Search results for: temporal convolutional net

Authors: Saurav Kumar Suman, P. Karthigayani

Abstract:

In this paper the height of the tree is estimated and forest types is classified from the multi temporal RISAT-1 Horizontal-Horizontal (HH) and Horizontal-Vertical (HV) Polarised Satellite Aperture Radar (SAR) data. The novelty of the proposed project is combined use of the Back-scattering Coefficients (Sigma Naught) and the Coherence. It uses Water Cloud Model (WCM). The approaches use two main steps. (a) Extraction of the different forest parameter data from the Product.xml, BAND-META file and from Grid-xxx.txt file come with the HH & HV polarized data from the ISRO (Indian Space Research Centre). These file contains the required parameter during height estimation. (b) Calculation of the Vegetation and Ground Backscattering, Coherence and other Forest Parameters. (c) Classification of Forest Types using the ENVI 5.0 Tool and ROI (Region of Interest) calculation.

Keywords: RISAT-1, classification, forest, SAR data

Procedia PDF Downloads 376

Authors: Rohit Semwal, Shivam Arora, Saurav, Sangita Roy

Abstract:

This work proposes a supervised framework with deep convolutional neural networks (CNNs) for vision-based sign language recognition of static gestures. Our approach addresses the acquisition and segmentation of correct inputs for the CNN-based classifier. Microsoft Kinect™ sensor, despite complex environmental conditions, can track hands efficiently. Skin Colour based segmentation is applied on cropped images of hands in different poses, used to depict different sign language gestures. The segmented hand images are used as an input for our classifier. The CNN classifier proposed in the paper is able to classify the input images with a high degree of accuracy. The system was trained and tested on 39 static sign language gestures, including 26 letters of the alphabet and 13 commonly used words. This paper includes a problem definition for building the proposed system, which acts as a sign language translator between deaf/mute and the rest of the society. It is then followed by a focus on reviewing existing knowledge in the area and work done by other researchers. It also describes the working principles behind different components of CNNs in brief. The architecture and system design specifications of the proposed system are discussed in the subsequent sections of the paper to give the reader a clear picture of the system in terms of the capability required. The design then gives the top-level details of how the proposed system meets the requirements.

Keywords: sign language, CNN, HCI, segmentation

Procedia PDF Downloads 120

Authors: Nicholas Freer

Abstract:

Rhythmic complexity in progressive metal is a developing area of analysis, particularly the interpretation of hyper-metric time spans as hierarchically significant rhythmic units of compositional organisation (Pieslak 2007, Charupakorn 2012, Capuzzo 2018, Calder 2018, Lucas 2018, Hannan 2020). This paper adds to this developing area by considering the relationships between the concepts of tactus, metric imposition, polymeter and rhythmic parallax in the Meshuggah composition “Do Not Look Down”. By considering an architectonic rhythmic framework within “Do Not Look Down” as the controlling organisation mechanism, an exploration of the interaction between distinct rhythmic layers and the composition’s formal segmentation and harmony (as riffs), reveals a pervasive structural misalignment between these elements. By exhibiting how Meshuggah’s manipulations of rhythmic complexities deliberately blur structural boundaries, creating misalignments in a flat approach to temporal partitioning (Nieto 2014), rhythmic characteristics of Meshuggah and the genre of Djent are exposed.

Keywords: hypermeter, rhythmic parallax, meshuggah, temporal partitioning

Procedia PDF Downloads 53

Authors: Yuchien Lin

Abstract:

This study attempted to investigate the changes in electroencephalography (EEG) and emotion regulation following eight-week inward-attention meditation training program. The subjects were 24 adults without meditation experiences divided into meditation and control groups. The quantitatively analyzed changes in psychophysiological parameters during inward-attention meditation, and evaluated the emotion scores assessed by the State-Trait Anxiety Inventory (STAI), the Positive and Negative Affect Schedule (PANAS), and the Emotion Regulation Scale (ERS). The results were found: (1) During meditation, significant EEG increased for theta-band activity in the frontal and the bilateral temporal areas, for alpha-band activity in the left and central frontal areas, and for gamma-band activity in the left frontal and the left temporal areas. (2) The meditation group had significantly higher positive affect in posttest than in pretest. (3) There was no significant difference in the changes of EEG spectral characteristics and emotion scores in posttest and pretest for the control group. In the present study, a unique meditative concentration task with a constant level of moderate mental effort focusing on the center of brain was used, so as to enhance frontal midline theta, alpha, and gamma-band activity. These results suggest that this mental training allows individual reach a specific mental state of relaxed but focused awareness. The gamma-band activity, in particular, enhanced over left frontoparietal area may suggest that inward-attention meditation training involves temporal integrative mechanisms and may induce short-term and long-term emotion regulation abilities.

