memory and Convolutional Neural Networks. These models were implemented using Python-based frameworks—TensorFlow and Keras. The targets of the research are the precision molding processes in which temperature ranges between 150°C and 220°C, the pressure ranges between 5 and 15 bar, and the material flow rate ranges between 10 and 50 kg/h, which are critical parameters that have a great effect on yield. A dataset of 1 million production cycles has been considered for five continuous years, where detailed logs are present showing the exact setting of parameters and yield output. The LSTM model would model time-dependent trends in production data, while CNN analyzed the spatial correlations between parameters. Models are designed in a supervised learning manner. For the model's loss, an MSE loss function is used, optimized through the Adam optimizer. After running a total of 100 training epochs, 95% accuracy was achieved by the models recommending optimal parameter configurations. Results indicated that with the use of RSM and DOE traditional methods, there was an increase in production yield of 12%. Besides, the error margin was reduced by 8%, hence consistent quality products from the deep learning models. The monetary value was annually around $2.5 million, the cost saved from material waste, energy consumption, and equipment wear resulting from the implementation of optimized process parameters. This system was deployed in an industrial production environment with the help of a hybrid cloud system: Microsoft Azure, for data storage, and the training and deployment of their models were performed on Google Cloud AI. The functionality of real-time monitoring of the process and automatic tuning of parameters depends on cloud infrastructure. To put it into perspective, deep learning models, especially those employing LSTM and CNN, optimize the production yield by fine-tuning process parameters. Future research will consider reinforcement learning with a view to achieving further enhancement of system autonomy and scalability across various manufacturing sectors.

Keywords: production yield optimization, deep learning, tuning of process parameters, LSTM, CNN, precision manufacturing, TensorFlow, Keras, cloud infrastructure, cost saving

Procedia PDF Downloads 42

Authors: Samira Baghbanbari, A. B. P. Lever, Payam S. Shabestari, Donald Weaver

Abstract:

Existing signal transmission models, although undoubtedly useful, have proven insufficient to explain the full complexity of information transfer within the central nervous system. The development of transformative models will necessitate a more comprehensive understanding of neuronal lipid membrane electrophysiology. Pursuant to this goal, the role of highly organized interfacial phospholipid-water layers emerges as a promising case study. A series of phospholipids in neural-glial gap junction interfaces as well as cholesterol molecules have been computationally modelled using high-performance density functional theory (DFT) calculations. Subsequent 'charge decomposition analysis' calculations have revealed a net transfer of charge from phospholipid orbitals through the organized interfacial water layer before ultimately finding its way to cholesterol acceptor molecules. The specific pathway of charge transfer from phospholipid via water layers towards cholesterol has been mapped in detail. Cholesterol is an essential membrane component that is overrepresented in neuronal membranes as compared to other mammalian cells; given this relative abundance, its apparent role as an electronic acceptor may prove to be a relevant factor in further signal transmission studies of the central nervous system. The timescales over which this electronic charge transfer occurs have also been evaluated by utilizing a system design that systematically increases the number of water molecules separating lipids and cholesterol. Memory loss through hydrogen-bonded networks in water can occur at femtosecond timescales, whereas existing action potential-based models are limited to micro or nanosecond scales. As such, the development of future models that attempt to explain faster timescale signal transmission in the central nervous system may benefit from our work, which provides additional information regarding fast timescale energy transfer mechanisms occurring through interfacial water. The study possesses a dataset that includes six distinct phospholipids and a collection of cholesterol. Ten optimized geometric characteristics (features) were employed to conduct binary classification through an artificial neural network (ANN), differentiating cholesterol from the various phospholipids. This stems from our understanding that all lipids within the first group function as electronic charge donors, while cholesterol serves as an electronic charge acceptor.

