Search results for: audio segmentation

Authors: Behnaz Sohani, Sahand Shahalinezhad, Amir Rahmani, Aliyu Aliyu

Abstract:

Recently, medical imaging and specifically medical image processing is becoming one of the most dynamically developing areas of medical science. It has led to the emergence of new approaches in terms of the prevention, diagnosis, and treatment of various diseases. In the process of diagnosis of lung cancer, medical professionals rely on computed tomography (CT) scans, in which failure to correctly identify masses can lead to incorrect diagnosis or sampling of lung tissue. Identification and demarcation of masses in terms of detecting cancer within lung tissue are critical challenges in diagnosis. In this work, a segmentation system in image processing techniques has been applied for detection purposes. Particularly, the use and validation of a novel lung cancer detection algorithm have been presented through simulation. This has been performed employing CT images based on multilevel thresholding. The proposed technique consists of segmentation, feature extraction, and feature selection and classification. More in detail, the features with useful information are selected after featuring extraction. Eventually, the output image of lung cancer is obtained with 96.3% accuracy and 87.25%. The purpose of feature extraction applying the proposed approach is to transform the raw data into a more usable form for subsequent statistical processing. Future steps will involve employing the current feature extraction method to achieve more accurate resulting images, including further details available to machine vision systems to recognise objects in lung CT scan images.

Keywords: lung cancer detection, image segmentation, lung computed tomography (CT) images, medical image processing

Procedia PDF Downloads 64

Authors: Yun Chen, Qihang Liu, Catherine Ticehurst, Chandrama Sarker, Fazlul Karim, Dave Penton, Ashmita Sengupta

Abstract:

The application of ICESAT-2 altimetry data in river hydrology critically depends on the accuracy of the mean water surface elevation (WSE) at a virtual station (VS) where satellite observations intersect with water. The ICESAT-2 track generates multiple VSs as it crosses the different water bodies. The difficulties are particularly pronounced in large river basins where there are many tributaries and meanders often adjacent to each other. One challenge is to split photon segments along a beam to accurately partition them to extract only the true representative water height for individual elements. As far as we can establish, there is no automated procedure to make this distinction. Earlier studies have relied on human intervention or river masks. Both approaches are unsatisfactory solutions where the number of intersections is large, and river width/extent changes over time. We describe here an automated approach called “auto-segmentation”. The accuracy of our method was assessed by comparison with river water level observations at 10 different stations on 37 different dates along the Lower Murray River, Australia. The congruence is very high and without detectable bias. In addition, we compared different outlier removal methods on the mean WSE calculation at VSs post the auto-segmentation process. All four outlier removal methods perform almost equally well with the same R2 value (0.998) and only subtle variations in RMSE (0.181–0.189m) and MAE (0.130–0.142m). Overall, the auto-segmentation method developed here is an effective and efficient approach to deriving accurate mean WSE at river VSs. It provides a much better way of facilitating the application of ICESAT-2 ATL13 altimetry to rivers compared to previously reported studies. Therefore, the findings of our study will make a significant contribution towards the retrieval of hydraulic parameters, such as water surface slope along the river, water depth at cross sections, and river channel bathymetry for calculating flow velocity and discharge from remotely sensed imagery at large spatial scales.

Keywords: lidar sensor, virtual station, cross section, mean water surface elevation, beam/track segmentation

Procedia PDF Downloads 35

Authors: Y. Trantafyllou, C. Alexandraki

Abstract:

Music interpretation accounts to the way musicians shape their performance by deliberately deviating from composers’ intentions, which are commonly communicated via some form of music transcription, such as a music score. For transcribed and non-improvised music, music expression is manifested by introducing subtle deviations in tempo, dynamics and articulation during the evolution of performance. This paper presents an application, named FlameCens, which, given two recordings of the same piece of music, presumably performed by different musicians, allow visualising deviations in tempo and dynamics during playback. The application may also compare a certain performance to the music score of that piece (i.e. MIDI file), which may be thought of as an expression-neutral representation of that piece, hence depicting the expressive queues employed by certain performers. FlameCens uses the Dynamic Time Warping algorithm to compare two audio sequences, based on CENS (Chroma Energy distribution Normalized Statistics) audio features. Expressive deviations are illustrated in a moving flame, which is generated by an animation of particles. The length of the flame is mapped to deviations in dynamics, while the slope of the flame is mapped to tempo deviations so that faster tempo changes the slope to the right and slower tempo changes the slope to the left. Constant slope signifies no tempo deviation. The detected deviations in tempo and dynamics can be additionally recorded in a text file, which allows for offline investigation. Moreover, in the case of monophonic music, the color of particles is used to convey the pitch of the notes during performance. FlameCens has been implemented in Python and it is openly available via GitHub. The application has been experimentally validated for different music genres including classical, contemporary, jazz and popular music. These experiments revealed that FlameCens can be a valuable tool for music specialists (i.e. musicians or musicologists) to investigate the expressive performance strategies employed by different musicians, as well as for music audience to enhance their listening experience.