Keywords: meditation, EEG, emotion regulation, gamma activity

Procedia PDF Downloads 186

Authors: Hsiao-Lan Wang, Chun-Han Chiang, I-Chen Chen

Abstract:

In Chinese Mandarin, lexical tones play an important role to provide contrasts in word meaning. They are pitch patterns and can be quantified as the fundamental frequency (F0), expressed in Hertz (Hz). In this study, we aim to investigate the influence of frequency discrimination on Chinese children’s performance of reading abilities. Fifty participants from 3rd to 4th grades, including 24 children with reading difficulties and 26 age-matched children, were examined. A serial of cognitive, language, reading and psychoacoustic tests were administrated. Magnetoencephalography (MEG) was also employed to study children’s auditory sensitivity. In the present study, auditory frequency was measured through slide-up pitch, slide-down pitch and frequency-modulated tone. The results showed that children with Chinese reading difficulties were significantly poor at phonological awareness and auditory discrimination for the identification of frequency-modulated tone. Chinese children’s character reading performance was significantly related to lexical tone awareness and auditory perception of frequency-modulated tone. In our MEG measure, we compared the mismatch negativity (MMNm), from 100 to 200 ms, in two groups. There were no significant differences between groups during the perceptual discrimination of standard sounds, fast-up and fast-down frequencies. However, the data revealed significant cluster differences between groups in the slow-up and slow-down frequencies discrimination. In the slow-up stimulus, the cluster demonstrated an upward field map at 106-151 ms (p < .001) with a strong peak time at 127ms. The source analyses of two dipole model and localization resolution model (CLARA) from 100 to 200 ms both indicated a strong source from the left temporal area with 45.845% residual variance. Similar results were found in the slow-down stimulus with a larger upward current at 110-142 ms (p < 0.05) and a peak time at 117 ms in the left temporal area (47.857% residual variance). In short, we found a significant group difference in the MMNm while children processed frequency-modulated tones with slow temporal changes. The findings may imply that perception of sound frequency signals with slower temporal modulations was related to reading and language development in Chinese. Our study may also support the recent hypothesis of underlying non-verbal auditory temporal deficits accounting for the difficulties in literacy development seen developmental dyslexia.

Keywords: Chinese Mandarin, frequency modulation sweeps, magnetoencephalography, mismatch negativity, reading difficulties

Procedia PDF Downloads 551

Authors: Zeinab Jafari A., Ali Sharifnezhad B., Mohammad Razi C., Mohammad Haghpanahi D., Arash Maghsoudi

Abstract:

Background and Objective: Sports-related rupture of the anterior cruciate ligament (ACL) and following injuries have been associated with various disorders, such as long-lasting changes in muscle activation patterns in athletes, which might last after ACL reconstruction (ACLR). The rupture of the ACL might result in abnormal patterns of movement execution, extending the treatment period and delaying athletes’ return to sports (RTS). As ACL injury is especially prevalent among athletes, the lengthy treatment process and athletes’ absence from sports are of great concern to athletes and coaches. Thus, estimating safe time of RTS is of crucial importance. Therefore, using a deep neural network (DNN) to classify the health levels of ACL in injured athletes, this study aimed to estimate the safe time for athletes to return to competitions. Methods: Ten athletes with ACLR and fourteen healthy controls participated in this study. Three health levels of ACL were defined: healthy, six-month post-ACLR surgery and nine-month post-ACLR surgery. Athletes with ACLR were tested six and nine months after the ACLR surgery. During the course of this study, surface electromyography (sEMG) signals were recorded from five knee muscles, namely Rectus Femoris (RF), Vastus Lateralis (VL), Vastus Medialis (VM), Biceps Femoris (BF), Semitendinosus (ST), during single-leg drop landing (SLDL) and forward hopping (SLFH) tasks. The Pseudo-Wigner-Ville distribution (PWVD) was used to produce three-dimensional (3-D) images of the energy distribution patterns of sEMG signals. Then, these 3-D images were converted to two-dimensional (2-D) images implementing the heat mapping technique, which were then fed to a deep convolutional neural network (DCNN). Results: In this study, we estimated the safe time of RTS by designing a DCNN classifier with an accuracy of 90 %, which could classify ACL into three health levels. Discussion: The findings of this study demonstrate the potential of the DCNN classification technique using sEMG signals in estimating RTS time, which will assist in evaluating the recovery process of ACLR in athletes.