Keywords: charge transfer, signal transmission, phospholipids, water layers, ANN

Procedia PDF Downloads 81

Authors: Amal Khalifa, Nicolas Vana Santos

Abstract:

Steganography has been known for centuries as an efficient approach for covert communication. Due to its popularity and ease of access, image steganography has attracted researchers to find secure techniques for hiding information within an innocent looking cover image. In this research, we propose a novel deep-learning approach to digital image steganography. The proposed method, DeepWaveletFusion, uses convolutional neural networks (CNN) to hide a secret image into a cover image of the same size. Two CNNs are trained back-to-back to merge the Discrete Wavelet Transform (DWT) of both colored images and eventually be able to blindly extract the hidden image. Based on two different image similarity metrics, a weighted gain function is used to guide the learning process and maximize the quality of the retrieved secret image and yet maintaining acceptable imperceptibility. Experimental results verified the high recoverability of DeepWaveletFusion which outperformed similar deep-learning-based methods.

Keywords: deep learning, steganography, image, discrete wavelet transform, fusion

Procedia PDF Downloads 98

Authors: Qingqing Gai, Junxing Shen, Yu Luo

Abstract:

Due to the hardware architecture characteristics, some operators tend to acquire better performance if the input/output tensor dimensions are aligned to a certain minimum granularity, such as convolution and deconvolution commonly used in deep learning. Furthermore, if the requirements are not met, the general strategy is to pad with 0 to satisfy the requirements, potentially leading to the under-utilization of the hardware resources. Therefore, for the convolution and deconvolution whose input and output channels do not meet the minimum granularity alignment, we propose to transfer the W-dimensional data to the C-dimension for computation (W2C) to enable the C-dimension to meet the hardware requirements. This scheme also reduces the number of computations in the W-dimension. Although this scheme substantially increases computation, the operator’s speed can improve significantly. It achieves remarkable speedups on multiple hardware accelerators, including Nvidia Tensor cores, Qualcomm digital signal processors (DSPs), and Huawei neural processing units (NPUs). All you need to do is modify the network structure and rearrange the operator weights offline without retraining. At the same time, for some operators, such as the Reducemax, we observe that transferring the Cdimensional data to the W-dimension(C2W) and replacing the Reducemax with the Maxpool can accomplish acceleration under certain circumstances.

Keywords: convolution, deconvolution, W2C, C2W, alignment, hardware accelerator

Procedia PDF Downloads 111

Authors: Seyed Mohsen Jameii

Abstract:

Wireless underwater sensor networks are a type of sensor networks that are located in underwater environments and linked together by acoustic waves. The application of these kinds of network includes monitoring of pollutants (chemical, biological, and nuclear), oil fields detection, prediction of the likelihood of a tsunami in coastal areas, the use of wireless sensor nodes to monitor the passing submarines, and determination of appropriate locations for anchoring ships. This paper proposes a boundary coverage algorithm for intrusion detection in underwater sensor networks. In the first phase of the proposed algorithm, optimal deployment of nodes is done in the water. In the second phase, after the employment of nodes at the proper depth, clustering is executed to reduce the exchanges of messages between the sensors. In the third phase, the algorithm of "divide and conquer" is used to save energy and increase network efficiency. The simulation results demonstrate the efficiency of the proposed algorithm.

Keywords: boundary coverage, clustering, divide and ‎conquer, underwater sensor nodes

Procedia PDF Downloads 347

Authors: Wei Lu

Abstract:

With the development of information technology in China, network consumption is becoming more and more popular. As a special group, college students have a high degree of education and distinct opinions and personalities. In the future, the key groups of network consumption have gradually become the focus groups of network consumption. Studying college students’ online consumption behavior has important theoretical significance and practical value. Based on the Stimulus-Organism-Response (SOR) driving model and the structural equation model, this paper establishes the influencing factors model of College students’ online consumption behavior, evaluates and amends the model by using SPSS and AMOS software, analyses and determines the positive factors of marketing college students’ consumption, and provides an effective basis for guiding and promoting college student consumption.

