Search results for: deep supervision

Authors: Shenlun Chen, Leonard Wee

Abstract:

Tumor grading is an essential reference for colorectal cancer (CRC) staging and survival prognostication. The widely used World Health Organization (WHO) grading system defines histological grade of CRC adenocarcinoma based on the density of glandular formation on whole slide images (WSI). Tumors are classified as well-, moderately-, poorly- or un-differentiated depending on the percentage of the tumor that is gland forming; >95%, 50-95%, 5-50% and <5%, respectively. However, manually grading WSIs is a time-consuming process and can cause observer error due to subjective judgment and unnoticed regions. Furthermore, pathologists’ grading is usually coarse while a finer and continuous differentiation grade may help to stratifying CRC patients better. In this study, a deep learning based automatic differentiation grading algorithm was developed and evaluated by survival analysis. Firstly, a gland segmentation model was developed for segmenting gland structures. Gland regions of WSIs were delineated and used for differentiation annotating. Tumor regions were annotated by experienced pathologists into high-, medium-, low-differentiation and normal tissue, which correspond to tumor with clear-, unclear-, no-gland structure and non-tumor, respectively. Then a differentiation prediction model was developed on these human annotations. Finally, all enrolled WSIs were processed by gland segmentation model and differentiation prediction model. The differentiation grade can be calculated by deep learning models’ prediction of tumor regions and tumor differentiation status according to WHO’s defines. If multiple WSIs were possessed by a patient, the highest differentiation grade was chosen. Additionally, the differentiation grade was normalized into scale between 0 to 1. The Cancer Genome Atlas, project COAD (TCGA-COAD) project was enrolled into this study. For the gland segmentation model, receiver operating characteristic (ROC) reached 0.981 and accuracy reached 0.932 in validation set. For the differentiation prediction model, ROC reached 0.983, 0.963, 0.963, 0.981 and accuracy reached 0.880, 0.923, 0.668, 0.881 for groups of low-, medium-, high-differentiation and normal tissue in validation set. Four hundred and one patients were selected after removing WSIs without gland regions and patients without follow up data. The concordance index reached to 0.609. Optimized cut off point of 51% was found by “Maxstat” method which was almost the same as WHO system’s cut off point of 50%. Both WHO system’s cut off point and optimized cut off point performed impressively in Kaplan-Meier curves and both p value of logrank test were below 0.005. In this study, gland structure of WSIs and differentiation status of tumor regions were proven to be predictable through deep leaning method. A finer and continuous differentiation grade can also be automatically calculated through above models. The differentiation grade was proven to stratify CAC patients well in survival analysis, whose optimized cut off point was almost the same as WHO tumor grading system. The tool of automatically calculating differentiation grade may show potential in field of therapy decision making and personalized treatment.

Keywords: colorectal cancer, differentiation, survival analysis, tumor grading

Procedia PDF Downloads 134

Authors: Alvyra Galkienė, Ona Monkevičienė

Abstract:

The full participation of all pupils in the overall educational process is defined by the concept of inclusive education, which is gradually evolving in education policy and practice. It includes the full participation of all pupils in a shared learning experience and educational practices that address barriers to learning. Inclusive education applying the principles of Universal Design for Learning (UDL), which includes promoting students' involvement in learning processes, guaranteeing a deep understanding of the analysed phenomena, initiating self-directed learning, and using e-tools to create a barrier-free environment, is a prerequisite for the personal success of each pupil. However, the sustainability of quality education is affected by the transformation of education systems. This was particularly evident during the period of the forced transition from contact to distance education in the COVID-19 pandemic. Research Problem: The transformation of the educational environment from real to virtual one and the loss of traditional forms of educational support highlighted the need for new research, revealing the individual profiles of teachers using UDL-based learning and the pathways of sustainable transfer of successful practices to non-conventional learning environments. Research Methods: In order to identify individual latent teacher profiles that encompass the essential components of UDL-based inclusive teaching and direct leadership of students' learning, the quantitative analysis software Mplius was used for latent profile analysis (LPA). In order to reveal proven, i.e., sustainable, pathways for the transit of the components of UDL-based inclusive learning to distance learning, latent profile transit analysis (LPTA) via Mplius was used. An online self-reported questionnaire was used for data collection. It consisted of blocks of questions designed to reveal the experiences of subject teachers in contact and distance learning settings. 1432 Lithuanian, Latvian, and Estonian subject teachers took part in the survey. Research Results: The LPA analysis revealed eight latent teacher profiles with different characteristics of UDL-based inclusive education or traditional teaching in contact teaching conditions. Only 4.1% of the subject teachers had a profile characterised by a sustained UDL approach to teaching: promoting pupils' self-directed learning; empowering pupils' engagement, understanding, independent action, and expression; promoting pupils' e-inclusion; and reducing the teacher's direct supervision of the students. Other teacher profiles were characterised by limited UDL-based inclusive education either due to the lack of one or more of its components or to the predominance of direct teacher guidance. The LPTA analysis allowed us to highlight the following transit paths of teacher profiles in the extreme conditions of the transition from contact to distance education: teachers staying in the same profile of UDL-based inclusive education (sustainable transit) or jumping to other profiles (unsustainable transit in case of barriers), and teachers from other profiles moving to this profile (ongoing transit taking advantage of the changed new possibilities in the teaching process).

