Search results for: multi-agent double deep Q-network (MADDQN)

Authors: Safiah Ahmed Madkhali

Abstract:

The grammatical relation object has not attracted the same attention in the literature as subject has. Where there is a clearly monotransitive verb such as kick, the criteria for identifying the grammatical relation may converge. However, the term object is also used to refer to phenomena that do not subsume all, or even most, of the recognized properties of the canonical object. Instances of such phenomena include non-canonical objects such as the ones in the so-called double-object construction i.e. the indirect object and the direct object as in (He bought his dog a new collar). In this paper, it is demonstrated how criteria of identifying the grammatical relation object that are found in the theoretical and typological literature can be applied to Arabic. Also, further language-specific criteria are here derived from the regularities of the canonical object in the language. The criteria established in this way are then applied to the non-canonical objects to demonstrate how far they conform to, or diverge from, the canonical object. Contrary to the claim that the direct object is more similar to the canonical object than is the indirect object, it was found that it is, in fact, the indirect object rather than the direct object that shares most of the aspects of the canonical object in monotransitive clauses.

Keywords: canonical objects, double-object constructions, cognate object constructions, non-canonical objects

Procedia PDF Downloads 218

Authors: Buse T. Aydın, Enver Ozdemir

Abstract:

In this study, a double layer authentication scheme between the aircraft and the Air Traffic Control (ATC) tower is designed to prevent any unauthorized aircraft from introducing themselves as friends. The method is a combination of classical cryptographic methods and new generation physical layers. The first layer has employed the embedded key of the aircraft. The embedded key is assumed to installed during the construction of the utility. The other layer is a physical attribute (flight path, distance, etc.) between the aircraft and the ATC tower. We create a mathematical model so that two layers’ information is employed and an aircraft is authenticated as a friend or foe according to the accuracy of the results of the model. The results of the aircraft are compared with the results of the ATC tower and if the values found by the aircraft and ATC tower match within a certain error margin, we mark the aircraft as a friend. In this method, even if embedded key is captured by the enemy aircraft, without the information of the second layer, the enemy can easily be determined. Overall, in this work, we present a more reliable system by adding a physical layer in the authentication process.

Keywords: ADS-B, communication with physical layer security, cryptography, identification friend or foe

Procedia PDF Downloads 149

Authors: Woo-seok Choi, Eun-sup Kim, Nam-Seo Park

Abstract:

The demand for new technique in soft ground improvement continuously increases as general soft ground methods like PBD and DCM have a application problem in soft grounds with deep depth and wide distribution in Southern coast of Korea and Southeast. In this study, partial cement mixing method utilizing geogrid and fixing unit(CMG) is suggested and Finite element analysis is performed for analyzing the depth of surface soil and deep soil stabilization and comparing with DCM method. In the result of the experiment, the displacement in DCM method were lower than the displacement in CMG, it's because the upper load is transferred to deep part soil not treated by cement in CMG method case. The differential settlement in DCM method was higher than the differential settlement in CMG, because of the effect load transfer effect by surface part soil treated by cement and geogrid. In conclusion, CMG method has the advantage of economics and constructability in embankment road, railway, etc in which differential settlement is the important consideration.

Keywords: soft ground, geogrid, fixing unit, partial cement mixing, finite element analysis

Procedia PDF Downloads 370

Authors: Shaibu Baanni Azumah, Ignatius Tindjina, Stella Obanyi, Tara N. Wood

Abstract:

This study examined the effect of Urea Deep Placement (UDP) technology on the output of irrigated rice farmers in the northern region of Ghana. Multi-stage sampling technique was used to select 142 rice farmers from the Golinga and Bontanga irrigation schemes, around Tamale. A treatment effect model was estimated at two stages; firstly, to determine the factors that influenced farmers’ decision to adopt the UDP technology and secondly, to determine the effect of the adoption of the UDP technology on the output of rice farmers. The significant variables that influenced rice farmers’ adoption of the UPD technology were sex of the farmer, land ownership, off-farm activity, extension service, farmer group participation and training. The results also revealed that farm size and the adoption of UDP technology significantly influenced the output of rice farmers in the northern region of Ghana. In addition to the potential of the technology to improve yields, it also presents an employment opportunity for women and youth, who are engaged in the deep placement of Urea Super Granules (USG), as well as in the transplantation of rice. It is recommended that the government of Ghana work closely with the IFDC to embed the UDP technology in the national agricultural programmes and policies. The study also recommends an effective collaboration between the government, through the Ministry of Food and Agriculture (MoFA) and the International Fertilizer Development Center (IFDC) to train agricultural extension agents on UDP technology in the rice producing areas of the country.