Keywords: anterior cruciate ligament reconstruction, return to sports, surface electromyography, deep convolutional neural network

Procedia PDF Downloads 48

Authors: Dongju Kim, Youngjoo Suh, Hyojin Kim, Gyeongyeong Kim

Abstract:

Acoustic Emission Testing (AET) is widely used to test the structural integrity of an operational hydrogen storage container, and clustering algorithms are frequently used in pattern recognition methods to interpret AET results. However, the interpretation of AET results can vary from user to user as the tuning of the relevant parameters relies on the user's experience and knowledge of AET. Therefore, it is necessary to use a deep learning model to identify patterns in acoustic emission (AE) signal data that can be used to classify defects instead. In this paper, a deep learning-based model for classifying the types of defects in hydrogen storage tanks, using AE sensor waveforms, is proposed. As hydrogen storage tanks are commonly constructed using carbon fiber reinforced polymer composite (CFRP), a defect classification dataset is collected through a tensile test on a specimen of CFRP with an AE sensor attached. The performance of the classification model, using one-dimensional convolutional neural network (1-D CNN) and synthetic minority oversampling technique (SMOTE) data augmentation, achieved 91.09% accuracy for each defect. It is expected that the deep learning classification model in this paper, used with AET, will help in evaluating the operational safety of hydrogen storage containers.

Keywords: acoustic emission testing, carbon fiber reinforced polymer composite, one-dimensional convolutional neural network, smote data augmentation

Procedia PDF Downloads 66

Authors: Sushish Baral, Pratibha Joshi, Yaman Maharjan

Abstract:

Glaucoma is a chronic eye condition that causes vision loss that is irreversible. Early detection and treatment are critical to prevent vision loss because it can be asymptomatic. For the identification of glaucoma, multiple deep learning algorithms are used. Transformer-based architectures, which use the self-attention mechanism to encode long-range dependencies and acquire extremely expressive representations, have recently become popular. Convolutional architectures, on the other hand, lack knowledge of long-range dependencies in the image due to their intrinsic inductive biases. The aforementioned statements inspire this thesis to look at transformer-based solutions and investigate the viability of adopting transformer-based network designs for glaucoma detection. Using retinal fundus images of the optic nerve head to develop a viable algorithm to assess the severity of glaucoma necessitates a large number of well-curated images. Initially, data is generated by augmenting ocular pictures. After that, the ocular images are pre-processed to make them ready for further processing. The system is trained using pre-processed images, and it classifies the input images as normal or glaucoma based on the features retrieved during training. The Vision Transformer (ViT) architecture is well suited to this situation, as it allows the self-attention mechanism to utilise structural modeling. Extensive experiments are run on the common dataset, and the results are thoroughly validated and visualized.

Keywords: glaucoma, vision transformer, convolutional architectures, retinal fundus images, self-attention, deep learning

Procedia PDF Downloads 167

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

Pedestrian detection in image or video data is a very important and challenging task in security surveillance. The difficulty of this task is to locate and detect pedestrians of different scales in complex scenes accurately. To solve these problems, a deep neural network (RT-YOLOv3) is proposed to realize real-time pedestrian detection at different scales in security monitoring. RT-YOLOv3 improves the traditional YOLOv3 algorithm. Firstly, the deep residual network is added to extract vehicle features. Then six convolutional neural networks with different scales are designed and fused with the corresponding scale feature maps in the residual network to form the final feature pyramid to perform pedestrian detection tasks. This method can better characterize pedestrians. In order to further improve the accuracy and generalization ability of the model, a hybrid pedestrian data set training method is used to extract pedestrian data from the VOC data set and train with the INRIA pedestrian data set. Experiments show that the proposed RT-YOLOv3 method achieves 93.57% accuracy of mAP (mean average precision) and 46.52f/s (number of frames per second). In terms of accuracy, RT-YOLOv3 performs better than Fast R-CNN, Faster R-CNN, YOLO, SSD, YOLOv2, and YOLOv3. This method reduces the missed detection rate and false detection rate, improves the positioning accuracy, and meets the requirements of real-time detection of pedestrian objects.