Keywords: distance education, latent teacher profiles, sustainable transit, UDL

Procedia PDF Downloads 101

Authors: K.T Alade, A.F Lawal, A.A Omonori

Abstract:

Construction is an everlasting activity across the globe. Likewise, the problem of delay in the construction industry is a global phenomenon. Although there are several reasons that may be responsible for delay during construction, this may vary from place to place and can be reduced to the minimum when identified. This study considered the major causes and effects of delay in the execution of construction projects in Akure, Ondo State, Nigeria. Using literatures, a total number of 30 causes of construction delays were identified. The convenient sampling technique was used to select sixty respondents for a survey. The respondents comprise twenty-two (22) clients, eighteen consultants (18) and twenty (20) contractors. The analyses of the primary data revealed that the three most important causes of delay in construction projects in Akure, Ondo State Nigeria are poor site management and supervision, inadequate contractors experience and client’s financial difficulties. Based on the findings of this study, recommendations were given on how the causes and effects of delay in construction can be mitigated.

Keywords: Akure, causes, construction projects, delay, effects

Procedia PDF Downloads 508

Authors: Sihem Salmi Laouar, Khoudair Chabane, Rabah Laouar, Adrian J. Boyce et Anthony E. Fallick

Abstract:

The solid mass of Essouabaa belongs paléogéography to the field téthysian and belonged to the area of the Mounts of Mellègue. This area was not saved by the oceanic-2 event anoxic (EAO-2) which was announced, over one short period, around the limit cénomanian-turonian. In the solid mass of Essouabba, the dominant sediments, pertaining to this period, are generally fine, dark, laminated and sometimes rolled deposits. They contain a rather rich planktonic microfaune, pyrite, and grains of phosphate, thus translating an environment rather deep and reducing rather deep and reducing. For targeting well the passage Cénomanian-Turonian (C-T) in the solid mass of Essouabaa, of the studies lithological and biostratigraphic were combined with the data of the isotopic analyses carbon and oxygen like with the contents of CaCO3. The got results indicate that this passage is marked by a biological event translated by the appearance of the "filaments" like by a positive excursion of the δ13C and δ18O. The cénomanian-turonian passage in the solid mass of Essouabaa represents a good example where during the oceanic event anoxic a facies with organic matter with contents of COT which can reach 1.36%. C E massive presents biostratigraphic and isotopic similarities with those obtained as well in the areas bordering (ex: Tunisia and Morocco) that throughout the world.

Keywords: limit cénomanian-turonian (C-T), COT, filaments, event anoxic 2 (EAO-2), stable isotopes, mounts of Mellègue, Algeria

Procedia PDF Downloads 516

Authors: Fulya Gokalp Yavuz, Mark Daniel Ward

Abstract:

This study focuses on a contemporary and inevitable topic of Data Science and its exemplary application for early career building: Big Data and Leaving Learning Community (LLC). ‘Academia’ and ‘Industry’ have a common sense on the importance of Big Data. However, both of them are in a threat of missing the training on this interdisciplinary area. Some traditional teaching doctrines are far away being effective on Data Science. Practitioners needs some intuition and real-life examples how to apply new methods to data in size of terabytes. We simply explain the scope of Data Science training and exemplified its early stage application with LLC, which is a National Science Foundation (NSF) founded project under the supervision of Prof. Ward since 2014. Essentially, we aim to give some intuition for professors, researchers and practitioners to combine data science tools for comprehensive real-life examples with the guides of mentees’ feedback. As a result of discussing mentoring methods and computational challenges of Big Data, we intend to underline its potential with some more realization.

Keywords: Big Data, computation, mentoring, training

Procedia PDF Downloads 362

Authors: Iqra Yaseen

Abstract:

One of the well-known areas of computer science and engineering, image processing in the context of computer vision has been essential to automation. In remote sensing, medical science, and many other fields, it has made it easier to uncover previously undiscovered facts. Grading of diverse items is now possible because of neural network algorithms, categorization, and digital image processing. Its use in the classification of agricultural products, particularly in the grading of seeds or grains and their cultivars, is widely recognized. A grading and sorting system enables the preservation of time, consistency, and uniformity. Global population growth has led to an increase in demand for food staples, biofuel, and other agricultural products. To meet this demand, available resources must be used and managed more effectively. Image processing is rapidly growing in the field of agriculture. Many applications have been developed using this approach for crop identification and classification, land and disease detection and for measuring other parameters of crop. Vegetation localization is the base of performing these task. Vegetation helps to identify the area where the crop is present. The productivity of the agriculture industry can be increased via image processing that is based upon Unmanned Aerial Vehicle photography and satellite. In this paper we use the machine learning techniques like Convolutional Neural Network, deep learning, image processing, classification, You Only Live Once to UAV imaging dataset to divide the crop into distinct groups and choose the best way to use it.