Keywords: Northern Ghana, output , irrigation rice farmers, treatment effect model, urea deep placement

Procedia PDF Downloads 419

Authors: Dawoon Choi, Jian Li, Yunhyun Cho

Abstract:

Axial Flux Permanent Magnet (AFPM) machines have been widely used in various applications due to their important merits, such as compact structure, high efficiency and high torque density. This paper presents one of the most important characteristics in the design process of the AFPM device, which is a recent issue. To design AFPM machine, the predicting electromagnetic forces between the permanent magnets and stator is important. Because of the magnitude of electromagnetic force affects many characteristics such as machine size, noise, vibration, and quality of output power. Theoretically, this force is canceled by the equilibrium of force when it is in the middle of the gap, but it is inevitable to deviate due to manufacturing problems in actual machine. Such as large scale wind generator, because of the huge attractive force between rotor and stator disks, this is more serious in getting large power applications such as large. This paper represents the characteristics of Double-Stator Inner –Rotor AFPM machines when it has rotor eccentricity. And, unbalanced air-gap and inclined air-gap condition which is caused by rotor offset and tilt in a double-stator single inner-rotor AFPM machine are each studied in electromagnetic and mechanical aspects. The output voltage and cogging torque under un-normal air-gap condition of AF machines are firstly calculated using a combined analytical and numerical methods, followed by a structure analysis to study the effect to mechanical stress, deformation and bending forces on bearings. Results and conclusions given in this paper are instructive for the successful development of AFPM machines.

Keywords: axial flux permanent magnet machine, inclined air gap, unbalanced air gap, rotor eccentricity

Procedia PDF Downloads 203

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs –Sigmoid, ReLU, and Tanh–have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment with multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLUReLU) combination. Our results show that using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: activation function, universal approximation function, neural networks, convergence

Procedia PDF Downloads 142

Authors: Wojciech Gilewski, Anna Al Sabouni-Zawadzka, Jan Pelczynski

Abstract:

This paper focuses on the analysis of tensile stresses perpendicular to the grain in simply supported beams with different geometry made of glued laminated timber. Two types of beams are considered: standard double-tapered beams described in Eurocode 5 and non-standard glulam beams with a flattened apex. The beams are analyzed using two methodology approaches: a code design verification method and a finite element method (FEM) in terms of the linear theory of elasticity with plane stress assumption. The performed analyses proved that both methodologies lead to consistent results in case of standard glulam beams and therefore, the FEM can be used in case of non-standard structures, which are not included in Eurocode 5. Moreover, the FE analysis of the glulam beam with a flattened apex showed that it can be treated as a structure with two apex zones.

Keywords: double-tapered beams, finite element analysis, glued laminated timber, perpendicular to grain stress

Procedia PDF Downloads 222

Authors: Ziying Wu, Danfeng Yan

Abstract:

Multi-Access Edge Computing (MEC) is one of the key technologies of the future 5G network. By deploying edge computing centers at the edge of wireless access network, the computation tasks can be offloaded to edge servers rather than the remote cloud server to meet the requirements of 5G low-latency and high-reliability application scenarios. Meanwhile, with the development of IOV (Internet of Vehicles) technology, various delay-sensitive and compute-intensive in-vehicle applications continue to appear. Compared with traditional internet business, these computation tasks have higher processing priority and lower delay requirements. In this paper, we design a 5G-based Vehicle-Aware Multi-Access Edge Computing Network (VAMECN) and propose a joint optimization problem of minimizing total system cost. In view of the problem, a deep reinforcement learning-based joint computation offloading and task migration optimization (JCOTM) algorithm is proposed, considering the influences of multiple factors such as concurrent multiple computation tasks, system computing resources distribution, and network communication bandwidth. And, the mixed integer nonlinear programming problem is described as a Markov Decision Process. Experiments show that our proposed algorithm can effectively reduce task processing delay and equipment energy consumption, optimize computing offloading and resource allocation schemes, and improve system resource utilization, compared with other computing offloading policies.

