Search results for: neural networks Mel-Spectrogram

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 289

Authors: Jessica Hemberg, Amanda Sundqvist, Yulia Korzhina, Lillemor Östman, Sofia Gylfe, Frida Gädda, Lisbet Nyström, Henrik Groundstroem, Pia Nyman-Kurkiala

Abstract:

Purpose: There are large gaps in the literature on COVID-19 pandemic-related mental health outcomes and after-effects specific to adolescents and young adults. The study's aim was to explore adolescents’ and young adults’ experiences of well-being, health, and loneliness during the COVID-19 pandemic. Method: A qualitative exploratory design with qualitative content analysis was used. Twenty-three participants (aged 19-27; four men and 19 women) were interviewed. Results: Four themes emerged: Changed social networks – fewer and closer contacts, changed mental and physical health, increased physical and social loneliness, well-being, internal growth, and need for support. Conclusion: Adolescents’ and young adults’ experiences of well-being, health, and loneliness are subtle and complex. Participants experienced changed social networks, mental and physical health, and well-being. Also, internal growth, need for support, and increased loneliness were seen. Clear information on how to seek help and support from professionals should be made available.

Keywords: adolescents, COVID-19 pandemic, health, interviews, loneliness, qualitative, well-being, young adults

Procedia PDF Downloads 96

Authors: Farhad Salek, Shahaboddin Resalati

Abstract:

The production of electric vehicles (EVs) featuring lithium-ion battery technology has substantially escalated over the past decade, demonstrating a steady and persistent upward trajectory. The imminent retirement of electric vehicle (EV) batteries after approximately eight years underscores the critical need for their redirection towards recycling, a task complicated by the current inadequacy of recycling infrastructures globally. A potential solution for such concerns involves extending the operational lifespan of electric vehicle (EV) batteries through their utilization in stationary energy storage systems during secondary applications. Such adoptions, however, require addressing the safety concerns associated with batteries’ knee points and thermal runaways. This paper develops an accurate mathematical model representative of the second-life battery packs from a cell-to-pack scale using an equivalent circuit model (ECM) methodology. Neural network algorithms are employed to forecast the degradation parameters based on the EV batteries' aging history to develop a degradation model. The degradation model is integrated with the ECM to reflect the impacts of the cycle aging mechanism on battery parameters during operation. The developed model is tested under real-life load profiles to evaluate the life span of the batteries in various operating conditions. The methodology and the algorithms introduced in this paper can be considered the basis for Battery Management System (BMS) design and techno-economic analysis of such technologies.

Keywords: second life battery, electric vehicles, degradation, neural network

Procedia PDF Downloads 65

Authors: Moheb R. Girgis, Tarek M. Mahmoud, Bahgat A. Abdullatif, Ahmed M. Rabie

Abstract:

Mesh clients, mesh routers and gateways are components of Wireless Mesh Network (WMN). In WMN, gateways connect to Internet using wireline links and supply Internet access services for users. We usually need multiple gateways, which takes time and costs a lot of money set up, due to the limited wireless channel bit rate. WMN is a highly developed technology that offers to end users a wireless broadband access. It offers a high degree of flexibility contrasted to conventional networks; however, this attribute comes at the expense of a more complex construction. Therefore, a challenge is the planning and optimization of WMNs. In this paper, we concentrate on this challenge using a genetic algorithm and simulated annealing. The genetic algorithm and simulated annealing enable searching for a low-cost WMN configuration with constraints and determine the number of used gateways. Experimental results proved that the performance of the genetic algorithm and simulated annealing in minimizing WMN network costs while satisfying quality of service. The proposed models are presented to significantly outperform the existing solutions.

Keywords: wireless mesh networks, genetic algorithms, simulated annealing, topology design

Procedia PDF Downloads 458

Authors: Lizhi Ma, Dan Liu

Abstract:

Pipeline parallelism has been widely used to accelerate distributed deep learning to alleviate GPU memory bottlenecks and to ensure that models can be trained and deployed smoothly under limited graphics memory conditions. However, in highly heterogeneous distributed clusters, traditional model partitioning methods are not able to achieve load balancing. The overlap of communication and computation is also a big challenge. In this paper, HePipe is proposed, an efficient pipeline parallel training method for highly heterogeneous clusters. According to the characteristics of the neural network model pipeline training task, oriented to the 2-level heterogeneous cluster computing topology, a training method based on the 2-level stage division of neural network modeling and partitioning is designed to improve the parallelism. Additionally, a multi-forward 1F1B scheduling strategy is designed to accelerate the training time of each stage by executing the computation units in advance to maximize the overlap between the forward propagation communication and backward propagation computation. Finally, a dynamic recomputation strategy based on task memory requirement prediction is proposed to improve the fitness ratio of task and memory, which improves the throughput of the cluster and solves the memory shortfall problem caused by memory differences in heterogeneous clusters. The empirical results show that HePipe improves the training speed by 1.6×−2.2× over the existing asynchronous pipeline baselines.