Keywords: college students, online consumption, stimulate-organism-reaction driving model, structural equation model

Procedia PDF Downloads 157

Authors: Trung Hieu Tran, Jesse O'Hanley, Russell Fowler

Abstract:

When in-wheel wireless charging technology for electric vehicles becomes mature, a need for such integrated charging stations network development is essential. In this paper, we thus investigate the optimisation problem of in-wheel wireless electric vehicle charging network design. A mixed-integer linear programming model is formulated to solve into optimality the problem. In addition, a meta-heuristic algorithm is proposed for efficiently solving large-sized instances within a reasonable computation time. A parallel computing strategy is integrated into the algorithm to speed up its computation time. Experimental results carried out on the benchmark instances show that our model and algorithm can find the optimal solutions and their potential for practical applications.

Keywords: electric vehicle, wireless charging station, mathematical programming, meta-heuristic algorithm, parallel computing

Procedia PDF Downloads 85

Authors: Seyed-Mohammad-Kazem Emami, Behrang Saki, Majid Mohammadian

Abstract:

The wastewater flow field inside a sewage network including pipe and ‎manhole was investigated using a Computational Fluid Dynamics ‎‎(CFD) model. The numerical model is developed by incorporating a ‎rheological model to calculate the viscosity of wastewater fluid by ‎means of open source toolbox OpenFOAM. The rheological ‎properties of prepared wastewater fluid suspensions are first measured ‎using a BrookField LVDVII Pro+ viscometer with an enhanced UL ‎adapter and then correlated the suitable rheological viscosity model ‎values from the measured rheological properties. The results show the ‎significant effects of rheological characteristics of wastewater fluid on ‎the flow domain of sewer system. Results were compared and ‎discussed with the commonly used Newtonian model to evaluate the ‎differences for velocity profile, pressure and shear stress. ‎

Keywords: Non-Newtonian flows, Wastewater, Numerical simulation, Rheology, Sewage Network

Procedia PDF Downloads 140

Authors: Maryam Heidari, James H. Jones Jr.

Abstract:

Millions of online posts about different topics and products are shared on popular social media platforms. One use of this content is to provide crowd-sourced information about a specific topic, event or product. However, this use raises an important question: what percentage of information available through these services is trustworthy? In particular, might some of this information be generated by a machine, i.e., a bot, instead of a human? Bots can be, and often are, purposely designed to generate enough volume to skew an apparent trend or position on a topic, yet the consumer of such content cannot easily distinguish a bot post from a human post. In this paper, we introduce a model for social media bot detection which uses Bidirectional Encoder Representations from Transformers (Google Bert) for sentiment classification of tweets to identify topic-independent features. Our use of a Natural Language Processing approach to derive topic-independent features for our new bot detection model distinguishes this work from previous bot detection models. We achieve 94\% accuracy classifying the contents of data as generated by a bot or a human, where the most accurate prior work achieved accuracy of 92\%.

Keywords: bot detection, natural language processing, neural network, social media

Procedia PDF Downloads 118

Authors: Somesh Kumar Sharma, Sunanad Gupta

Abstract:

The contribution of aviation to society and economy is undisputedly significant. The aviation industry drives economic and social progress by contributing prominently to tourism, commerce and improved quality of life. Identifying the amount of fuel consumed by an aircraft while moving in both airspace and ground networks is critical to air transport economics. Aviation fuel is a major operating cost parameter of the aviation industry and at the same time it is prone to various constraints. This article aims to develop a model for fuel consumption of aviation product. The paper tailors the information for the fuel consumption optimization in terms of information development, information evaluation and information refinement. The information is evaluated and refined using statistical package R and Factor Analysis which is further validated with neural networking. The study explores three primary dimensions which are finally summarized into 23 influencing variables in contrast to 96 variables available in literature. The 23 variables explored in this study should be considered as highly influencing variables for fuel consumption which will contribute significantly towards fuel optimization.

Keywords: fuel consumption, civil aviation industry, neural networking, optimization

Procedia PDF Downloads 344

Authors: Fernanda M. Assef, Maria Teresinha A. Steiner

Abstract:

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.

Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines

Procedia PDF Downloads 107

Authors: Nishank Raisinghani

Abstract:

Efficiently predicting drug response remains a challenge in the realm of drug discovery. To address this issue, we propose four model architectures that combine graphical representation with varying positions of multiheaded self-attention mechanisms. By leveraging two types of multi-omics data, transcriptomics and genomics, we create a comprehensive representation of target cells and enable drug response prediction in precision medicine. A majority of our architectures utilize multiple transformer models, one with a graph attention mechanism and the other with a multiheaded self-attention mechanism, to generate latent representations of both drug and omics data, respectively. Our model architectures apply an attention mechanism to both drug and multiomics data, with the goal of procuring more comprehensive latent representations. The latent representations are then concatenated and input into a fully connected network to predict the IC-50 score, a measure of cell drug response. We experiment with all four of these architectures and extract results from all of them. Our study greatly contributes to the future of drug discovery and precision medicine by looking to optimize the time and accuracy of drug response prediction.

Keywords: drug discovery, transformers, graph neural networks, multiomics

Procedia PDF Downloads 161

Authors: A. Prajapati, K. L. Koo, F. Ghassemi, M. Mulimakwenda

Abstract:

In the UK, as the volume of non-linear loads connected to transmission grid continues to rise steeply, the harmonic distortion levels on transmission network are becoming a serious concern for the network owners and system operators. This paper outlines the findings of the study conducted to verify the proposal that the harmonic mitigation could be optimized and can be managed economically and effectively at the transmission network level by the Transmission Owner (TO) instead of the individual polluter connected to the grid. Harmonic mitigation studies were conducted on selected regions of the transmission network in England for recently connected offshore wind power plants to strategize and optimize selected harmonic filter options. The results – filter volume and capacity – were then compared against the mitigation measures adopted by the individual connections. Estimation ratios were developed based on the actual installed and optimal proposed filters. These estimation ratios were then used to derive harmonic filter requirements for future contracted connections. The study has concluded that a saving of 37% in the filter volume/capacity could be achieved if the TO is to centrally manage the harmonic mitigation instead of individual polluter installing their own mitigation solution.

Keywords: C-type filter, harmonics, optimization, offshore wind farms, interconnectors, HVDC, renewable energy, transmission owner

Procedia PDF Downloads 162

Authors: Tingyu Zhang

Abstract:

This paper utilizes the Super-SBM model to assess water resources green efficiency (WRGE) among provinces in China and investigate its spatial and temporal features, based on the characteristic framework of “economy-environment-society.” The social network analysis is employed to examine the network pattern and spatial interaction of WRGE. Further, the quadratic assignment procedure method is utilized for examining the influencing factors of the spatial association of WRGE regarding “relationship.” The study reveals that: (1) the spatial distribution of WRGE demonstrates a distribution pattern of Eastern>Western>Central; (2) a remarkable spatial association exists among provinces; however, no strict hierarchical structure is observed. The internal structure of the WRGE network is characterized by the feature of "Eastern strong and Western weak". The block model analysis discovers that the members of the “net spillover” and “two-way spillover” blocks are mostly in the eastern and central provinces; “broker” block, which plays an intermediary role, is mostly in the central provinces; and members of the “net beneficiary” block are mostly in the western region. (3) Differences in economic development, degree of urbanization, water use environment, and water management have significant impacts on the spatial connection of WRGE. This study is dedicated to the realization of regional linkages and synergistic enhancement of WRGE, which provides a meaningful basis for building a harmonious society of human and water coexistence.

