Search results for: automated teller machine

Authors: S. Maniruzzaman, N. Ramanujam, Qazi Akhter Rasool, Swapan Kumar Biswas, P. Prasad, Chandrakanta Ojha

Abstract:

Landslide is one of the major natural disasters in South Asian countries. Applying 2D Electrical Resistivity Tomographic Imaging estimation of geometry, thickness, and depth of failure zone of the landslide can be made. Landslide is a pertinent problem in Nilgris plateau next to Himalaya. Nilgris range consists of hard Archean metamorphic rocks. Intense weathering prevailed during the Pre-Cambrian time had deformed the rocks up to 45m depth. The landslides are dominant in the southern and eastern part of plateau of is comparatively smaller than the northern drainage basins, as it has low density of drainage; coarse texture permitted the more of infiltration of rainwater, whereas in the northern part of the plateau entombed with high density of drainage pattern and fine texture with less infiltration than run off, and low to the susceptible to landslide. To get comprehensive information about the landslide zone 2D Electrical Resistivity Tomographic imaging study with CRM 500 Resistivity meter are used in Coonoor– Mettupalyam sector of Nilgiris plateau. To calculate Factor of Safety the infinite slope model of Brunsden and Prior is used. Factor of Safety can be expressed (FS) as the ratio of resisting forces to disturbing forces. If FS < 1 disturbing forces are larger than resisting forces and failure may occur. The geotechnical parameters of soil samples are calculated on the basis upon the apparent resistivity values for litho units of measured from 2D ERT image of the landslide zone. Relationship between friction angles for various soil properties is established by simple regression analysis from apparent resistivity data. Increase of water content in slide zone reduces the effectiveness of the shearing resistance and increase the sliding movement. Time-lapse resistivity changes to slope failure is determined through geophysical Factor of Safety which depends on resistivity and site topography. This ERT technique infers soil property at variable depths in wider areas. This approach to retrieve the soil property and overcomes the limit of the point of information provided by rain gauges and porous probes. Monitoring of slope stability without altering soil structure through the ERT technique is non-invasive with low cost. In landslide prone area an automated Electrical Resistivity Tomographic Imaging system should be installed permanently with electrode networks to monitor the hydraulic precursors to monitor landslide movement.

Keywords: 2D ERT, landslide, safety factor, slope stability

Procedia PDF Downloads 291

Authors: Anastasios Papathanasiou, George Liontos, Athanasios Katsouras, Vasiliki Liagkou, Euripides Glavas

Abstract:

Email remains a crucial communication tool due to its efficiency, accessibility and cost-effectiveness, enabling rapid information exchange across global networks. However, the global adoption of email has also made it a prime target for cyber threats, including phishing, malware and Business Email Compromise (BEC) attacks, which exploit its integral role in personal and professional realms in order to perform fraud and data breaches. To combat these threats, this research advocates for a multi-layered defense strategy incorporating advanced technological tools such as anti-spam and anti-malware software, machine learning algorithms and authentication protocols. Moreover, we developed an artificial intelligence model specifically designed to analyze email headers and assess their security status. This AI-driven model examines various components of email headers, such as "From" addresses, ‘Received’ paths and the integrity of SPF, DKIM and DMARC records. Upon analysis, it generates comprehensive reports that indicate whether an email is likely to be malicious or benign. This capability empowers users to identify potentially dangerous emails promptly, enhancing their ability to avoid phishing attacks, malware infections and other cyber threats.

Keywords: email security, artificial intelligence, header analysis, threat detection, phishing, DMARC, DKIM, SPF, ai model

Procedia PDF Downloads 21

Authors: Kothuri Sriraman, Mattupalli Komal Teja

Abstract:

In this paper, a novel algorithm is proposed for the recognition of hulls in a hand written images that might be irregular or digit or character shape. Identification of objects and internal objects is quite difficult to extract, when the structure of the image is having bulk of clusters. The estimation results are easily obtained while going through identifying the sub-regional objects by using the SASK algorithm. Focusing mainly to recognize the number of internal objects exist in a given image, so as it is shadow-free and error-free. The hard clustering and density clustering process of obtained image rough set is used to recognize the differentiated internal objects, if any. In order to find out the internal hull regions it involves three steps pre-processing, Boundary Extraction and finally, apply the Hull Detection system. By detecting the sub-regional hulls it can increase the machine learning capability in detection of characters and it can also be extend in order to get the hull recognition even in irregular shape objects like wise black holes in the space exploration with their intensities. Layered hulls are those having the structured layers inside while it is useful in the Military Services and Traffic to identify the number of vehicles or persons. This proposed SASK algorithm is helpful in making of that kind of identifying the regions and can useful in undergo for the decision process (to clear the traffic, to identify the number of persons in the opponent’s in the war).

Keywords: chain code, Hull regions, Hough transform, Hull recognition, Layered Outline Extraction, SASK algorithm

Procedia PDF Downloads 318

Authors: Hui Zhang, Ye Tian, Fang Ye, Ziming Guo

Abstract:

Communication signal modulation recognition technology is one of the key technologies in the field of modern information warfare. At present, communication signal automatic modulation recognition methods are mainly divided into two major categories. One is the maximum likelihood hypothesis testing method based on decision theory, the other is a statistical pattern recognition method based on feature extraction. Now, the most commonly used is a statistical pattern recognition method, which includes feature extraction and classifier design. With the increasingly complex electromagnetic environment of communications, how to effectively extract the features of various signals at low signal-to-noise ratio (SNR) is a hot topic for scholars in various countries. To solve this problem, this paper proposes a feature extraction algorithm for the communication signal based on the improved Holder cloud feature. And the extreme learning machine (ELM) is used which aims at the problem of the real-time in the modern warfare to classify the extracted features. The algorithm extracts the digital features of the improved cloud model without deterministic information in a low SNR environment, and uses the improved cloud model to obtain more stable Holder cloud features and the performance of the algorithm is improved. This algorithm addresses the problem that a simple feature extraction algorithm based on Holder coefficient feature is difficult to recognize at low SNR, and it also has a better recognition accuracy. The results of simulations show that the approach in this paper still has a good classification result at low SNR, even when the SNR is -15dB, the recognition accuracy still reaches 76%.