Keywords: pipeline parallelism, heterogeneous cluster, model training, 2-level stage partitioning

Procedia PDF Downloads 18

Authors: J. Andrade-Garda, A. Anguera, J. Ares-Casal, M. Hidalgo-Lorenzo, J.-A. Lara, D. Lizcano, S. Suárez-Garaboa

Abstract:

In the current constantly changing economic context, collaborative networks allow partners to undertake projects that would not be possible if attempted by them individually. These projects usually involve the performance of a group of tasks (named roles) that have to be distributed among the partners. Thus, an allocation/matching problem arises that will be referred to as Role-Partner Allocation problem. In real life this situation is addressed by negotiation between partners in order to reach ad hoc agreements. Besides taking a long time and being hard work, both historical evidence and economic analysis show that such approach is not recommended. Instead, the allocation process should be automated by means of a centralized matching scheme. However, as a preliminary step to start the search for such a matching mechanism (or even the development of a new one), the problem and its core components must be specified. To this end, this paper establishes (i) the definition of the problem and its constraints, (ii) the key features of the involved elements (i.e., roles and partners); and (iii) how to create preference lists both for roles and partners. Only this way it will be possible to conduct subsequent methodological research on the solution method.     

Keywords: collaborative network, matching, partner, preference list, role

Procedia PDF Downloads 233

Authors: Chien-Ho Lin, Ho-Ching Yang, Barbara Knowlton, Shin-Leh Huang, Ming-Chang Chiang

Abstract:

Practicing motor tasks arranged in an interleaved order (interleaved practice, or IP) generally leads to better learning than practicing tasks in a repetitive order (repetitive practice, or RP), an example of how desirable difficulty during practice benefits learning. Greater difficulty during practice, e.g. IP, is associated with greater brain activity measured by higher blood-oxygen-level dependent (BOLD) signal in functional magnetic resonance imaging (fMRI) in the sensorimotor areas of the brain. In this study resting-state fMRI was applied to investigate whether increase in resting-state brain connectivity immediately after practice predicts the benefit of desirable difficulty to motor learning. 26 healthy adults (11M/15F, age = 23.3±1.3 years) practiced two sets of three sequences arranged in a repetitive or an interleaved order over 2 days, followed by a retention test on Day 5 to evaluate learning. On each practice day, fMRI data were acquired in a resting state after practice. The resting-state fMRI data was decomposed using a group-level spatial independent component analysis (ICA), yielding 9 independent components (IC) matched to the precuneus network, primary visual networks (two ICs, denoted by I and II respectively), sensorimotor networks (two ICs, denoted by I and II respectively), the right and the left frontoparietal networks, occipito-temporal network, and the frontal network. A weighted resting-state functional connectivity (wRSFC) was then defined to incorporate information from within- and between-network brain connectivity. The within-network functional connectivity between a voxel and an IC was gauged by a z-score derived from the Fisher transformation of the IC map. The between-network connectivity was derived from the cross-correlation of time courses across all possible pairs of ICs, leading to a symmetric nc x nc matrix of cross-correlation coefficients, denoted by C = (pᵢⱼ). Here pᵢⱼ is the extremum of cross-correlation between ICs i and j; nc = 9 is the number of ICs. This component-wise cross-correlation matrix C was then projected to the voxel space, with the weights for each voxel set to the z-score that represents the above within-network functional connectivity. The wRSFC map incorporates the global characteristics of brain networks measured by the between-network connectivity, and the spatial information contained in the IC maps measured by the within-network connectivity. Pearson correlation analysis revealed that greater IP-minus-RP difference in wRSFC was positively correlated with the RP-minus-IP difference in the response time on Day 5, particularly in brain regions crucial for motor learning, such as the right dorsolateral prefrontal cortex (DLPFC), and the right premotor and supplementary motor cortices. This indicates that enhanced resting brain connectivity during the early phase of memory consolidation is associated with enhanced learning following interleaved practice, and as such wRSFC could be applied as a biomarker that measures the beneficial effects of desirable difficulty on motor sequence learning.

Keywords: desirable difficulty, functional magnetic resonance imaging, independent component analysis, resting-state networks

Procedia PDF Downloads 203

Authors: Bin Feng, Zhulin Zong

Abstract:

Radar systems are critical in the modern military, aviation, and maritime operations, and their proper functioning is essential for the success of these operations. However, due to the complexity and sensitivity of radar systems, they are susceptible to various faults that can significantly affect their performance. Traditional radar fault diagnosis strategies rely on expert knowledge and rule-based approaches, which are often limited in effectiveness and require a lot of time and resources. Deep learning has recently emerged as a promising approach for fault diagnosis due to its ability to learn features and patterns from large amounts of data automatically. In this paper, we propose a radar fault diagnosis strategy based on deep learning that can accurately identify and classify faults in radar systems. Our approach uses convolutional neural networks (CNN) to extract features from radar signals and fault classify the features. The proposed strategy is trained and validated on a dataset of measured radar signals with various types of faults. The results show that it achieves high accuracy in fault diagnosis. To further evaluate the effectiveness of the proposed strategy, we compare it with traditional rule-based approaches and other machine learning-based methods, including decision trees, support vector machines (SVMs), and random forests. The results demonstrate that our deep learning-based approach outperforms the traditional approaches in terms of accuracy and efficiency. Finally, we discuss the potential applications and limitations of the proposed strategy, as well as future research directions. Our study highlights the importance and potential of deep learning for radar fault diagnosis. It suggests that it can be a valuable tool for improving the performance and reliability of radar systems. In summary, this paper presents a radar fault diagnosis strategy based on deep learning that achieves high accuracy and efficiency in identifying and classifying faults in radar systems. The proposed strategy has significant potential for practical applications and can pave the way for further research.