Keywords: pedestrian detection, feature detection, convolutional neural network, real-time detection, YOLOv3

Procedia PDF Downloads 115

Authors: Milagros Jaén-Vargas, Javier García Martínez, Karla Miriam Reyes Leiva, María Fernanda Trujillo-Guerrero, Francisco Fernandes, Sérgio Barroso Gonçalves, Miguel Tavares Silva, Daniel Simões Lopes, José Javier Serrano Olmedo

Abstract:

Human Activity Recognition (HAR) is having a growing impact in creating new applications and is responsible for emerging new technologies. Also, the use of wearable sensors is an important key to exploring the human body's behavior when performing activities. Hence, the use of these dispositive is less invasive and the person is more comfortable. In this study, a database that includes three activities is used. The activities were acquired from inertial measurement unit sensors (IMU) and motion capture systems (MOCAP). The main objective is differentiating the performance from four Deep Learning (DL) models: Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and hybrid model Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), when considering acceleration, velocity and position and evaluate if integrating the IMU acceleration to obtain velocity and position represent an increment in performance when it works as input to the DL models. Moreover, compared with the same type of data provided by the MOCAP system. Despite the acceleration data is cleaned when integrating, results show a minimal increase in accuracy for the integrated signals.

Keywords: HAR, IMU, MOCAP, acceleration, velocity, position, feature maps

Procedia PDF Downloads 57

Authors: Diamant Irene, Dar Tamar

Abstract:

Burnout, conceptualized within the framework of stress research, is to a large extent a result of a threat on resources of time or a feeling of time shortage. In reaction to numerous tasks, deadlines, high output, management of different duties encompassing work-home conflicts, many individuals experience ‘time pressure’. Time pressure is characterized as the perception of a lack of available time in relation to the amount of workload. It can be a result of local objective constraints, but it can also be a chronic attribute in coping with life. As such, time pressure is associated in the literature with general stress experience and can therefore be a direct, contributory burnout factor. The present study examines the relation of chronic time pressure – feeling of time shortage and of being rushed, with another central aspect in subjective temporal experience - time perspective. Time perspective is a stable personal disposition, capturing the extent to which people subjectively remember the past, live the present and\or anticipate the future. Based on Hobfoll’s Conservation of Resources Theory, it was hypothesized that individuals with chronic time pressure would experience a permanent threat on their time resources resulting in relatively increased burnout. In addition, it was hypothesized that different time perspective profiles, based on Zimbardo’s typology of five dimensions – Past Positive, Past Negative, Present Hedonistic, Present Fatalistic, and Future, would be related to different magnitudes of chronic time pressure and of burnout. We expected that individuals with ‘Past Negative’ or ‘Present Fatalist’ time perspectives would experience more burnout, with chronic time pressure being a moderator variable. Conversely, individuals with a ‘Present Hedonistic’ - with little concern with the future consequences of actions, would experience less chronic time pressure and less burnout. Another temporal experience angle examined in this study is the difference between the actual distribution of time (as in a typical day) versus desired distribution of time (such as would have been distributed optimally during a day). It was hypothesized that there would be a positive correlation between the gap between these time distributions and chronic time pressure and burnout. Data was collected through an online self-reporting survey distributed on social networks, with 240 participants (aged 21-65) recruited through convenience and snowball sampling methods from various organizational sectors. The results of the present study support the hypotheses and constitute a basis for future debate regarding the elements of burnout in the modern work environment, with an emphasis on subjective temporal experience. Our findings point to the importance of chronic and stable temporal experiences, as time pressure and time perspective, in occupational experience. The findings are also discussed with a view to the development of practical methods of burnout prevention.

Keywords: conservation of resources, burnout, time pressure, time perspective

Procedia PDF Downloads 146

Authors: Tianhao Zhang, Cen Chen, Dawei Cheng, Yuqi Liang, Yuanyuan Liang

Abstract:

Dealing with anomalies is a crucial preprocessing step for multivariate time series prediction. However, existing methods that separate anomaly preprocessing and model training into two stages have certain limitations. Specifically, these methods fail to leverage auxiliary information necessary to distinguish latent anomalies related to spatiotemporal factors during the preprocessing stage. Instead, they solely rely on data distribution for detection which may lead to incorrect processing of many samples that are beneficial for training. To address this, we propose STTS-EAD, an end-to-end method that seamlessly integrates anomaly detection into the training process of multivariate time series forecasting and aims to improve Spatio-Temporal learning based Time Series prediction via Embedded Anomaly Detection. Our proposed STTS-EAD leverages spatio-temporal information for forecasting and anomaly detection, with the two parts alternately executed and optimized for each other. To the best of our knowledge, STTS-EAD is the first to integrate anomaly detection and forecasting tasks in the training phase for improving the accuracy of multivariate time series forecasting. Extensive experiments on a public stock dataset and two real-world sales datasets from a renowned coffee chain enterprise show that our proposed method can effectively process detected anomalies in the training stage to improve forecasting performance in the inference stage and significantly outperform baselines.