Keywords: audio synchronization, computational music analysis, expressive music performance, information visualization

Procedia PDF Downloads 107

Authors: Safak Isik, Ozalp Vayvay

Abstract:

Strategic partnerships with suppliers play a vital role for the long-term value-based supply chain. This strategic collaboration keeps still being one of the top priority of many business organizations in order to create more additional value; benefiting mainly from supplier’s specialization, capacity and innovative power, securing supply and better managing costs and quality. However, many organizations encounter difficulties in initiating, developing and managing those partnerships and many attempts result in failures. One of the reasons for such failure is the incompatibility of members of this partnership or in other words wrong supplier selection which emphasize the significance of the selection process since it is the beginning stage. An effective selection process of strategic suppliers is critical to the success of the partnership. Although there are several research studies to select the suppliers in literature, only a few of them is related to strategic supplier selection for long-term partnership. The purpose of this study is to propose a conceptual model for the selection of strategic partnership suppliers. A two-stage approach has been used in proposed model incorporating first segmentation and second selection. In the first stage; considering the fact that not all suppliers are strategically equal and instead of a long list of potential suppliers, Kraljic’s purchasing portfolio matrix can be used for segmentation. This supplier segmentation is the process of categorizing suppliers based on a defined set of criteria in order to identify types of suppliers and determine potential suppliers for strategic partnership. In the second stage, from a pool of potential suppliers defined at first phase, a comprehensive evaluation and selection can be performed to finally define strategic suppliers considering various tangible and intangible criteria. Since a long-term relationship with strategic suppliers is anticipated, criteria should consider both current and future status of the supplier. Based on an extensive literature review; strategical, operational and organizational criteria have been determined and elaborated. The result of the selection can also be used to determine suppliers who are not ready for a partnership but to be developed for strategic partnership. Since the model is based on multiple criteria for both stages, it provides a framework for further utilization of Multi-Criteria Decision Making (MCDM) techniques. The model may also be applied to a wide range of industries and involve managerial features in business organizations.

Keywords: Kraljic’s matrix, purchasing portfolio, strategic supplier selection, supplier collaboration, supplier partnership, supplier segmentation

Procedia PDF Downloads 219

Authors: A. Bensaid, T. Mostephaoui, R. Nedjai

Abstract:

A considerable area of Algerian lands is threatened by the phenomenon of wind erosion. For a long time, wind erosion and its associated harmful effects on the natural environment have posed a serious threat, especially in the arid regions of the country. In recent years, as a result of increases in the irrational exploitation of natural resources (fodder) and extensive land clearing, wind erosion has particularly accentuated. The extent of degradation in the arid region of the Algerian Mecheria department generated a new situation characterized by the reduction of vegetation cover, the decrease of land productivity, as well as sand encroachment on urban development zones. In this study, we attempt to investigate the potential of remote sensing and geographic information systems for detecting the spatial dynamics of the ancient dune cords based on the numerical processing of LANDSAT images (5, 7, and 8) of three scenes 197/37, 198/36 and 198/37 for the year 2020. As a second step, we prospect the use of geospatial techniques to monitor the progression of sand dunes on developed (urban) lands as well as on the formation of sandy accumulations (dune, dunes fields, nebkha, barkhane, etc.). For this purpose, this study made use of the semi-automatic processing method for the dynamic segmentation of images with very high spatial resolution (SENTINEL-2 and Google Earth). This study was able to demonstrate that urban lands under current conditions are located in sand transit zones that are mobilized by the winds from the northwest and southwest directions.

Keywords: land development, GIS, segmentation, remote sensing

Procedia PDF Downloads 124

Authors: Jessica Chorostecki, Aashka Shah, Fen Bao, Ginny Bao, Edwin George, Navid Seraji-Bozorgzad, Veronica Gorden, Christina Caon, Elliot Frohman

Abstract:

Background: Parkinson’s Disease (PD) is a neuro degenerative disorder associated with the loss of dopaminergic cells and the presence α-synuclein (AS) aggregation in of Lewy bodies. Both dopaminergic cells and AS are found in the retina. Optical coherence tomography (OCT) allows high-resolution in-vivo examination of retinal structure injury in neuro degenerative disorders including PD. Methods: We performed a cross-section OCT study in patients with definite PD and healthy controls (HC) using Spectral Domain SD-OCT platform to measure the peripapillary retinal nerve fiber layer (pRNFL) thickness and total macular volume (TMV). We performed intra-retinal segmentation with fully automated segmentation software to measure the volume of the RNFL, ganglion cell layer (GCL), inner plexiform layer (IPL), inner nuclear layer (INL), outer plexiform layer (OPL), and the outer nuclear layer (ONL). Segmentation was performed blinded to the clinical status of the study participants. Results: 101 eyes from 52 PD patients (mean age 65.8 years) and 46 eyes from 24 HC subjects (mean age 64.1 years) were included in the study. The mean pRNFL thickness was not significantly different (96.95 μm vs 94.42 μm, p=0.07) but the TMV was significantly lower in PD compared to HC (8.33 mm3 vs 8.58 mm3 p=0.0002). Intra-retinal segmentation showed no significant difference in the RNFL volume between the PD and HC groups (0.95 mm3 vs 0.92 mm3 p=0.454). However, GCL, IPL, INL, and ONL volumes were significantly reduced in PD compared to HC. In contrast, the volume of OPL was significantly increased in PD compared to HC. Conclusions: Our finding of the enlarged OPL corresponds with mRNA expression studies showing localization of AS in the OPL across vertebrate species and autopsy studies demonstrating AS aggregation in the deeper layers of retina in PD. We propose that the enlargement of the OPL may represent a potential biomarker of AS aggregation in PD. Longitudinal studies in larger cohorts are warranted to confirm our observations that may have significant implications in disease monitoring and therapeutic development.