Keywords: radar system, fault diagnosis, deep learning, radar fault

Procedia PDF Downloads 90

Authors: Aishwarya Shekhar, Devesh Kumar Srivastava

Abstract:

Cloud computing has emerged as a promising direction for cost efficient and reliable service delivery across data communication networks. The dynamic location of service facilities and the virtualization of hardware and software elements are stressing the communication networks and protocols, especially when data centres are interconnected through the internet. Although the computing aspects of cloud technologies have been largely investigated, lower attention has been devoted to the networking services without involving IT operating overhead. Cloud computing has enabled elastic and transparent access to infrastructure services without involving IT operating overhead. Virtualization has been a key enabler for cloud computing. While resource virtualization and service abstraction have been widely investigated, networking in cloud remains a difficult puzzle. Even though network has significant role in facilitating hybrid cloud scenarios, it hasn't received much attention in research community until recently. We propose Network as a Service (NaaS), which forms the basis of unifying public and private clouds. In this paper, we identify various challenges in adoption of hybrid cloud. We discuss the design and implementation of a cloud platform.

Keywords: cloud computing, networking, infrastructure, hybrid cloud, open stack, naas

Procedia PDF Downloads 427

Authors: Khalid Kaddoura, Tarek Zayed

Abstract:

Sewer networks are constructed to protect the communities and the environment from any contact with the sewer mediums. Pipelines, being laterals or sewer mains, and manholes form the huge underground infrastructure in every urban city. Due to the sewer networks importance, the infrastructure asset management field has extensive advancement in condition assessment and rehabilitation decision models. However, most of the focus was devoted to pipelines giving little attention toward manholes condition assessment. In fact, recent studies started to emerge in this area to preserve manholes from any malfunction. Therefore, the main objective of this study is to propose a condition assessment model for sewer manholes. The model divides the manhole into several components and determines the relative importance weight of each component using the Analytic Network Process (ANP) decision-making method. Later, the condition of the manhole is computed by aggregating the condition of each component with its corresponding weight. Accordingly, the proposed assessment model will enable decision-makers to have a final index suggesting the overall condition of the manhole and a backward analysis to check the condition of each component. Consequently, better decisions are made pertinent to maintenance, rehabilitation, and replacement actions.

Keywords: Analytic Network Process (ANP), condition assessment, decision-making, manholes

Procedia PDF Downloads 354

Authors: Gaye Ibrahima, Mendy Gervais, Seck Diaraf, Ouya Samuel

Abstract:

In this paper, we consider the influence maximization in social networks. Here we give importance to initial diffuser called the seeds. The goal is to find efficiently a subset of k elements in the social network that will begin and maximize the information diffusion process. A new approach which treats the social network before to determine the seeds, is proposed. This treatment eliminates the information feedback toward a considered element as seed by extracting an acyclic spanning social network. At first, we propose two algorithm versions called SCG − algoritm (v1 and v2) (Spanning Connected Graphalgorithm). This algorithm takes as input data a connected social network directed or no. And finally, a generalization of the SCG − algoritm is proposed. It is called SG − algoritm (Spanning Graph-algorithm) and takes as input data any graph. These two algorithms are effective and have each one a polynomial complexity. To show the pertinence of our approach, two seeds set are determined and those given by our approach give a better results. The performances of this approach are very perceptible through the simulation carried out by the R software and the igraph package.

Keywords: acyclic spanning graph, centrality measures, information feedback, influence maximization, social network

Procedia PDF Downloads 248

Authors: Devadrita Dey Sarkar

Abstract:

Regardless of the many technologic advances in the past decade, increased training and experience, and the obvious benefits of uniform standards, the false-negative rate in screening mammography remains unacceptably high .A computer aided neural network classification of regions of suspicion (ROS) on digitized mammograms is presented in this abstract which employs features extracted by a new technique based on independent component analysis. CAD is a concept established by taking into account equally the roles of physicians and computers, whereas automated computer diagnosis is a concept based on computer algorithms only. With CAD, the performance by computers does not have to be comparable to or better than that by physicians, but needs to be complementary to that by physicians. In fact, a large number of CAD systems have been employed for assisting physicians in the early detection of breast cancers on mammograms. A CAD scheme that makes use of lateral breast images has the potential to improve the overall performance in the detection of breast lumps. Because breast lumps can be detected reliably by computer on lateral breast mammographs, radiologists’ accuracy in the detection of breast lumps would be improved by the use of CAD, and thus early diagnosis of breast cancer would become possible. In the future, many CAD schemes could be assembled as packages and implemented as a part of PACS. For example, the package for breast CAD may include the computerized detection of breast nodules, as well as the computerized classification of benign and malignant nodules. In order to assist in the differential diagnosis, it would be possible to search for and retrieve images (or lesions) with these CAD systems, which would be reliable and useful method for quantifying the similarity of a pair of images for visual comparison by radiologists.

Keywords: CAD(computer-aided design), lesions, neural network, ROS(region of suspicion)

Procedia PDF Downloads 456

Authors: Maria Pavlova

Abstract:

In our days, it is possible to put the camera on different vehicles like quadcopter, train, airplane and etc. The camera also can be the input sensor in many different systems. That means the object recognition like non separate part of monitoring control can be key part of the most intelligent systems. The aim of this paper is to focus of the object recognition process during vehicles movement. During the vehicle’s movement the camera takes pictures from the environment without storage in Data Base. In case the camera detects a special object (for example human or animal), the system saves the picture and sends it to the work station in real time. This functionality will be very useful in emergency or security situations where is necessary to find a specific object. In another application, the camera can be mounted on crossroad where do not have many people and if one or more persons come on the road, the traffic lights became the green and they can cross the road. In this papers is presented the system has solved the aforementioned problems. It is presented architecture of the object recognition system includes the camera, Raspberry platform, GPS system, neural network, software and Data Base. The camera in the system takes the pictures. The object recognition is done in real time using the OpenCV library and Raspberry microcontroller. An additional feature of this library is the ability to display the GPS coordinates of the captured objects position. The results from this processes will be sent to remote station. So, in this case, we can know the location of the specific object. By neural network, we can learn the module to solve the problems using incoming data and to be part in bigger intelligent system. The present paper focuses on the design and integration of the image recognition like a part of smart systems.