Keywords: image processing, UAV, YOLO, CNN, deep learning, classification

Procedia PDF Downloads 107

Authors: Xinghang Lv, Tao Peng, Jia Chen, Junping Liu, Xinrong Hu, Ruhan He, Minghua Jiang, Wenli Cao

Abstract:

As one of the most dangerous vulnerabilities, effective detection of buffer overflow vulnerabilities is extremely necessary. Traditional detection methods are not accurate enough and consume more resources to meet complex and enormous code environment at present. In order to resolve the above problems, we propose the method for Buffer overflow detection based on Abstract syntax tree, Control flow graph, and Data dependency graph (BodeACD) in C/C++ programs with source code. Firstly, BodeACD constructs the function samples of buffer overflow that are available on Github, then represents them as code representation sequences, which fuse control flow, data dependency, and syntax structure of source code to reduce information loss during code representation. Finally, BodeACD learns vulnerability patterns for vulnerability detection through deep learning. The results of the experiments show that BodeACD has increased the precision and recall by 6.3% and 8.5% respectively compared with the latest methods, which can effectively improve vulnerability detection and reduce False-positive rate and False-negative rate.

Keywords: vulnerability detection, abstract syntax tree, control flow graph, data dependency graph, code representation, deep learning

Procedia PDF Downloads 170

Authors: H. Selcuk Halkacı, Mevlüt Türköz, Ekrem Öztürk, Murat Dilmec

Abstract:

Various attempts concerning the low formability issue for lightweight materials like aluminium and magnesium alloys are being investigated in many studies. Advanced forming processes such as hydroforming is one of these attempts. In last decades sheet hydroforming process has an increasing interest, particularly in the automotive and aerospace industries. This process has many advantages such as enhanced formability, the capability to form complex parts, higher dimensional accuracy and surface quality, reduction of tool costs and reduced die wear compared to the conventional sheet metal forming processes. There are two types of sheet hydroforming. One of them is hydromechanical deep drawing (HDD) that is a special drawing process in which pressurized fluid medium is used instead of one of the die half compared to the conventional deep drawing (CDD) process. Another one is sheet hydroforming with die (SHF-D) in which blank is formed with the act of fluid pressure and it takes the shape of die half. In this study, transition of cup height according to cup diameter between the processes was determined by performing simulation of the processes in Finite Element Analysis. Firstly SHF-D process was simulated for 40 mm cup diameter at different cup heights chancing from 10 mm to 30 mm and the cup height to diameter ratio value in which it is not possible to obtain a successful forming was determined. Then the same ratio was checked for a different cup diameter of 60 mm. Then thickness distributions of the cups formed by SHF-D and HDD processes were compared for the cup heights. Consequently, it was found that the thickness distribution in HDD process in the analyses was more uniform.

Keywords: finite element analysis, HDD, hydroforming sheet metal forming, SHF-D

Procedia PDF Downloads 429

Authors: Krasimir Ivanov, Elitsa Kolentsova, Dimitar Dimitrov, Petya Petrova, Tatyana Tabakova

Abstract:

This work studies the effect of chemical composition on the activity and selectivity of γ–alumina supported CuO/ MnO2/Cr2O3 catalysts toward deep oxidation of CO, dimethyl ether (DME) and methanol. The catalysts were prepared by impregnation of the support with an aqueous solution of copper nitrate, manganese nitrate and CrO3 under different conditions. Thermal, XRD and TPR analysis were performed. The catalytic measurements of single compounds oxidation were carried out on continuous flow equipment with a four-channel isothermal stainless steel reactor. Flow-line equipment with an adiabatic reactor for simultaneous oxidation of all compounds under the conditions that mimic closely the industrial ones was used. The reactant and product gases were analyzed by means of on-line gas chromatographs. On the basis of XRD analysis it can be concluded that the active component of the mixed Cu-Mn-Cr/γ–alumina catalysts consists of at least six compounds – CuO, Cr2O3, MnO2, Cu1.5Mn1.5O4, Cu1.5Cr1.5O4 and CuCr2O4, depending on the Cu/Mn/Cr molar ratio. Chemical composition strongly influences catalytic properties, this influence being quite variable with regards to the different processes. The rate of CO oxidation rapidly decrease with increasing of chromium content in the active component while for the DME was observed the reverse trend. It was concluded that the best compromise are the catalysts with Cu/(Mn + Cr) molar ratio 1:5 and Mn/Cr molar ratio from 1:3 to 1:4.