Keywords: Optical Coherence Tomography, biomarker, Parkinson's disease, alpha-synuclein, retina

Procedia PDF Downloads 414

Authors: Elias Nemer, Greg Vines

Abstract:

Time-frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training networks on frequency features such as the Mel-Spectrogram or Cochleogram have been proven more effective and convenient than training on-time samples. In practical realizations, these features are created on a different processor and/or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with different features. In this paper, we provide a PyTorch framework for creating various spectral features as well as time-frequency transformation and time-domain filter-banks using the built-in trainable conv1d() layer. This allows computing these features on the fly as part of a larger network and enabling easier experimentation with various combinations and parameters. Our work extends the work in the literature developed for that end: First, by adding more of these features and also by allowing the possibility of either starting from initialized kernels or training them from random values. The code is written as a template of classes and scripts that users may integrate into their own PyTorch classes or simply use as is and add more layers for various applications.

Keywords: neural networks Mel-Spectrogram, chromagram, cochleogram, discrete Fourrier transform, PyTorch conv1d()

Procedia PDF Downloads 201

Authors: Lamees Nasser, Yago Diez, Robert Martí, Joan Martí, Ibrahim Sadek

Abstract:

Automated 3D breast ultrasound (ABUS) screening is a novel modality in medical imaging because of its common characteristics shared with other ultrasound modalities in addition to the three orthogonal planes (i.e., axial, sagittal, and coronal) that are useful in analysis of tumors. In the literature, few automatic approaches exist for typical tasks such as segmentation or registration. In this work, we deal with two problems concerning ABUS images: nipple and rib detection. Nipple and ribs are the most visible and salient features in ABUS images. Determining the nipple position plays a key role in some applications for example evaluation of registration results or lesion follow-up. We present a nipple detection algorithm based on color and shape of the nipple, besides an automatic approach to detect the ribs. In point of fact, rib detection is considered as one of the main stages in chest wall segmentation. This approach consists of four steps. First, images are normalized in order to minimize the intensity variability for a given set of regions within the same image or a set of images. Second, the normalized images are smoothed by using anisotropic diffusion filter. Next, the ribs are detected in each slice by analyzing the eigenvalues of the 3D Hessian matrix. Finally, a breast mask and a probability map of regions detected as ribs are used to remove false positives (FP). Qualitative and quantitative evaluation obtained from a total of 22 cases is performed. For all cases, the average and standard deviation of the root mean square error (RMSE) between manually annotated points placed on the rib surface and detected points on rib borders are 15.1188 mm and 14.7184 mm respectively.

Keywords: Automated 3D Breast Ultrasound, Eigenvalues of Hessian matrix, Nipple detection, Rib detection

Procedia PDF Downloads 307

Authors: Suparman

Abstract:

Piecewise polynomial regression model is very flexible model for modeling the data. If the piecewise polynomial regression model is matched against the data, its parameters are not generally known. This paper studies the parameter estimation problem of piecewise polynomial regression model. The method which is used to estimate the parameters of the piecewise polynomial regression model is Bayesian method. Unfortunately, the Bayes estimator cannot be found analytically. Reversible jump MCMC algorithm is proposed to solve this problem. Reversible jump MCMC algorithm generates the Markov chain that converges to the limit distribution of the posterior distribution of piecewise polynomial regression model parameter. The resulting Markov chain is used to calculate the Bayes estimator for the parameters of piecewise polynomial regression model.

Keywords: piecewise regression, bayesian, reversible jump MCMC, segmentation

Procedia PDF Downloads 345

Authors: Joseph M. Rich, Vinay A. Duddalwar, Assad A. Oberai

Abstract:

Prostate adenocarcinoma is the most common cancer in males, with osseous metastases as the commonest site of metastatic prostate carcinoma (mPC). Treatment monitoring is based on the evaluation and characterization of lesions on multiple imaging studies, including Computed Tomography (CT). Monitoring of the osseous disease burden, including follow-up of lesions and identification and characterization of new lesions, is a laborious task for radiologists. Deep learning algorithms are increasingly used to perform tasks such as identification and segmentation for osseous metastatic disease and provide accurate information regarding metastatic burden. Here, nnUNet was used to produce a model which can segment CT scan images of prostate adenocarcinoma vertebral bone metastatic lesions. nnUNet is an open-source Python package that adds optimizations to deep learning-based UNet architecture but has not been extensively combined with transfer learning techniques due to the absence of a readily available functionality of this method. The IRB-approved study data set includes imaging studies from patients with mPC who were enrolled in clinical trials at the University of Southern California (USC) Health Science Campus and Los Angeles County (LAC)/USC medical center. Manual segmentation of metastatic lesions was completed by an expert radiologist Dr. Vinay Duddalwar (20+ years in radiology and oncologic imaging), to serve as ground truths for the automated segmentation. Despite nnUNet’s success on some medical segmentation tasks, it only produced an average Dice Similarity Coefficient (DSC) of 0.31 on the USC dataset. DSC results fell in a bimodal distribution, with most scores falling either over 0.66 (reasonably accurate) or at 0 (no lesion detected). Applying more aggressive data augmentation techniques dropped the DSC to 0.15, and reducing the number of epochs reduced the DSC to below 0.1. Datasets have been identified for transfer learning, which involve balancing between size and similarity of the dataset. Identified datasets include the Pancreas data from the Medical Segmentation Decathlon, Pelvic Reference Data, and CT volumes with multiple organ segmentations (CT-ORG). Some of the challenges of producing an accurate model from the USC dataset include small dataset size (115 images), 2D data (as nnUNet generally performs better on 3D data), and the limited amount of public data capturing annotated CT images of bone lesions. Optimizations and improvements will be made by applying transfer learning and generative methods, including incorporating generative adversarial networks and diffusion models in order to augment the dataset. Performance with different libraries, including MONAI and custom architectures with Pytorch, will be compared. In the future, molecular correlations will be tracked with radiologic features for the purpose of multimodal composite biomarker identification. Once validated, these models will be incorporated into evaluation workflows to optimize radiologist evaluation. Our work demonstrates the challenges of applying automated image segmentation to small medical datasets and lays a foundation for techniques to improve performance. As machine learning models become increasingly incorporated into the workflow of radiologists, these findings will help improve the speed and accuracy of vertebral metastatic lesions detection.