Keywords: camera, object recognition, OpenCV, Raspberry

Procedia PDF Downloads 218

Authors: Maoxin Ye

Abstract:

This study examines the relationship between social network sites (SNS) usage and social capital. Because SNS usage can expand the users’ networks, and people who are connected in this networks may become resources to SNS users and lead them to advantage in some situation, it is important to estimate the relationship between SNS usage and ‘who’ is connected or what resources the SNS users can get. Additionally, ‘who’ can be divided in two aspects – people who possess high position and people who are different, hence, it is important to estimate the relationship between SNS usage and high position people and different people. This study adapts Lin’s definition of social capital and the measurement of position generator which tells us who was connected, and can be divided into the same two aspects as well. A national data of America (N = 2,255) collected by Pew Research Center is utilized to do a general regression analysis about SNS usage and social capital. The results indicate that SNS usage is negatively associated with each factor of social capital, and it suggests that, in fact, comparing with non-users, although SNS users can get more connections, the variety and resources of these connections are fewer. For this reason, we could lose benefits through SNS usage.

Keywords: social network sites, social capital, position generator, general regression

Procedia PDF Downloads 262

Authors: Mohammad Rostami, Mohammad Reza Forghani, Elahe Neshat, Fatemeh Yaghoobi

Abstract:

An Ad Hoc network consists of wireless mobile equipment which connects to each other without any infrastructure, using connection equipment. The best way to form a hierarchical structure is clustering. Various methods of clustering can form more stable clusters according to nodes' mobility. In this research we propose an algorithm, which allocates some weight to nodes based on factors, i.e. link stability and power reduction rate. According to the allocated weight in the previous phase, the cellular learning automaton picks out in the second phase nodes which are candidates for being cluster head. In the third phase, learning automaton selects cluster head nodes, member nodes and forms the cluster. Thus, this automaton does the learning from the setting and can form optimized clusters in terms of power consumption and link stability. To simulate the proposed algorithm we have used omnet++4.2.2. Simulation results indicate that newly formed clusters have a longer lifetime than previous algorithms and decrease strongly network overload by reducing update rate.

Keywords: mobile Ad Hoc networks, clustering, learning automaton, cellular automaton, battery power

Procedia PDF Downloads 411

Authors: Dhruv J. Limaye, Hanga Galfalvy, Cheick A. Sissoko, Yung-yu Huang, Chunanning Tang, Ying Liu, Shu-Chi Hsiung, Andrew J. Dwork, Gorazd B. Rosoklija, Victoria Arango, Lewis Brown, J. John Mann, Maura Boldrini

Abstract:

Memory and emotion require hippocampal cell viability and connectivity and are disrupted in major depressive disorder (MDD). Applying shotgun proteomics and stereological quantification of neural progenitor cells (NPCs), intermediate neural progenitors (INPs), and mature granule neurons (GNs), to postmortem human hippocampus, identified differentially expressed proteins (DEPs), and fewer NPCs, INPs and GNs, in untreated MDD (uMDD) compared with non-psychiatric controls (CTRL) and antidepressant-treated MDD (MDDT). DEPs lower in uMDD vs. CTRL promote mitosis, differentiation, and prevent apoptosis. DEPs higher in uMDD vs. CTRL inhibit the cell cycle, and regulate cell adhesion, neurite outgrowth, and DNA repair. DEPs lower in MDDT vs. uMDD block cell proliferation. We observe group-specific correlations between numbers of NPCs, INPs, and GNs and an abundance of proteins regulating mitosis, differentiation, and apoptosis. Altered protein expression underlies hippocampus cellular and volume loss in uMDD, supports a trophic effect of antidepressants, and offers new treatment targets.

Keywords: proteomics, hippocampus, depression, mitosis, migration, differentiation, mitochondria, apoptosis, antidepressants, human brain

Procedia PDF Downloads 100

Authors: Chung-Nan Lee, Sheng-Wei Chu, You-Chiun Wang

Abstract:

LTE (Long Term Evolution) employs the eMBMS (evolved Multimedia Broadcast/Multicast Service) protocol to deliver video streams to a multicast group of users. However, it requires all multicast members to receive a video stream in the same transmission rate, which would degrade the overall service quality when some users encounter bad channel conditions. To overcome this problem, this paper provides two efficient resource allocation schemes in such LTE network: The symbol synchronization (S2) scheme assumes that the macro and pico eNodeBs use the same frequency channel to deliver the video stream to all users. It then adopts a multicast transmission index to guarantee the fairness among users. On the other hand, the resource reuse (R2) scheme allows eNodeBs to transmit data on different frequency channels. Then, by introducing the concept of frequency reuse, it can further improve the overall service quality. Extensive simulation results show that the S2 and R2 schemes can respectively improve around 50% of fairness and 14% of video quality as compared with the common maximum throughput method.