Keywords: multi-access edge computing, computation offloading, 5th generation, vehicle-aware, deep reinforcement learning, deep q-network

Procedia PDF Downloads 95

Authors: Abdul Wajid Ali

Abstract:

Supersonic flight promises speed, but the design of the air inlet faces an obstacle: shock waves. They prevent air flow in the mixed compression ports, which reduces engine performance. Our research investigates this using supersonic wind tunnels and schlieren imaging to reveal the complex dance between shock waves and airflow. The findings show clear patterns of shock wave formation influenced by internal/external pressure surfaces. We looked at the boundary layer, the slow-moving air near the inlet walls, and its interaction with shock waves. In addition, the study emphasizes the dependence of the shock wave behaviour on the Mach number, which highlights the need for adaptive models. This knowledge is key to optimizing the combined compression inputs, paving the way for more powerful and efficient supersonic vehicles. Future engineers can use this knowledge to improve existing designs and explore innovative configurations for next-generation ultrasonic applications.

Keywords: oblique shock formation, boundary layer interaction, schlieren images, double wedge surface

Procedia PDF Downloads 48

Authors: Andrii Natochii

Abstract:

We are currently presenting the recent results from the CERN accelerator facilities obtained in the frame of the UA9 Collaboration. The UA9 experiment investigates how a tiny silicon bent crystal (few millimeters long) can be used for various high-energy physics applications. Due to the huge electrostatic field (tens of GV/cm) between crystalline planes, there is a probability for charged particles, impinging the crystal, to be trapped in the channeling regime. It gives a possibility to steer a high intensity and momentum beam by bending the crystal: channeled particles will follow the crystal curvature and deflect on the certain angle (from tens microradians for LHC to few milliradians for SPS energy ranges). The measurements at SPS, performed in 2017 and 2018, confirmed that the protons deflected by the first crystal, inserted in the primary beam halo, can be caught and channeled by the second crystal. In this configuration, we measure the single pass deflection efficiency of the second crystal and prove our opportunity to perform the fixed target experiment at SPS accelerator (LHC in the future).

Keywords: channeling, double-crystal setup, fixed target experiment, Timepix detector

Procedia PDF Downloads 141

Authors: Sonia Perez-Gamboa, Qingquan Sun, Yan Zhang

Abstract:

Non-intrusive sensor-based human activity recognition (HAR) is utilized in a spectrum of applications, including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short term memory (LSTM) recurrent neural networks (RNNs) provide a way to achieve HAR accurately and effectively. In this paper, we design a multi-layer hybrid architecture with CNN and LSTM and explore a variety of multi-layer combinations. Based on the exploration, we present a lightweight, hybrid, and multi-layer model, which can improve the recognition performance by integrating local features and scale-invariant with dependencies of activities. The experimental results demonstrate the efficacy of the proposed model, which can achieve a 94.7% activity recognition rate on a benchmark human activity dataset. This model outperforms traditional machine learning and other deep learning methods. Additionally, our implementation achieves a balance between recognition rate and training time consumption.

Keywords: deep learning, LSTM, CNN, human activity recognition, inertial sensor

Procedia PDF Downloads 138

Authors: Benyamina Imane, Benalioua Bahia, Mansour Meriem, Bentouami Abdelhadi

Abstract:

The objective of this study is to use a synthetic route of the layered double hydroxide as a method of zinc oxide by doping a transition metal. The material is heat-treated at different temperatures then tested on the photo-fading of acid dye indigo carmine under visible radiation compared with ZnO. The material having a better efficacy was characterized by XRD and thereafter SEM. The result of XRD untreated Bi-Zn-LDH material thermally revealed peaks characteristic lamellar materials. Indeed, the lamellar morphology is very visible, observed by scanning electron microscopy (SEM). Furthermore, the lamellar character partially disappears when the material is treated at 550 °C in a muffle furnace. Thus obtained, a zinc oxide doped with bismuth confirmed by XRD. The photocatalytic efficiency of Bi-ZnO in a visible light of 500 W at 114,6 µw/cm2 as maximum of irradiance was tested on photo-bleaching of an indigoid dye in comparison with the commercial ZnO. Indeed, a complete discoloration of indigo carmine solution of 16 mg / L was obtained after 40 and 120 minutes of irradiation in the presence of Bi-ZnO and ZnO respectively.