Keywords: deep learning, image segmentation, medicine, nnUNet, prostate carcinoma, radiomics

Procedia PDF Downloads 71

Authors: Douglas W. Scott

Abstract:

The Allemande from J. S. Bach's Partita for solo flute (BWV 1013) presents many unique challenges for any flautist, especially in terms of segmentation analysis required to select breathing places in the first half. Without claiming to identify a 'correct' solution to this problem, this paper analyzes the section in terms of a set of techniques based around a statistical property commonly (if not ubiquitously) found in music, namely Zipf’s law. Specifically, the paper considers violations of this expected profile at various levels of analysis, an approach which has yielded interesting insights in previous studies. The investigation is then grounded by considering four actual solutions to the problem found in recordings made by different flautists, which opens up the possibility of expanding Zipfian analysis to include a consideration of inter-onset-intervals (IOIs). It is found that significant deviations from the expected Zipfian distributions can reveal and highlight stylistic choices made by different performers.

Keywords: inter-onset-interval, Partita for solo flute, BWV 1013, segmentation analysis, Zipf’s law

Procedia PDF Downloads 152

Authors: Indu ray

Abstract:

In today’s digital world the internet is already flooded with information on how to master grammar in a foreign language. It is well known that one cannot master a language without grammar. Grammar is the backbone of any language. Without grammar there would be no structure to help you speak/write or listen/read. Successful communication is only possible if the form and function of linguistic utterances are firmly related to one another. Grammar has its own rules of use to formulate an easier-to-understand language. Like a tool, grammar formulates our thoughts and knowledge in a meaningful way. Every language has its own grammar. With grammar, we can quickly analyze whether there is any action in this text: (Present, past, future). Knowledge of grammar is an important prerequisite for mastering a foreign language. What’s most important is how teachers can make grammar lessons more interesting for students and thus promote grammar skills more successfully. Through this paper, we discuss a few important methods like (Interactive Grammar Exercises between students, Interactive Grammar Exercise between student to teacher, Grammar translation method, Audio -Visual Method, Deductive Method, Inductive Method). This paper is divided into two sections. In the first part, brief definitions and principles of these approaches will be provided. Then the possibility and the case of combination of this approach will be analyzed. In the last section of the paper, I would like to present a survey result conducted at my university on a few methods to quickly learn grammar in Foreign Language. We divided the Grammatical Skills in six Parts. 1.Grammatical Competence 2. Speaking Skills 3. Phonology 4. The syntax and the Semantics 5. Rule 6. Cognitive Function and conducted a survey among students. From our survey results, we can observe that phonology, speaking ability, syntax and semantics can be improved by inductive method, Audio-visual Method, and grammatical translation method, for grammar rules and cognitive functions we should choose IGE (teacher-student) method. and the IGE method (pupil-pupil). The study’s findings revealed, that the teacher delivery Methods should be blend or fusion based on the content of the Grammar.

Keywords: innovative method, grammatical skills, audio-visual, translation

Procedia PDF Downloads 46

Authors: Mohit Modi, Rajiv Kumar, Manojraj Saxena, G. Ravi Shankar

Abstract:

Change detection of coastal ecosystem plays a vital role in monitoring and managing natural resources along the coastal regions. The present study mainly focuses on the decadal change in Kochi islands connecting the urban flatland areas and the coastal regions where sand deposits have taken place. With this, in view, the change detection has been monitored in the Kochi area to apprehend the urban growth and industrialization leading to decrease in the wetland ecosystem. The region lies between 76°11'19.134"E to 76°25'42.193"E and 9°52'35.719"N to 10°5'51.575"N in the south-western coast of India. The IRS LISS-IV satellite image has been processed using a rule-based algorithm to classify the LULC and to interpret the changes between 2005 & 2015. The approach takes two steps, i.e. extracting features as a single GIS vector layer using different parametric values and to dissolve them. The multi-resolution segmentation has been carried out on the scale ranging from 10-30. The different classes like aquaculture, agricultural land, built-up, wetlands etc. were extracted using parameters like NDVI, mean layer values, the texture-based feature with corresponding threshold values using a rule set algorithm. The objects obtained in the segmentation process were visualized to be overlaying the satellite image at a scale of 15. This layer was further segmented using the spectral difference segmentation rule between the objects. These individual class layers were dissolved in the basic segmented layer of the image and were interpreted in vector-based GIS programme to achieve higher accuracy. The result shows a rapid increase in an industrial area of 40% based on industrial area statistics of 2005. There is a decrease in wetlands area which has been converted into built-up. New roads have been constructed which are connecting the islands to urban areas as well as highways. The increase in coastal region has been visualized due to sand depositions. The outcome is well supported by quantitative assessments which will empower rich understanding of land use land cover change for appropriate policy intervention and further monitoring.

