Search results for: deep seated gravitational slope deformation

Authors: Ji Chen, Chunhui Zhang, Fanming Zeng, Lei Zhang, Ying Li, Wei Zhang

Abstract:

Based on the synthetic principle of force, a pre-compressed nonlinear isolator with quasi-zero-stiffness (QZS) is developed for shock isolation of ship equipment. The proposed isolator consists of a vertical spring with positive stiffness and several lateral springs with negative stiffness. An analytical expression of vertical stiffness of the nonlinear isolator is derived and numerical simulation on the effect of the geometric design parameters is carried out. Besides, a pre-compressed QZS shock isolation system model is established. The stiffness characteristic of the system is studied and the effects of excitation amplitude and friction damping on shock isolation performance are discussed respectively. The research results show that in comparison with linear shock isolation system, the pre-compressed QZS shock isolation system could realize constant-force or approximately constant-force function and perform better anti-impact performance.

Keywords: quasi-zero-stiffness, constant-force, pre-compressed, large deformation, shock isolation, friction damping

Procedia PDF Downloads 697

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 158

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN

Procedia PDF Downloads 128

Authors: Derejaw Lake Melie, Alemu Kumlachew Tegegne

Abstract:

The increasing prevalence of social media in Ethiopia has exacerbated societal challenges by fostering the proliferation of negative emotional posts and comments. Illicit use of social media has further exacerbated divisions among the population. Addressing these issues through manual identification and aggregation of emotions from millions of users for swift decision-making poses significant challenges, particularly given the rapid growth of Amharic language usage on social platforms. Consequently, there is a critical need to develop an intelligent system capable of automatically detecting and categorizing negative emotional content into social, religious, and political categories while also filtering out toxic online content. This paper aims to leverage sentiment analysis techniques to achieve automatic detection and filtering of negative emotional content from Amharic social media texts, employing a comparative study of deep learning algorithms. The study utilized a dataset comprising 29,962 comments collected from social media platforms using comment exporter software. Data pre-processing techniques were applied to enhance data quality, followed by the implementation of deep learning methods for training, testing, and evaluation. The results showed that CNN, GRU, LSTM, and Bi-LSTM classification models achieved accuracies of 83%, 50%, 84%, and 86%, respectively. Among these models, Bi-LSTM demonstrated the highest accuracy of 86% in the experiment.

Keywords: negative emotion, emotion detection, social media filtering sentiment analysis, deep learning.

Procedia PDF Downloads 23

Authors: Zhong Ma, Zhuping Wang, Congxin Liu, Xiangzeng Liu

Abstract:

Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.

Keywords: satellite imagery classification, deep convolution network, genetic algorithm, hyper-parameter optimization

Procedia PDF Downloads 300

Authors: Natsuki Tsuda, Kiyotaka Obunai, Kazuya Okubo, Hideyuki Tashiro, Yoshinori Yamaji, Hideyuki Kato

Abstract:

The objective of this study is to investigate the effect of belt stiffness on the performance of the CVT unit, such as the required pulley thrust force and the ratio coverage. The CVT unit consists of the V-grooved pulleys and the rubber CVT belt. The width of the driving pulley groove was controlled by the stepper motor, while that of the driven pulley was controlled by the hydraulic pressure. The generated mechanical power on the motor was transmitted from the driving axis to the driven axis through the CVT unit. The rotational speed and the transmitting torque of both axes were measured by the tachometers and the torque meters attached with these axes, respectively. The transmitted, mechanical power was absorbed by the magnetic powder brake. The thrust force acting on both pulleys and the force between both shafts were measured by the load cell. The back face profile of the rubber CVT belt along with width direction was measured by the 2-dimensional laser displacement meter. This paper found that when the stiffness of the rubber CVT belt in the belt width direction was reduced, the thrust force required for shifting was reduced. Moreover, when the stiffness of the rubber CVT belt in the belt width direction was reduced, the ratio coverage of the CVT unit was reduced. Due to the decrement of stiffness in belt width direction, the excessive concave deformation of belt in pulley groove was confirmed. Because of this excessive concave deformation, apparent wrapping radius of belt would have been reduced. Proposed model could be effectively estimated the difference of ratio coverage due to concave deformation. The proposed model could also be utilized for designing the rubber CVT belt with optimal bending stiffness in width direction.

