Search results for: Static neural networks

Authors: Jong Han Joo, Jeong Hun Lee, Young Sun Kim, Jae Young Kang, Seung Ho Choi

Abstract:

In this study, we propose a novel technique for acoustic echo suppression (AES) during speech recognition under barge-in conditions. Conventional AES methods based on spectral subtraction apply fixed weights to the estimated echo path transfer function (EPTF) at the current signal segment and to the EPTF estimated until the previous time interval. However, the effects of echo path changes should be considered for eliminating the undesired echoes. We describe a new approach that adaptively updates weight parameters in response to abrupt changes in the acoustic environment due to background noises or double-talk. Furthermore, we devised a voice activity detector and an initial time-delay estimator for barge-in speech recognition in communication networks. The initial time delay is estimated using log-spectral distance measure, as well as cross-correlation coefficients. The experimental results show that the developed techniques can be successfully applied in barge-in speech recognition systems.

Keywords: Acoustic echo suppression, barge-in, speech recognition, echo path transfer function, initial delay estimator, voice activity detector.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2278

Authors: Niloofar Yousefi, Marie Alaghband, Ivan Garibay

Abstract:

With the increase of credit card usage, the volume of credit card misuse also has significantly increased, which may cause appreciable financial losses for both credit card holders and financial organizations issuing credit cards. As a result, financial organizations are working hard on developing and deploying credit card fraud detection methods, in order to adapt to ever-evolving, increasingly sophisticated defrauding strategies and identifying illicit transactions as quickly as possible to protect themselves and their customers. Compounding on the complex nature of such adverse strategies, credit card fraudulent activities are rare events compared to the number of legitimate transactions. Hence, the challenge to develop fraud detection that are accurate and efficient is substantially intensified and, as a consequence, credit card fraud detection has lately become a very active area of research. In this work, we provide a survey of current techniques most relevant to the problem of credit card fraud detection. We carry out our survey in two main parts. In the first part, we focus on studies utilizing classical machine learning models, which mostly employ traditional transnational features to make fraud predictions. These models typically rely on some static physical characteristics, such as what the user knows (knowledge-based method), or what he/she has access to (object-based method). In the second part of our survey, we review more advanced techniques of user authentication, which use behavioral biometrics to identify an individual based on his/her unique behavior while he/she is interacting with his/her electronic devices. These approaches rely on how people behave (instead of what they do), which cannot be easily forged. By providing an overview of current approaches and the results reported in the literature, this survey aims to drive the future research agenda for the community in order to develop more accurate, reliable and scalable models of credit card fraud detection.

Keywords: credit card fraud detection, user authentication, behavioral biometrics, machine learning, literature survey

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 481

Authors: Guiheng Zhang, Wei Zhang, Jun Fu, Yudong Wang

Abstract:

A 900 MHz three-stage SiGe power amplifier (PA) with high power gain is presented in this paper. Volterra Series is applied to analyze nonlinearity sources of SiGe HBT device model clearly. Meanwhile, the influence of operating current to IMD3 is discussed. Then a β-helper current mirror bias circuit is applied to improve linearity, since the β-helper current mirror bias circuit can offer stable base biasing voltage. Meanwhile, it can also work as predistortion circuit when biasing voltages of three bias circuits are fine-tuned, by this way, the power gain and operating current of PA are optimized for best linearity. The three power stages which fabricated by 0.18 μm SiGe technology are bonded to the printed circuit board (PCB) to obtain impedances by Load-Pull system, then matching networks are done for best linearity with discrete passive components on PCB. The final measured three-stage PA exhibits 21.1 dBm of output power at 1 dB compression point (OP1dB) with power added efficiency (PAE) of 20.6% and 33 dB power gain under 3.3 V power supply voltage.

Keywords: High gain power amplifier, linearization bias circuit, SiGe HBT model, Volterra Series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 956

Authors: Davide D’Aria, Paolo Falcone, Luigi Maggi, Aldo Cero, Giovanni Amoroso

Abstract:

The paper presents a methodology for real-time structural health monitoring and geophysical applications. The key elements of the system are a high performance MIMO RADAR sensor, an optical camera and a dedicated set of software algorithms encompassing interferometry, tomography and photogrammetry. The MIMO Radar sensor proposed in this work, provides an extremely high sensitivity to displacements making the system able to react to tiny deformations (up to tens of microns) with a time scale which spans from milliseconds to hours. The MIMO feature of the system makes the system capable of providing a set of two-dimensional images of the observed scene, each mapped on the azimuth-range directions with noticeably resolution in both the dimensions and with an outstanding repetition rate. The back-scattered energy, which is distributed in the 3D space, is projected on a 2D plane, where each pixel has as coordinates the Line-Of-Sight distance and the cross-range azimuthal angle. At the same time, the high performing processing unit allows to sense the observed scene with remarkable refresh periods (up to milliseconds), thus opening the way for combined static and dynamic structural health monitoring. Thanks to the smart TX/RX antenna array layout, the MIMO data can be processed through a tomographic approach to reconstruct the three-dimensional map of the observed scene. This 3D point cloud is then accurately mapped on a 2D digital optical image through photogrammetric techniques, allowing for easy and straightforward interpretations of the measurements. Once the three-dimensional image is reconstructed, a 'repeat-pass' interferometric approach is exploited to provide the user of the system with high frequency three-dimensional motion/vibration estimation of each point of the reconstructed image. At this stage, the methodology leverages consolidated atmospheric correction algorithms to provide reliable displacement and vibration measurements.

Keywords: Interferometry, MIMO RADAR, SAR, tomography.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 868

Authors: C. Chitra, P. Subbaraj

Abstract:

The shortest path routing problem is a multiobjective nonlinear optimization problem with constraints. This problem has been addressed by considering Quality of service parameters, delay and cost objectives separately or as a weighted sum of both objectives. Multiobjective evolutionary algorithms can find multiple pareto-optimal solutions in one single run and this ability makes them attractive for solving problems with multiple and conflicting objectives. This paper uses an elitist multiobjective evolutionary algorithm based on the Non-dominated Sorting Genetic Algorithm (NSGA), for solving the dynamic shortest path routing problem in computer networks. A priority-based encoding scheme is proposed for population initialization. Elitism ensures that the best solution does not deteriorate in the next generations. Results for a sample test network have been presented to demonstrate the capabilities of the proposed approach to generate well-distributed pareto-optimal solutions of dynamic routing problem in one single run. The results obtained by NSGA are compared with single objective weighting factor method for which Genetic Algorithm (GA) was applied.

Keywords: Multiobjective optimization, Non-dominated SortingGenetic Algorithm, Routing, Weighted sum.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3228

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean   Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: Air quality prediction, deep learning algorithms, time series forecasting, look-back window.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1057

Authors: Padmanabhan Balasubramanian, C. Ardil

Abstract:

In this paper, we consider the problem of logic simplification for a special class of logic functions, namely complementary Boolean functions (CBF), targeting low power implementation using static CMOS logic style. The functions are uniquely characterized by the presence of terms, where for a canonical binary 2-tuple, D(mj) ∪ D(mk) = { } and therefore, we have | D(mj) ∪ D(mk) | = 0 [19]. Similarly, D(Mj) ∪ D(Mk) = { } and hence | D(Mj) ∪ D(Mk) | = 0. Here, 'mk' and 'Mk' represent a minterm and maxterm respectively. We compare the circuits minimized with our proposed method with those corresponding to factored Reed-Muller (f-RM) form, factored Pseudo Kronecker Reed-Muller (f-PKRM) form, and factored Generalized Reed-Muller (f-GRM) form. We have opted for algebraic factorization of the Reed-Muller (RM) form and its different variants, using the factorization rules of [1], as it is simple and requires much less CPU execution time compared to Boolean factorization operations. This technique has enabled us to greatly reduce the literal count as well as the gate count needed for such RM realizations, which are generally prone to consuming more cells and subsequently more power consumption. However, this leads to a drawback in terms of the design-for-test attribute associated with the various RM forms. Though we still preserve the definition of those forms viz. realizing such functionality with only select types of logic gates (AND gate and XOR gate), the structural integrity of the logic levels is not preserved. This would consequently alter the testability properties of such circuits i.e. it may increase/decrease/maintain the same number of test input vectors needed for their exhaustive testability, subsequently affecting their generalized test vector computation. We do not consider the issue of design-for-testability here, but, instead focus on the power consumption of the final logic implementation, after realization with a conventional CMOS process technology (0.35 micron TSMC process). The quality of the resulting circuits evaluated on the basis of an established cost metric viz., power consumption, demonstrate average savings by 26.79% for the samples considered in this work, besides reduction in number of gates and input literals by 39.66% and 12.98% respectively, in comparison with other factored RM forms.