Keywords: photocatalysis, Bi-ZnO-LDH, doping, ZnO

Procedia PDF Downloads 498

Authors: Ghobad Gorji, Hasan Golabi

Abstract:

The goal of this paper is to describe the design of an ultra-wideband (UWB) system that is optimized for the low-rate wireless personal area network application. To this aim, we propose a system based on direct chaotic communication (DCC) technology. Based on this system, a 2-GHz wide chaotic signal is directly generated into the lower band of the UWB spectrum, i.e., 3.1–5.1 GHz. For this system, two simple modulation schemes, namely chaotic on-off keying (COOK) and differential chaos shift keying (DCSK), were studied before, and their performance was evaluated. We propose a modulation scheme, namely Double DCSK, to improve the performance of UWB DCC. Different characteristics of these systems, with Monte Carlo simulations based on the Additive White Gaussian Noise (AWGN) and the IEEE 802.15.4a standard channel models, are compared.

Keywords: UWB, DCC, IEEE 802.15.4a, COOK, DCSK

Procedia PDF Downloads 63

Authors: Hy Dang, Bo Mei

Abstract:

The development of machine learning methods and techniques has opened doors for investigation in many areas such as medicines, economics, finance, etc. One active research area involving machine learning is stock market prediction. This research paper tries to consider multiple techniques and methods for stock movement prediction using historical price or price factors. The paper explores the effectiveness of some deep learning frameworks for forecasting stock. Moreover, an architecture (TimeStock) is proposed which takes the representation of time into account apart from the price information itself. Our model achieves a promising result that shows a potential approach for the stock movement prediction problem.

Keywords: classification, machine learning, time representation, stock prediction

Procedia PDF Downloads 135

Authors: Tong He, Long Chen, Irag Mantegh, Wen-Fang Xie

Abstract:

This paper proposes an image-based obstacle avoidance and tracking target identification strategy in GPS-degraded or GPS-denied environment for an Unmanned Aerial Vehicle (UAV). The traditional force algorithm for obstacle avoidance could produce local minima area, in which UAV cannot get away obstacle effectively. In order to eliminate it, an artificial potential approach based on harmonic potential is proposed to guide the UAV to avoid the obstacle by using the vision system. And image-based visual servoing scheme (IBVS) has been adopted to implement the proposed obstacle avoidance approach. In IBVS, the pixel accuracy is a key factor to realize the obstacle avoidance. In this paper, the deep reinforcement learning framework has been applied by reducing pixel errors through constant interaction between the environment and the agent. In addition, the combination of OpenTLD and Tensorflow based on neural network is used to identify the type of tracking target. Numerical simulation in Matlab and ROS GAZEBO show the satisfactory result in target identification and obstacle avoidance.

Keywords: image-based visual servoing, obstacle avoidance, tracking target identification, deep reinforcement learning, artificial potential approach, neural network

Procedia PDF Downloads 130

Authors: Mohammad Mardi

Abstract:

Generally, the resistivity is high in oil layer and low in water layer. Yet there are intervals of oil-bearing zones showing low resistivity, high porosity, and low resistance. In the typical example, well A (depth: 4341.5-4372.0m), both Spectral Gamma Ray (SGR) and Corrected Gamma Ray (CGR) are relatively low; porosity varies from 12-22%. Above 4360 meters, the reservoir shows the conventional positive difference between deep and shallow resistivity with high resistance; below 4360m, the reservoir shows a negative difference with low resistance, especially at depths of 4362.4 meters and 4371 meters, deep resistivity is only 2Ω.m, and the CAST-V imaging map shows that there are low resistance substances contained in the pores or matrix in the reservoirs of this interval. The rock slice analysis data shows that the pyrite volume is 2-3% in the interval 4369.08m-4371.55m. A comprehensive analysis on the volume of shale (Vsh), porosity, invasion features of resistivity, mud logging, and mineral volume indicates that the possible causes for the negative difference between deep and shallow resistivities with relatively low resistance are erosional pores, caves, micritic texture and the presence of pyrite. Full-bore Drill Stem Test (DST) verified 4991.09 bbl/d in this interval. To identify and thoroughly characterize low resistivity intervals coring, Nuclear Magnetic Resonance (NMR) logging and further geological evaluation are needed.

