1,720,971 research outputs found
Colorectal Polyp Segmentation In Colonoscopy Image Using Mask RCNN
Get PDFThe incidence rate of colorectal cancer is high worldwide, but the survival rate is
greatly improved by early identication of polyps. Colonoscopy is the gold stan dard procedure for diagnosis and removal of colorectal lesions with the potential to
evolve into cancer. Computer-aided detection systems can help gastroenterologists
find polyps more accurately, which is one of the key signs of a good colonoscopy
and a predictor of the likelihood of developing colorectal cancer. The size, shape,
and texture of the colorectal polyp is challenging factor for computer aided detection
systems. Mask RCNN is one of computer aided detection and segmentation sys tem to alleviate these challenges. In this study, we use Mask R-CNN for colorectal
polyp segmentation in colonoscopy images. We used a large dataset and optimized
the existing Mask RCNN model to improve its performance. We have used publicly
available datasets for training 3,946 images and for testing 444 images. The trained
model achieved a mean average precision of 95.75%, mean average recall of 96%
and f1 score of 95.87%. Thus, optimizing the hyperparameter of Mask R-CNN us ing a large colonoscopy image dataset improves its polyp segmentation performance
in colonoscopy images. The proposed method improves the early diagnosis of col orectal polyps and helps to save live
Pornographic Video Classification Using Convolutional Neural Network and Gated recurrent unit (GRU)
No full textChanges and advancement in many fields become eminent in the world where we live. In the last
ten years, there has been a high coverage and availability of internet connection. These the
advancement of technology and emerging of advanced computing platform bring a lot of
advantages and negative influences on our community. From those negative threats, one that
harshly attacks the youth’s productive class of the population is the videos with pornographic
contents. According to the annual statistics released by PornHub videos, 64 million people
visited PornHub every day. This is the noticeable number. This will lead youths to exercise
unsafe sexual behavior and of course they are exposed to sexually transmitted diseases like HIV. In this study we have proposed an automated classification of the pornographic videos. A
combined effect of CNN pretrained models along with GRU has been employed to tackle this
problem. The CNN pretrained model such as EfficientNet has been used for relevant feature
extraction. Where the sequential learner bidirectional GRU is responsible for detecting the
instance of video frames as porn video content or not. To evaluate the proposed model a publicly
available 2K NPDI dataset from the university of Campinas, Brazil and applied has been used. A
preliminary preprocessing steps such as normalization and cleaning has been applied on the
dataset. We have used EfficientNet as a fine-tuned feature extractor in order to extract important
features from the frames of the video and then the sequential information from the frame is learnt
by DB-GRU network. In this DB-GRU network multiple layers are stacked together in both
forward and backward pass in order to increase its depth and get good accuracy. Beside this
various parameter optimization has been applied to increase the accuracy and performance of the
proposed model. Following this, the experimental evaluation has showed a significant result of
99.68%. This result has improved by 0.68% and there is an improvement in efficiency in training
and testing when compared to previous attempts on similar datasets. Various visualization
methods have been used to present the result in more interpretable and human interpretable way. This will help readers to reproduce our work. Finally, we have tried to show the real time
application of the proposed system by integrating and deploying the model, which has been
already developed in this study along with web-based API. Thus, any user can scan to detect
early whether a pornographic content present in a certain video stream or no
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Sitting Position Analysis for Determining Low Back Pain Using Surface Electromyography
No full textLow back pain is grouped under the musculoskeletal disorders which lead to disability, reduced
engagement in work activities, and considerable annual cost. It is a common and regular reason
for medical consultations, a large number of individuals experience low back pain at least once in
their lifetime. The onset of low back pain is unclear, which makes the diagnosis and prevention
process difficult. Different causes are set as a risk factor for low-back pain, sitting is one of them.
This study concentrates on the analysis of five different sitting positions, which are common sitting
positions in our daily activity. These positions include sitting on a stool (60-degree), sitting on a
reading chair (75-degree), upright sitting (90-degree), upright sitting with support (90 degrees with
lumbar support), and a relaxed sitting position (120-degree).