Keywords: water resources green efficiency, super-SBM model, social network analysis, quadratic assignment procedure

Procedia PDF Downloads 71

Authors: Hang Yang, Jiahao Liu, Jichao Li, Kewei Yang, Minghao Li, Bingfeng Ge

Abstract:

The system-of-systems (SoS) are utilized to characterize networks formed by integrating individual complex systems that demonstrate interdependence and interconnectedness. Research on the disintegration issue in SoS is significant in improving network survivability, maintaining network security, and optimizing SoS architecture. Accordingly, this study proposes an integrated framework called resilience-oriented disintegration in SoS (SoSRD), for modeling and solving the issue of SoS disintegration. Firstly, a SoS disintegration index (SoSDI) is presented to evaluate the disintegration effect of SoS. This index provides a practical description of the disintegration process and is the first integration of the network disintegration model and resilience models. Subsequently, we propose a resilience-oriented disintegration method based on reinforcement learning (RDRL) to enhance the efficiency of SoS disintegration. This method is not restricted by the problem scenario as well as considering the coexistence of disintegration (node/link removal) and recovery (node/link addition) during the process of SoS disintegration. Finally, the effectiveness and superiority of the proposed SoSRD are demonstrated through a case study. We demonstrate that our proposed framework outperforms existing indexes and methods in both node and link disintegration scenarios, providing a fresh perspective on network disintegration. The findings provide crucial insights into dismantling harmful SoS and designing a more resilient SoS.

Keywords: system-of-systems, disintegration index, resilience, reinforcement learning

Procedia PDF Downloads 23

Authors: Eric Asare, Jamie Evans, Mark Newton, Emiliano Bilotti

Abstract:

Two types of filler shapes (sphere and flakes) and three different sizes are employed to study the size effect on PTC. The composite is prepared using a mini-extruder with high-density polyethylene (HDPE) as the matrix. A computer modelling is used to fit the experimental results. The percolation threshold decreases with decreasing filler size and this was observed for both the spherical particles as well as the flakes. This was caused by the decrease in interparticle distance with decreasing filler size. The 100 µm particles showed a larger PTC intensity compared to the 5 µm particles for the metal coated glass sphere and flake. The small particles have a large surface area and agglomeration and this makes it difficult for the conductive network to e disturbed. Increasing the filler content decreased the PTC intensity and this is due to an increase in the conductive network within the polymer matrix hence more energy is needed to disrupt the network.

Keywords: positive temperature coefficient (PTC) effect, conductive polymer composite (CPC), electrical conductivity

Procedia PDF Downloads 432

Authors: Zhenyu Zhang, Hsi-Hsien Wei

Abstract:

Highway network systems play a vital role in disaster response for disaster-damaged areas. Damaged bridges in such network systems can impede disaster response by disrupting transportation of rescue teams or humanitarian supplies. Therefore, emergency inspection and repair of bridges to quickly collect damage information of bridges and recover the functionality of highway networks is of paramount importance to disaster response. A widely used measure of a network’s capability to recover from disasters is resilience. To enhance highway network resilience, plenty of studies have developed various repair scheduling methods for the prioritization of bridge-repair tasks. These methods assume that repair activities are performed after the damage to a highway network is fully understood via inspection, although inspecting all bridges in a regional highway network may take days, leading to the significant delay in repairing bridges. In reality, emergency repair activities can be commenced as soon as the damage data of some bridges that are crucial to emergency response are obtained. Given that emergency bridge inspection and repair (EBIR) activities are executed simultaneously in the response phase, the real-time interactions between these activities can occur – the blockage of highways due to repair activities can affect inspection routes which in turn have an impact on emergency repair scheduling by providing real-time information on bridge damages. However, the impact of such interactions on the optimal emergency inspection routes (EIR) and emergency repair schedules (ERS) has not been discussed in prior studies. To overcome the aforementioned deficiencies, this study develops a routing and scheduling model for EBIR while accounting for real-time inspection-repair interactions to maximize highway network resilience. A stochastic, time-dependent integer program is proposed for the complex and real-time interacting EBIR problem given multiple inspection and repair teams at locations as set post-disaster. A hybrid genetic algorithm that integrates a heuristic approach into a traditional genetic algorithm to accelerate the evolution process is developed. Computational tests are performed using data from the 2008 Wenchuan earthquake, based on a regional highway network in Sichuan, China, consisting of 168 highway bridges on 36 highways connecting 25 cities/towns. The results show that the simultaneous implementation of bridge inspection and repair activities can significantly improve the highway network resilience. Moreover, the deployment of inspection and repair teams should match each other, and the network resilience will not be improved once the unilateral increase in inspection teams or repair teams exceeds a certain level. This study contributes to both knowledge and practice. First, the developed mathematical model makes it possible for capturing the impact of real-time inspection-repair interactions on inspection routing and repair scheduling and efficiently deriving optimal EIR and ERS on a large and complex highway network. Moreover, this study contributes to the organizational dimension of highway network resilience by providing optimal strategies for highway bridge management. With the decision support tool, disaster managers are able to identify the most critical bridges for disaster management and make decisions on proper inspection and repair strategies to improve highway network resilience.