Keywords: low resistivity pay, carbonates petrophysics, microporosity, porosity

Procedia PDF Downloads 152

Authors: Raphael Naryongo, Philip Ngare, Anthony Waititu

Abstract:

This paper deals with numerical simulation of Wishart processes for a single asset risky pricing model whose volatility is described by Wishart affine diffusion processes. The multi-factor specification of volatility will make the model more flexible enough to fit the stock market data for short or long maturities for better returns. The Wishart process is a stochastic process which is a positive semi-definite matrix-valued generalization of the square root process. The aim of the study is to model the log asset stock returns under the double Wishart stochastic volatility model. The solution of the log-asset return dynamics for Bi-Wishart processes will be obtained through Euler-Maruyama discretization schemes. The numerical results on the asset returns are compared to the existing models returns such as Heston stochastic volatility model and double Heston stochastic volatility model

Keywords: euler schemes, log-asset return, infinitesimal generator, wishart diffusion affine processes

Procedia PDF Downloads 365

Authors: Sunil Bandaru, Suresh Yv, Srinivas Vanapalli

Abstract:

Heavy machinery especially compactors has more vibrations induced from the compactor mechanism than the engines. Since the operator’s comfort is most important in any of the machines, this paper shows interest in studying the vibrations on the steering wheel for a double drum compactor. As there are no standard procedures available for testing vibrations on the steering wheel of double drum compactors, this paper tries to evaluate the vibrations on the steering wheel by considering most of the possibilities. In addition to the feasibility for the operator to adjust the steering wheel tilt as in the case of automotive, there is an option for the operator to change the orientation of the operator platform for the complete view of the road’s edge on both the ends of the front and rear drums. When the orientation is either +/-180°, the operator will be closer to the compactor mechanism; also there is a possibility for the shuffle in the modes with respect to the operator. Hence it is mandatory to evaluate the vibrations levels in both cases. This paper attempts to evaluate the vibrations on the steering wheel by considering the two operator platform positions and three steering wheel tilting angles.

Keywords: FEA, CAE, steering column, steering column orientation position

Procedia PDF Downloads 215

Authors: Supriya H. S., Chandrakala B. M.

Abstract:

Deep learning based models have been recently successful adoption for network traffic prediction. However, training a deep learning model for various prediction tasks is considered one of the critical tasks due to various reasons. This research work develops Multi-Layer Hybrid Network (MLHN) for network traffic prediction and analysis; MLHN comprises the three distinctive networks for handling the different inputs for custom feature extraction. Furthermore, an optimized and efficient parameter-tuning algorithm is introduced to enhance parameter learning. MLHN is evaluated considering the “Big Data Challenge” dataset considering the Mean Absolute Error, Root Mean Square Error and R^2as metrics; furthermore, MLHN efficiency is proved through comparison with a state-of-art approach.

Keywords: MLHN, network traffic prediction

Procedia PDF Downloads 73

Authors: Imene Skhakhfa, Lahbaci Ouerdachi

Abstract:

The design of sewerage systems is directly related to rainfall, which has a highly random character. Showers are usually described by three characteristics: intensity, volume and duration. Several studies considered only in two of the three models. The objective of our work is to perform an analysis of the impact of three variables on put in charge of sewerage system, responsible for misbehavior, origin of urban flooding. 30 events were considered events for the longest, most rushed and most intense period which runs from 1986 -2001. We built the IDF curves and heavy projects double symmetrical triangles associated with this selection. A simulation of the operation, with the model canoe, sewage from the city of Annaba (Algeria) in the three rain solicitation project, double triangles associated with events considered. It appears that the sewage of the city of Annaba, in terms of charging, is much more sensitive to rain most precipitous, and the more intense causing loadings and last the longest. Further analysis of all the rain and the field measurements are underway to confirm the test simulations.