Keywords: land use land cover, multiresolution segmentation, NDVI, object based classification

Procedia PDF Downloads 163

Authors: Nihad Alem

Abstract:

Nowadays, distance learning (DL) is widely perceived as a reformed type of education that takes advantage of technology to give more appealing opportunities especially for learners whose life conditions impede their attendance to regular classrooms however, creating interactional environment for students to expand their learning community and alleviate the feeling of loneliness and isolation should receive more attention when designing a distance learning course. This research aims to explore whether the audio/video peer learning can offer pedagogical add-ons to the Algerian distance learners and what are the pros and cons of its application as an educational experience in a synchronous environment mediated by Skype. Data were collected using video recordings of six sessions, reflective logs, and in-depth semi-structured interviews and will be analyzed by qualitatively identifying and measuring the three constitutional elements of the educational experience of peer learning namely the social presence, the cognitive presence, and the facilitation presence using a modified community of inquiry coding template. The findings from this study will provide recommendations for effective peer learning educational experience using the facilitation presence concept.

Keywords: audio/visual peer learning, community of inquiry, distance learning, facilitation presence

Procedia PDF Downloads 118

Authors: Sadeq Al Yaari, Muhammad Alkhunayn, Adham Al Yaari, Aayah Al Yaari, Montaha Al Yaari, Ayman Al Yaari, Sajedah Al Yaari, Fatehi Eissa

Abstract:

The recent rise of smart educational aids and the move away from traditional listening aids are leading to a fundamental shift in the way in which individuals with attention and listening problems (ALP) manipulate listening inputs and/or act appropriately to the spoken information presented to them. A total sample of twenty-six ALP pupils (m=20 and f=6) between 7-12 years old was selected from different strata based on gender, region and school. In the sample size, thirteen (10 males and 3 females) received the treatment in terms of smart classes provided with smart educational aids in a listening course that lasted for four months, while others did not (they studied the same course by the same instructor but in ordinary class). A pretest was administered to assess participants’ levels, and a posttest was given to evaluate their attention and listening comprehension performance, namely in phonetic and phonological tests with sociolinguistic themes that have been designed for this purpose. Test results were analyzed both psychoneurolinguistically and statistically. Results reveal a remarkable change in pupils’ behavioral listening where scores witnessed a significant difference in the performance of the experimental ALP group in the pretest compared to the posttest (Pupils performed better at the pretest-posttest on phonetics than at the two tests on phonology). It is concluded that smart educational aids designed for listening skills help not only increase the listening command of pupils with ALP to understand what they listen to but also develop their interactive listening capability and, at the same rate, are responsible for increasing concentrated and in-depth listening capacity. Plus, ALP pupils become able to grasp the audio content of text recordings, including educational audio recordings, news, oral stories and tales, views, spiritual/religious text and general knowledge. However, the pupils have not experienced individual smart audio-visual aids that connect listening to other language receptive and productive skills, which could be the future area of research.

Keywords: smart aids, attention, listening, problems

Procedia PDF Downloads 12

Authors: Haoqi Gao, Koichi Ogawara

Abstract:

Retinal vascular segmentation of color fundus is the basis of ophthalmic computer-aided diagnosis and large-scale disease screening systems. Early screening of fundus diseases has great value for clinical medical diagnosis. The traditional methods depend on the experience of the doctor, which is time-consuming, labor-intensive, and inefficient. Furthermore, medical images are scarce and fraught with legal concerns regarding patient privacy. In this paper, we propose a new Generative Adversarial Network based on CycleGAN for retinal fundus images. This method can generate not only synthetic fundus images but also generate corresponding segmentation masks, which has certain application value and challenge in computer vision and computer graphics. In the results, we evaluate our proposed method from both quantitative and qualitative. For generated segmented images, our method achieves dice coefficient of 0.81 and PR of 0.89 on DRIVE dataset. For generated synthetic fundus images, we use ”Toy Experiment” to verify the state-of-the-art performance of our method.

Keywords: retinal vascular segmentations, generative ad-versarial network, cyclegan, fundus images

Procedia PDF Downloads 115

Authors: Sadeq Al Yaari, Muhammad Alkhunayn, Adham Al Yaari, Ayah Al Yaari, Ayman Al Yaari, Montaha Al Yaari, Sajedah Al Yaari, Fatehi Eissa

Abstract:

The recent rise of smart educational aids and the move away from traditional listening aids are leading to a fundamental shift in the way in which individuals with attention and listening problems (ALP) manipulate listening inputs and/or act appropriately to the spoken information presented to them. A total sample of twenty-six ALP pupils (m=20 and f=6) between 7-12 years old was selected from different strata based on gender, region and school. In the sample size, thirteen (10 males and 3 females) received the treatment in terms of smart classes provided with smart educational aids in a listening course that lasted for four months, while others did not (they studied the same course by the same instructor but in ordinary class). A pretest was administered to assess participants’ levels, and a posttest was given to evaluate their attention and listening comprehension performance, namely in phonetic and phonological tests with sociolinguistic themes that have been designed for this purpose. Test results were analyzed both psychoneurolinguistically and statistically. Results reveal a remarkable change in pupils’ behavioral listening where scores witnessed a significant difference in the performance of the experimental ALP group in the pretest compared to the posttest (Pupils performed better at the pretest-posttest on phonetics than at the two tests on phonology). It is concluded that smart educational aids designed for listening skills help not only increase the listening command of pupils with ALP to understand what they listen to but also develop their interactive listening capability and, at the same rate, are responsible for increasing concentrated and in-depth listening capacity. Plus, ALP pupils become able to grasp the audio content of text recordings, including educational audio recordings, news, oral stories and tales, views, spiritual/religious text and general knowledge. However, the pupils have not experienced individual smart audio-visual aids that connect listening to other language receptive and productive skills, which could be the future area of research.