Keywords: CVT, countinuously variable transmission, rubber, belt stiffness, transmission

Procedia PDF Downloads 143

Authors: Tokihiko Akita, Seiichi Mita

Abstract:

A millimeter-wave radar is the most robust against adverse environments, making it an essential environment recognition sensor for automated driving. However, the reflection signal is sparse and unstable, so it is difficult to obtain the high recognition accuracy. Deep learning provides high accuracy even for them in recognition, but requires large scale datasets with ground truth. Specially, it takes a lot of cost to annotate for a millimeter-wave radar. For the solution, utilizing a simulator that can generate an annotated huge dataset is effective. Simulation of the radar is more difficult to match with real world data than camera image, and recognition by deep learning with higher-order features using the simulator causes further deviation. We have challenged to improve the accuracy of traffic participant classification by fusing simulator and real-world data with domain adaptation technique. Experimental results with the domain adaptation network created by us show that classification accuracy can be improved even with a few real-world data.

Keywords: millimeter-wave radar, object classification, deep learning, simulation, domain adaptation

Procedia PDF Downloads 93

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 94

Authors: Kashika P. H.

Abstract:

The development of computer vision systems has been greatly aided by the efficient and precise detection of images and videos. Although the ability to recognize and comprehend images is a strength of the human brain, employing technology to tackle this issue is exceedingly challenging. In the past few years, the use of Deep Learning algorithms to treat object detection has dramatically expanded. One of the key issues in the realm of image recognition is the recognition and detection of certain notable people from randomly acquired photographs. Face recognition uses a way to identify, assess, and compare faces for a variety of purposes, including user identification, user counting, and classification. With the aid of an accessible deep learning-based API, this article intends to recognize various faces of people and their facial descriptors more accurately. The purpose of this study is to locate suitable individuals and deliver accurate information about them by using the Amazon Rekognition system to identify a specific human from a vast image dataset. We have chosen the Amazon Rekognition system, which allows for more accurate face analysis, face comparison, and face search, to tackle this difficulty.

Keywords: Amazon rekognition, API, deep learning, computer vision, face detection, text detection

Procedia PDF Downloads 104

Authors: Avalloy McCarthy-Curvin

Abstract:

For over fifty years there has been widespread dissatisfaction with the teaching of Mathematics in Jamaica. Studies, done in the Jamaican context highlight that teachers at the end of training do not have a deep understanding of the mathematics content they teach. Little research has been done in the Jamaican context that targets the advancement of contextual knowledge on the problem to ultimately provide a solution. The aim of the study is to identify what influences this outcome of teacher education in Jamaica so as to remedy the problem. This study formatively evaluated the curriculum documents, assessments and the delivery of the curriculum that are being used in teacher training institutions in Jamaica to determine their rigor -the extent to which written document, instruction, and the assessments focused on enabling pre-service teachers to develop deep understanding of mathematics and relevance- the extent to which the curriculum document, instruction, and the assessments are focus on developing the requisite knowledge for teaching mathematics. The findings show that neither the curriculum document, instruction nor assessments ensure rigor and enable pre-service teachers to develop the knowledge and skills they need to teach mathematics effectively.