Keywords: Cu-Mn-Cr oxide catalysts, volatile organic compounds, deep oxidation, dimethyl ether (DME)

Procedia PDF Downloads 369

Authors: M. Lesage, G. Raîche, M. Riopel, F. Fortin, D. Sebkhi

Abstract:

This paper describes a Web server implementation of the hierarchical aggregate assessment process in the field of education. This process describes itself as a field of teamwork assessment where teams can have multiple levels of hierarchy and supervision. This process is applied everywhere and is part of the management, education, assessment and computer science fields. The E-Assessment website named “Cluster” records in its database the students, the course material, the teams and the hierarchical relationships between the students. For the present research, the hierarchical relationships are team member, team leader and group administrator appointments. The group administrators have the responsibility to supervise team leaders. The experimentation of the application has been performed by high school students in geology courses and Canadian army cadets for navigation patrols in teams. This research extends the work of Nance that uses a hierarchical aggregation process similar as the one implemented in the “Cluster” application.

Keywords: e-learning, e-assessment, teamwork assessment, hierarchical aggregate assessment

Procedia PDF Downloads 369

Authors: Vathsala Kaluarachchi, Oshani Wimalarathna, Charith Vandebona, Gayani Chandrarathna, Lakmal Rupasinghe, Windhya Rankothge

Abstract:

It is the fundamental function of a monitoring system to allow users to collect and process data. A worldwide threat, the corona outbreak has wreaked havoc in Sri Lanka, and the situation has gotten out of hand. Since the epidemic, the Sri Lankan government has been unable to establish a systematic system for monitoring corona patients and providing emergency care in the event of an outbreak. Most patients have been held at home because of the high number of patients reported in the nation, but they do not yet have access to a functioning medical system. It has resulted in an increase in the number of patients who have been left untreated because of a lack of medical care. The absence of competent medical monitoring is the biggest cause of mortality for many people nowadays, according to our survey. As a result, a smartphone app for analyzing the patient's state and determining whether they should be hospitalized will be developed. Using the data supplied, we are aiming to send an alarm letter or SMS to the hospital once the system recognizes them. Since we know what those patients need and when they need it, we will put up a desktop program at the hospital to monitor their progress. Deep learning, image processing and application development, natural language processing, and blockchain management are some of the components of the research solution. The purpose of this research paper is to introduce a mechanism to connect hospitals and patients even when they are physically apart. Further data security and user-friendliness are enhanced through blockchain and NLP.

Keywords: blockchain, deep learning, NLP, monitoring system

Procedia PDF Downloads 133

Authors: Kavita Bodke

Abstract:

Structural health monitoring (SHM) is experiencing growth, necessitating the development of distinct methodologies to address its expanding scope effectively. In this study, we developed automatic structure damage identification, which incorporates three unique types of a building’s structural integrity. The first pertains to the presence of fractures within the structure, the second relates to the issue of dampness within the structure, and the third involves corrosion inside the structure. This study employs image classification techniques to discern between intact and impaired structures within structural data. The aim of this research is to find automatic damage detection with the probability of each damage class being present in one image. Based on this probability, we know which class has a higher probability or is more affected than the other classes. Utilizing photographs captured by a mobile camera serves as the input for an image classification system. Image classification was employed in our study to perform multi-class and multi-label classification. The objective was to categorize structural data based on the presence of cracks, moisture, and corrosion. In the context of multi-class image classification, our study employed three distinct methodologies: Random Forest, Multilayer Perceptron, and CNN. For the task of multi-label image classification, the models employed were Rasnet, Xceptionet, and Inception.

Keywords: SHM, CNN, deep learning, multi-class classification, multi-label classification

Procedia PDF Downloads 36

Authors: Neşe Işık, Şenol Altıok, Galip Devrim Eryılmaz, Aydın durukan, Hasan Özgür Daş

Abstract:

In this study, an active landslide zone affecting the road alignment on the Tortum-Uzundere (Erzurum/Turkey) highway was investigated. Due to the landslide movement, problems have occurred in the existing road pavement, which has caused both safety problems and reduced driving comfort in the operation of the road. In order to model the landslide, drilling, geophysical and inclinometer studies were carried out in the field within the scope of ground investigation. Laboratory tests were carried out on soil and rock samples obtained from the borings. When the drilling and geophysical studies were evaluated together, it was determined that the study area has a complex geological structure. In addition, according to the inclinometer results, the direction and speed of movement of the landslide mass were observed. In order to create an idealized geological profile, all field and laboratory studies were evaluated together and then the sliding surface of the landslide was determined by back analysis method. According to the findings obtained, it was determined that the landslide was massively large, and the movement occurred had a deep sliding surface. As a result of the numerical analyses, it was concluded that the Slope angle reduction is the most economical and environmentally friendly method for the control of the landslide mass.