Keywords: communication signal, feature extraction, Holder coefficient, improved cloud model

Procedia PDF Downloads 129

Authors: Rana Alaa El-Deen Ahmed, M. Elemam Shehab, Shereen Morsy, Nermeen Mekawie

Abstract:

With the growing popularity and acceptance of e-commerce platforms, users face an ever increasing burden in actually choosing the right product from the large number of online offers. Thus, techniques for personalization and shopping guides are needed by users. For a pleasant and successful shopping experience, users need to know easily which products to buy with high confidence. Since selling a wide variety of products has become easier due to the popularity of online stores, online retailers are able to sell more products than a physical store. The disadvantage is that the customers might not find products they need. In this research the customer will be able to find the products he is searching for, because recommender systems are used in some ecommerce web sites. Recommender system learns from the information about customers and products and provides appropriate personalized recommendations to customers to find the needed product. In this paper eleven classification algorithms are comparatively tested to find the best classifier fit for consumer online shopping attitudes and behavior in the experimented dataset. The WEKA knowledge analysis tool, which is an open source data mining workbench software used in comparing conventional classifiers to get the best classifier was used in this research. In this research by using the data mining tool (WEKA) with the experimented classifiers the results show that decision table and filtered classifier gives the highest accuracy and the lowest accuracy classification via clustering and simple cart.

Keywords: classification, data mining, machine learning, online shopping, WEKA

Procedia PDF Downloads 333

Authors: Arash Sharafat Vaziri, Leila Aghaghazvini, Soodeh Jahangiri, Mohammad Tahami, Roham Borazjani, Mohammad Naghi Tahmasebi, Hamid Rabie, Hesan Jelodari Mamaghani, Fardis Vosoughi, Maryam Salimi

Abstract:

Aims: It is essential to know the normal extrusion measures in order to detect pathological ones. In this study, we aimed to define some normal reference values for meniscal extrusion in the normal knees during different ranges of motion. Methods: The amount of anterior and posterior portion of meniscal extrusion among twenty-one asymptomatic volunteers (42 knees) were tracked at 0, 45, and 90 degrees of knee flexion using an ultrasound machine. The repeated measures analysis of variance (ANOVA) was used to show the interaction between the amounts of meniscal extrusion and the different degrees of knee flexion. Result: The anterior portion of the lateral menisci at full knee extension (0.59±1.40) and the posterior portion of the medial menisci during 90° flexion (3.06±2.36) showed the smallest and the highest mean amount of extrusion, respectively. The normal average amounts of anterior extrusion were 1.12± 1.17 mm and 0.99± 1.34 mm for medial and lateral menisci, respectively. The posterior meniscal normal extrusions were significantly increasing in both medial and lateral menisci during the survey (F= 20.250 and 11.298; both P-values< 0.001) as they were measured at 2.37± 2.16 mm and 1.53± 2.18 mm in order. Conclusion: The medial meniscus can extrude 1.74± 1.84 mm normally, while this amount was 1.26± 1.82 mm for the lateral meniscus. These measures commonly increased with the rising of knee flexion motion. Likewise, the posterior portion showed more extrusion than the anterior portion on both sides. These measures commonly increased with higher knee flexion.

Keywords: meniscal extrusion, ultrasonography, knee

Procedia PDF Downloads 75

Authors: Derjew Ayele Ejigu, Houde Song, Xiaojing Liu

Abstract:

This work presents the particle swarm optimization trained neural network (PSO-NN) supervisory proportional integral derivative (PID) control method to monitor the pressurized water reactor (PWR) core power for safe operation. The proposed control approach is implemented on the transfer function of the PWR core, which is computed from the state-space model. The PWR core state-space model is designed from the neutronics, thermal-hydraulics, and reactivity models using perturbation around the equilibrium value. The proposed control approach computes the control rod speed to maneuver the core power to track the reference in a closed-loop scheme. The particle swarm optimization (PSO) algorithm is used to train the neural network (NN) and to tune the PID simultaneously. The controller performance is examined using integral absolute error, integral time absolute error, integral square error, and integral time square error functions, and the stability of the system is analyzed by using the Bode diagram. The simulation results indicated that the controller shows satisfactory performance to control and track the load power effectively and smoothly as compared to the PSO-PID control technique. This study will give benefit to design a supervisory controller for nuclear engineering research fields for control application.

Keywords: machine learning, neural network, pressurized water reactor, supervisory controller

Procedia PDF Downloads 133

Authors: Adam Patterson

Abstract:

This study analyzes the self-reported experiences of virtual reality users to develop insight into an optimal learning path for education within virtual reality. This research uses a sample of 1000 observations to statistically define factors influencing (i) immersion level and (ii) motion sickness rating for virtual reality experience respondents of college age. This paper recommends an efficient duration for each virtual reality session, to minimize sickness and maximize engagement, utilizing modern machine learning methods such as association rules. The goal of this research, in augmentation with previous literature, is to inform logistical decisions relating to implementation of pilot instruction for virtual reality at the collegiate level. Future research will include a Randomized Control Trial (RCT) to quantify the effect of virtual reality education on student learning outcomes and engagement measures. Current research aims to maximize the treatment effect within the RCT by optimizing the learning benefits of virtual reality. Results suggest significant gender heterogeneity amongst likelihood of reporting motion sickness. Females are 1.7 times more likely, than males, to report high levels of motion sickness resulting from a virtual reality experience. Regarding duration, respondents were 1.29 times more likely to select the lowest level of motion sickness after an engagement lasting between 24.3 and 42 minutes. Conversely, respondents between 42 to 60 minutes were 1.2 times more likely to select the higher levels of motion sickness.