Keywords: disaster management, emergency bridge inspection and repair, highway network, resilience, uncertainty

Procedia PDF Downloads 113

Authors: Jayanta Kumar Ghosh, Swastik Sunil Goriwale, Himangshu Sarkar

Abstract:

Groundwater is one of the most valuable natural resources that society consumes for its domestic, industrial, and agricultural water supply. Its bulk and indiscriminate consumption affects the groundwater resource. Often, it has been found that the groundwater recharge rate is much lower than its demand. Thus, to maintain water and food security, it is necessary to monitor and management of groundwater storage. However, it is challenging to estimate groundwater storage (GWS) by making use of existing hydrological models. To overcome the difficulties, machine learning (ML) models are being introduced for the evaluation of groundwater level (GWL). Thus, the objective of this research work is to develop an ML-based model for the prediction of GWL. This objective has been realized through the development of an artificial neural network (ANN) model based on hydro-gravimetry. The model has been developed using training samples from field observations spread over 8 months. The developed model has been tested for the prediction of GWL in an observation well. The root means square error (RMSE) for the test samples has been found to be 0.390 meters. Thus, it can be concluded that the hydro-gravimetric-based ANN model can be used for the prediction of GWL. However, to improve the accuracy, more hydro-gravimetric parameter/s may be considered and tested in future.

Keywords: machine learning, hydro-gravimetry, ground water level, predictive model

Procedia PDF Downloads 133

Authors: Umesh Kumar Singh, Chanchala Joshi

Abstract:

With increasing dependency on IT infrastructure, the main objective of a system administrator is to maintain a stable and secure network, with ensuring that the network is robust enough against malicious network users like attackers and intruders. Security risk management provides a way to manage the growing threats to infrastructures or system. This paper proposes a framework for risk level estimation which uses vulnerability database National Institute of Standards and Technology (NIST) National Vulnerability Database (NVD) and the Common Vulnerability Scoring System (CVSS). The proposed framework measures the frequency of vulnerability exploitation; converges this measured frequency with standard CVSS score and estimates the security risk level which helps in automated and reasonable security management. In this paper equation for the Temporal score calculation with respect to availability of remediation plan is derived and further, frequency of exploitation is calculated with determined temporal score. The frequency of exploitation along with CVSS score is used to calculate the security risk level of the system. The proposed framework uses the CVSS vectors for risk level estimation and measures the security level of specific network environment, which assists system administrator for assessment of security risks and making decision related to mitigation of security risks.

Keywords: CVSS score, risk level, security measurement, vulnerability category

Procedia PDF Downloads 326

Authors: (Ted) Edward Holmberg, Mahdi Abdelguerfi, Elias Ioup

Abstract:

This research details a coverage measure for evaluating the effectiveness of observer node placements in a spatial bipartite network. This coverage measure can be used to optimize the configuration of stationary or mobile spatially oriented observer nodes, or a hybrid of the two, over time in order to fully utilize their capabilities. To demonstrate the practical application of this approach, we construct a SpatioTemporal Bipartite Network (STBN) using real-time crime center (RTCC) camera nodes and NOPD calls for service (CFS) event nodes from New Orleans, La (NOLA). We use the coverage measure to identify optimal placements for moving mobile RTCC camera vans to improve coverage of vulnerable areas based on temporal patterns.