Keywords: relevance, rigor, deep understanding, formative evaluation

Procedia PDF Downloads 237

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 68

Authors: Shawn G. Gallaher, Lilli E. Hirth

Abstract:

As permafrost thaws with the continued warming of the Alaskan North Slope, a progressively thicker active thaw layer is evidently releasing previously sequestered nutrients, metals, and particulate matter exposed to fluvial transport. In this study, we estimate material fluxes on the North Slope of Alaska during the 2019-2022 melt seasons. The watershed of the Alaskan North Slope can be categorized into three regions: mountains, tundra, and coastal plain. Precipitation and discharge data were collected from repeat visits to 14 sample sites for biogeochemical surface water samples, 7 point discharge measurements, 3 project deployed meteorology stations, and 2 U. S. Geological Survey (USGS) continuous discharge observation sites. The timing, intensity, and spatial distribution of precipitation determine the material flux composition in the Sagavanirktok and surrounding bodies of water, with geogenic constituents (e.g., dissolved inorganic carbon (DIC)) expected from mountain flushed events and biogenic constituents (e.g., dissolved organic compound (DOC)) expected from transitional tundra precipitation events. Project goals include connecting late summer precipitation events to peak discharge to determine the responses of the watershed to localized atmospheric forcing. Field study measurements showed widespread precipitation in August 2019, generating an increase in total suspended solids, dissolved organic carbon, and iron fluxes from the tundra, shifting the main-stem mountain river biogeochemistry toward tundra source characteristics typically only observed during the spring floods. Intuitively, a large-scale precipitation event (as defined by this study as exceeding 12.5 mm of precipitation on a single observation day) would dilute a body of water; however, in this study, concentrations increased with higher discharge responses on several occasions. These large-scale precipitation events continue to produce peak constituent fluxes as the thaw layer increases in depth and late summer precipitation increases, evidenced by 6 large-scale events in July 2022 alone. This increase in late summer events is in sharp contrast to the 3 or fewer large events in July in each of the last 10 years. Changes in precipitation intensity, timing, and location have introduced late summer peak constituent flux events previously confined to the spring freshet.

Keywords: Alaska North Slope, arctic rivers, material flux, precipitation

Procedia PDF Downloads 75

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: deep-learning, image classification, image identification, industrial engineering.

Procedia PDF Downloads 160

Authors: Roman Kalvin, Saba Arif, Anam Nadeem, Burhan Ali Ghumman, Juntakan Taweekun

Abstract:

Bicycles are important parts of the transportation industry. In the current world, use of sprocket is very high on bicycles these days. Sprocket and chains are important parts of the transmission of power in the bicycle. However, transmission of power is highly dependent on sprocket design. In conventional bicycles, sprockets are made up of mild steel which undergoes wear and tears with the passage of time due to high pressures applied on it. In the current research, a new sprocket is designed by changing its structure and material to carbon fiber from mild steel. The existing sprocket of a bicycle is compared with the new and modified sprocket design. However, new design has structural and material changes as well. According to the results, in carbon fiber, sprocket deformation is 0.091 mm while sprocket stress value is 371.13N/mm². Also, comparison based analysis is done by physical testing and software analysis. There is 8.1% variation in software and experimental results of steel. Additionally, the difference between both methods comes 8 to 9%. This improved design can be used in future for more durability and long run timings for bicycles.

Keywords: sprocket, mild steel, drafting, stress, deformation

Procedia PDF Downloads 254

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.

Keywords: skin cancer, deep learning, performance measures, accuracy, datasets

Procedia PDF Downloads 129

Authors: Stacey Herzog, Mitchell McCleary, Istvan Kovacs

Abstract:

Purpose: Maximal strength and maximal power are key athletic abilities in many sports disciplines. In recent years, velocity-based training (VBT) with a relatively high 75-85% 1RM resistance has been popularized in preparation for powerlifting and various other sports. The purpose of this study was to discover differences between beginner/intermediate and advanced lifters’ push/press performances after a heavy resistance-based BP training program. Methods: A six-week, three-workouts per week program was administered to 52 young, physically active adults (age: 22.4±5.1; 12 female). The majority of the participants (84.6%) had prior experience in bench pressing. Typical workouts began with BP using 75-95% 1RM in the 1-5 repetition range. The sets in the lower part of the range (75-80% 1RM) were performed with velocity-focus as well. The BP sets were followed by seated dumbbell presses and six additional upper-body assistance exercises. Pre- and post-tests were conducted on five test exercises: one-repetition maximum BP (1RM), calculated relative strength index: BP/BW (RSI), four-repetition maximal-effort dynamic BP for peak concentric velocity with 80% 1RM (4RV), 4-repetition ballistic pushups (BPU) for height (4PU), and seated medicine ball toss for distance (MBT). For analytic purposes, the participant group was divided into two subgroups: self-indicated beginner or intermediate initial resistance training status (BITS) [n=21, age: 21.9±3.6; 10 female] and advanced initial resistance training status (ATS) [n=31, age: 22.7±5.9; 2 female]. Pre- and post-test results were compared within subgroups. Results: Paired-sample t-tests indicated significant within-group improvements in all five test exercises in both groups (p < 0.05). BITS improved 18.1 lbs. (13.0%) in 1RM, 0.099 (12.8%) in RSI, 0.133 m/s (23.3%) in 4RV, 1.55 in. (27.1%) in BPU, and 1.00 ft. (5.8%) in MBT, while the ATS group improved 13.2 lbs. (5.7%) in 1RM, 0.071 (5.8%) in RSI, 0.051 m/s (9.1%) in 4RV, 1.20 in. (13.7%) in BPU, and 1.15 ft. (5.5%) in MBT. Conclusion: While the two training groups had different initial resistance training backgrounds, both showed significant improvements in all test exercises. As expected, the beginner/intermediate group displayed better relative improvements in four of the five test exercises. However, the medicine ball toss, which had the lightest resistance among the tests, showed similar relative improvements between the two groups. These findings relate to two important training principles: specificity and transfer. The ATS group had more specific experiences with heavy-resistance BP. Therefore, fewer improvements were detected in their test performances with heavy resistances. On the other hand, while the heavy resistance-based training transferred to increased power outcomes in light-resistance power exercises, the difference in the rate of improvement between the two groups disappeared. Practical applications: Based on initial training status, S&C coaches should expect different performance gains in maximal strength training-specific test exercises. However, the transfer from maximal strength to a non-training-specific performance category along the F-v curve continuum (i.e., light resistance and high velocity) might not depend on initial training status.

Keywords: exercise, power, resistance training, strength

Procedia PDF Downloads 70

Authors: Chandrakant Gurav, Md. Babar

Abstract:

In the present study, an attempt is made to delineate the comparative morphometric analysis of Ambardi and Mangari watersheds of Kadvi and Kasari rivers sub-basins, Kolhapur District, Maharashtra India, using Geographical Information System (GIS) techniques. GIS is a computer assisted information method to store, analyze and display spatial data. Both the watersheds originate from Masai plateau of Jotiba- Panhala Hill range in Panhala Taluka of Kolhapur district. Ambardi watersheds cover 42.31 Sq. km. area and occur in northern hill slope, whereas Mangari watershed covers 54.63 Sq. km. area and occur on southern hill slope. Geologically, the entire study area is covered by Deccan Basaltic Province (DBP) of late Cretaceous to early Eocene age. Laterites belonging to late Pleistocene age also occur in the top of the hills. The objective of the present study is to carry out the morphometric parameters of watersheds, which occurs in differing slopes of the hill. Morphometric analysis of Ambardi watershed indicates it is of 4th order stream and Mangari watershed is of 5th order stream. Average bifurcation ratio of both watersheds is 5.4 and 4.0 showing that in both the watersheds streams flow from homogeneous nature of lithology and there is no structural controlled in development of the watersheds. Drainage density of Ambardi and Mangari watersheds is 3.45 km/km2 and 3.81 km/km2 respectively, and Stream Frequency is 4.51 streams/ km2 and 5.97 streams/ km2, it indicates that high drainage density and high stream frequency is governed by steep slope and low infiltration rate of the area for groundwater recharge. Textural ratio of both the watersheds is 6.6 km-1 and 9.6 km-1, which indicates that the drainage texture is fine to very fine. Form factor, circularity ratio and elongation ratios of the Ambardi and Mangari watersheds shows that both the watersheds are elongated in shape. The basin relief of Ambardi watershed is 447 m, while Mangari is 456 m. Relief ratio of Ambardi is 0.0428 and Mangari is 0.040. The ruggedness number of Ambardi is 1.542 and Mangari watershed is 1.737. The ruggedness number of both the watersheds is high which indicates the relief and drainage density is high.