Keywords: smart educational aids, listening attention, pupils, problems

Procedia PDF Downloads 12

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 125

Authors: Xiaoxiao Li, Shuangcheng Jia, Qian Li

Abstract:

Keypoint detection has always been a challenge in the field of image recognition. This paper proposes a novelty keypoint detection method which is called Multi-Scale Feature Fusion Convolutional Network with Attention (MFFCNA). We verified that the multi-scale features with the attention mechanism module have better feature expression capability. The feature fusion between different scales makes the information that the network model can express more abundant, and the network is easier to converge. On our self-made street sign corner dataset, we validate the MFFCNA model with an accuracy of 97.8% and a recall of 81%, which are 5 and 8 percentage points higher than the HRNet network, respectively. On the COCO dataset, the AP is 71.9%, and the AR is 75.3%, which are 3 points and 2 points higher than HRNet, respectively. Extensive experiments show that our method has a remarkable improvement in the keypoint recognition tasks, and the recognition effect is better than the existing methods. Moreover, our method can be applied not only to keypoint detection but also to image classification and semantic segmentation with good generality.

Keywords: keypoint detection, feature fusion, attention, semantic segmentation

Procedia PDF Downloads 97

Authors: Chun-Min Lin, Yuh-Jen Wu, Ching-Ting Chung

Abstract:

The formulation of tourism policies requires objective academic research and evidence as support, especially research from local academia. Taiwan is a small island, and its economic growth relies heavily on tourism revenue. Taiwanese government has been devoting to the promotion of the tourism industry over the past few decades. Scientific research outcomes by Taiwanese scholars may and will help lay the foundations for drafting future tourism policy by the government. In this study, a total of 120 full journal articles published between 2008 and 2016 from the Journal of Tourism and Leisure Studies (JTSL) were examined to explore the scientific research trend of tourism study in Taiwan. JTSL is one of the most important Taiwanese journals in the tourism discipline which focuses on tourism-related issues and uses traditional Chinese as the study language. The method of co-word analysis from bibliometrics approaches was employed for semantic analysis in this study. When analyzing Chinese words and phrases, word segmentation analysis is a crucial step. It must be carried out initially and precisely in order to obtain meaningful word or word chunks for further frequency calculation. A word segmentation system basing on N-gram algorithm was developed in this study to conduct semantic analysis, and 100 groups of meaningful phrases with the highest recurrent rates were located. Subsequently, co-word analysis was employed for semantic classification. The results showed that the themes of tourism research in Taiwan in recent years cover the scope of tourism education, environmental protection, hotel management, information technology, and senior tourism. The results can give insight on the related issues and serve as a reference for tourism-related policy making and follow-up research.

Keywords: bibliometrics, co-word analysis, word segmentation, tourism research, policy

Procedia PDF Downloads 206

Authors: Jaiden Xuan Schraut, Leon Liu, Yiqiao Yin

Abstract:

Computer vision in medical diagnosis has achieved a high level of success in diagnosing diseases with high accuracy. However, conventional classifiers that produce an image to-label result provides insufficient information for medical professionals to judge and raise concerns over the trust and reliability of a model with results that cannot be explained. In order to gain local insight into cancerous regions, separate tasks such as imaging segmentation need to be implemented to aid the doctors in treating patients, which doubles the training time and costs which renders the diagnosis system inefficient and difficult to be accepted by the public. To tackle this issue and drive AI-first medical solutions further, this paper proposes a multi-output network that follows a U-Net architecture for image segmentation output and features an additional convolutional neural networks (CNN) module for auxiliary classification output. Class activation maps are a method of providing insight into a convolutional neural network’s feature maps that leads to its classification but in the case of lung diseases, the region of interest is enhanced by U-net-assisted Class Activation Map (CAM) visualization. Therefore, our proposed model combines image segmentation models and classifiers to crop out only the lung region of a chest X-ray’s class activation map to provide a visualization that improves the explainability and is able to generate classification results simultaneously which builds trust for AI-led diagnosis systems. The proposed U-Net model achieves 97.61% accuracy and a dice coefficient of 0.97 on testing data from the COVID-QU-Ex Dataset which includes both diseased and healthy lungs.

Keywords: multi-output network model, U-net, class activation map, image classification, medical imaging analysis

Procedia PDF Downloads 170

Authors: Sadeq Al Yaari, Muhammad Alkhunayn, Aayah Al Yaari, Ayman Al Yaari, Montaha Al Yaari, Sajedah Al Yaari, Fatehi Eissa

Abstract:

The recent rise of smart educational aids and the move away from traditional listening aids are leading to a fundamental shift in the way in which individuals with attention and listening problems (ALP) manipulate listening inputs and/or act appropriately to the spoken information presented to them. A total sample of twenty-six ALP pupils (m=20 and f=6) between 7-12 years old was selected from different strata based on gender, region and school. In the sample size, thirteen (10 males and 3 females) received the treatment in terms of smart classes provided with smart educational aids in a listening course that lasted for four month-semester while others did not (they studied the same course by the same instructor but in ordinary class). A pretest was administered to assess participants’ levels, and a posttest was given to evaluate their attention and listening comprehension performance, namely in phonetic and phonological tests with sociolinguistic themes that have been designed for this purpose. Test results were analyzed both psychoneurolinguistically and statistically. Results reveal a remarkable change in pupils’ behavioral listening where scores witnessed a significant difference in the performance of the experimental ALP group in the pretest compared to the posttest (Pupils performed better at the pretest-posttest on phonetics than at the two tests on phonology). It is concluded that smart educational aids designed for listening skills help not only increase the listening command of pupils with ALP to understand what they listen to but also develop their interactive listening capability and, at the same rate, are responsible for increasing concentrated and in-depth listening capacity. Plus, ALP pupils become able to grasp the audio content of text recordings, including educational audio recordings, news, oral stories and tales, views, spiritual/religious text and general knowledge. However, the pupils have not experienced individual smart audio-visual aids that connect listening to other language receptive and productive skills, which could be the future area of research.