Keywords: applications and integration of e-education, practices and cases in e-education, systems and technologies in e-education, technology adoption and diffusion of e-learning

Procedia PDF Downloads 47

Authors: Ewa M. Laskowska, Jorn Vatn

Abstract:

Industry 4.0 focuses on digital optimization of industrial processes. The idea is to use extracted data in order to build a decision support model enabling use of those data for real time decision making. In terms of predictive maintenance, the desired decision support tool would be a model enabling prognostics of system's health based on the current condition of considered equipment. Within area of system prognostics and health management, a commonly used health indicator is Remaining Useful Lifetime (RUL) of a system. Because the RUL is a random variable, it has to be estimated based on available health indicators. Health indicators can be of different types and come from different sources. They can be process variables, equipment performance variables, data related to number of experienced failures, etc. The aim of this study is the analysis of performance variables of emergency shutdown valves (ESV) used in oil and gas industry. ESV is inspected periodically, and at each inspection torque and time of valve operation are registered. The data will be analyzed by means of machine learning or statistical analysis. The purpose is to investigate whether the available data could be used as a health indicator for a prognostic purpose. The second objective is to examine what is the most efficient way to incorporate the data into predictive model. The idea is to check whether the data can be applied in form of explanatory variables in Markov process or whether other stochastic processes would be a more convenient to build an RUL model based on the information coming from registered data.

Keywords: emergency shutdown valves, health indicator, prognostics, remaining useful lifetime, RUL

Procedia PDF Downloads 70

Authors: B. B. S. Pereira, M. O. Souza, L. P. Zanetti, L. C. S. Oliveira, J. R. P. Moreno, M. P. Souza, V. R. Colturato, C. M. Machado

Abstract:

Background: The introduction of prophylactic or preemptive therapies has effectively decreased the CMV mortality rates after hematopoietic stem cell transplantation (HSCT). CMV antigenemia (pp65) or quantitative PCR are methods currently approved for CMV surveillance in pre-emptive strategies. Commercial assays are preferred as cut-off levels defined by in-house assays may vary among different protocols and in general show low reproducibility. Moreover, comparison of published data among different centers is only possible if international standards of quantification are included in the assays. Recently, the World Health Organization (WHO) established the first international standard for CMV detection. The real time PCR COBAS Ampliprep/ CobasTaqMan (CAP/CTM) (Roche®) was developed using the WHO standard for CMV quantification. However, the cut-off for the introduction of antiviral has not been determined yet. Methods: We conducted a retrospective study to determine: 1) the sensitivity and specificity of the new CMV CAP/CTM test in comparison with pp65 antigenemia to detect episodes of CMV infection/reactivation, and 2) the cut-off of viral load for introduction of ganciclovir (GCV). Pp65 antigenemia was performed and the corresponding plasma samples were stored at -20°C for further CMV detection by CAP/CTM. Comparison of tests was performed by kappa index. The appearance of positive antigenemia was considered the state variable to determine the cut-off of CMV viral load by ROC curve. Statistical analysis was performed using SPSS software version 19 (SPSS, Chicago, IL, USA.). Results: Thirty-eight patients were included and followed from August 2014 through May 2015. The antigenemia test detected 53 episodes of CMV infection in 34 patients (89.5%), while CAP/CTM detected 37 episodes in 33 patients (86.8%). AG and PCR results were compared in 431 samples and Kappa index was 30.9%. The median time for first AG detection was 42 (28-140) days, while CAP/CTM detected at a median of 7 days earlier (34 days, ranging from 7 to 110 days). The optimum cut-off value of CMV DNA was 34.25 IU/mL to detect positive antigenemia with 88.2% of sensibility, 100% of specificity and AUC of 0.91. This cut-off value is below the limit of detection and quantification of the equipment which is 56 IU/mL. According to CMV recurrence definition, 16 episodes of CMV recurrence were detected by antigenemia (47.1%) and 4 (12.1%) by CAP/CTM. The duration of viremia as detected by antigenemia was shorter (60.5% of the episodes lasted ≤ 7 days) in comparison to CAP/CTM (57.9% of the episodes lasting 15 days or more). This data suggests that the use of antigenemia to define the duration of GCV therapy might prompt early interruption of antiviral, which may favor CMV reactivation. The CAP/CTM PCR could possibly provide a safer information concerning the duration of GCV therapy. As prolonged treatment may increase the risk of toxicity, this hypothesis should be confirmed in prospective trials. Conclusions: Even though CAP/CTM by ROCHE showed great qualitative correlation with the antigenemia technique, the fully automated CAP/CTM did not demonstrate increased sensitivity. The cut-off value below the limit of detection and quantification may result in delayed introduction of pre-emptive therapy.

Keywords: antigenemia, CMV COBAS/TAQMAN, cytomegalovirus, antiviral cut-off

Procedia PDF Downloads 172

Authors: Larbi Belagraa, Miloud Beddar, Abderrazak Bouzid

Abstract:

The needs of the construction sector still increasing for concrete. However, the shortage of natural resources of aggregate could be a problem for the concrete industry, in addition to the negative impact on the environment due to the demolition wastes. Recycling aggregate from construction and demolition (C&D) waste presents a major interest for users and researchers of concrete since this constituent can occupies more than 70% of concrete volume. The aim of the study here in is to assess the effect of sulfate resistant cement combined with the local mineral addition of marble waste fillers on the mechanical behavior of a recycled aggregate concrete (RAC). Physical and mechanical properties of RAC including the density, the flexural and the compressive strength were studied. The non destructive test methods (pulse-velocity, rebound hammer) were performed . The results obtained were compared to crushed aggregate concrete (CAC) using the normal compressive testing machine test method. The optimal content of 5% marble fillers showed an improvement for both used test methods (compression, flexion and NDT). Non-destructive methods (ultrasonic and rebound hammer test) can be used to assess the strength of RAC, but a correction coefficient is required to obtain a similar value to the compressive strength given by the compression tests. The study emphasizes that these waste materials can be successfully and economically utilized as additional inert filler in RAC formulation within similar performances compared to a conventional concrete.