Keywords: coverage measure, mobile node dynamics, Monte Carlo simulation, observer nodes, observable nodes, spatiotemporal bipartite knowledge graph, temporal spatial analysis

Procedia PDF Downloads 120

Authors: Shanaka Gunasekara, Maleen Jayasuriya, Nalin Harischandra, Lilantha Samaranayake, Gamini Dissanayake

Abstract:

One serious facet of the worsening Human-Elephant conflict (HEC) in nations such as Sri Lanka involves elephant-train collisions. Endangered Asian elephants are maimed or killed during such accidents, which also often result in orphaned or disabled elephants, contributing to the phenomenon of lone elephants. These lone elephants are found to be more likely to attack villages and showcase aggressive behaviour, which further exacerbates the overall HEC. Furthermore, Railway Services incur significant financial losses and disruptions to services annually due to such accidents. Most elephant-train collisions occur due to a lack of adequate reaction time. This is due to the significant stopping distance requirements of trains, as the full braking force needs to be avoided to minimise the risk of derailment. Thus, poor driver visibility at sharp turns, nighttime operation, and poor weather conditions are often contributing factors to this problem. Initial investigations also indicate that most collisions occur in localised “hotspots” where elephant pathways/corridors intersect with railway tracks that border grazing land and watering holes. Taking these factors into consideration, this work proposes the leveraging of recent developments in Convolutional Neural Network (CNN) technology to detect elephants using an RGB/infrared capable camera around known hotspots along the railway track. The CNN was trained using a curated dataset of elephants collected on field visits to elephant sanctuaries and wildlife parks in Sri Lanka. With this vision-based detection system at its core, a prototype unit of an early warning system was designed and tested. This weatherised and waterproofed unit consists of a Reolink security camera which provides a wide field of view and range, an Nvidia Jetson Xavier computing unit, a rechargeable battery, and a solar panel for self-sufficient functioning. The prototype unit was designed to be a low-cost, low-power and small footprint device that can be mounted on infrastructures such as poles or trees. If an elephant is detected, an early warning message is communicated to the train driver using the GSM network. A mobile app for this purpose was also designed to ensure that the warning is clearly communicated. A centralized control station manages and communicates all information through the train station network to ensure coordination among important stakeholders. Initial results indicate that detection accuracy is sufficient under varying lighting situations, provided comprehensive training datasets that represent a wide range of challenging conditions are available. The overall hardware prototype was shown to be robust and reliable. We envision a network of such units may help contribute to reducing the problem of elephant-train collisions and has the potential to act as an important surveillance mechanism in dealing with the broader issue of human-elephant conflicts.

Keywords: computer vision, deep learning, human-elephant conflict, wildlife early warning technology

Procedia PDF Downloads 231

Authors: S. Sudhharani

Abstract:

Energy distribution networks are the main link between the energy industry and consumers and are subject to the most scrutiny and testing of any category. As a result, it is important to monitor energy levels during the distribution phase. Power distribution networks, on the other hand, remain subject to common problems, including voltage breakdown, power outages, harmonics, and capacitor switching, all of which disrupt sinusoidal waveforms and reduce the quality and power of the network. Using power appliances in the form of custom power appliances is one way to deal with energy quality issues. Dynamic Voltage Restorer (DVR), integrated with network and distribution networks, is one of these devices. At the same time, by injecting voltage into the system, it can adjust the voltage amplitude and phase in the network. In the form of injections and three-phase syncing, it is used to compensate for the difficulty of energy quality. This article examines the recent use of DVR for power compensation and provides data on the control of each DVR in distribution networks.