Keywords: Reed-Muller forms, Logic function, Hammingdistance, Algebraic factorization, Low power design.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1779

Authors: Candido Alcaide, Manuel Dıaz, Luis Llopis, Antonio Marquez, Bartolome Rubio, Enrique Soler

Abstract:

The increasing complexity of software development based on peer to peer networks makes necessary the creation of new frameworks in order to simplify the developer-s task. Additionally, some applications, e.g. fire detection or security alarms may require real-time constraints and the high level definition of these features eases the application development. In this paper, a service model based on a component model with real-time features is proposed. The high-level model will abstract developers from implementation tasks, such as discovery, communication, security or real-time requirements. The model is oriented to deploy services on small mobile devices, such as sensors, mobile phones and PDAs, where the computation is light-weight. Services can be composed among them by means of the port concept to form complex ad-hoc systems and their implementation is carried out using a component language called UM-RTCOM. In order to apply our proposals a fire detection application is described.

Keywords: Peer-to-peer, mobile systems, real-time, service-oriented architecture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1650

Authors: M. Pandi, K. Premalatha

Abstract:

A DNA microarray technology is a collection of microscopic DNA spots attached to a solid surface. Scientists use DNA microarrays to measure the expression levels of large numbers of genes simultaneously or to genotype multiple regions of a genome. Elucidating the patterns hidden in gene expression data offers a tremendous opportunity for an enhanced understanding of functional genomics. However, the large number of genes and the complexity of biological networks greatly increase the challenges of comprehending and interpreting the resulting mass of data, which often consists of millions of measurements. It is handled by clustering which reveals the natural structures and identifying the interesting patterns in the underlying data. In this paper, gene based clustering in gene expression data is proposed using Cuckoo Search with Differential Evolution (CS-DE). The experiment results are analyzed with gene expression benchmark datasets. The results show that CS-DE outperforms CS in benchmark datasets. To find the validation of the clustering results, this work is tested with one internal and one external cluster validation indexes.

Keywords: DNA, Microarray, genomics, Cuckoo Search, Differential Evolution, Gene expression data, Clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1450

Authors: Manish Kumar, Pradeep Rout Aditya Kumar Jha, Pankaj Gupta

Abstract:

Wings are structural components of an aeroplane that are used to produce lift while the aircraft is in flight. The initial assault angle of the wing is definite. Due to the pressure difference at the top and bottom surfaces of the wing, lift force is produced when the flow passes over it. This paper explains the fundamental concept of the structural behaviour of a wing threatened by flowing loads during the voyage. The study comprises the use of concepts and analysis with the help of finite element analysis. Wing assembly is the first stage of wing model and design, which are determined by fascinating factual features. The basic gathering wing consists of a thin membrane, two poles, and several ribs. It has two spars, the major spar and the secondary spar. Here, NACA 23015 is selected as the standard model for all types of aerofoil structures since it is more akin to the custom aerofoil utilized in large aircraft, specifically the Airbus A320. Two rods mostly endure the twisting moment and trim strength, which is finished with titanium contamination to ensure enough inflexibility. The covering and wing spars are made of aluminium amalgam to lessen the structural heaviness. Following that, a static underlying examination is performed, and the general contortion, equivalent flexible strain, and comparing Von-Mises pressure are obtained to aid in investigations of the mechanical behaviour of the wing. Moreover, the modular examination is being upheld to decide the normal pace of repetition as well as the modular state of the three orders, which are obtained through the pre-stress modular investigation. The findings of the modular investigation assist engineers in reducing their excitement about regular events and turning away the wing from the whirlwind. Based on the findings of the study, planners can prioritise union and examination of the pressure mindfulness range and tremendous twisting region. All in all, the entertainment outcomes demonstrate that the game plan is feasible and further develop the data grade of the lifting surface.

Keywords: FEM, Airbus, NACA, modulus of elasticity, aircraft wing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 479

Authors: Gamze Uslu, Sebnem Baydere, Alper K. Demir

Abstract:

In this study, data loss tolerance of Support Vector Machines (SVM) based activity recognition model and multi activity classification performance when data are received over a lossy wireless sensor network is examined. Initially, the classification algorithm we use is evaluated in terms of resilience to random data loss with 3D acceleration sensor data for sitting, lying, walking and standing actions. The results show that the proposed classification method can recognize these activities successfully despite high data loss. Secondly, the effect of differentiated quality of service performance on activity recognition success is measured with activity data acquired from a multi hop wireless sensor network, which introduces  high data loss. The effect of number of nodes on the reliability and multi activity classification success is demonstrated in simulation environment. To the best of our knowledge, the effect of data loss in a wireless sensor network on activity detection success rate of an SVM based classification algorithm has not been studied before.