Keywords: language skills, implementing, listening skill, attention, smart aids

Procedia PDF Downloads 16

Authors: Pengfei Meng, Shuangcheng Jia, Qian Li

Abstract:

We proposed a real-time high-precision semantic segmentation network based on a multi-resolution feature fusion module, the auxiliary feature extracting module, upsampling module, and atrous spatial pyramid pooling (ASPP) module. We designed a feature fusion structure, which is integrated with sufficient features of different resolutions. We also studied the effect of side-branch structure on the network and made discoveries. Based on the discoveries about the side-branch of the network structure, we used a side-branch auxiliary feature extraction layer in the network to improve the effectiveness of the network. We also designed upsampling module, which has better results than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules and modified the network structure according to the experimental results to further improve the effectiveness of the network. The network presented in this paper takes the backbone network of Bisenetv2 as a basic network, based on which we constructed a network structure on which we made improvements. We named this network deep multiple-resolution bilateral networks for real-time, referred to as DMBR-Net. After experimental testing, our proposed DMBR-Net network achieved 81.2% mIoU at 119FPS on the Cityscapes validation dataset, 80.7% mIoU at 109FPS on the CamVid test dataset, 29.9% mIoU at 78FPS on the COCOStuff test dataset. Compared with all lightweight real-time semantic segmentation networks, our network achieves the highest accuracy at an appropriate speed.

Keywords: multi-resolution feature fusion, atrous convolutional, bilateral networks, pyramid pooling

Procedia PDF Downloads 112

Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas

Abstract:

An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.

Keywords: anthrophony, hydrophone, k-means, machine learning

Procedia PDF Downloads 137

Authors: Anoop T. R., Otman Basir, Robert F. Hess, Ben Thompson

Abstract:

Strabismus refers to a misalignment of the eyes. Early detection and treatment of strabismus in childhood can prevent the development of permanent vision loss due to abnormal development of visual brain areas. Currently, many children with strabismus remain undiagnosed until school entry because current automated screening methods have limited success in the preschool age range. A method for strabismus detection using eye alignment stability (EAS) is proposed. This method starts with face detection, followed by facial landmark detection, eye region segmentation, eye gaze extraction, and eye alignment stability estimation. Binarization and morphological operations are performed for segmenting the pupil region from the eye. After finding the EAS, its absolute value is used to differentiate the strabismic eye from the non-strabismic eye. If the value of the eye alignment stability is greater than a particular threshold, then the eyes are misaligned, and if its value is less than the threshold, the eyes are aligned. The method was tested on 175 strabismic and non-strabismic images obtained from Kaggle and Google Photos. The strabismic eye is taken as a positive class, and the non-strabismic eye is taken as a negative class. The test produced a true positive rate of 100% and a false positive rate of 7.69%.

Keywords: strabismus, face detection, facial landmarks, eye segmentation, eye gaze, binarization

Procedia PDF Downloads 52

Authors: Abiodun Afolabi, Rufus Adesoji Adedoyin

Abstract:

This study investigated and compared the effects of gym-based exercise programme (GEBP) and audio-visual guided home-based exercise programme (AVGHBEP) on selected Anthropometric variables (Weight (W), Body Mass Index (BMI), Waist Circumference (WC), Hip Circumference (HC), Thigh Circumference (TC), Waist-Hip-Ratio (WHR), Waist-Height-Ratio (WHtR), Waist-Thigh-Ratio (WTR), Biceps Skinfold Thickness (BSFT), Triceps Skinfold Thickness (TSFT), Suprailliac Skinfold Thickness (SISFT), Subscapular Skinfold Thickness (SSSFT) and Percent Body Fat (PBF)); and Cardiovasular variables (Systolic Blood Pressure (SBP), Diastolic Blood Pressure (DBP) and Heart Rate (HR)) of overweight and obese students of Federal College of Education (Special), Oyo, Oyo State, Nigeria, with a view to providing information and evidence for GBEP and AVGHBEP in reducing overweight and obesity for promoting cardiovascular fitness. Eighty overweight and obese students (BMI ≥ 25 Kg/m²) were involved in this pretest-posttest quasi experimental study. Participants were randomly assigned into GBEP (n = 40) and AVGBBEP (n = 40) groups. Anthropometric and cardiovascular variables were measured using a weighing scale, height meter, tape measure, skinfold caliper and electronic sphygmomanometer following standard protocols. GBEP and AVGHBEP were implemented following a circuit training (aerobic and resistance training) pattern with a duration of 40-60 minutes, thrice weekly for twelve weeks. GBEP consisted of gymnasium supervised exercise programme while AVGHBEP is a Visual Display guided exercise programme conducted at the home setting. Data were analyzed by Descriptive and Inferential Statistics. The mean ages of the participants were 22.55 ± 2.55 and 23.65 ± 2.89 years for the GBEP group and AVGHBEP group, respectively. Findings showed that in the GBEP group, there were significant reductions in anthropometric variables and adiposity measures of Weight, BMI, BSFT, TSFT, SISFT, SSSFT, WC, HC, TC, WHtR, and PBF at week 12 of the study. Similarly, in the AVGHBEP group, there were significant reductions in Weight, BMI, BSFT, TSFT, SISFT, SSSFT, WC, HC, TC, WHtR and PBF at the 12th week of intervention. Comparison of the effects of GEBP and AVGHBEP on anthropometric variables and measures of adiposity showed that there was no significant difference between the two groups in weight, BMI, BSFT, TSFT, SISFT, SSSFT, WC, HC, TC, WHR, WHtR, WTR and PBF between the two groups at week 12 of the study. Furthermore, findings on the effects of exercise on programmes on cardiovascular variables revealed that significant reductions occurred in SBP in GBEP group and AVGHBEP group respectively. Comparison of the effects of GBEP and AVGHBEP on cardiovascular variables showed that there was no significant difference in SBP, DBP and HR between the two groups at week 12 of the study. It was concluded that the Audio-Visual Guided Home-based Exercise Programme was as effective as the Gym-Based Exercise Programme in causing a significant reduction in anthropometric variables and body fat among college students who are overweight and obese over a period of twelve weeks. Both Gymnasium-Based Exercise Programme and Audio-Visual Guided Home-Based Exercise Programme led to significant reduction in Systolic Blood Pressure over a period of weeks. Audio-Visual Guided Home-Based Exercise Programme can, therefore, be used as an alternative therapy in the non-pharmacological management of people who are overweight and obese.