Keywords: landslide, geotechnical methods, geophysics, monitoring, highway

Procedia PDF Downloads 68

Authors: Mark Jason E. Arca, Jay Vee R. Linatoc, Rex Francis N. Lupango, Michael Joe A. Ramirez

Abstract:

Participation promises an avenue for citizens to take part in governance, but it does not necessarily mean effective participation. The proper integration of participants in the decision-making process should be properly addressed to ensure effectiveness. This study explores the integration of the participants in the decision-making process to reveal the level of participation in the Solid Waste Management audit done by the Citizen Participatory Audit (CPA), a program under the supervision of the Commission on Audit. Specifically, this study will use the experience of participation to identify emerging themes that will help reveal the level of participation through the integrated ladder of participation. The researchers used key informant interviews to gather necessary data from the actors of the program. The findings revealed that the level of participation present in the CPA is at the Placation level, a level below the program’s targeted level of participation. The study also allowed the researchers to reveal facilitating factors in the program that contributed to a better understanding of the practice of participation.

Keywords: citizen participation, culture of participation, ladder of participation, level of participation

Procedia PDF Downloads 411

Authors: Muhammad Ilham Agus Salim, Muhammad Ikbal

Abstract:

The ASEAN Economic Community (AEC) was set up in 2003 with the objectives of creating a single market and production base, enhancing equitable economic development as well as facilitating the integration into the global economy. The AEC involves liberalization and facilitation of trade in goods, skilled labour, services, and investment, as well as protection and promotion of investment. The thesis outlines the AEC Blueprint actions in scope of globalization of investment and capital market. Free flows of investment and freer flows of capital market urge countries in South East Asia to coordinate and to collaborate in securing the interest of public, and this leads to the importance of financial services authorities in ASEAN to prepare the mechanism of guarding the flows of investment. There is no exception, especially for Indonesian Financial Services Authority (OJK) as one of the authorized body in capital market supervision, to enforce its authorities as supervisory body.

Keywords: AEC blueprint, OJK, capital market, integration

Procedia PDF Downloads 312

Authors: Khamis Al-Gharbi, Said M. Gattoufi, Ali H. Al-Badi, Ali Al-Hashmi

Abstract:

The case study presents the progression of a project management of Al-Shifa, a healthcare information system in Oman. The case study describes the evolution of the implementation of a healthcare information system tailored to meet the needs of the healthcare units under the supervision of the Ministry of Health (MOH) in Oman. A focus group methodology was used for collecting the relevant information from the main project's stakeholders. In addition reports about the project made available for the researchers. The case analysis is made based on the Project Management approach developed by the Project Management Institute (PMI). The main finding that there was no formal project management approach adopted by the MOH for the development and implementation of the herewith mentioned healthcare information system project. Furthermore, the project had suffered a scope creep in terms of features, cost and time-schedule. The recommendations of the authors, for the rescue of the project from its current dilemma, consist of technological, administrative and human resources development actions.

Keywords: project management, information system, healthcare, Al-Shifa, Oman

Procedia PDF Downloads 390

Authors: Hamidreza Torabi, Mohsen Moghtaderi

Abstract:

Introduction: Currently, deep vitrectomy with silicone oil tamponade is the standard treatment method for patients with Rhegmatogenous Retinal Detachment (RRD). After retinal repair, it is necessary to remove silicone oil from the eye, but the appropriate time to remove the oil and complications related to that time has been less studied. The aim of this study was to compare the results of the early removal of silicone oil with the delayed removal of silicone oil in patients with RRD. Method & material: Patients who were referred to the Ophthalmology Clinic of Baqiyatallah Hospital, Tehran, Iran, due to RRD with detached macula in 2021 & 2022 were evaluated. These patients were treated with deep vitrectomy and silicone oil tamponade. Patients whose retinas were attached after the passage of time were candidates for silicone oil removal (SOR) surgery. For patients in the early SOR group, SOR surgery was performed 3-6 months after the initial vitrectomy surgery, and for the late SOR group, SOR was performed after 6 months after the initial vitrectomy surgery. Results: In this study, 60 patients with RRD were evaluated. 23 (38.3%) patients were in the early group, and 37 (61.7%) patients were in the late group. Based on our findings, it was seen that the mean visual acuity of patients based on the Snellen chart in the early group (0.48 ± 0.23 Decimal) was better than the late group (0.33 ± 0.18 Decimal) (P-value=0.009). Retinal re-detachment has happened only in one patient with early SOR. Conclusion: Early removal of silicone oil (less than 6 months) from the eyes of patients undergoing RRD surgery has been associated with better vision results compared to late removal.