Keywords: Activity recognition, support vector machines, acceleration sensor, wireless sensor networks, packet loss.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2835

Authors: Ifeyinwa E. Achumba, Djamel Azzi, Rinat Khusainov

Abstract:

There are three approaches to complete Bayesian Network (BN) model construction: total expert-centred, total datacentred, and semi data-centred. These three approaches constitute the basis of the empirical investigation undertaken and reported in this paper. The objective is to determine, amongst these three approaches, which is the optimal approach for the construction of a BN-based model for the performance assessment of students- laboratory work in a virtual electronic laboratory environment. BN models were constructed using all three approaches, with respect to the focus domain, and compared using a set of optimality criteria. In addition, the impact of the size and source of the training, on the performance of total data-centred and semi data-centred models was investigated. The results of the investigation provide additional insight for BN model constructors and contribute to literature providing supportive evidence for the conceptual feasibility and efficiency of structure and parameter learning from data. In addition, the results highlight other interesting themes.

Keywords: Bayesian networks, model construction, parameterlearning, structure learning, performance index, model comparison.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1695

Authors: Salha Alshamrani, Maha Aljohni, Eman Aldhaheri

Abstract:

With the proliferation of Internet of Things (IoT) devices in various industries, there has been a concurrent rise in security vulnerabilities, particularly spoofing attacks. This study explores the potential of blockchain technology in enhancing the security of IoT systems and mitigating these attacks. Blockchain's decentralized and immutable ledger offers significant promise for improving data integrity, transaction transparency, and tamper-proofing. This research develops and implements a blockchain-based IoT architecture and a reference network to simulate real-world scenarios and evaluate a blockchain-integrated intrusion detection system. Performance measures including time delay, security, and resource utilization are used to assess the system's effectiveness, comparing it to conventional IoT networks without blockchain. The results provide valuable insights into the practicality and efficacy of employing blockchain as a security mechanism, shedding light on the trade-offs between speed and security in blockchain deployment for IoT. The study concludes that despite minor increases in time consumption, the security benefits of incorporating blockchain technology into IoT systems outweigh potential drawbacks, demonstrating a significant potential for blockchain in bolstering IoT security.

Keywords: Internet of Thing, Spoofing, IoT, Access control, Blockchain, Raspberry pi.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 49

Authors: Abdullah Faqihi, John Hedley

Abstract:

Biosensors play a significant role in the healthcare sectors, scientific and technological progress. Developing electrodes that are easy to manufacture and deliver better electrochemical performance is advantageous for diagnostics and biosensing. They can be implemented extensively in various analytical tasks such as drug discovery, food safety, medical diagnostics, process controls, security and defence, in addition to environmental monitoring. Development of biosensors aims to create high-performance electrochemical electrodes for diagnostics and biosensing. A biosensor is a device that inspects the biological and chemical reactions generated by the biological sample. A biosensor carries out biological detection via a linked transducer and transmits the biological response into an electrical signal; stability, selectivity, and sensitivity are the dynamic and static characteristics that affect and dictate the quality and performance of biosensors. In this research, a developed experimental study for laser scribing technique for graphene oxide inside a vacuum chamber for processing of graphene oxide is presented. The processing of graphene oxide (GO) was achieved using the laser scribing technique. The effect of the laser scribing on the reduction of GO was investigated under two conditions: atmosphere and vacuum. GO solvent was coated onto a LightScribe DVD. The laser scribing technique was applied to reduce GO layers to generate rGO. The micro-details for the morphological structures of rGO and GO were visualised using scanning electron microscopy (SEM) and Raman spectroscopy so that they could be examined. The first electrode was a traditional graphene-based electrode model, made under normal atmospheric conditions, whereas the second model was a developed graphene electrode fabricated under a vacuum state using a vacuum chamber. The purpose was to control the vacuum conditions, such as the air pressure and the temperature during the fabrication process. The parameters to be assessed include the layer thickness and the continuous environment. Results presented show high accuracy and repeatability achieving low cost productivity.

Keywords: Laser scribing, LightScribe DVD, graphene oxide, scanning electron microscopy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 609

Authors: Jung-Hun Cho, Tae-Heon Moon, Jin-Hak Lee

Abstract:

Land price contains the comprehensive characteristics of urban space, representing the social and economic features of the city. Accordingly, land price can be utilized as an indicator, which can identify the changes of spatial structure and socioeconomic variations caused by urban development. This study attempted to explore the changes in land price by a new road construction. Methodologically, it adopted Space Syntax, which can interpret urban spatial structure comprehensively, to identify the relationship between the forms of road networks and land price. The result of the regression analysis showed the ‘integration index’ of Space Syntax is statistically significant and has a strong correlation with land price. If the integration value is high, land price increases proportionally. Subsequently, using regression equation, it tried to predict the land price changes of each of the lots surrounding the roads that are newly opened. The research methods or study results have the advantage of predicting the changes in land price in an easy way. In addition, it will contribute to planners and project managers to establish relevant polices and smoothing urban regeneration projects through enhancing residents’ understanding by providing possible results and advantages in their land price before the execution of urban regeneration and development projects.