Keywords: marble waste fillers, mechanical strength, natural aggregate, non-destructive testing (NDT), recycled aggregate concrete

Procedia PDF Downloads 287

Authors: Tonislav Ivanov, Oleksii Nedashkivskyi, Denis Babeshko, Vadim Pinskiy, Matthew Putman

Abstract:

Training a machine learning model for object detection that generalizes well is known to benefit from a training dataset with diverse examples. However, training datasets usually contain many repeats of common examples of a class and lack rarely seen examples. This is due to the process commonly used during human annotation where a person would proceed sequentially through a list of images labeling a sufficiently high total number of examples. Instead, the method presented involves an active process where, after the initial labeling of several images is completed, the next subset of images for labeling is selected by an algorithm. This process of algorithmic image selection and manual labeling continues in an iterative fashion. The algorithm used for the image selection is a deep learning algorithm, based on the U-shaped architecture, which quantifies the presence of unseen data in each image in order to find images that contain the most novel examples. Moreover, the location of the unseen data in each image is highlighted, aiding the labeler in spotting these examples. Experiments performed using semiconductor wafer data show that labeling a subset of the data, curated by this algorithm, resulted in a model with a better performance than a model produced from sequentially labeling the same amount of data. Also, similar performance is achieved compared to a model trained on exhaustive labeling of the whole dataset. Overall, the proposed approach results in a dataset that has a diverse set of examples per class as well as more balanced classes, which proves beneficial when training a deep learning model.

Keywords: computer vision, deep learning, object detection, semiconductor

Procedia PDF Downloads 115

Authors: Ahmed H. Elkholy

Abstract:

An elastic analysis is developed to obtain the distribution of stresses, strains, bending moment and deformation for a thin hollow, variable thickness cylindrical specimen when subjected to different biaxial loadings. The specimen was subjected to a combination of internal pressure, axial tensile loading and external pressure. Several axial to circumferential stress ratios were investigated in detail. The analytical model was then validated using experimental results obtained from a test rig using several biaxial loadings. Based on the preliminary results obtained, the specimen was then modified geometrically to ensure uniform strain distribution through its wall thickness and along its gauge length. The new design of the specimen has a higher buckling strength and a maximum value of equivalent stress according to the maximum distortion energy theory. A cyclic function generator of the standard servo-controlled, electro-hydraulic testing machine is used to generate a specific signal shape (sine, square,…) at a certain frequency. The two independent controllers of the electronic circuit cause an independent movement to each servo-valve piston. The movement of each piston pressurizes the upper and lower sides of the actuators alternately. So, the specimen will be subjected to axial and diametral loads independent of each other. The hydraulic system has two different pressures: one pressure will be responsible for axial stress produced in the specimen and the other will be responsible for the tangential stress. Changing the two pressure ratios will change the stress ratios accordingly. The only restriction on the maximum stress obtained is the capacity of the testing system and specimen instability due to buckling.

Keywords: biaxial, fatigue, stress, testing

Procedia PDF Downloads 106

Authors: Lal Hussain, Wajid Aziz, Imtiaz Ahmed Awan, Sharjeel Saeed

Abstract:

Multiscale entropy analysis (MSE) is a useful technique recently developed to quantify the dynamics of physiological signals at different time scales. This study is aimed at investigating the electroencephalogram (EEG) signals to analyze the background activity of alcoholic and control subjects by inspecting various coarse-grained sequences formed at different time scales. EEG recordings of alcoholic and control subjects were taken from the publically available machine learning repository of University of California (UCI) acquired using 64 electrodes. The MSE analysis was performed on the EEG data acquired from all the electrodes of alcoholic and control subjects. Mann-Whitney rank test was used to find significant differences between the groups and result were considered statistically significant for p-values<0.05. The area under receiver operator curve was computed to find the degree separation between the groups. The mean ranks of MSE values at all the times scales for all electrodes were higher control subject as compared to alcoholic subjects. Higher mean ranks represent higher complexity and vice versa. The finding indicated that EEG signals acquired through electrodes C3, C4, F3, F7, F8, O1, O2, P3, T7 showed significant differences between alcoholic and control subjects at time scales 1 to 5. Moreover, all electrodes exhibit significance level at different time scales. Likewise, the highest accuracy and separation was obtained at the central region (C3 and C4), front polar regions (P3, O1, F3, F7, F8 and T8) while other electrodes such asFp1, Fp2, P4 and F4 shows no significant results.