Keywords: retinal detachment, vitrectomy, silicone oil, silicone oil removal, visual acuity

Procedia PDF Downloads 77

Authors: Jean Marriz M. Manzano, Marc D. Rosales, Magdaleno R. Vasquez Jr., Maria Theresa G. De Leon

Abstract:

This paper discusses the effects of surface roughness on a cantilever beam vibrational energy harvester. A silicon sample was fabricated using MEMS fabrication processes. When etching silicon using deep reactive ion etching (DRIE) at large etch depths, rougher surfaces are observed as a result of increased response in process pressure, amount of coil power and increased helium backside cooling readings. To account for the effects of surface roughness on the characteristics of the cantilever beam, finite element method (FEM) modeling was performed using actual roughness data from fabricated samples. It was found that when etching about 550um of silicon, root mean square roughness parameter, Sq, varies by 1 to 3 um (at 100um thick) across a 6-inch wafer. Given this Sq variation, FEM simulations predict an 8 to148 Hz shift in the resonant frequency while having no significant effect on the output power. The significant shift in the resonant frequency implies that careful consideration of surface roughness from fabrication processes must be done when designing energy harvesters.

Keywords: deep reactive ion etching, finite element method, microelectromechanical systems, multiphysics analysis, surface roughness, vibrational energy harvester

Procedia PDF Downloads 121

Authors: Daniel R. dos Santos, Mateus S. Maldonado, Estevão J. R. Batista

Abstract:

The military commanders increasingly dependent on spatial awareness, as knowing where enemy are, understanding how war battle scenarios change over time, and visualizing these trends in ways that offer insights for decision-making. Thanks to advancements in geospatial technologies and artificial intelligence algorithms, the commanders are now able to modernize military operations on a universal scale. Thus, geovisualisation has become an essential asset in the defense sector. It has become indispensable for better decisionmaking in dynamic/temporal scenarios, operation planning and management for the war field, situational awareness, effective planning, monitoring, and others. For example, a 3D visualization of war field data contributes to intelligence analysis, evaluation of postmission outcomes, and creation of predictive models to enhance decision-making and strategic planning capabilities. However, old-school visualization methods are slow, expensive, and unscalable. Despite modern technologies in generating 3D point clouds, such as LIDAR and stereo sensors, monocular depth values based on deep learning can offer a faster and more detailed view of the environment, transforming single images into visual information for valuable insights. We propose a dedicated monocular depth reconstruction approach via deep learning techniques for 3D geovisualisation of satellite images. It introduces scalability in terrain reconstruction and data visualization. First, a dataset with more than 7,000 satellite images and associated digital elevation model (DEM) is created. It is based on high resolution optical and radar imageries collected from Planet and Copernicus, on which we fuse highresolution topographic data obtained using technologies such as LiDAR and the associated geographic coordinates. Second, we developed an imagery-DEM fusion strategy that combine feature maps from two encoder-decoder networks. One network is trained with radar and optical bands, while the other is trained with DEM features to compute dense 3D depth. Finally, we constructed a benchmark with sparse depth annotations to facilitate future research. To demonstrate the proposed method's versatility, we evaluated its performance on no annotated satellite images and implemented an enclosed environment useful for Geovisualisation applications. The algorithms were developed in Python 3.0, employing open-source computing libraries, i.e., Open3D, TensorFlow, and Pythorch3D. The proposed method provides fast and accurate decision-making with GIS for localization of troops, position of the enemy, terrain and climate conditions. This analysis enhances situational consciousness, enabling commanders to fine-tune the strategies and distribute the resources proficiently.

Keywords: depth, deep learning, geovisualisation, satellite images

Procedia PDF Downloads 10

Authors: Celso L. Fernando, Toshio Yoshii, Takahiro Tsubota

Abstract:

Understanding the causes of a road accident and predicting their occurrence is key to preventing deaths and serious injuries from road accident events. Traditional statistical methods such as the Poisson and the Logistics regressions have been used to find the association of the traffic environmental factors with the accident occurred; recently, an artificial neural network, ANN, a computational technique that learns from historical data to make a more accurate prediction, has emerged. Although the ability to make accurate predictions, the ANN has difficulty dealing with highly unbalanced attribute patterns distribution in the training dataset; in such circumstances, the ANN treats the minority group as noise. However, in the real world data, the minority group is often the group of interest; e.g., in the road traffic accident data, the events of the accident are the group of interest. This study proposes a combination of the k-means with the ANN to improve the predictive ability of the neural network model by alleviating the effect of the unbalanced distribution of the attribute patterns in the training dataset. The results show that the proposed method improves the ability of the neural network to make a prediction on a highly unbalanced distributed attribute patterns dataset; however, on an even distributed attribute patterns dataset, the proposed method performs almost like a standard neural network.