Keywords: Space syntax, urban regeneration, spatial structure, official land price.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1242

Authors: Burak Köken, Hatice D. Arslan, Bilgehan Y. Çakmak

Abstract:

Analyzing the relation networks between the hospital buildings which have complex structure and distinctive spatial relationships is quite difficult. The hospital buildings which require specialty in spatial relationship solutions during design and selfinnovation through the developing technology should survive and keep giving service even after the disasters such as earthquakes. In this study, a hospital building where the load-bearing system was strengthened because of the insufficient earthquake performance and the construction of an additional building was required to meet the increasing need for space was discussed and a comparative spatial evaluation of the hospital building was made with regard to its status before the change and after the change. For this reason, spatial organizations of the building before change and after the change were analyzed by means of Space Syntax method and the effects of the change on space organization parameters were searched by applying an analytical procedure. Using Depthmap UCL software, Connectivity, Visual Mean Depth, Beta and Visual Integration analyses were conducted. Based on the data obtained after the analyses, it was seen that the relationships between spaces of the building increased after the change and the building has become more explicit and understandable for the occupants. Furthermore, it was determined according to findings of the analysis that the increase in depth causes difficulty in perceiving the spaces and the changes considering this problem generally ease spatial use.

Keywords: Architecture, hospital building, space syntax, strengthening.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2175

Authors: C. Chitra, P. Subbaraj

Abstract:

The shortest path routing problem is a multiobjective nonlinear optimization problem with constraints. This problem has been addressed by considering Quality of service parameters, delay and cost objectives separately or as a weighted sum of both objectives. Multiobjective evolutionary algorithms can find multiple pareto-optimal solutions in one single run and this ability makes them attractive for solving problems with multiple and conflicting objectives. This paper uses an elitist multiobjective evolutionary algorithm based on the Non-dominated Sorting Genetic Algorithm (NSGA), for solving the dynamic shortest path routing problem in computer networks. A priority-based encoding scheme is proposed for population initialization. Elitism ensures that the best solution does not deteriorate in the next generations. Results for a sample test network have been presented to demonstrate the capabilities of the proposed approach to generate well-distributed pareto-optimal solutions of dynamic routing problem in one single run. The results obtained by NSGA are compared with single objective weighting factor method for which Genetic Algorithm (GA) was applied.

Keywords: Multiobjective optimization, Non-dominated Sorting Genetic Algorithm, Routing, Weighted sum.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1892

Authors: A. Ghaffari, A. S. Mostafavi

Abstract:

Complex assemblies of interacting proteins carry out most of the interesting jobs in a cell, such as metabolism, DNA synthesis, mitosis and cell division. These physiological properties play out as a subtle molecular dance, choreographed by underlying regulatory networks that control the activities of cyclin-dependent kinases (CDK). The network can be modeled by a set of nonlinear differential equations and its behavior predicted by numerical simulation. In this paper, an innovative approach has been proposed that uses genetic algorithms to mine a set of behavior data output by a biological system in order to determine the kinetic parameters of the system. In our approach, the machine learning method is integrated with the framework of existent biological information in a wiring diagram so that its findings are expressed in a form of system dynamic behavior. By numerical simulations it has been illustrated that the model is consistent with experiments and successfully shown that such application of genetic algorithms will highly improve the performance of mathematical model of the cell division cycle to simulate such a complicated bio-system.

Keywords: Cell cycle, Cyclin-dependent kinase, Fission yeast, Genetic algorithms, Mathematical modeling, Wiring diagram

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1478

Authors: Raymond Xu, Ashley Hua, Andrew Wang, Yuru Lin

Abstract:

During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.