Keywords: LTE networks, multicast, resource allocation, layered video

Procedia PDF Downloads 389

Authors: Nathenal Thomas

Abstract:

In the food chain and in many other agricultural products, corn, also known as maize, which goes by the scientific name Zea mays subsp, is a widely produced agricultural product. Corn has the highest adaptability. It comes in many different types, is employed in many different industrial processes, and is more adaptable to different agro-climatic situations. In Ethiopia, maize is among the most widely grown crop. Small-scale corn farming may be a household's only source of food in developing nations like Ethiopia. The aforementioned data demonstrates that the country's requirement for this crop is excessively high, and conversely, the crop's productivity is very low for a variety of reasons. The most damaging disease that greatly contributes to this imbalance between the crop's supply and demand is the corn disease. The failure to diagnose diseases in maize plant until they are too late is one of the most important factors influencing crop output in Ethiopia. This study will aid in the early detection of such diseases and support farmers during the cultivation process, directly affecting the amount of maize produced. The diseases in maize plants, such as northern leaf blight and cercospora leaf spot, have distinct symptoms that are visible. This study aims to detect the most frequent and degrading maize diseases using the most efficiently used subset of machine learning technology, deep learning so, called Image Processing. Deep learning uses networks that can be trained from unlabeled data without supervision (unsupervised). It is a feature that simulates the exercises the human brain goes through when digesting data. Its applications include speech recognition, language translation, object classification, and decision-making. Convolutional Neural Network (CNN) for Image Processing, also known as convent, is a deep learning class that is widely used for image classification, image detection, face recognition, and other problems. it will also use this algorithm as the state-of-the-art for my research to detect maize diseases by photographing maize leaves using a mobile phone.

Keywords: CNN, zea mays subsp, leaf blight, cercospora leaf spot

Procedia PDF Downloads 74

Authors: Farzaneh Tahmoorian, Bijan Samali, John Yeaman

Abstract:

Road networks are expanding all over the world during the past few decades to meet the increasing freight volumes created by the population growth and industrial development. At the same time, the rate of generation of solid wastes in the society is increasing with the population growth, technological development, and changes in the lifestyle of people. Thus, the management of solid wastes has become an acute problem. Accordingly, there is a need for greater efficiency in the construction and maintenance of road networks, in reducing the overall cost, especially the utilization of natural materials such as aggregates. An efficient means to reduce construction and maintenance costs of road networks is to replace natural (virgin) materials by secondary, recycled materials. Recycling will also help to reduce pressure on landfills and demand for extraction of natural virgin materials thus ensuring sustainability. Application of solid wastes in asphalt layer reduces not only environmental issues associated with waste disposal but also the demand for virgin materials which will subsequently result in sustainability. Therefore, this research aims to investigate the feasibility of the application of some of the waste materials such as glass, construction and demolition wastes, etc. as alternative materials in pavement construction, particularly flexible pavements. To this end, various combination of different waste materials in certain percentages is considered in designing the asphalt mixture. One of the goals of this research is to determine the optimum percentage of all these materials in the mixture. This is done through a series of tests to evaluate the volumetric properties and resilient modulus of the mixture. The information and data collected from these tests are used to select the adequate samples for further assessment through advanced tests such as triaxial dynamic test and fatigue test, in order to investigate the asphalt mixture resistance to permanent deformation and also cracking. This paper presents the results of these investigations on the application of waste materials in asphalt mixture for production of a sustainable asphalt mix.

Keywords: asphalt, glass, pavement, recycled aggregate, sustainability

Procedia PDF Downloads 236

Authors: Aishi Kundu, Elhan Raza

Abstract:

"Necessity is the mother of invention" - Rapid increase in the global human population has directed the agricultural domain toward machine learning. The basic need of human beings is considered to be food which can be satisfied through farming. Farming is one of the major revenue generators for the Indian economy. Agriculture is not only considered a source of employment but also fulfils humans’ basic needs. So, agriculture is considered to be the source of employment and a pillar of the economy in developing countries like India. This paper provides a brief review of the progress made in implementing Machine Learning in the agricultural sector. Accurate predictions are necessary at the right time to boost production and to aid the timely and systematic distribution of agricultural commodities to make their availability in the market faster and more effective. This paper includes a thorough analysis of various machine learning algorithms applied in different aspects of agriculture (crop management, soil management, water management, yield tracking, livestock management, etc.).Due to climate changes, crop production is affected. Machine learning can analyse the changing patterns and come up with a suitable approach to minimize loss and maximize yield. Machine Learning algorithms/ models (regression, support vector machines, bayesian models, artificial neural networks, decision trees, etc.) are used in smart agriculture to analyze and predict specific outcomes which can be vital in increasing the productivity of the Agricultural Food Industry. It is to demonstrate vividly agricultural works under machine learning to sensor data. Machine Learning is the ongoing technology benefitting farmers to improve gains in agriculture and minimize losses. This paper discusses how the irrigation and farming management systems evolve in real-time efficiently. Artificial Intelligence (AI) enabled programs to emerge with rich apprehension for the support of farmers with an immense examination of data.