Keywords: intensity, volume, duration, sewerage, design, simulation

Procedia PDF Downloads 436

Authors: Shiying Fan, Xinyong Li

Abstract:

The development of highly efficient multifunctional catalytic materials towards HER, ORR and Photo-fuel cell applications in terms of combined electrochemical and photo-electrochemical principles have currently confronted with dire challenges. In this study, novel palladium (Pd) and ruthenium (Ru) Bimetal Quantum Dots (BQDs) co-anchored on Titania nanotube (NTs) arrays electrodes have been successfully constructed by facial two-step electrochemical strategy. Double Schottky junctions with superior performance in electrocatalytic (EC) hydrogen generations and solar fuel cell energy conversions (PE) have been found. Various physicochemical techniques including UV-vis spectroscopy, TEM/EDX/HRTEM, SPV/TRV and electro-chemical strategy including EIS, C-V, I-V, and I-T, etc. were chronically utilized to systematically characterize the crystal-, electronic and micro-interfacial structures of the composites with double Schottky junction, respectively. The characterizations have implied that the marvelous enhancement of separation efficiency of electron-hole pairs generations is mainly caused by the Schottky-barriers within the nanocomposites, which would greatly facilitate the interfacial charge transfer for H₂ generations and solar fuel cell energy conversions. Moreover, the DFT calculations clearly indicated that the oriented growth of Ru and Pd bimetal atoms at the anatase (101) surface is mainly driven by the interaction between Ru/Pd and surface atoms, and the most active site for bimetal Ru and Pd adatoms on the perfect TiO₂ (101) surface is the 2cO-6cTi-3cO bridge sites and the 2cO-bridge sites with the highest adsorption energy of 9.17 eV. Furthermore, the electronic calculations show that in the nanocomposites, the number of impurity (i.e., co-anchored Ru-Pd BQDs) energy levels near Fermi surface increased and some were overlapped with original energy level, promoting electron energy transition and reduces the band gap. Therefore, this work shall provide a deeper insight for the molecular design of Bimetal Quantum Dots (BQDs) assembled onto Tatiana NTs composites with superior performance for electrocatalytic hydrogen productions and solar fuel cell energy conversions (PE) simultaneously.

Keywords: eletrocatalytic, Ru-Pd bimetallic quantum dots, titania nanotube arrays, double Schottky junctions, hydrogen production

Procedia PDF Downloads 135

Authors: Bin Wang, Yong Xu, Honggang Qu, Rongmei Liu, Zhenji Gao

Abstract:

Based on the geodynamic environment, basic geological characteristics of minerals and so on, gold deposits in China are divided into 11 categories, of which tectonic fracture altered rock, mid-intrudes and contact zone, micro-fine disseminated and continental volcanic types are the main prospecting kinds. The metallogenic age of gold deposits in China is dominated by the Mesozoic and Cenozoic. According to the geotectonic units, geological evolution, geological conditions, spatial distribution, gold deposits types, metallogenic factors etc., 42 gold concentration areas are initially determined and have a concentrated distribution feature. On the basis of the gold exploration density, gold concentration areas are divided into high, medium and low level areas. High ones are mainly distributed in the central and eastern regions. 93.04% of the gold exploration drillings are within 500 meters, but there are some problems, such as less and shallower of drilling verification etc.. The paper discusses the resource potentials of gold deposits and proposes the future prospecting directions and suggestions. The deep and periphery of old mines in the central and eastern regions and western area, especially in Xinjiang and Qinghai, will be the future key prospecting one and have huge potential gold reserves. If the exploration depth is extended to 2,000 meters shallow, the gold resources will double.

Keywords: gold deposits, gold deposits types, gold concentration areas, prospecting, resource potentiality

Procedia PDF Downloads 60

Authors: Bahareh Golchin, Nooshin Riahi

Abstract:

One of the most significant issues as attended a lot in recent years is that of recognizing the sentiments and emotions in social media texts. The analysis of sentiments and emotions is intended to recognize the conceptual information such as the opinions, feelings, attitudes and emotions of people towards the products, services, organizations, people, topics, events and features in the written text. These indicate the greatness of the problem space. In the real world, businesses and organizations are always looking for tools to gather ideas, emotions, and directions of people about their products, services, or events related to their own. This article uses the Twitter social network, one of the most popular social networks with about 420 million active users, to extract data. Using this social network, users can share their information and opinions about personal issues, policies, products, events, etc. It can be used with appropriate classification of emotional states due to the availability of its data. In this study, supervised learning and deep neural network algorithms are used to classify the emotional states of Twitter users. The use of deep learning methods to increase the learning capacity of the model is an advantage due to the large amount of available data. Tweets collected on various topics are classified into four classes using a combination of two Bidirectional Long Short Term Memory network and a Convolutional network. The results obtained from this study with an average accuracy of 93%, show good results extracted from the proposed framework and improved accuracy compared to previous work.

Keywords: emotion classification, sentiment analysis, social networks, deep neural networks

Procedia PDF Downloads 128

Authors: Amir Aziz, Martin Tuner, Sebastian Verhelst, Oivind Andersson

Abstract:

Partially Premixed Combustion (PPC) is a combustion concept which aims to simultaneously achieve high efficiency and low engine-out emissions. Extending the ignition delay to promote the premixing, has been recognized as one of the key factor to achieve PPC. Fuels with high octane number have been proven to be a good candidates to extend the ignition delay. In this work, E85 (85% ethanol) has been used as a PPC fuel. The aim of this work was to investigate a suitable injection strategy for PPC combustion fueled with E85 in a single-cylinder heavy-duty engine. Single and double injection strategy were applied with different injection timing and the ratio between different injection pulses was varied. The performance and emission were investigated at low load. The results show that the double injection strategy should be preferred for PPC fueled with E85 due to low emissions and high efficiency, while keeping the pressure raise rate at very low levels.

Keywords: E85, partially premixed combustion, injection strategy, performance and emission

Procedia PDF Downloads 167

Authors: P. R. Prabhu, S. M. Kulkarni, S. S. Sharma, K. Jagannath, Achutha Kini U.

Abstract:

In the present study, response surface methodology has been used to optimize turn-assisted deep cold rolling process of AISI 4140 steel. A regression model is developed to predict surface hardness and surface roughness using response surface methodology and central composite design. In the development of predictive model, deep cold rolling force, ball diameter, initial roughness of the workpiece, and number of tool passes are considered as model variables. The rolling force and the ball diameter are the significant factors on the surface hardness and ball diameter and numbers of tool passes are found to be significant for surface roughness. The predicted surface hardness and surface roughness values and the subsequent verification experiments under the optimal operating conditions confirmed the validity of the predicted model. The absolute average error between the experimental and predicted values at the optimal combination of parameter settings for surface hardness and surface roughness is calculated as 0.16% and 1.58% respectively. Using the optimal processing parameters, the hardness is improved from 225 to 306 HV, which resulted in an increase in the near surface hardness by about 36% and the surface roughness is improved from 4.84µm to 0.252 µm, which resulted in decrease in the surface roughness by about 95%. The depth of compression is found to be more than 300µm from the microstructure analysis and this is in correlation with the results obtained from the microhardness measurements. Taylor Hobson Talysurf tester, micro Vickers hardness tester, optical microscopy and X-ray diffractometer are used to characterize the modified surface layer.

Keywords: hardness, response surface methodology, microstructure, central composite design, deep cold rolling, surface roughness

Procedia PDF Downloads 409

Authors: Xiaoyan Dai, Hsieh Yisan

Abstract:

Barcode processing of captured images is a huge challenge, as different shooting conditions can result in different barcode appearances. This paper proposes a deep learning-based barcode detection using synthetic-to-real data augmentation. We first augment barcodes themselves; we then augment images containing the barcodes to generate a large variety of data that is close to the actual shooting environments. Comparisons with previous works and evaluations with our original data show that this approach achieves state-of-the-art performance in various real images. In addition, the system uses hybrid resolution for barcode “scan” and is applicable to real-time applications.