Surface electromyogram was applied on Iliocostalis lumborum muscle which is under the erector
spinae muscle group then signal was acquired and analyzed. A total of eleven features from the
time and frequency domain were extracted and analyzed. The ANOVA test was applied to identify
the significant features to study the five sitting positions. Force calculation using EMG signal was
calculated then the five sitting postures compared, sitting positions as supported and unsupported,
and on male and female subject differences were studied.
The best features identified to predict muscular force and fatigue from an EMG signal were mean
absolute value, mean frequency, and median frequency. The comparison of sitting postures with
and without a support shows that supported postures have less muscle load and fatigue than
unsupported postures. In male individuals, there was also reduced muscle load and less muscle
fatigue. Distinct sitting positions have different effects on muscle activity, according to the study.
Sitting 90 degrees with lumbar support is the best sitting position with minimum muscle load
(10.2885N) and less muscle fatigue. The posture at 60 and 75 degrees exhibits the largest muscle
stress (66.3207N and 60.9370N respectively) and maximum muscle fatigue. As a result, the two
positions are the least healthy and should be avoided at work or at home. This study will have a
significant impact on preventing low back pain and determining the ideal seating positions for a
healthy lifestyle
Optical Transport Network Performance Analysis Using Optimally Placed FBG as Dispersion Compensation
Get PDFThe optical communication system can transmit video, voice, data, and multimedia services
across long distances. The performances of all optical fiber communications systems affected
by factors like chromatic dispersion, polarization mode dispersion, attenuation, and non-linear
effects at the time of transmitting information are from one place to another. Therefore, it is
vital to minimize the dispersion and amplify all the light signals at the same time after a certain
interval of light propagation to recover the original signal.
In this thesis, investigation done to improve the overall system of the optical transport network
performance by using optimally placed Fiber Bragg Grating for dispersion compensation and
an optical amplifier to increase the attenuated signal power. In this thesis, performance analysis
of different channels of the Dense Wave Division Multiplexing network at different parameters
done based on fiber Bragg grating and erbium-doped fiber amplifier as dispersion
compensation and amplification mechanism using opti-system software. Here first we analyzed
the fiber communication system without Erbium Doped Fiber Amplifier and Fiber Bragg
Grating dispersions compensations techniques. Secondly, optical communications systems
evaluated by using different dispersions compensator techniques of Fiber Bragg grating and
Erbium Doped Fiber Amplifier.
The performances of the three dispersions compensators of the FBG has been evaluated based
on various parameters like input power, distance, Q factor, Bit Error Rate, eye height, and
threshold level at the receiving end. It is possible to observe and easily take the best dispersions
compensators for new deployment of DWDM systems for a given distance, data rate,
transmission power, and capacity, especially for campus, huge private and public service that
needs long haul high traffic network. In our work Symmetry FBG dispersions compensators
are the best compensators than pre and post FBG dispersions compensators for long distance
communications. Symmetry FBG dispersions compensators have a good quality factor and
BER than pre and post FBG desperations compensators for a given four, eight, thirty and forty
numbers of channels. For four channels, quality factor improved using Mix-FBG and EDFA
for 2.5, 5 and 10Gbps to the maximum / minimum of 65.6/57.9, 57.9/4.6 and 4.6 respectively.
From the result, Mix-FBG dispersion compensators for four channels DWDM systems have a
good quality factor than pre and post FBG dispersions compensators.
In addition, I suggest for the future work to do for higher data rate transmissions by different
configurations of dispersions compensations techniques of FBG for a number of channel
Image Based 3D Model Reconstruction of Ethiopian Museum Artifacts Using Deep Learning Technique
Get PDFMuseum heritages are the legacy that have been passed from generation to generation.
Presently, in the world, particularly in Ethiopia, several tangible heritage artifacts are
available with great care physically. However, some artifacts were handled
unprofessionally and are exposed to damages due to various reasons that include heritage
damage due to lack of awareness or ignorance of the stakeholders, heritage theft,
inappropriate conservation practices, and natural damage or deterioration. Moreover, the
quality of services offered by these physical museum artifacts is not good at all for visitors.