Keywords: machine Learning, artificial intelligence, crop management, precision farming, smart farming, pre-harvesting, harvesting, post-harvesting

Procedia PDF Downloads 104

Authors: Mohammad Zaeimzade

Abstract:

The development of communication technologies is clearly and rapidly moving towards reducing the distance between the virtual and real worlds. Of course, living in a two-spatial or two-globalized world or any other interpretation that means mixing real and virtual life is still relevant and debatable. In the present age of communication, where social networks have transformed the message equation and turned the audience out of passivity and turned into a user. Platforms have penetrated widely in various aspects of human life, from culture and education and economy. Among the messengers, Instagram, which is one of the most extensive image-based interactive networks, plays a significant role in the new economic life. It doesn't need much explanation that the era of thinking of every messenger as a non-insulating conductor that is just a neutral load has passed. Every messenger has its own economic, political and of course security background, Instagram is no exception to this rule and of course it leaves its effects in bio-economics as well. Iran, as the 19th largest economy in the world, has not been unaffected by new platforms, including Instagram, and their consequences in the economy. Generally, in the policy-making space, there are two simple and inflexible pessimistic or optimistic views on this issue, and each of the holders of these views usually have their own one-dimensional policy recommendations regarding how to deal with Instagram. Prescriptions that are usually very different and sometimes contradictory. In this article, we show that this confusion of policymakers is the result of not accurately describing the reality of its effect, and the reason for this inaccurate description is the existence of a conflict of interests in the eyes of describers and researchers. In this article, we first take a look at the main indicators of the Iranian economy, estimate the role of the digital economy in Iran's economic growth, then study the conflicting descriptions of the Instagram-based digital economy, the statistics that show the tolerance of economic users of Instagram in Iran. 300 thousand to 9 million have been estimated. Finally, we take a look at the government's actions in this matter, especially in the context of street riots in October and November 2022. And we suggest an intermediate idea.

Keywords: digital economy, instagram, conflict of interest, social networks

Procedia PDF Downloads 76

Authors: Xi Liu, Fan Yuan

Abstract:

In the evolving landscape of physics-based machine learning (PBML), particularly within fluid dynamics and its applications in electromechanical engineering, robot vision, and robot learning, achieving precision and alignment with researchers' specific needs presents a formidable challenge. In response, this work proposes a methodology that integrates neural transformation with a modified smoothed particle hydrodynamics model for generating transformed 3D fluid simulations. This approach is useful for nanoscale science, where the unique and complex behaviors of viscoelastic medium demand accurate neurally-transformed simulations for materials understanding and manipulation. In electromechanical engineering, the method enhances the design and functionality of fluid-operated systems, particularly microfluidic devices, contributing to advancements in nanomaterial design, drug delivery systems, and more. The proposed approach also aligns with the principles of PBML, offering advantages such as multi-fluid stylization and consistent particle attribute transfer. This capability is valuable in various fields where the interaction of multiple fluid components is significant. Moreover, the application of neurally-transformed hydrodynamical models extends to manufacturing processes, such as the production of microelectromechanical systems, enhancing efficiency and cost-effectiveness. The system's ability to perform neural transfer on 3D fluid scenes using a deep learning algorithm alongside physical models further adds a layer of flexibility, allowing researchers to tailor simulations to specific needs across scientific and engineering disciplines.

Keywords: physics-based machine learning, robot vision, robot learning, hydrodynamics

Procedia PDF Downloads 66

Authors: Luke McDonagh

Abstract:

Over the past three decades, free and open source software (FOSS) programmers have developed new, innovative and legally binding licences that have in turn enabled the creation of innumerable pieces of everyday software, including Linux, Mozilla Firefox and Open Office. That FOSS has been highly successful in competing with 'closed source software' (e.g. Microsoft Office) is now undeniable, but in noting this success, it is important to examine in detail why this system of FOSS has been so successful. One key reason is the existence of networks or communities of programmers, who are bound together by a key shared social norm of 'reciprocity'. At the same time, these FOSS networks are not unitary – they are highly diverse and there are large divergences of opinion between members regarding which licences are generally preferable: some members favour the flexible ‘free’ or 'no copyleft' licences, such as BSD and MIT, while other members favour the ‘strong open’ or 'strong copyleft' licences such as GPL. This paper argues that without both the existence of the shared norm of reciprocity and the diversity of licences, it is unlikely that the innovative legal framework provided by FOSS would have succeeded to the extent that it has.

Keywords: open source, copyright, licensing, copyleft

Procedia PDF Downloads 373

Authors: Kaustav Mukherjee

Abstract:

In this paper we propose a Neural Style Transfer solution whereby we have created a Lightweight Separable Convolution Kernel Based GAN Architecture (SC-GAN) which will very useful for designing filter for Mobile Phone Cameras and also Edge Devices which will convert any image to its 2D ANIMATED COMIC STYLE Movies like HEMAN, SUPERMAN, JUNGLE-BOOK. This will help the 2D animation artist by relieving to create new characters from real life person's images without having to go for endless hours of manual labour drawing each and every pose of a cartoon. It can even be used to create scenes from real life images.This will reduce a huge amount of turn around time to make 2D animated movies and decrease cost in terms of manpower and time. In addition to that being extreme light-weight it can be used as camera filters capable of taking Comic Style Shots using mobile phone camera or edge device cameras like Raspberry Pi 4,NVIDIA Jetson NANO etc. Existing Methods like CartoonGAN with the model size close to 170 MB is too heavy weight for mobile phones and edge devices due to their scarcity in resources. Compared to the current state of the art our proposed method which has a total model size of 31 MB which clearly makes it ideal and ultra-efficient for designing of camera filters on low resource devices like mobile phones, tablets and edge devices running OS or RTOS. .Owing to use of high resolution input and usage of bigger convolution kernel size it produces richer resolution Comic-Style Pictures implementation with 6 times lesser number of parameters and with just 25 extra epoch trained on a dataset of less than 1000 which breaks the myth that all GAN need mammoth amount of data. Our network reduces the density of the Gan architecture by using Depthwise Separable Convolution which does the convolution operation on each of the RGB channels separately then we use a Point-Wise Convolution to bring back the network into required channel number using 1 by 1 kernel.This reduces the number of parameters substantially and makes it extreme light-weight and suitable for mobile phones and edge devices. The architecture mentioned in the present paper make use of Parameterised Batch Normalization Goodfellow etc al. (Deep Learning OPTIMIZATION FOR TRAINING DEEP MODELS page 320) which makes the network to use the advantage of Batch Norm for easier training while maintaining the non-linear feature capture by inducing the learnable parameters