Keywords: Artificial intelligence, depression detection, facial emotion recognition, natural language processing, mental disorder.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1106

Authors: S. Arrizabalaga, A. Salterain, M. Domínguez, I. Alvaro

Abstract:

Traditionally, Internet has provided best-effort service to every user regardless of its requirements. However, as Internet becomes universally available, users demand more bandwidth and applications require more and more resources, and interest has developed in having the Internet provide some degree of Quality of Service. Although QoS is an important issue, the question of how it will be brought into the Internet has not been solved yet. Researches, due to the rapid advances in technology are proposing new and more desirable capabilities for the next generation of IP infrastructures. But neither all applications demand the same amount of resources, nor all users are service providers. In this way, this paper is the first of a series of papers that presents an architecture as a first step to the optimization of QoS in the Internet environment as a solution to a SMSE's problem whose objective is to provide public service to internet with certain Quality of Service expectations. The service provides new business opportunities, but also presents new challenges. We have designed and implemented a scalable service framework that supports adaptive bandwidth based on user demands, and the billing based on usage and on QoS. The developed application has been evaluated and the results show that traffic limiting works at optimum and so it does exceeding bandwidth distribution. However, some considerations are done and currently research is under way in two basic areas: (i) development and testing new transfer protocols, and (ii) developing new strategies for traffic improvements based on service differentiation.

Keywords: Differentiated Services, Linux, Quality of Service, queueing disciplines, web application.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1893

Authors: Chakraborty Sudipta, A. R. Kambekar, Sarma Arnab

Abstract:

Sea-level rise being one of the most important impacts of anthropogenic induced climate change resulting from global warming and melting of icebergs at Arctic and Antarctic, the investigations done by various researchers both on Indian Coast and elsewhere during the last decade has been reviewed in this paper. The paper aims to ascertain the propensity of consistency of different suggested methods to predict the near-accurate future sea level rise along the coast of Mumbai. Case studies at East Coast, Southern Tip and West and South West coast of India have been reviewed. Coastal Vulnerability Index of several important international places has been compared, which matched with Intergovernmental Panel on Climate Change forecasts. The application of Geographic Information System mapping, use of remote sensing technology, both Multi Spectral Scanner and Thematic Mapping data from Landsat classified through Iterative Self-Organizing Data Analysis Technique for arriving at high, moderate and low Coastal Vulnerability Index at various important coastal cities have been observed. Instead of data driven, hindcast based forecast for Significant Wave Height, additional impact of sea level rise has been suggested. Efficacy and limitations of numerical methods vis-à-vis Artificial Neural Network has been assessed, importance of Root Mean Square error on numerical results is mentioned. Comparing between various computerized methods on forecast results obtained from MIKE 21 has been opined to be more reliable than Delft 3D model.

Keywords: Climate change, coastal vulnerability index, global warming, sea level rise.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1474

Authors: Jung-Min Yun, Jong-Hyun Baek, Byoung Ky Kang, Peom Park

Abstract:

In this study, workplace environmental monitoring systems were established using USN(Ubiquitous Sensor Networks) and LabVIEW. Although existing direct sampling methods enable finding accurate values as of the time points of measurement, those methods are disadvantageous in that continuous management and supervision are difficult and costs for are high when those methods are used. Therefore, the efficiency and reliability of workplace management by supervisors are relatively low when those methods are used. In this study, systems were established so that information on workplace environmental factors such as temperatures, humidity and noises is measured and transmitted to the PC in real time to enable supervisors to monitor workplaces through LabVIEW on the PC. When any accidents have occurred in workplaces, supervisors can immediately respond through the monitoring system and this system enables integrated workplace management and the prevention of safety accidents. By introducing these monitoring systems, safety accidents due to harmful environmental factors in workplaces can be prevented and these monitoring systems will be also helpful in finding out the correlation between safety accidents and occupational diseases by comparing and linking databases established by this monitoring system with existing statistical data.

Keywords: Ubiquitous Sensor Nework, LabVIEW, Environment Monitoring.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2507

Authors: A. A Velásquez, J.Baena

Abstract:

This article presents the simulation, parameterization and optimization of an electromagnet with the C–shaped configuration, intended for the study of magnetic properties of materials. The electromagnet studied consists of a C-shaped yoke, which provides self–shielding for minimizing losses of magnetic flux density, two poles of high magnetic permeability and power coils wound on the poles. The main physical variable studied was the static magnetic flux density in a column within the gap between the poles, with 4cm2 of square cross section and a length of 5cm, seeking a suitable set of parameters that allow us to achieve a uniform magnetic flux density of 1x104 Gaussor values above this in the column, when the system operates at room temperature and with a current consumption not exceeding 5A. By means of a magnetostatic analysis by the finite element method, the magnetic flux density and the distribution of the magnetic field lines were visualized and quantified. From the results obtained by simulating an initial configuration of electromagnet, a structural optimization of the geometry of the adjustable caps for the ends of the poles was performed. The magnetic permeability effect of the soft magnetic materials used in the poles system, such as low– carbon steel (0.08% C), Permalloy (45% Ni, 54.7% Fe) and Mumetal (21.2% Fe, 78.5% Ni), was also evaluated. The intensity and uniformity of the magnetic field in the gap showed a high dependence with the factors described above. The magnetic field achieved in the column was uniform and its magnitude ranged between 1.5x104 Gauss and 1.9x104 Gauss according to the material of the pole used, with the possibility of increasing the magnetic field by choosing a suitable geometry of the cap, introducing a cooling system for the coils and adjusting the spacing between the poles. This makes the device a versatile and scalable tool to generate the magnetic field necessary to perform magnetic characterization of materials by techniques such as vibrating sample magnetometry (VSM), Hall-effect, Kerr-effect magnetometry, among others. Additionally, a CAD design of the modules of the electromagnet is presented in order to facilitate the construction and scaling of the physical device.