Keywords: multivariate time series, anomaly detection, time series forecasting, spatiotemporal feature learning

Procedia PDF Downloads 13

Authors: Jyoti Rani, Ashima Anand, Shivendra Shivani

Abstract:

In recent years, physiological signals obtained in telemedicine have been stored independently from patient information. In addition, people have increasingly turned to mobile devices for information on health-related topics. Major authentication and security issues may arise from this storing, degrading the reliability of diagnostics. This study introduces an approach to reversible watermarking, which ensures security by utilizing the electrocardiogram (ECG) signal as a carrier for embedding patient information. In the proposed work, Pan-Tompkins++ is employed to convert the 1D ECG signal into a 2D signal. The frequency subbands of a signal are extracted using RDWT(Redundant discrete wavelet transform), and then one of the subbands is subjected to MSVD (Multiresolution singular valued decomposition for masking. Finally, the encrypted watermark is embedded within the signal. The experimental results show that the watermarked signal obtained is indistinguishable from the original signals, ensuring the preservation of all diagnostic information. In addition, the DnCNN (Denoising convolutional neural network) concept is used to denoise the retrieved watermark for improved accuracy. The proposed ECG signal-based watermarking method is supported by experimental results and evaluations of its effectiveness. The results of the robustness tests demonstrate that the watermark is susceptible to the most prevalent watermarking attacks.

Keywords: ECG, VMD, watermarking, PanTompkins++, RDWT, DnCNN, MSVD, chaotic encryption, attacks

Procedia PDF Downloads 62

Authors: Hongyun Li, Zhibin Jiang

Abstract:

The travel of passengers in the urban rail transit network is influenced by changes in network structure and operational status, and the response of individual travel preferences to these changes also varies. Firstly, the influence of the suspension of urban rail transit line sections on passenger travel along the line is analyzed. Secondly, passenger travel trajectories containing multi-dimensional semantics are described based on network UD data. Next, passenger panel data based on spatio-temporal sequences is constructed to achieve frequent passenger clustering. Then, the Graph Convolutional Network (GCN) is used to model and identify the changes in travel modes of different types of frequent passengers. Finally, taking Shanghai Metro Line 11 as an example, the travel behavior patterns of frequent passengers after the Huaqiao section shutdown during the COVID-19 epidemic are analyzed. The results showed that after the section shutdown, most passengers would transfer to the nearest Anting station for boarding, while some passengers would transfer to other stations for boarding or cancel their travels directly. Among the passengers who transferred to Anting station for boarding, most of passengers maintained the original normalized travel mode, a small number of passengers waited for a few days before transferring to Anting station for boarding, and only a few number of passengers stopped traveling at Anting station or transferred to other stations after a few days of boarding on Anting station. The results can provide a basis for understanding urban rail transit passenger travel patterns and improving the accuracy of passenger flow prediction in abnormal operation scenarios.

Keywords: urban rail transit, section shutdown, frequent passenger, travel behavior pattern

Procedia PDF Downloads 52

Authors: Aurore Cauquis, Philippe Heinrich, Mario Ricchiuto, Audrey Gailler

Abstract:

In this talk, we look for an accurate time scheme to model the propagation of waves. Several numerical schemes have been developed to solve the extended weakly nonlinear weakly dispersive Boussinesq Equations. The temporal schemes used are two Lax-Wendroff schemes, second or third order accurate, two Runge-Kutta schemes of second and third order and a simplified third order accurate Lax-Wendroff scheme. Spatial derivatives are evaluated with fourth order accuracy. The numerical model is applied to two monodimensional benchmarks on a flat bottom. It is also applied to the simulation of the Algerian tsunami generated by a Mw=6 seism on the 18th March 2021. The tsunami propagation was highly dispersive and propagated across the Mediterranean Sea. We study here the effects of the order of temporal discretization on the accuracy of the results and on the time of computation.

Keywords: numerical analysis, tsunami propagation, water wave, boussinesq equations

Procedia PDF Downloads 205

Authors: Navya Saira George, Patroba Achola Odera

Abstract:

This study aims to determine spatio-temporal expansion of Kochi City, situated on the west coast of Kerala State in India. Remote sensing and GIS techniques have been used to determine land use/cover and urban expansion of the City. Classification of Landsat images of the years 1973, 1988, 2002 and 2018 have been used to reproduce a visual story of the growth of the City over a period of 45 years. Accuracy range of 0.79 ~ 0.86 is achieved with kappa coefficient range of 0.69 ~ 0.80. Results show that the areas covered by vegetation and water bodies decreased progressively from 53.0 ~ 30.1% and 34.1 ~ 26.2% respectively, while built-up areas increased steadily from 12.5 to 42.2% over the entire study period (1973 ~ 2018). The shift in land use from agriculture to non-agriculture may be attributed to the land reforms since 1980s.