Keywords: accident risks estimation, artificial neural network, deep learning, k-mean, road safety

Procedia PDF Downloads 163

Authors: Feng Yang

Abstract:

Machine learning (ML), especially deep learning (DL), has been extensively applied to many applications in recently years and gained great success in solving different problems, including scientific problems. However, conventional ML/DL methodologies are purely data-driven which have the limitations, such as need of ample amount of labelled training data, lack of consistency to physical principles, and lack of generalizability to new problems/domains. Recently, there is a growing consensus that ML models need to further take advantage of prior knowledge to deal with these limitations. Physics-informed machine learning, aiming at integration of physics/domain knowledge into ML, has been recognized as an emerging area of research, especially in the recent 2 to 3 years. In this work, physics-informed ML, specifically physics-informed neural network (NN), is employed and implemented to estimate the displacements at x, y, z directions in a solid mechanics problem that is controlled by equilibrium equations with boundary conditions. By incorporating the physics (i.e. the equilibrium equations) into the learning process of NN, it is showed that the NN can be trained very efficiently with a small set of labelled training data. Experiments with different settings of the NN model and the amount of labelled training data were conducted, and the results show that very high accuracy can be achieved in fulfilling the equilibrium equations as well as in predicting the displacements, e.g. in setting the overall displacement of 0.1, a root mean square error (RMSE) of 2.09 × 10−4 was achieved.

Keywords: deep learning, neural network, physics-informed machine learning, solid mechanics

Procedia PDF Downloads 150

Authors: Shaira L. Kee, Michael Aaron G. Sy, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar AlDahoul

Abstract:

Skin diseases are considered the fourth most common disease, with melanoma and non-melanoma skin cancer as the most common type of cancer in Caucasians. The alarming increase in Skin Cancer cases shows an urgent need for further research to improve diagnostic methods, as early diagnosis can significantly improve the 5-year survival rate. Machine Learning algorithms for image pattern analysis in diagnosing skin lesions can dramatically increase the accuracy rate of detection and decrease possible human errors. Several studies have shown the diagnostic performance of computer algorithms outperformed dermatologists. However, existing methods still need improvements to reduce diagnostic errors and generate efficient and accurate results. Our paper proposes an ensemble method to classify dermoscopic images into benign and malignant skin lesions. The experiments were conducted using the International Skin Imaging Collaboration (ISIC) image samples. The dataset contains 3,297 dermoscopic images with benign and malignant categories. The results show improvement in performance with an accuracy of 88% and an F1 score of 87%, outperforming other existing models such as support vector machine (SVM), Residual network (ResNet50), EfficientNetB0, EfficientNetB4, and VGG16.

Keywords: deep learning - VGG16 - efficientNet - CNN – ensemble – dermoscopic images - melanoma

Procedia PDF Downloads 81

Authors: Ehsan Sadie

Abstract:

Despite the experience of heavy losses and damages of recent earthquakes such as 8 km E of Pāhala, Hawaii, 11 km W of Salvaleón de Higüey, Dominican Republic and 49 km SSE of Punta Cana, Dominican Republic earthquakes, the possibility of large earthquakes in most populated areas of any country and the serious need for quality control in the design and implementation of buildings, not enough attention has been paid to the proper construction. Steel structures constitute a significant part of construction in any metropolitan area. This article gives a brief overview of the implementation status of these buildings in urban areas and considers the weaknesses of performance that typically occur due to negligence or insufficient mastery of the building supervisor in the principles of operation of earthquake-resistant buildings, and provides appropriate and possible solutions to improve the construction.

Keywords: bracing member, concentrated load, diaphragm system, earthquake engineering, load-bearing system, shear force, seismic retrofitting, steel building, strip foundation, supervising engineer, vulnerability of building

Procedia PDF Downloads 131

Authors: Ali Hamza

Abstract:

Accurate segmentation of breast ultrasound images is of paramount importance in enhancing the diagnostic capabilities of breast cancer detection. This study presents an approach utilizing the U-Net architecture for segmenting breast ultrasound images aimed at improving the accuracy and reliability of mass identification within the breast tissue. The proposed method encompasses a multi-stage process. Initially, preprocessing techniques are employed to refine image quality and diminish noise interference. Subsequently, the U-Net architecture, a deep learning convolutional neural network (CNN), is employed for pixel-wise segmentation of regions of interest corresponding to potential breast masses. The U-Net's distinctive architecture, characterized by a contracting and expansive pathway, enables accurate boundary delineation and detailed feature extraction. To evaluate the effectiveness of the proposed approach, an extensive dataset of breast ultrasound images is employed, encompassing diverse cases. Quantitative performance metrics such as the Dice coefficient, Jaccard index, sensitivity, specificity, and Hausdorff distance are employed to comprehensively assess the segmentation accuracy. Comparative analyses against traditional segmentation methods showcase the superiority of the U-Net architecture in capturing intricate details and accurately segmenting breast masses. The outcomes of this study emphasize the potential of the U-Net-based segmentation approach in bolstering breast ultrasound image analysis. The method's ability to reliably pinpoint mass boundaries holds promise for aiding radiologists in precise diagnosis and treatment planning. However, further validation and integration within clinical workflows are necessary to ascertain their practical clinical utility and facilitate seamless adoption by healthcare professionals. In conclusion, leveraging the U-Net architecture for breast ultrasound image segmentation showcases a robust framework that can significantly enhance diagnostic accuracy and advance the field of breast cancer detection. This approach represents a pivotal step towards empowering medical professionals with a more potent tool for early and accurate breast cancer diagnosis.