Keywords: dynamic voltage restorer (DVR), power quality, distribution networks, control systems(PWM)

Procedia PDF Downloads 143

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 129

Authors: Nathenal Thomas Lambamo

Abstract:

Based on the fact that more than 85% of the labor force and 90% of the export earnings are taken by agriculture in Ethiopia and it can be said that it is the backbone of the overall socio-economic activities in the country. Among the cereal crops that the agriculture sector provides for the country, wheat is the third-ranking one preceding teff and maize. In the present day, wheat is in higher demand related to the expansion of industries that use them as the main ingredient for their products. The local supply of wheat for these companies covers only 35 to 40% and the rest 60 to 65% percent is imported on behalf of potential customers that exhaust the country’s foreign currency reserves. The above facts show that the need for this crop in the country is too high and in reverse, the productivity of the crop is very less because of these reasons. Wheat disease is the most devastating disease that contributes a lot to this unbalance in the demand and supply status of the crop. It reduces both the yield and quality of the crop by 27% on average and up to 37% when it is severe. This study aims to detect the most frequent and degrading wheat diseases, Septoria and Leaf rust, using the most efficiently used subset of machine learning technology, deep learning. As a state of the art, a deep learning class classification technique called Convolutional Neural Network (CNN) has been used to detect diseases and has an accuracy of 99.01% is achieved.

Keywords: septoria, leaf rust, deep learning, CNN

Procedia PDF Downloads 80

Authors: Mannan Malik Muhammad Naeem, Jeong Myung Yung

Abstract:

Functional near infrared spectroscopy (fNIRS) has a favorable position in non-invasive brain imaging techniques. The concentration change of oxygenated hemoglobin and de-oxygenated hemoglobin during particular cognitive activity is the basis for this neuro-imaging modality. Two wavelengths of near-infrared light can be used with modified Beer-Lambert law to explain the indirect status of neuronal activity inside brain. The temporal resolution of fNIRS is very good for real-time brain computer-interface applications. The portability, low cost and an acceptable temporal resolution of fNIRS put it on a better position in neuro-imaging modalities. In this study, an optimization model for impulse response function has been used to estimate/predict initial dip using fNIRS data. In addition, the activity strength parameter related to motor based cognitive task has been analyzed. We found an initial dip that remains around 200-300 millisecond and better localize neural activity.

Keywords: fNIRS, brain-computer interface, optimization algorithm, adaptive signal processing

Procedia PDF Downloads 228

Authors: Anum Ali, Kashaf ad Dooja, Asif Saleem

Abstract:

The future smart cities trend will be towards Internet of Things (IoT); IoT creates dynamic connections in a ubiquitous manner. Smart cities offer ease and flexibility for daily life matters. By using small devices that are connected to cloud servers based on IoT, network traffic between these devices is growing exponentially, whose security is a concerned issue, since ratio of cyber attack may make the network traffic vulnerable. This paper discusses the latest machine learning approaches in related work further to tackle the increasing rate of cyber attacks, machine learning algorithm is applied to IoT-based network traffic data. The proposed algorithm train itself on data and identify different sections of devices interaction by using supervised learning which is considered as a classifier related to a specific IoT device class. The simulation results clearly identify the attacks and produce fewer false detections.

Keywords: IoT, traffic security, deep learning, classification

Procedia PDF Downloads 157

Authors: Fuyuan Ma, Ying Wang, Xin Wang

Abstract:

Social networks have become breeding grounds for the rapid spread of rumors and malicious information, posing threats to societal stability and causing significant public harm. Existing research focuses on simulating the spread of information and its impact on users through propagation dynamics and applies methods such as greedy approximation strategies to approximate the optimal control solution at the global scale. However, the greedy strategy at the global scale may fall into locally optimal solutions, and the approximate simulation of information spread may accumulate more errors. Therefore, we propose a multi-scale control model for network group behavior, introducing individual and group scales on top of the greedy strategy’s global scale. At the individual scale, we calculate the propagation influence of nodes based on their structural attributes to alleviate the issue of local optimality. At the group scale, we conduct precise propagation simulations to avoid introducing cumulative errors from approximate calculations without increasing computational costs. Experimental results on three real-world datasets demonstrate the effectiveness of our proposed multi-scale model in controlling network group behavior.

Keywords: influence blocking maximization, competitive linear threshold model, social networks, network group behavior

Procedia PDF Downloads 25