Keywords: Ambardi, Deccan basalt, GIS, morphometry, Mangari, watershed

Procedia PDF Downloads 301

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 278

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 125

Authors: Monireh Ahmadi Bani, Adel Khorramrouz, Lalenoor Morvarid, Bagheri Mahtab

Abstract:

Background:- Foot disorders are common in musculoskeletal problems. Plantar pressure distribution measurement is one the most important part of foot disorders diagnosis for quantitative analysis. However, the association of plantar pressure and foot disorders is not clear. With the growth of dataset and machine learning methods, the relationship between foot disorders and plantar pressures can be detected. Significance of the study:- The purpose of this study was to predict the probability of common foot disorders based on peak plantar pressure distribution and center of pressure during walking. Methodologies:- 2323 participants were assessed in a foot therapy clinic between 2015 and 2021. Foot disorders were diagnosed by an experienced physician and then they were asked to walk on a force plate scanner. After the data preprocessing, due to the difference in walking time and foot size, we normalized the samples based on time and foot size. Some of force plate variables were selected as input to a deep neural network (DNN), and the probability of any each foot disorder was measured. In next step, we used support vector machine (SVM) and run dataset for each foot disorder (classification of yes or no). We compared DNN and SVM for foot disorders prediction based on plantar pressure distributions and center of pressure. Findings:- The results demonstrated that the accuracy of deep learning architecture is sufficient for most clinical and research applications in the study population. In addition, the SVM approach has more accuracy for predictions, enabling applications for foot disorders diagnosis. The detection accuracy was 71% by the deep learning algorithm and 78% by the SVM algorithm. Moreover, when we worked with peak plantar pressure distribution, it was more accurate than center of pressure dataset. Conclusion:- Both algorithms- deep learning and SVM will help therapist and patients to improve the data pool and enhance foot disorders prediction with less expense and error after removing some restrictions properly.

Keywords: deep neural network, foot disorder, plantar pressure, support vector machine

Procedia PDF Downloads 358

Authors: Wissem Tighidet, Faïçal Naït Bouda, Moussa Allouche

Abstract:

The numerical study of the Fluid-Structure Interaction (FSI) in a partially filled flexible tank submitted to a horizontal harmonic excitation motion. It is investigated by using two-way Fluid-Structure Interaction (FSI) in a flexible tank by Coupling between the Transient Structural (Mechanical) and Fluid Flow (Fluent) in ANSYS-Workbench Student version. The Arbitrary Lagrangian-Eulerian (ALE) formulation is adopted to solve with the finite volume method, the Navier-Stokes equations in two phases in a moving domain. The Volume of Fluid (VOF) method is applied to track the free surface. However, the equations of the dynamics of the structure are solved with the finite element method assuming a linear elastic behavior. To conclude, the Fluid-Structure Interaction (IFS) has a vital role in the analysis of the dynamic behavior of the rectangular tank. The results indicate that the flexibility of the tank walls has a significant impact on the amplitude of tank sloshing and the deformation of the free surface as well as the effect of liquid sloshing on wall deformation.