Keywords: mage segmentation, U-Net, deep learning, breast cancer detection, diagnostic accuracy, mass identification, convolutional neural network

Procedia PDF Downloads 84

Authors: M. Al Huwayz, A. Salhi, S. Alhassan, S. Alotaibi, A. Almalki, M.Almunyif, A. Alhassni, M. Henini

Abstract:

Recently, there has been much research carried out to investigate quantum dots (QDs) lasers with the aim to increase the gain of quantum well lasers. However, one of the difficulties with these structures is that electrically active defects can lead to serious issues in the performance of these devices. It is therefore essential to fully understand the types of defects introduced during the growth and/or the fabrication process. In this study, the effects of Gamma radiation on the electrically active defects in p-i-n InAs/InGaAsQDs laser structures grown by Molecular Beam Epitaxy (MBE) technique on GaAs substrates were investigated. Deep Level Transient Spectroscopy (DLTS), current-voltage (I-V), and capacitance-voltage (C-V) measurements were performed to explore these effects on the electrical properties of these QDs lasers. I-V measurements showed that as-grown sample had better electrical properties than the irradiated sample. However, DLTS and Laplace DLTS measurements at different reverse biases revealed that the defects in the-region of the p-i-n structures were decreased in the irradiated sample. In both samples, a trap with an activation energy of ~ 0.21 eV was assigned to the well-known defect M1 in GaAs layers

Keywords: quantum dots laser structures, gamma radiation, DLTS, defects, nAs/IngaAs

Procedia PDF Downloads 187

Authors: Kirolos Gerges Yakoub Gerges

Abstract:

Self-sustaining agricultural machines act in stochastic surroundings and therefore, should be capable of perceive the surroundings in real time. This notion can be done using image sensors blended with superior device learning, mainly Deep mastering. Deep convolutional neural networks excel in labeling and perceiving colour pix and since the fee of RGB-cameras is low, the hardware cost of accurate notion relies upon heavily on memory and computation power. This paper investigates the opportunity of designing lightweight convolutional neural networks for semantic segmentation (pixel clever class) with reduced hardware requirements, to allow for embedded usage in self-reliant agricultural machines. The usage of compression techniques, a lightweight convolutional neural community is designed to carry out actual-time semantic segmentation on an embedded platform. The community is skilled on two big datasets, ImageNet and Pascal Context, to apprehend as much as four hundred man or woman instructions. The 400 training are remapped into agricultural superclasses (e.g. human, animal, sky, road, area, shelterbelt and impediment) and the capacity to provide correct actual-time perception of agricultural environment is studied. The network is carried out to the case of self-sufficient grass mowing the usage of the NVIDIA Tegra X1 embedded platform. Feeding case-unique pics to the community consequences in a fully segmented map of the superclasses within the picture. As the network remains being designed and optimized, handiest a qualitative analysis of the technique is entire on the abstract submission deadline. intending this cut-off date, the finalized layout is quantitatively evaluated on 20 annotated grass mowing pictures. Light-weight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show aggressive performance on the subject of accuracy and speed. It’s miles viable to offer value-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: centrifuge pump, hydraulic energy, agricultural applications, irrigationaxial flux machines, axial flux applications, coreless machines, PM machinesautonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 26

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 78

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 191

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 142

Authors: Jean-Francois Rajotte, Martin Sotir, Frank Gouineau

Abstract:

The installation and management of traffic monitoring devices can be costly from both a financial and resource point of view. It is therefore important to take advantage of in-place infrastructures to extract the most information. Here we show how low-quality urban road traffic images from cameras already available in many cities (such as Montreal, Vancouver, and Toronto) can be used to estimate traffic flow. To this end, we use a pre-trained neural network, developed for object detection, to count vehicles within images. We then compare the results with human annotations gathered through crowdsourcing campaigns. We use this comparison to assess performance and calibrate the neural network annotations. As a use case, we consider six months of continuous monitoring over hundreds of cameras installed in the city of Montreal. We compare the results with city-provided manual traffic counting performed in similar conditions at the same location. The good performance of our system allows us to consider applications which can monitor the traffic conditions in near real-time, making the counting usable for traffic-related services. Furthermore, the resulting annotations pave the way for building a historical vehicle counting dataset to be used for analysing the impact of road traffic on many city-related issues, such as urban planning, security, and pollution.

Keywords: traffic monitoring, deep learning, image annotation, vehicles, roads, artificial intelligence, real-time systems

Procedia PDF Downloads 200