Keywords: comic stylisation from camera image using GAN, creating 2D animated movie style custom stickers from images, depth-wise separable convolutional neural network for light-weight GAN architecture for EDGE devices, GAN architecture for 2D animated cartoonizing neural style, neural style transfer for edge, model distilation, perceptual loss

Procedia PDF Downloads 132

Authors: Shokoufeh Abrisham, Seyed Mahmoud Hossieni, Elham Pishbin

Abstract:

In this paper, a hybrid method based on the fault tree analysis (FTA) and Bayesian networks (BNs) are employed to evaluate the team performance quality of advanced cardiac life support (ACLS) procedures in emergency department. According to American Heart Association (AHA) guidelines, a category relying on staff action leading to clinical incidents and also some discussions with emergency medicine experts, a fault tree model for ACLS procedure is obtained based on the human performance. The obtained FTA model is converted into BNs, and some different scenarios are defined to demonstrate the efficiency and flexibility of the presented model of BNs. Also, a sensitivity analysis is conducted to indicate the effects of team leader presence and uncertainty knowledge of experts on the quality of ACLS. The proposed model based on BNs shows that how the results of risk analysis can be closed to reality comparing to the obtained results based on only FTA in medical procedures.

Keywords: advanced cardiac life support, fault tree analysis, Bayesian belief networks, numan performance, healthcare systems

Procedia PDF Downloads 147

Authors: Amanda Kavner, Richard Lamb

Abstract:

Faster growth in science and technology of other nations may make staying globally competitive more difficult without shifting focus on how science is taught in US classes. An integral part of learning science involves visual and spatial thinking since complex, and real-world phenomena are often expressed in visual, symbolic, and concrete modes. The primary barrier to spatial thinking and visual literacy in Science, Technology, Engineering, and Math (STEM) fields is representational competence, which includes the ability to generate, transform, analyze and explain representations, as opposed to generic spatial ability. Although the relationship is known between the foundational visual literacy and the domain-specific science literacy, science literacy as a function of science learning is still not well understood. Moreover, the need for a more reliable measure is necessary to design resources which enhance the fundamental visuospatial cognitive processes behind scientific literacy. To support the improvement of students’ representational competence, first visualization skills necessary to process these science representations needed to be identified, which necessitates the development of an instrument to quantitatively measure visual literacy. With such a measure, schools, teachers, and curriculum designers can target the individual skills necessary to improve students’ visual literacy, thereby increasing science achievement. This project details the development of an artificial neural network capable of measuring science literacy using functional Near-Infrared Spectroscopy (fNIR) data. This data was previously collected by Project LENS standing for Leveraging Expertise in Neurotechnologies, a Science of Learning Collaborative Network (SL-CN) of scholars of STEM Education from three US universities (NSF award 1540888), utilizing mental rotation tasks, to assess student visual literacy. Hemodynamic response data from fNIRsoft was exported as an Excel file, with 80 of both 2D Wedge and Dash models (dash) and 3D Stick and Ball models (BL). Complexity data were in an Excel workbook separated by the participant (ID), containing information for both types of tasks. After changing strings to numbers for analysis, spreadsheets with measurement data and complexity data were uploaded to RapidMiner’s TurboPrep and merged. Using RapidMiner Studio, a Gradient Boosted Trees artificial neural network (ANN) consisting of 140 trees with a maximum depth of 7 branches was developed, and 99.7% of the ANN predictions are accurate. The ANN determined the biggest predictors to a successful mental rotation are the individual problem number, the response time and fNIR optode #16, located along the right prefrontal cortex important in processing visuospatial working memory and episodic memory retrieval; both vital for science literacy. With an unbiased measurement of science literacy provided by psychophysiological measurements with an ANN for analysis, educators and curriculum designers will be able to create targeted classroom resources to help improve student visuospatial literacy, therefore improving science literacy.