Keywords: arbitrary lagrangian-eulerian, fluid-structure interaction, sloshing, volume of fluid

Procedia PDF Downloads 105

Authors: Anwar U. Haque, Waqar Asrar, Ashraf Ali Omar, Erwin Sulaeman, Jaffer Sayed Mohamed Ali

Abstract:

Due to the interference effects, the intrinsic aerodynamic parameters obtained from the individual component testing are always fundamentally different than those obtained for complete model testing. Consideration and limitation for such testing need to be taken into account in any design work related to the component buildup method. In this paper, the scaled model of a straight rectangular canard of a hybrid buoyant aircraft is tested at 50 m/s in IIUM-LSWT (Low-Speed Wind Tunnel). Model and its attachment with the balance are kept rigid to have results free from the aeroelastic distortion. Based on the velocity profile of the test section’s floor; the height of the model is kept equal to the corresponding boundary layer displacement. Balance measurements provide valuable but limited information of the overall aerodynamic behavior of the model. Zero lift coefficient is obtained at -2.2o and the corresponding drag coefficient was found to be less than that at zero angles of attack. As a part of the validation of low fidelity tool, the plot of lift coefficient plot was verified by the experimental data and except the value of zero lift coefficient, the overall trend has under-predicted the lift coefficient. Based on this comparative study, a correction factor of 1.36 is proposed for lift curve slope obtained from the panel method.

Keywords: wind tunnel testing, boundary layer displacement, lift curve slope, canard, aerodynamics

Procedia PDF Downloads 469

Authors: Amir Hossein Haji, Nabeel Al-Rawahi, Gholamreza Vakili-Nezhaad

Abstract:

An innovative design has been examined for a gas-oil separator based on pressure reduction over an airfoil surface. The primary motivations are to shorten the release trajectory of the bubbles by minimizing the thickness of the oil layer as well as improving uniform pressure reduction zones. Restricted airflow over an airfoil is investigated for its effect on the pressure drop enhancement and the maximum attainable attack angle prior to the stall condition. Aerodynamic separation is delayed based on numerical simulation of Wortmann FX 63137 Airfoil in a confined domain using FLUENT 6.3.26. The proposed set up results in higher pressure drop compared with the free stream case. With the aim of optimum power consumption we have pursued further restriction to an air jet case over the airfoil. Then, a curved strip model is suggested for the air jet which can be applied as an analysis/design tool for the best performance conditions. Pressure reduction is shown to be inversely proportional to the curvature of the upper airfoil profile. This reduction occurs within the tracking zones where the air jet is effectively attached to the airfoil surface. The zero slope condition is suggested to estimate the onset of these zones after which the minimum curvature should be searched. The corresponding zero slope curvature is applied for estimation of the maximum pressure drop which shows satisfactory agreement with the simulation results.

Keywords: airfoil, air jet, curved fluid flow, gas-oil separator

Procedia PDF Downloads 472

Authors: Zaki Abiza, Miguel Chavez, David M. Holman, Ruddy Brionnaud

Abstract:

In this paper, the prediction of the aerodynamic behavior of the flow around a Finned Projectile will be validated using a Computational Fluid Dynamics (CFD) solution, XFlow, based on the Lattice-Boltzmann Method (LBM). XFlow is an innovative CFD software developed by Next Limit Dynamics. It is based on a state-of-the-art Lattice-Boltzmann Method which uses a proprietary particle-based kinetic solver and a LES turbulent model coupled with the generalized law of the wall (WMLES). The Lattice-Boltzmann method discretizes the continuous Boltzmann equation, a transport equation for the particle probability distribution function. From the Boltzmann transport equation, and by means of the Chapman-Enskog expansion, the compressible Navier-Stokes equations can be recovered. However to simulate compressible flows, this method has a Mach number limitation because of the lattice discretization. Thanks to this flexible particle-based approach the traditional meshing process is avoided, the discretization stage is strongly accelerated reducing engineering costs, and computations on complex geometries are affordable in a straightforward way. The projectile that will be used in this work is the Army-Navy Basic Finned Missile (ANF) with a caliber of 0.03 m. The analysis will consist in varying the Mach number from M=0.5 comparing the axial force coefficient, normal force slope coefficient and the pitch moment slope coefficient of the Finned Projectile obtained by XFlow with the experimental data. The slope coefficients will be obtained using finite difference techniques in the linear range of the polar curve. The aim of such an analysis is to find out the limiting Mach number value starting from which the effects of high fluid compressibility (related to transonic flow regime) lead the XFlow simulations to differ from the experimental results. This will allow identifying the critical Mach number which limits the validity of the isothermal formulation of XFlow and beyond which a fully compressible solver implementing a coupled momentum-energy equations would be required.