Keywords: gym-based exercises, audio-visual guided home-based exercises, anthropometric parameters, cardiovascular parameters, overweight students, obese students

Procedia PDF Downloads 14

Authors: Deepika Christopher, Garima Anand

Abstract:

To determine the best model for churn prediction in the telecom industry, this paper compares 11 machine learning algorithms, namely Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, XGBoost, LightGBM, Cat Boost, AdaBoost, Extra Trees, Deep Neural Network, and Hybrid Model (MLPClassifier). It also aims to pinpoint the top three factors that lead to customer churn and conducts customer segmentation to identify vulnerable groups. According to the data, the Logistic Regression model performs the best, with an F1 score of 0.6215, 81.76% accuracy, 68.95% precision, and 56.57% recall. The top three attributes that cause churn are found to be tenure, Internet Service Fiber optic, and Internet Service DSL; conversely, the top three models in this article that perform the best are Logistic Regression, Deep Neural Network, and AdaBoost. The K means algorithm is applied to establish and analyze four different customer clusters. This study has effectively identified customers that are at risk of churn and may be utilized to develop and execute strategies that lower customer attrition.

Keywords: attrition, retention, predictive modeling, customer segmentation, telecommunications

Procedia PDF Downloads 29

Authors: António J. R. Neves, Rui Garcia, Paulo Dias, Alina Trifan

Abstract:

With the aging of the world population and the continuous growth in technology, service robots are more and more explored nowadays as alternatives to healthcare givers or personal assistants for the elderly or disabled people. Any service robot should be capable of interacting with the human companion, receive commands, navigate through the environment, either known or unknown, and recognize objects. This paper proposes an approach for object recognition based on the use of depth information and color images for a service robot. We present a study on two of the most used methods for object detection, where 3D data is used to detect the position of objects to classify that are found on horizontal surfaces. Since most of the objects of interest accessible for service robots are on these surfaces, the proposed 3D segmentation reduces the processing time and simplifies the scene for object recognition. The first approach for object recognition is based on color histograms, while the second is based on the use of the SIFT and SURF feature descriptors. We present comparative experimental results obtained with a real service robot.

Keywords: object detection, feature, descriptors, SIFT, SURF, depth images, service robots

Procedia PDF Downloads 514

Authors: Flaurence Benjamain, Michel Casperance

Abstract:

We present in this paper, first, a comparative study of three mathematical theories to achieve the fusion of information sources. This study aims to identify the characteristics inherent in theories of possibilities, belief functions (DST) and plausible and paradoxical reasoning to establish a strategy of choice that allows us to adopt the most appropriate theory to solve a problem of fusion in order, taking into account the acquired information and imperfections that accompany them. Using the new theory of plausible and paradoxical reasoning, also called Dezert-Smarandache Theory (DSmT), to fuse information multi-sources needs, at first step, the generation of the composites events witch is, in general, difficult. Thus, we present in this paper a new approach to construct pertinent paradoxical classes based on gray levels histograms, which also allows to reduce the cardinality of the hyper-powerset. Secondly, we developed a new technique for order and coding generalized focal elements. This method is exploited, in particular, to calculate the cardinality of Dezert and Smarandache. Then, we give an experimentation of classification of a remote sensing image that illustrates the given methods and we compared the result obtained by the DSmT with that resulting from the use of the DST and theory of possibilities.

Keywords: segmentation, image, approach, vision computing

Procedia PDF Downloads 253

Authors: Anastasia Rita Widiarti, Agus Harjoko, Marsono, Sri Hartati

Abstract:

This paper presents the results of a study to test whether the Javanese character manuscript image preprocessing model that have been more widely applied, can also be applied to segment of the Batak characters manuscripts. The treatment process begins by converting the input image into a binary image. After the binary image is cleaned of noise, then the segmentation lines using projection profile is conducted. If unclear histogram projection is found, then the smoothing process before production indexes line segments is conducted. For each line image which has been produced, then the segmentation scripts in the line is applied, with regard of the connectivity between pixels which making up the letters that there is no characters are truncated. From the results of manuscript preprocessing system prototype testing, it is obtained the information about the system truth percentage value on pieces of Pustaka Batak Podani Ma AjiMamisinon manuscript ranged from 65% to 87.68% with a confidence level of 95%. The value indicates the truth percentage shown the initial processing model in Javanese characters manuscript image can be applied also to the image of the Batak characters manuscript.

Keywords: connected component, preprocessing, manuscript image, projection profiles

Procedia PDF Downloads 378