Keywords: electroencephalogram (EEG), multiscale sample entropy (MSE), Mann-Whitney test (MMT), Receiver Operator Curve (ROC), complexity analysis

Procedia PDF Downloads 355

Authors: Khairul Zahreen Mohd Arof, Rahimah Muhamad

Abstract:

Oil palm fiber (OPF) is a fibrous material produced from the waste of palm oil industry which is suitable to be used in construction industry. The applications of OPF in concrete can reduce the material costs and enhance concrete behavior. Dog-bone test provides significant results for investigating the behavior of fiber reinforced concrete under tensile loading. It is able to provide stress-strain profile, modulus of elasticity, stress at cracking point and total crack width. In this research, dog-bone tests have been conducted to analyze total crack width, stress-strain profile, and modulus of elasticity of OPFC. Specimens are in a dog-bone shape with a long notch in the middle as compared to the end, to ensure cracks occur only within the notch. Tests were instrumented using a universal testing machine Shimadzu 300kN, a linear variable differential transformer and two strain gauges. A total of nine specimens with different fibers at fiber volume fractions of 0.75%, 1.00%, and 1.25% have been tested to analyze the behavior under tensile loading. Also, three specimens of plain concrete fiber have been tested as control specimens. The tensile test of all specimens have been carried out for concrete age exceed 28 days. It shows that OPFC able to reduce total crack width. In addition, OPFC has higher cracking stress than plain concrete. The study shows plain concrete can be improved with the addition of OPF.

Keywords: cracks, crack width, dog-bone test, oil palm fiber concrete

Procedia PDF Downloads 311

Authors: Sebastian Kölbl, Thomas Reitmaier, Mathias Hartmann

Abstract:

Trial and error approaches to adapt wearable support structures to human physiology are time consuming and elaborate. However, during preliminary design, the focus lies on understanding the interaction between exoskeleton and the human body in terms of forces and moments, namely body mechanics. For the study at hand, a multi-body simulation approach has been enhanced to evaluate actual forces and moments in a human dummy model with and without a digital mock-up of an active exoskeleton. Therefore, different motion data have been gathered and processed to perform a musculosceletal analysis. The motion data are ground reaction forces, electromyography data (EMG) and human motion data recorded with a marker-based motion capture system. Based on the experimental data, the response of the human dummy model has been calibrated. Subsequently, the scalable human dummy model, in conjunction with the motion data, is connected with the exoskeleton structure. The results of the human-machine interaction (HMI) simulation platform are in particular resulting contact forces and human joint forces to compare with admissible values with regard to the human physiology. Furthermore, it provides feedback for the sizing of the exoskeleton structure in terms of resulting interface forces (stress justification) and the effect of its compliance. A stepwise approach for the setup and validation of the modeling strategy is presented and the potential for a more time and cost-effective development of wearable support structures is outlined.

Keywords: assistive devices, ergonomic design, inverse dynamics, inverse kinematics, multibody simulation

Procedia PDF Downloads 138

Authors: Junbeom Lee, Jaehyuck Cho, Wookyeong Jeong, Jonghan Won, Jungmin Hwang, Youngseok Song, Taikyeong Jeong

Abstract:

This paper investigates and analyzes meta-learning technologies that use multiple-cameras to monitor and check abnormal behavior in people in real-time in the area of healthcare fields. Advances in artificial intelligence and computer vision technologies have confirmed that cameras can be useful for individual health monitoring and abnormal behavior detection. Through this, it is possible to establish a system that can respond early by automatically detecting abnormal behavior of the elderly, such as patients and the elderly. In this paper, we use a technique called meta-learning to analyze image data collected from cameras and develop a commercial product to determine abnormal behavior. Meta-learning applies machine learning algorithms to help systems learn and adapt quickly to new real data. Through this, the accuracy and reliability of the abnormal behavior discrimination system can be improved. In addition, this study proposes a meta-learning-based abnormal behavior detection system that includes steps such as data collection and preprocessing, feature extraction and selection, and classification model development. Various healthcare scenarios and experiments analyze the performance of the proposed system and demonstrate excellence compared to other existing methods. Through this study, we present the possibility that camera-based meta-learning technology can be useful for monitoring and testing abnormal behavior in the healthcare area.

Keywords: artificial intelligence, abnormal behavior, early detection, health monitoring

Procedia PDF Downloads 64

Authors: Yibeltal Chanie Manie, Zebider Asire Munyelet

Abstract:

5G and 6G technology offers enhanced quality of service with high data transmission rates, which necessitates the implementation of the Internet of Things (IoT) in 5G/6G architecture. In this paper, we proposed the integration of free space optical communication (FSO) with fiber sensor networks for IoT applications. Recently, free-space optical communications (FSO) are gaining popularity as an effective alternative technology to the limited availability of radio frequency (RF) spectrum. FSO is gaining popularity due to flexibility, high achievable optical bandwidth, and low power consumption in several applications of communications, such as disaster recovery, last-mile connectivity, drones, surveillance, backhaul, and satellite communications. Hence, high-speed FSO is an optimal choice for wireless networks to satisfy the full potential of 5G/6G technology, offering 100 Gbit/s or more speed in IoT applications. Moreover, machine learning must be integrated into the design, planning, and optimization of future optical wireless communication networks in order to actualize this vision of intelligent processing and operation. In addition, fiber sensors are important to achieve real-time, accurate, and smart monitoring in IoT applications. Moreover, we proposed deep learning techniques to estimate the strain changes and peak wavelength of multiple Fiber Bragg grating (FBG) sensors using only the spectrum of FBGs obtained from the real experiment.

Keywords: optical sensor, artificial Intelligence, Internet of Things, free-space optics

Procedia PDF Downloads 38

Authors: Sanghoon Shim, Jaehwan Jung, Sung-Ah Kim

Abstract:

As the digital technology develops, studies on the TUI (Tangible User Interface) that links the physical environment utilizing the human senses with the virtual environment through the computer are actively being conducted. In addition, there has been a tremendous advance in computer design making through the use of computer-aided design techniques, which enable optimized decision-making through comparison with machine learning and parallel comparison of alternatives. However, a complex design that can respond to user requirements or performance can emerge through the intuition of the designer, but it is difficult to actualize the emerged design by the designer's ability alone. Ancillary tools such as Gaudí's Sandbag can be an instrument to reinforce and evolve emerged ideas from designers. With the advent of many commercial tools that support 3D objects, designers' intentions are easily reflected in their designs, but the degree of their reflection reflects their intentions according to the proficiency of design tools. This study embodies the environment in which the form can be implemented by the fingers of the most basic designer in the initial design phase of the complex type building design. Leapmotion is used as a sensor to recognize the hand motions of the designer, and it is converted into digital information to realize an environment that can be linked in real time in virtual reality (VR). In addition, the implemented design can be linked with Rhino™, a 3D authoring tool, and its plug-in Grasshopper™ in real time. As a result, it is possible to design sensibly using TUI, and it can serve as a tool for assisting designer intuition.