Keywords: Electromagnet, Finite Elements Method, Magnetostatic, Magnetometry, Modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1902

Authors: H. Baskar, A. S. Chakravarthy, P. Garg, D. Goel, A. S. Raj, K. Kumar, Lakshya, R. Parvatham, V. Sushant, B. Kumar Rout

Abstract:

In this paper, we present a computer vision task called nighttime dehaze-enhancement. This task aims to jointly perform dehazing and lightness enhancement. Our task fundamentally differs from nighttime dehazing – our goal is to jointly dehaze and enhance scenes, while nighttime dehazing aims to dehaze scenes under a nighttime setting. In order to facilitate further research on this task, we release a benchmark dataset called Reside-β Night dataset, consisting of 4122 nighttime hazed images from 2061 scenes and 2061 ground truth images. Moreover, we also propose a network called NDENet (Nighttime Dehaze-Enhancement Network), which jointly performs dehazing and low-light enhancement in an end-to-end manner. We evaluate our method on the proposed benchmark and achieve Structural Index Similarity (SSIM) of 0.8962 and Peak Signal to Noise Ratio (PSNR) of 26.25. We also compare our network with other baseline networks on our benchmark to demonstrate the effectiveness of our approach. We believe that nighttime dehaze-enhancement is an essential task particularly for autonomous navigation applications, and hope that our work will open up new frontiers in research. The code for our network is made publicly available.

Keywords: Dehazing, image enhancement, nighttime, computer vision.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 572

Authors: Muhammad Aqil, Ichiro Kita, Moses Macalinao

Abstract:

Reliable water level forecasts are particularly important for warning against dangerous flood and inundation. The current study aims at investigating the suitability of the adaptive network based fuzzy inference system for continuous water level modeling. A hybrid learning algorithm, which combines the least square method and the back propagation algorithm, is used to identify the parameters of the network. For this study, water levels data are available for a hydrological year of 2002 with a sampling interval of 1-hour. The number of antecedent water level that should be included in the input variables is determined by two statistical methods, i.e. autocorrelation function and partial autocorrelation function between the variables. Forecasting was done for 1-hour until 12-hour ahead in order to compare the models generalization at higher horizons. The results demonstrate that the adaptive networkbased fuzzy inference system model can be applied successfully and provide high accuracy and reliability for river water level estimation. In general, the adaptive network-based fuzzy inference system provides accurate and reliable water level prediction for 1-hour ahead where the MAPE=1.15% and correlation=0.98 was achieved. Up to 12-hour ahead prediction, the model still shows relatively good performance where the error of prediction resulted was less than 9.65%. The information gathered from the preliminary results provide a useful guidance or reference for flood early warning system design in which the magnitude and the timing of a potential extreme flood are indicated.

Keywords: Neural Network, Fuzzy, River, Forecasting

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1258

Authors: Y. Harold Robinson, M. Rajaram, E. Golden Julie, S. Balaji

Abstract:

This paper describes the proficient way of choosing the cluster head based on dominating set algorithm in a wireless sensor network (WSN). The algorithm overcomes the energy deterioration problems by this selection process of cluster heads. Clustering algorithms such as LEACH, EEHC and HEED enhance scalability in WSNs. Dominating set algorithm keeps the first node alive longer than the other protocols previously used. As the dominating set of cluster heads are directly connected to each node, the energy of the network is saved by eliminating the intermediate nodes in WSN. Security and trust is pivotal in network messaging. Cluster head is secured with a unique key. The member can only connect with the cluster head if and only if they are secured too. The secured trust model provides security for data transmission in the dominated set network with the group key. The concept can be extended to add a mobile sink for each or for no of clusters to transmit data or messages between cluster heads and to base station. Data security id preferably high and data loss can be prevented. The simulation demonstrates the concept of choosing cluster heads by dominating set algorithm and trust evaluation using DSTE. The research done is rationalized.