Keywords: CFD, computational fluid dynamics, drag, finned projectile, lattice-boltzmann method, LBM, lift, mach, pitch

Procedia PDF Downloads 421

Authors: Abdulfatah Faraj Aboufayed

Abstract:

Water erosion is the most important problems of the soil in the Jebel Nefusa area located in north west of Libya, therefore erosion station had been established in the Faculty of Veterinary and rainfed agriculture research Station, University of the Jepel Algherbee in Zentan. The length of the station is 72.6 feet, 6 feet width, and the percentage of it's slope is 3%. The station was established to measure the mount of soil eroded and amount of surface water produced during the seasons 95/96 and 96/97 from each rain storms. The Monitoring shows that there was a difference between the two seasons in the number of rainstorms which made differences in the amount of surface runoff water and the amount of soil eroded between the two seasons. Although the slope is low (3%), the soil texture is sandy and the land ploughed twice during each season surface runoff and soil eroded occurred. The average amount of eroded soil was 3792 grams (gr) per season and the average amount of surface runoff water was 410 litter (L) per season. The amount of surface runoff water would be much greater from Jebel Nefusa upland with steep slopes and collecting of them will save a valuable amount of water which lost as a runoff while this area is in desperate of this water. The regression analysis of variance show strong correlation between rainfall depth and the other two depended variable (the amount of surface runoff water and the amount of eroded soil). It shows also strong correlation between amount of surface runoff water and amount of eroded soil.

Keywords: rain, surface runoff water, soil, water erosion, soil erosion

Procedia PDF Downloads 403

Authors: A. Metioui

Abstract:

Research related to the student’s conceptual difficulties in sciences, particularly in the field of physics, are relatively numerous. In this work, we will analyze the results of qualitative research conducted with 80 elementary preservice teachers from Quebec in Canada on their understandings after studying the free fall bodies. First, we will illustrate the paper-pencil questionnaire built for this purpose. Then we will give the analysis of the experimental data. The results show that, even though there is a continuing physics education, many misconceptions persist despite the teaching provided.

Keywords: pre-service teachers, elementary school, conceptual difficulties, free fall bodies

Procedia PDF Downloads 126

Authors: Mouli Banga, Chaya Ravindra

Abstract:

Wound classification is a crucial step in wound diagnosis. An effective classifier can aid wound specialists in identifying wound types with reduced financial and time investments, facilitating the determination of optimal treatment procedures. This study presents a deep neural network-based classifier that leverages wound images and their corresponding locations to categorize wounds into various classes, such as diabetic, pressure, surgical, and venous ulcers. By incorporating a developed body map, the process of tagging wound locations is significantly enhanced, providing healthcare specialists with a more efficient tool for wound analysis. We conducted a comparative analysis between two prominent convolutional neural network models, ResNet50 and MobileNetV2, utilizing a dataset of 730 images. Our findings reveal that the RestNet50 outperforms MovileNetV2, achieving an accuracy of approximately 90%, compared to MobileNetV2’s 83%. This disparity highlights the superior capability of ResNet50 in the context of this dataset. The results underscore the potential of integrating deep learning with spatial data to improve the precision and efficiency of wound diagnosis, ultimately contributing to better patient outcomes and reducing healthcare costs.