Keywords: design environment, digital modeling, hand gesture, TUI, virtual reality

Procedia PDF Downloads 349

Authors: Chen Chan Wei

Abstract:

The purpose of this study was to investigate the impact of swim 1500m, 10000m run, VO2 max, and body fat on Olympic distance triathlon competition performance. The subjects were thirteen college triathletes with endurance training, with an average age, height and weight of 20.61±1.04 years (mean ± SD), 171.76±8.54 cm and 65.32±8.14 kg respectively. All subjects were required to take the tests of swim 1500m, run 10000m, VO2 max, body fat, and participate in the Olympic distance triathlon competition. First, the swim 1500m test was taken in the standardized 50m pool, with a depth of 2m, and the 10000m run test on the standardized 400m track. After three days, VO2 max was tested with the MetaMax 3B and body fat was measured with the DEXA machine. After two weeks, all 13 subjects joined the Olympic distance triathlon competition at the 2016 New Taipei City Asian Cup. The relationships between swim 1500m, 10000m run, VO2 max, body fat test, and Olympic distance triathlon competition performance were evaluated using Pearson's product-moment correlation. The results show that 10000m run and body fat had a significant positive correlation with Olympic distance triathlon performance (r=.830, .768), but VO2 max has a significant negative correlation with Olympic distance triathlon performance (r=-.735). In conclusion, for improved non-draft Olympic distance triathlon performance, triathletes should focus on running than swimming training and can be measure VO2 max to prediction triathlon performance. Also, managing body fat can improve Olympic distance triathlon performance. In addition, swimming performance was not significantly correlated to Olympic distance triathlon performance, possibly because the 2016 New Taipei City Asian Cup age group was not a drafting competition. The swimming race is the shortest component of Olympic distance triathlons. Therefore, in a non-draft competition, swimming ability is not significantly correlated with overall performance.

Keywords: triathletes, olympic, non-drafting, correlation

Procedia PDF Downloads 234

Authors: Noboru Wakamoto, Kiyotaka Obunai, Kazuya Okubo, Toru Fujii

Abstract:

The aim of this study is to moderate the dependence of counter frictional coefficient on temperature between counter surfaces and to reduce the wear of C/C composites at low temperature. To modify the C/C composites, Silica (SiO₂) powders were added into phenolic resin for carbon precursor. The preform plate of the precursor of C/C composites was prepared by conventional filament winding method. The C/C composites plates were obtained by carbonizing preform plate at 2200 °C under an argon atmosphere. At that time, the silicon carbides (SiC) were synthesized around the surfaces and the internal vacancies of the C/C composites. The frictional coefficient on the counter surfaces and specific wear volumes of the C/C composites were measured by our developed frictional test machine like pin-on disk type. The XRD indicated that SiC was synthesized in the body of C/C composite fabricated by current method. The results of friction test showed that coefficient of friction of unmodified C/C composites have temperature dependence when the test condition was changed. In contrast, frictional coefficient of the C/C composite modified with SiO₂ powders was almost constant at about 0.27 when the temperature condition was changed from Room Temperature (RT) to 300 °C. The specific wear rate decreased from 25×10^-6 mm²/N to 0.1×10^-6 mm²/N. The observations of the surfaces after friction tests showed that the frictional surface of the modified C/C composites was covered with a film produced by the friction. This study found that synthesizing SiC around surface and internal vacancies of C/C composites was effective to moderate the dependence on the frictional coefficient and reduce to the abrasion of C/C composites.

Keywords: C/C composites, friction coefficient, wear, SiC

Procedia PDF Downloads 324

Authors: Jochen Nelles, Susanne Kohns, Julia Spies, Friederike Schmitz-Buhl, Roland Thietje, Christopher Brandl, Alexander Mertens, Christopher M. Schlick

Abstract:

Industrial robots as part of highly automated manufacturing are recently developed to cooperative (light-weight) robots. This offers the opportunity of using them as assistance robots and to improve the participation in professional life of disabled or handicapped people such as tetraplegics. Robots under development are located within a cooperation area together with the working person at the same workplace. This cooperation area is an area where the robot and the working person can perform tasks at the same time. Thus, working people and robots are operating in the immediate proximity. Considering the physical restrictions and the limited mobility of tetraplegics, a hands-free robot control could be an appropriate approach for a cooperative assistance robot. To meet these requirements, the research project MeRoSy (human-robot synergy) develops methods for cooperative assistance robots based on the measurement of head movements of the working person. One research objective is to improve the participation in professional life of people with disabilities and, in particular, mobility impaired persons (e.g. wheelchair users or tetraplegics), whose participation in a self-determined working life is denied. This raises the research question, how a human-robot cooperation workplace can be designed for hands-free robot control. Here, the example of a library scenario is demonstrated. In this paper, an empirical study that focuses on the impact of head movement related stress is presented. 12 test subjects with tetraplegia participated in the study. Tetraplegia also known as quadriplegia is the worst type of spinal cord injury. In the experiment, three various basic head movements were examined. Data of the head posture were collected by a motion capture system; muscle activity was measured via surface electromyography and the subjective mental stress was assessed via a mental effort questionnaire. The muscle activity was measured for the sternocleidomastoid (SCM), the upper trapezius (UT) or trapezius pars descendens, and the splenius capitis (SPL) muscle. For this purpose, six non-invasive surface electromyography sensors were mounted on the head and neck area. An analysis of variance shows differentiated muscular strains depending on the type of head movement. Systematically investigating the influence of different basic head movements on the resulting strain is an important issue to relate the research results to other scenarios. At the end of this paper, a conclusion will be drawn and an outlook of future work will be presented.