Keywords: Geographical Information Systems, Kochi City, Land use/cover, Remote Sensing, Urban Sprawl

Procedia PDF Downloads 106

Authors: A. Er-Raki, D. Hartmann, J. P. Belaud, S. Negny

Abstract:

This paper has a double purpose: firstly, a literature review of the life cycle analysis (LCA) and secondly a comparison between conventional (static) LCA and multi-level dynamic LCA on the following items: (i) inventories evolution with time (ii) temporal evolution of the databases. The first part of the paper summarizes the state of the art of the static LCA approach. The different static LCA limits have been identified and especially the non-consideration of the spatial and temporal evolution in the inventory, for the characterization factors (FCs) and into the databases. Then a description of the different levels of integration of the notion of temporality in life cycle analysis studies was made. In the second part, the dynamic inventory has been evaluated firstly for a single nuclear plant and secondly for the entire French nuclear power fleet by taking into account the construction durations of all the plants. In addition, the databases have been adapted by integrating the temporal variability of the French energy mix. Several iterations were used to converge towards the real environmental impact of the energy mix. Another adaptation of the databases to take into account the temporal evolution of the market data of the raw material was made. An identification of the energy mix of the time studied was based on an extrapolation of the production reference values of each means of production. An application to the construction of the French nuclear power plants from 1971 to 2000 has been performed, in which a dynamic inventory of raw material has been evaluated. Then the impacts were characterized by the ILCD 2011 characterization method. In order to compare with a purely static approach, a static impact assessment was made with the V 3.4 Ecoinvent data sheets without adaptation and a static inventory considering that all the power stations would have been built at the same time. Finally, a comparison between static and dynamic LCA approaches was set up to determine the gap between them for each of the two levels of integration. The results were analyzed to identify the contribution of the evolving nuclear power fleet construction to the total environmental impacts of the French energy mix during the same period. An equivalent strategy using a dynamic approach will further be applied to identify the environmental impacts that different scenarios of the energy transition could bring, allowing to choose the best energy mix from an environmental viewpoint.

Keywords: LCA, static, dynamic, inventory, construction, nuclear energy, energy mix, energy transition

Procedia PDF Downloads 81

Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa

Abstract:

A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.

Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever

Procedia PDF Downloads 83

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

Abstract:

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

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

Procedia PDF Downloads 69

Authors: Vinay C. Doranalu, Amba Shetty

Abstract:

In recent days due to climate change, there is a large variation in spatial distribution of daily rainfall within a small region. Rainfall is one of the main end climatic variables which affect spatio-temporal patterns of water availability. The real task postured by the change in climate is identification, estimation and understanding the uncertainty of rainfall. This study intended to analyze the spatial variations and temporal trends of daily precipitation using high resolution (0.25º x 0.25º) gridded data of Indian Meteorological Department (IMD). For the study, 38 grid points were selected in the study area and analyzed for daily precipitation time series (113 years) over the period 1901-2013. Grid points were divided into two zones based on the elevation and situated location of grid points: Low Land (exposed to sea and low elevated area/ coastal region) and High Land (Interior from sea and high elevated area/western Ghats). Time series were applied to examine the spatial analysis and temporal trends in each grid points by non-parametric Mann-Kendall test and Theil-Sen estimator to perceive the nature of trend and magnitude of slope in trend of rainfall. Pettit-Mann-Whitney test is applied to detect the most probable change point in trends of the time period. Results have revealed remarkable monotonic trend in each grid for daily precipitation of the time series. In general, by the regional cluster analysis found that increasing precipitation trend in shoreline region and decreasing trend in Western Ghats from recent years. Spatial distribution of rainfall can be partly explained by heterogeneity in temporal trends of rainfall by change point analysis. The Mann-Kendall test shows significant variation as weaker rainfall towards the rainfall distribution over eastern parts of the Western Ghats region of Karnataka.

Keywords: change point analysis, coastal region India, gridded rainfall data, non-parametric

Procedia PDF Downloads 265

Authors: M. Dagim Yoseph, M. K. Savage, A. D. Jolly, C. J. Ebinger

Abstract:

Whakaari/White Island has been the most active New Zealand volcano in the 21st century, producing small phreatic and phreatomagmatic eruptions, which are hard to predict. The most recent eruption occurred in 2019, tragically claiming the lives of 22 individuals and causing numerous injuries. We employed shear-wave splitting analyses to investigate variations in anisotropy between 2018 and 2020, during quiescence, unrest, and the eruption. We examined spatial and temporal variations in 3499 shear-wave splitting and 2656 V_p/V_s ratio measurements. Comparing shear-wave splitting parameters from similar earthquake paths across different times indicates that the observed temporal changes are unlikely to result from variations in earthquake paths through media with spatial variability. Instead, these changes may stem from variations in anisotropy over time, likely caused by changes in crack alignment due to stress or varying fluid content.