Therefore, to keep these artifacts safe and have global importance, it is important to
digitally record, preserve and display these heritages. In this research, we have proposed
an image-based 3D model reconstruction system for Ethiopian museum artifacts using a
deep learning technique called NeRF with a single 2D image supervision only. The model
has been trained and optimized to reconstruct the 3D model of Ethiopian museum artifacts
with a marching cube algorithm in limited cost and time, in which visitors and researchers
can be immersed and understand a culture and ancient civilization in the museums with
the help of augmented and virtual reality applications. To the knowledge of these authors,
there were no publicly available datasets of Ethiopian museum artifacts. Therefore, we
started by collecting and preparing six different types of museum artifact datasets from the
National Museum of Ethiopia and the Jimma museum. During experimental work, the
effect of different batch sizes, learning rates, image resolution, and optimizers are tested
and analyzed to fit the model and achieve a high-quality 3D model of the museum artifacts.
In this study, differentiable volume rendering has been used for rendering tasks. The
experiment is done on Google Colab pro with 30 epochs. We have measured the
performance of a model using MSE and PSNR in our test cases, which contain a single 2D
image. When analyzing the experimental result, we have achieved an effective 3D models
for all collected Ethiopian museum at image resolution 504×378, a learning rate of 5×10-
4, batch size of 1024, and optimizer of a ranger
Performance Analysis of Cooperative SWIPT mm-Wave NOMA for Cell Edge Users
Get PDFIn a cellular network, a cell-edge user usually suffers from poor quality of service
(QoS) and low signal-to-interference and noise ratio (SINR), This is due to low received
signal power as the propagation distance increase and high fading effects, which leads
to a considerable outage probability and low achievable data rate.
The performance of the cell-edge users is an essential issue in non-orthogonal multiple
access (NOMA) systems. In this paper, we investigate the performance of the Simulta neous Wireless Information and Power Transfer (SWIPT) cooperative non-orthogonal
multiple access (C-NOMA) system in half-duplex, decode and forward (DF), energy
harvesting (EH), and power splitting relay networks over different scenarios which are
characterized by Rayleigh fading channels and capacity advantage of maximum-ratio
combining (MRC) over selection combining (SC) technique analyzed. The system per formance of such networks is analyzed in terms of outage probability (OP), achievable
capacity, and sum throughput, in comparison to the non-cooperative non-orthogonal
multiple access and conventional orthogonal multiple access (OMA) system
In this paper, published research that focuses on the improvement of cell edge perfor mance is reviewed. We consider a two-user non-orthogonal multiple access system in
which the cell-center user act as an energy harvester and information relaying for the
cell-edge user. We analyze the capacity advantage transmit antenna selection (TAS)
policy at BS. To evaluate the performance of considered systems, we used a closed-form
expression for the OP of both cell-center and cell-edge users, in addition to that we
use Rayleigh fading channel, selection combining (SC), and maximum-ratio combining
(MRC) at the cell-edge user, and also use a gradient decent algorithm that finds The
optimal value of Power splitting(PS) coefficient, which maximize throughput for the
cell-edge user.
Matlab simulation of numerical results has shown a cooperative SWIPT-NOMA us ing MRC has decreased in OP 40% compared to non-cooperative NOMA, 25.98% com pared to cooperative NOMA without a direct link, and 9.02% compared to cooperative
SWIPT-NOMA with SC techniques. The optimal value of the β is between 0.1 to 0.3
from the simulation result. Cooperative SWIPT-NOMA with MRC also provides an
increase in achievable capacity, 66.12% compared to the conventional OMA system,
12.88% compared to the non-cooperative NOMA system, and a 2.18% improvement
over SC techniques. Cooperative SWIPT-NOMA with MRC has a sum throughput
improvement of 7.64% over the SC technique, 11.68% over the non-cooperative NOMA
system, and 15.58% over the conventional OMA systems at low SNR
- …