Keywords: assistance robot, human-robot interaction, motion capture, stress-strain-concept, surface electromyography, tetraplegia

Procedia PDF Downloads 295

Authors: Chevon Fernando, Banuka Athuraliya

Abstract:

The purpose of this research is to provide a solution to the students’ time management, which usually becomes an issue because students must study and manage their personal commitments. "TimeTune," an AI-based study planner that provides an opportunity to maneuver study timeframes by incorporating modern machine learning algorithms with calendar applications, is unveiled as the ideal solution. The research is focused on the development of LSTM models that connect to the Google Calendar API in the process of developing learning paths that would be fit for a unique student's daily life experience and study history. A key finding of this research is the success in building the LSTM model to predict optimal study times, which, integrating with the real-time data of Google Calendar, will generate the timetables automatically in a personalized and customized manner. The methodology encompasses Agile development practices and Object-Oriented Analysis and Design (OOAD) principles, focusing on user-centric design and iterative development. By adopting this method, students can significantly reduce the tension associated with poor study habits and time management. In conclusion, "TimeTune" displays an advanced step in personalized education technology. The fact that its application of ML algorithms and calendar integration is quite innovative is slowly and steadily revolutionizing the lives of students. The excellence of maintaining a balanced academic and personal life is stress reduction, which the applications promise to provide for students when it comes to managing their studies.

Keywords: personalized learning, study planner, time management, calendar integration

Procedia PDF Downloads 22

Authors: Kasidis Chomrat, Nopasit Chakpitak, Anukul Tamprasirt, Annop Thananchana

Abstract:

Internet of Things devices or IoT and Edge Computing has become one of the biggest things happening in innovations and one of the most discussed of the potential to improve and disrupt traditional business and industry alike. With rises of new hang cliff challenges like COVID-19 pandemic that posed a danger to workforce and business process of the system. Along with drastically changing landscape in business that left ruined aftermath of global COVID-19 pandemic, looming with the threat of global energy crisis, global warming, more heating global politic that posed a threat to become new Cold War. How emerging technology like edge computing and usage of specialized design visual processing units will be great opportunities for business. The literature reviewed on how the internet of things and disruptive wave will affect business, which explains is how all these new events is an effect on the current business and how would the business need to be adapting to change in the market and world, and example test benchmarking for consumer marketed of newer devices like the internet of things devices equipped with new edge computing devices will be increase efficiency and reducing posing a risk from a current and looming crisis. Throughout the whole paper, we will explain the technologies that lead the present technologies and the current situation why these technologies will be innovations that change the traditional practice through brief introductions to the technologies such as cloud computing, edge computing, Internet of Things and how it will be leading into future.

Keywords: internet of things, edge computing, machine learning, pattern recognition, image classification

Procedia PDF Downloads 134

Authors: Bongs Lainjo

Abstract:

Educational institutions and authorities that are mandated to run education systems in various countries need to implement a curriculum that considers the possibility and existence of elementary school dropouts. This research focuses on elementary school dropout rates and the ability to replicate various predictive models carried out globally on selected Elementary Schools. The study was carried out by comparing the classical case studies in Africa, North America, South America, Asia and Europe. Some of the reasons put forward for children dropping out include the notion of being successful in life without necessarily going through the education process. Such mentality is coupled with a tough curriculum that does not take care of all students. The system has completely led to poor school attendance - truancy which continuously leads to dropouts. In this study, the focus is on developing a model that can systematically be implemented by school administrations to prevent possible dropout scenarios. At the elementary level, especially the lower grades, a child's perception of education can be easily changed so that they focus on the better future that their parents desire. To deal effectively with the elementary school dropout problem, strategies that are put in place need to be studied and predictive models are installed in every educational system with a view to helping prevent an imminent school dropout just before it happens. In a competency-based curriculum that most advanced nations are trying to implement, the education systems have wholesome ideas of learning that reduce the rate of dropout.

Keywords: elementary school, predictive models, machine learning, risk factors, data mining, classifiers, dropout rates, education system, competency-based curriculum

Procedia PDF Downloads 150

Authors: Li Xu, Huanbao Jiang, Zhenfei Huang, Lailai Zhang

Abstract:

In recent years, as global warming, the sea-ice extent of North Arctic undergoes an evident decrease and Arctic channel has attracted the attention of shipping industry. Ice crystals existing in the seawater of Arctic channel which enter the seawater system of the ship with the seawater were found blocking the seawater pipe. The appearance of cooler paralysis, auxiliary machine error and even ship power system paralysis may be happened if seriously. In order to reduce the effect of high temperature in auxiliary equipment, seawater system will use external ice-water to participate in the cooling cycle and achieve the state of its flow. The distribution of ice crystals in seawater pipe can be achieved. As the ice slurry system is solid liquid two-phase system, the flow process of ice-water mixture is very complex and diverse. In this paper, the flow process in seawater pipe of ice slurry is simulated with fluid dynamics simulation software based on k-ε turbulence model. As the ice packing fraction is a key factor effecting the distribution of ice crystals, the influence of ice packing fraction on the flowing process of ice slurry is analyzed. In this work, the simulation results show that as the ice packing fraction is relatively large, the distribution of ice crystals is uneven in the flowing process of the seawater which has such disadvantage as increase the possibility of blocking, that will provide scientific forecasting methods for the forming of ice block in seawater piping system. It has important significance for the reliability of the operating of polar ships in the future.