Keywords: background seismic waves, fast orientations, seismic anisotropy, V_p/V_s ratio

Procedia PDF Downloads 14

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

The assessment of disease levels in crop fields is an important and time-consuming task that generally relies on expert knowledge of trained individuals. Image classification in agriculture problems historically has been based on classical machine learning strategies that make use of hand-engineered features in the top of a classification algorithm. This approach tends to not produce results with high accuracy and generalization to the classes classified by the system when the nature of the elements has a significant variability. The advent of deep convolutional neural networks has revolutionized the field of machine learning, especially in computer vision tasks. These networks have great resourcefulness of learning and have been applied successfully to image classification and object detection tasks in the last years. The objective of this work was to propose a new method based on deep learning convolutional neural networks towards the task of disease level monitoring. Common RGB images of winter wheat were obtained during a growing season. Five categories of disease levels presence were produced, in collaboration with agronomists, for the algorithm classification. Disease level tasks performed by experts provided ground truth data for the disease score of the same winter wheat plots were RGB images were acquired. The system had an overall accuracy of 84% on the discrimination of the disease level classes.

Keywords: crop disease assessment, deep learning, precision agriculture, residual neural networks

Procedia PDF Downloads 297

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 189

Authors: Mohamed Lotfy, Ghada Soliman

Abstract:

Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes. This paper presents an approach for recognizing Arabic digits printed in dot matrix format. The proposed model is based on Convolutional Neural Networks (CNN) that take the dot matrix as input and generate embeddings that are rounded to generate binary representations of the digits. The binary embeddings are then used to perform Optical Character Recognition (OCR) on the digit images. To overcome the challenge of the limited availability of dotted Arabic expiration date images, we developed a True Type Font (TTF) for generating synthetic images of Arabic dot-matrix characters. The model was trained on a synthetic dataset of 3287 images and 658 synthetic images for testing, representing realistic expiration dates from 2019 to 2027 in the format of yyyy/mm/dd. Our model achieved an accuracy of 98.94% on the expiry date recognition with Arabic dot matrix format using fewer parameters and less computational resources than traditional CNN-based models. By investigating and presenting our findings comprehensively, we aim to contribute substantially to the field of OCR and pave the way for advancements in Arabic dot-matrix character recognition. Our proposed approach is not limited to Arabic dot matrix digit recognition but can also be extended to text recognition tasks, such as text classification and sentiment analysis.

Keywords: computer vision, pattern recognition, optical character recognition, deep learning

Procedia PDF Downloads 51

Authors: Frederik Calsius, Mirela Popa, Alexia Briassouli

Abstract:

In the field of machine learning, it is common practice to use benchmark datasets to prove the working of a method. The domain of action recognition in videos often uses datasets like Kinet-ics, Something-Something, UCF-101 and HMDB-51 to report results. Considering the properties of the datasets, there are no datasets that focus solely on very short clips (2 to 3 seconds), and on highly-similar fine-grained actions within one specific domain. This paper researches how current state-of-the-art action recognition methods perform on a dataset that consists of highly similar, fine-grained actions. To do so, a dataset of skateboarding tricks was created. The performed analysis highlights both benefits and limitations of state-of-the-art methods, while proposing future research directions in the activity recognition domain. The conducted research shows that the best results are obtained by fusing RGB data with OpenPose data for the Temporal Shift Module.

Keywords: activity recognition, fused deep representations, fine-grained dataset, temporal modeling

Procedia PDF Downloads 202

Authors: Ronak Khosravi, Mahmood Abbasi Layegh, Siamak Haghipour, Avin Esmaili

Abstract:

In this paper, a study on classification of musical woodwind instruments using a small set of features selected from a broad range of extracted ones by the sequential forward selection method was carried out. Firstly, we extract 42 features for each record in the music database of 402 sound files belonging to five different groups of Flutes (end blown and internal duct), Single –reed, Double –reed (exposed and capped), Triple reed and Quadruple reed. Then, the sequential forward selection method is adopted to choose the best feature set in order to achieve very high classification accuracy. Two different classification techniques of support vector machines and relevance vector machines have been tested out and an accuracy of up to 96% can be achieved by using 21 time, frequency and coefficient features and relevance vector machine with the Gaussian kernel function.