Keywords: artificial intelligence, artificial neural network, machine learning, science literacy, neuroscience

Procedia PDF Downloads 119

Authors: Maja Ruzic-Baf, Vedrana Keteles, Andrea Debeljuh

Abstract:

Younger and younger children are now using a smartphone, a device which has become ‘a must have’ and the life of children would be almost ‘unthinkable’ without one. Devices are becoming lighter and lighter but offering an array of options and applications as well as the unavoidable access to the Internet, without which it would be almost unusable. Numerous features such as taking of photographs, listening to music, information search on the Internet, access to social networks, usage of some of the chatting and messaging services, are only some of the numerous features offered by ‘smart’ devices. They have replaced the alarm clock, home phone, camera, tablet and other devices. Their use and possession have become a part of the everyday image of young people. Apart from the positive aspects, the use of smartphones has also some downsides. For instance, free time was usually spent in nature, playing, doing sports or other activities enabling children an adequate psychophysiological growth and development. The greater usage of smartphones during classes to check statuses on social networks, message your friends, play online games, are just some of the possible negative aspects of their application. Considering that the age of the population using smartphones is decreasing and that smartphones are no longer ‘foreign’ to children of pre-school age (smartphones are used at home or in coffee shops or shopping centers while waiting for their parents, playing video games often inappropriate to their age), particular attention must be paid to a very sensitive group, the teenagers who almost never separate from their ‘pets’. This paper is divided into two sections, theoretical and empirical ones. The theoretical section gives an overview of the pros and cons of the usage of smartphones, while the empirical section presents the results of a research conducted in three elementary schools regarding the usage of smartphones and, specifically, their usage during classes, during breaks and to search information on the Internet, check status updates and 'likes’ on the Facebook social network.

Keywords: education, smartphone, social networks, teenagers

Procedia PDF Downloads 452

Authors: Kasim Görenekli, Ali Gülbağ

Abstract:

This study presents a comprehensive analysis of water consumption patterns in Kocaeli province, Turkey, utilizing various machine learning approaches. We analyzed data from 5,000 water subscribers across residential, commercial, and official categories over an 80-month period from January 2016 to August 2022, resulting in a total of 400,000 records. The dataset encompasses water consumption records, weather information, weekends and holidays, previous months' consumption, and the influence of the COVID-19 pandemic.We implemented and compared several machine learning models, including Linear Regression, Random Forest, Support Vector Regression (SVR), XGBoost, Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). Particle Swarm Optimization (PSO) was applied to optimize hyperparameters for all models.Our results demonstrate varying performance across subscriber types and models. For official subscribers, Random Forest achieved the highest R² of 0.699 with PSO optimization. For commercial subscribers, Linear Regression performed best with an R² of 0.730 with PSO. Residential water usage proved more challenging to predict, with XGBoost achieving the highest R² of 0.572 with PSO.The study identified key factors influencing water consumption, with previous months' consumption, meter diameter, and weather conditions being among the most significant predictors. The impact of the COVID-19 pandemic on consumption patterns was also observed, particularly in residential usage.This research provides valuable insights for effective water resource management in Kocaeli and similar regions, considering Turkey's high water loss rate and below-average per capita water supply. The comparative analysis of different machine learning approaches offers a comprehensive framework for selecting appropriate models for water consumption prediction in urban settings.

Keywords: mMachine learning, water consumption prediction, particle swarm optimization, COVID-19, water resource management

Procedia PDF Downloads 15

Authors: Somayeh Komeylian

Abstract:

The direction of arrival (DoA) estimation is the crucial aspect of the radar technologies for detecting and dividing several signal sources. In this scenario, the antenna array output modeling involves numerous parameters including noise samples, signal waveform, signal directions, signal number, and signal to noise ratio (SNR), and thereby the methods of the DoA estimation rely heavily on the generalization characteristic for establishing a large number of the training data sets. Hence, we have analogously represented the two different optimization models of the DoA estimation; (1) the implementation of the decision directed acyclic graph (DDAG) for the multiclass least-squares support vector machine (LS-SVM), and (2) the optimization method of the deep neural network (DNN) radial basis function (RBF). We have rigorously verified that the LS-SVM DDAG algorithm is capable of accurately classifying DoAs for the three classes. However, the accuracy and robustness of the DoA estimation are still highly sensitive to technological imperfections of the antenna arrays such as non-ideal array design and manufacture, array implementation, mutual coupling effect, and background radiation and thereby the method may fail in representing high precision for the DoA estimation. Therefore, this work has a further contribution on developing the DNN-RBF model for the DoA estimation for overcoming the limitations of the non-parametric and data-driven methods in terms of array imperfection and generalization. The numerical results of implementing the DNN-RBF model have confirmed the better performance of the DoA estimation compared with the LS-SVM algorithm. Consequently, we have analogously evaluated the performance of utilizing the two aforementioned optimization methods for the DoA estimation using the concept of the mean squared error (MSE).

Keywords: DoA estimation, Adaptive antenna array, Deep Neural Network, LS-SVM optimization model, Radial basis function, and MSE

Procedia PDF Downloads 100

Authors: Ching Louis Liu, Edmund Kazmierczak, Tim Miller

Abstract:

Safety analysis for multi-agent systems is complicated by the, potentially nonlinear, interactions between agents. This paper proposes a method for analyzing the safety of multi-agent systems by explicitly focusing on interactions and the accident data of systems that are similar in structure and function to the system being analyzed. The method creates a Bayesian network using the accident data from similar systems. A feature of our method is that the events in accident data are labeled with HAZOP guide words. Our method uses an Ontology to abstract away from the details of a multi-agent implementation. Using the ontology, our methods then constructs an “Interaction Map,” a graphical representation of the patterns of interactions between agents and other artifacts. Interaction maps combined with statistical data from accidents and the HAZOP classifications of events can be converted into a Bayesian Network. Bayesian networks allow designers to explore “what it” scenarios and make design trade-offs that maintain safety. We show how to use the Bayesian networks, and the interaction maps to improve multi-agent system designs.

Keywords: multi-agent system, safety analysis, safety model, integration map

Procedia PDF Downloads 417