Keywords: wound classification, MobileNetV2, ResNet50, multimodel

Procedia PDF Downloads 32

Authors: Seyed Mehdi Seyed Alizadeh, Christoph Arns, Shane Latham

Abstract:

Geomechanical characterization of rocks in detail and its possible implications on flow properties is an important aspect of reservoir characterization workflow. In order to gain more understanding of the microstructure evolution of reservoir rocks under stress a series of axisymmetric triaxial tests were performed on two different analogue rock samples. In-situ compression tests were coupled with high resolution micro-Computed Tomography to elucidate the changes in the pore/grain network of the rocks under pressurized conditions. Two outcrop sandstones were chosen in the current study representing a various cementation status of well-consolidated and weakly-consolidated granular system respectively. High resolution images were acquired while the rocks deformed in a purpose-built compression cell. A detailed analysis of the 3D images in each series of step-wise compression tests (up to the failure point) was conducted which includes the registration of the deformed specimen images with the reference pristine dry rock image. Digital Image Correlation (DIC) technique based on the intensity of the registered 3D subsets and particle tracking are utilized to map the displacement fields in each sample. The results suggest the complex architecture of the localized shear zone in well-cemented Bentheimer sandstone whereas for the weakly-consolidated Castlegate sandstone no discernible shear band could be observed even after macroscopic failure. Post-mortem imaging a sister plug from the friable rock upon undergoing continuous compression reveals signs of a shear band pattern. This suggests that for friable sandstones at small scales loading mode may affect the pattern of deformation. Prior to mechanical failure, the continuum digital image correlation approach can reasonably capture the kinematics of deformation. As failure occurs, however, discrete image correlation (i.e. particle tracking) reveals superiority in both tracking the grains as well as quantifying their kinematics (in terms of translations/rotations) with respect to any stage of compaction. An attempt was made to quantify the displacement field in compression using continuum Digital Image Correlation which is based on the reference and secondary image intensity correlation. Such approach has only been previously applied to unconsolidated granular systems under pressure. We are applying this technique to sandstones with various degrees of consolidation. Such element of novelty will set the results of this study apart from previous attempts to characterize the deformation pattern in consolidated sands.

Keywords: deformation mechanism, displacement field, shear behavior, triaxial compression, X-ray micro-CT

Procedia PDF Downloads 189

Authors: Ting Gao, Mingyue He

Abstract:

Reconfigurable intelligent surfaces (RISs) are expected to be an important part of next-generation wireless communication networks due to their potential to reduce the hardware cost and energy consumption of millimeter Wave (mmWave) massive multiple-input multiple-output (MIMO) technology. However, owing to the lack of signal processing abilities of the RIS, the perfect channel state information (CSI) in RIS-assisted communication systems is difficult to acquire. In this paper, the uplink channel estimation for mmWave systems with a hybrid active/passive RIS architecture is studied. Specifically, a deep learning-based estimation scheme is proposed to estimate the channel between the RIS and the user. In particular, the sparse structure of the mmWave channel is exploited to formulate the channel estimation as a sparse reconstruction problem. To this end, the proposed approach is derived to obtain the distribution of non-zero entries in a sparse channel. After that, the channel is reconstructed by utilizing the least-squares (LS) algorithm and compressed sensing (CS) theory. The simulation results demonstrate that the proposed channel estimation scheme is superior to existing solutions even in low signal-to-noise ratio (SNR) environments.

Keywords: channel estimation, reconfigurable intelligent surface, wireless communication, deep learning

Procedia PDF Downloads 150

Authors: A. Giniatoulline

Abstract:

A nonlinear model of the mathematical fluid dynamics which describes the motion of an incompressible viscous rotating fluid in a homogeneous gravitational field is considered. The model is a generalization of the known Navier-Stokes system with the addition of the Coriolis parameter and the equations for changeable density. An explicit algorithm for the solution is constructed, and the proof of the existence and uniqueness theorems for the strong solution of the nonlinear problem is given. For the linear case, the localization and the structure of the spectrum of inner waves are also investigated.

Keywords: Galerkin method, Navier-Stokes equations, nonlinear partial differential equations, Sobolev spaces, stratified fluid

Procedia PDF Downloads 309