Keywords: coefficient features, relevance vector machines, spectral features, support vector machines, temporal features

Procedia PDF Downloads 288

Authors: Gulfam Haider, sana danish

Abstract:

Convolutional Neural Networks (CNNs) have emerged as powerful tools for image classification, and the choice of optimizers profoundly affects their performance. The study of optimizers and their adaptations remains a topic of significant importance in machine learning research. While numerous studies have explored and advocated for various optimizers, the efficacy of these optimization techniques is still subject to scrutiny. This work aims to address the challenges surrounding the effectiveness of optimizers by conducting a comprehensive analysis and evaluation. The primary focus of this investigation lies in examining the performance of different optimizers when employed in conjunction with the popular activation function, Rectified Linear Unit (ReLU). By incorporating ReLU, known for its favorable properties in prior research, the aim is to bolster the effectiveness of the optimizers under scrutiny. Specifically, we evaluate the adjustment of these optimizers with both the original Softmax activation function and the modified ReLU activation function, carefully assessing their impact on overall performance. To achieve this, a series of experiments are conducted using a well-established benchmark dataset for image classification tasks, namely the Canadian Institute for Advanced Research dataset (CIFAR-10). The selected optimizers for investigation encompass a range of prominent algorithms, including Adam, Root Mean Squared Propagation (RMSprop), Adaptive Learning Rate Method (Adadelta), Adaptive Gradient Algorithm (Adagrad), and Stochastic Gradient Descent (SGD). The performance analysis encompasses a comprehensive evaluation of the classification accuracy, convergence speed, and robustness of the CNN models trained with each optimizer. Through rigorous experimentation and meticulous assessment, we discern the strengths and weaknesses of the different optimization techniques, providing valuable insights into their suitability for image classification tasks. By conducting this in-depth study, we contribute to the existing body of knowledge surrounding optimizers in CNNs, shedding light on their performance characteristics for image classification. The findings gleaned from this research serve to guide researchers and practitioners in making informed decisions when selecting optimizers and activation functions, thus advancing the state-of-the-art in the field of image classification with convolutional neural networks.

Keywords: deep neural network, optimizers, RMsprop, ReLU, stochastic gradient descent

Procedia PDF Downloads 66

Authors: Ani Thomas

Abstract:

Every narrative is a temporal construct. Every narrative creates a qualitative experience of time for the viewer. The paper argues for the concept of a qualified time that emerges from the interaction between the narrative and the audience. The paper also challenges the conventional understanding of narrative time as either story time, real time or discourse time. Looking at narratives through the medium of Cinema, the study examines how narratives create and manipulate duration or durée, the qualitative experience of time as theorized by Henri Bergson. The paper further analyzes how Cinema and, by extension, narratives are nothing but Durée and the filmmaker, the artist of durée, who shape and manipulate the perception and emotions of the viewer through the manipulation and construction of durée. The paper draws on cinematic works to look at the techniques to demonstrate how filmmakers use, for example, editing, sound, compositional and production narratives etc., to create various modes of durée that challenge, amplify or unsettle the viewer’s sense of time. Bringing together the Viewer’s durée and exploring its interaction with the narrative construct, the paper explores the emergence of the new qualitative time, the narrative durée, that defines the audience experience.

Keywords: cinema, time, bergson, duree

Procedia PDF Downloads 123

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 65

Authors: Muhammad Arslan Usman, Muhammad Rehan Usman, Soo Young Shin

Abstract:

Live video streaming is one of the most widely used service among end users, yet it is a big challenge for the network operators in terms of quality. The only way to provide excellent Quality of Experience (QoE) to the end users is continuous monitoring of live video streaming. For this purpose, there are several objective algorithms available that monitor the quality of the video in a live stream. Subjective tests play a very important role in fine tuning the results of objective algorithms. As human perception is considered to be the most reliable source for assessing the quality of a video stream, subjective tests are conducted in order to develop more reliable objective algorithms. Temporal impairments in a live video stream can have a negative impact on the end users. In this paper we have conducted subjective evaluation tests on a set of video sequences containing temporal impairment known as frame freezing. Frame Freezing is considered as a transmission error as well as a hardware error which can result in loss of video frames on the reception side of a transmission system. In our subjective tests, we have performed tests on videos that contain a single freezing event and also for videos that contain multiple freezing events. We have recorded our subjective test results for all the videos in order to give a comparison on the available No Reference (NR) objective algorithms. Finally, we have shown the performance of no reference algorithms used for objective evaluation of videos and suggested the algorithm that works better. The outcome of this study shows the importance of QoE and its effect on human perception. The results for the subjective evaluation can serve the purpose for validating objective algorithms.

Keywords: objective evaluation, subjective evaluation, quality of experience (QoE), video quality assessment (VQA)

Procedia PDF Downloads 580