Keywords: ice slurry, seawater pipe, ice packing fraction, numerical simulation

Procedia PDF Downloads 349

Authors: Julia Ive, Lucia Specia

Abstract:

Understanding and detecting toxicity is an important problem to support safer human interactions online. Our work focuses on the important problem of contextual toxicity detection, where automated classifiers are tasked with determining whether a short textual segment (usually a sentence) is toxic within its conversational context. We use “toxicity” as an umbrella term to denote a number of variants commonly named in the literature, including hate, abuse, offence, among others. Detecting toxicity in context is a non-trivial problem and has been addressed by very few previous studies. These previous studies have analysed the influence of conversational context in human perception of toxicity in controlled experiments and concluded that humans rarely change their judgements in the presence of context. They have also evaluated contextual detection models based on state-of-the-art Deep Learning and Natural Language Processing (NLP) techniques. Counterintuitively, they reached the general conclusion that computational models tend to suffer performance degradation in the presence of context. We challenge these empirical observations by devising better contextual predictive models that also rely on NLP data augmentation techniques to create larger and better data. In our study, we start by further analysing the human perception of toxicity in conversational data (i.e., tweets), in the absence versus presence of context, in this case, previous tweets in the same conversational thread. We observed that the conclusions of previous work on human perception are mainly due to data issues: The contextual data available does not provide sufficient evidence that context is indeed important (even for humans). The data problem is common in current toxicity datasets: cases labelled as toxic are either obviously toxic (i.e., overt toxicity with swear, racist, etc. words), and thus context does is not needed for a decision, or are ambiguous, vague or unclear even in the presence of context; in addition, the data contains labeling inconsistencies. To address this problem, we propose to automatically generate contextual samples where toxicity is not obvious (i.e., covert cases) without context or where different contexts can lead to different toxicity judgements for the same tweet. We generate toxic and non-toxic utterances conditioned on the context or on target tweets using a range of techniques for controlled text generation(e.g., Generative Adversarial Networks and steering techniques). On the contextual detection models, we posit that their poor performance is due to limitations on both of the data they are trained on (same problems stated above) and the architectures they use, which are not able to leverage context in effective ways. To improve on that, we propose text classification architectures that take the hierarchy of conversational utterances into account. In experiments benchmarking ours against previous models on existing and automatically generated data, we show that both data and architectural choices are very important. Our model achieves substantial performance improvements as compared to the baselines that are non-contextual or contextual but agnostic of the conversation structure.

Keywords: contextual toxicity detection, data augmentation, hierarchical text classification models, natural language processing

Procedia PDF Downloads 143

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Electricity prices have sophisticated features such as high volatility, nonlinearity and high frequency that make forecasting quite difficult. Electricity price has a volatile and non-random character so that, it is possible to identify the patterns based on the historical data. Intelligent decision-making requires accurate price forecasting for market traders, retailers, and generation companies. So far, many shallow-ANN (artificial neural networks) models have been published in the literature and showed adequate forecasting results. During the last years, neural networks with many hidden layers, which are referred to as DNN (deep neural networks) have been using in the machine learning community. The goal of this study is to investigate electricity price forecasting performance of the shallow-ANN and DNN models for the Turkish day-ahead electricity market. The forecasting accuracy of the models has been evaluated with publicly available data from the Turkish day-ahead electricity market. Both shallow-ANN and DNN approach would give successful result in forecasting problems. Historical load, price and weather temperature data are used as the input variables for the models. The data set includes power consumption measurements gathered between January 2016 and December 2017 with one-hour resolution. In this regard, forecasting studies have been carried out comparatively with shallow-ANN and DNN models for Turkish electricity markets in the related time period. The main contribution of this study is the investigation of different shallow-ANN and DNN models in the field of electricity price forecast. All models are compared regarding their MAE (Mean Absolute Error) and MSE (Mean Square) results. DNN models give better forecasting performance compare to shallow-ANN. Best five MAE results for DNN models are 0.346, 0.372, 0.392, 0,402 and 0.409.

Keywords: deep learning, artificial neural networks, energy price forecasting, turkey

Procedia PDF Downloads 272

Authors: Hugo Sampaio Libero, Max de Castro Magalhaes

Abstract:

The perception of sound radiated from a building floor is greatly influenced by the rooms in which it is immersed and by the position of both listener and source. The main question that remains unanswered is related to the influence of the source position on the sound power radiated by a complex wall-floor system in buildings. This research is concerned with the investigation of vibration transmission across walls and floors in buildings. It is primarily based on the determination of vibration reduction index via experimental tests. Knowledge of this parameter may help in predicting noise and vibration propagation in building components. First, the physical mechanisms involving vibration transmission across structural junctions are described. An experimental setup is performed to aid this investigation. The experimental tests have shown that the vibration generation in the walls and floors is directed related to their size and boundary conditions. It is also shown that the vibration source position can affect the overall vibration spectrum significantly. Second, the characteristics of the noise spectra inside the rooms due to an impact source (tapping machine) are also presented. Conclusions are drawn for the general trend of vibration and noise spectrum of the structural components and rooms, respectively. In summary, the aim of this paper is to investigate the vibro-acoustical behavior of building floors and walls under floor impact excitation. The impact excitation was at distinct positions on the slab. The analysis has highlighted the main physical characteristics of the vibration transmission mechanism.

Keywords: vibration transmission, vibration reduction index, impact excitation, experimental tests

Procedia PDF Downloads 75

Authors: Rao Fu, Jie Chen, Shutian Zeng, Yiping Zhuang, Agus Sudjianto

Abstract:

Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.

Keywords: conditional generative adversarial net, market and credit risk management, neural network, time series

Procedia PDF Downloads 120