Keywords: Wireless Sensor Networks, LEECH, EEHC, HEED, DSTE.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1373

Authors: C. C. Liang

Abstract:

MSN used to be the most popular application for communicating among social networks, but Facebook chat is now the most popular. Facebook and MSN have similar characteristics, including usefulness, ease-of-use, and a similar function, which is the exchanging of information with friends. Facebook outperforms MSN in both of these areas. However, the adoption of Facebook and abandonment of MSN have occurred for other reasons. Functions can be improved, but users’ willingness to use does not just depend on functionality. Flow status has been established to be crucial to users’ adoption of cyber applications and to affects users’ adoption of software applications. If users experience flow in using software application, they will enjoy using it frequently, and even change their preferred application from an old to this new one. However, no investigation has examined choice behavior related to switching from Facebook to MSN based on a consideration of flow experiences and functions. This investigation discusses the flow experiences and functions of social-networking applications. Flow experience is found to affect perceived ease of use and perceived usefulness; perceived ease of use influences information ex-change with friends, and perceived usefulness; information exchange influences perceived usefulness, but information exchange has no effect on flow experience.

Keywords: Consumer behavior, social media, technology acceptance model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1380

Authors: L. Parvizsedghy, I. Gkountis, A. Senouci, T. Zayed, M. Alsharqawi, H. El Chanati, M. El-Abbasy, F. Mosleh

Abstract:

The aging and deterioration of water pipelines in cities worldwide result in more frequent water main breaks, water service disruptions, and flooding damage. Therefore, there is an urgent need for undertaking proper maintenance procedures to avoid breaks and disastrous failures. However, due to budget limitations, the maintenance of water pipeline networks needs to be prioritized through efficient deterioration assessment models. Previous studies focused on the development of structural or physical deterioration assessment models, which require expensive inspection data. But, this paper aims at developing deterioration assessment models for water pipelines using statistical techniques. Several deterioration models were developed based on pipeline size, material type, and soil type using linear regression analysis. The categorical nature of some variables affecting pipeline deterioration was considered through developing several categorical models. The developed models were validated with an average validity percentage greater than 95%. Moreover, sensitivity analysis was carried out against different classifications and it displayed higher importance of age of pipes compared to other factors. The developed models will be helpful for the water municipalities and asset managers to assess the condition of their pipes and prioritize them for maintenance and inspection purposes.

Keywords: Water pipelines, deterioration assessment models, regression analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1159

Authors: Raksha Sharma, Vishnu Kant Soni, Manoj Kumar Mishra, Prachet Bhuyan, Utpal Chandra Dey

Abstract:

Grid computing is a group of clusters connected over high-speed networks that involves coordinating and sharing computational power, data storage and network resources operating across dynamic and geographically dispersed locations. Resource management and job scheduling are critical tasks in grid computing. Resource selection becomes challenging due to heterogeneity and dynamic availability of resources. Job scheduling is a NP-complete problem and different heuristics may be used to reach an optimal or near optimal solution. This paper proposes a model for resource and job scheduling in dynamic grid environment. The main focus is to maximize the resource utilization and minimize processing time of jobs. Grid resource selection strategy is based on Max Heap Tree (MHT) that best suits for large scale application and root node of MHT is selected for job submission. Job grouping concept is used to maximize resource utilization for scheduling of jobs in grid computing. Proposed resource selection model and job grouping concept are used to enhance scalability, robustness, efficiency and load balancing ability of the grid.

Keywords: Agent, Grid Computing, Job Grouping, Max Heap Tree (MHT), Resource Scheduling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2060

Authors: Eric P. Jiang

Abstract:

As the Internet continues to grow at a rapid pace as the primary medium for communications and commerce and as telecommunication networks and systems continue to expand their global reach, digital information has become the most popular and important information resource and our dependence upon the underlying cyber infrastructure has been increasing significantly. Unfortunately, as our dependency has grown, so has the threat to the cyber infrastructure from spammers, attackers and criminal enterprises. In this paper, we propose a new machine learning based network intrusion detection framework for cyber security. The detection process of the framework consists of two stages: model construction and intrusion detection. In the model construction stage, a semi-supervised machine learning algorithm is applied to a collected set of network audit data to generate a profile of normal network behavior and in the intrusion detection stage, input network events are analyzed and compared with the patterns gathered in the profile, and some of them are then flagged as anomalies should these events are sufficiently far from the expected normal behavior. The proposed framework is particularly applicable to the situations where there is only a small amount of labeled network training data available, which is very typical in real world network environments.

Keywords: classification, data analysis and mining, network intrusion detection, semi-supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1763