Keywords: barcode detection, data augmentation, deep learning, image-based processing

Procedia PDF Downloads 151

Authors: Aditya Karade, Sharada Falane, Dhananjay Deshmukh, Vijaykumar Mantri

Abstract:

Brain tumors pose a significant challenge in healthcare due to their complex nature and impact on patient outcomes. The application of deep learning (DL) algorithms in medical imaging have shown promise in accurate and efficient brain tumour detection. This paper explores the performance of various pre-trained DL models ResNet50, Xception, InceptionV3, EfficientNetB0, DenseNet121, NASNetMobile, VGG19, VGG16, and MobileNet on a brain tumour dataset sourced from Figshare. The dataset consists of MRI scans categorizing different types of brain tumours, including meningioma, pituitary, glioma, and no tumour. The study involves a comprehensive evaluation of these models’ accuracy and effectiveness in classifying brain tumour images. Data preprocessing, augmentation, and finetuning techniques are employed to optimize model performance. Among the evaluated deep learning models for brain tumour detection, ResNet50 emerges as the top performer with an accuracy of 98.86%. Following closely is Xception, exhibiting a strong accuracy of 97.33%. These models showcase robust capabilities in accurately classifying brain tumour images. On the other end of the spectrum, VGG16 trails with the lowest accuracy at 89.02%.

Keywords: brain tumour, MRI image, detecting and classifying tumour, pre-trained models, transfer learning, image segmentation, data augmentation

Procedia PDF Downloads 58

Authors: C. G. Shashi Kumar, G. Arun Maiya, H. Manjunath Hande, K. V. Rajagopal

Abstract:

Background: Diabetes mellitus (DM) is a metabolic disorder with involvement of neurovascular and muscular system. Studies have documented that the gait parameter is altered in type 2 diabetes mellitus with peripheral neuropathy. However, there is a dearth of literature regarding the gait characteristics in type 2 diabetes mellitus (T2DM) without peripheral neuropathy. Therefore, the present study is focused on identifying gait changes in early type 2 diabetes mellitus without peripheral neuropathy. Objective: To analyze the gait characteristics in Type 2 diabetes mellitus without peripheral neuropathy. Methods: After obtaining ethical clearance from Institutional Ethical Committee (IEC), 36 T2DM without peripheral neuropathy and 32 matched healthy subjects were recruited. Gait characteristics (step duration, gait cycle length, gait cycle duration, stride duration, step length, double stance duration) of all the subjects were analyzed using Windtrack dynamic foot scanner. Data were analyzed using Independent‘t’ test to find the difference between the groups (step duration, gait cycle length, gait cycle duration) and Mann-Whitney test was used to analyze the step length and double stance duration to find difference between the groups. Level of significance was kept at P<0.05. Results: Result analysis showed significant decrease in step duration, gait cycle length, gait cycle duration, step length, double stance duration in T2DM subjects as compared to healthy subjects. We also observed a mean increase in stride duration in T2DM subjects compared to healthy subjects.

Keywords: type 2 diabetes mellitus, dynamic foot scan, gait characteristics, medical and health sciences

Procedia PDF Downloads 425

Authors: Mehmet Karabekir

Abstract:

Attack helicopters (AHs) are usually deployed in conventional warfare to destroy armored and mechanized forces of enemy. In addition, AHs are able to perform various tasks in the deep, and close operations – intelligence, surveillance, reconnaissance, air assault operations, and search and rescue operations. Apache helicopters were properly employed in the Gulf Wars and contributed the success of campaign by destroying a large number of armored and mechanized vehicles of Iraq Army. The purpose of this article is to discuss the deployment of AHs in conventional warfare in the light of Gulf Wars. First, the employment of AHs in deep and close operations will be addressed regarding the doctrine. Second, the US armed forces AH-64 doctrinal and tactical usage will be argued in the 1st and 2nd Gulf Wars.

Keywords: attack helicopter, conventional warfare, gulf wars

Procedia PDF Downloads 460

Authors: Selim M. Khan

Abstract:

Indoor air quality is strongly influenced by the presence of radioactive radon (222Rn) gas. Indeed, exposure to high 222Rn concentrations is unequivocally linked to DNA damage and lung cancer and is a worsening issue in North American and European built environments, having increased over time within newer housing stocks as a function of as yet unclear variables. Indoor air radon concentration can be influenced by a wide range of environmental, structural, and behavioral factors. As some of these factors are quantitative while others are qualitative, no single statistical model can determine indoor radon level precisely while simultaneously considering all these variables across a complex and highly diverse dataset. The ability of AI- machine (deep) learning to simultaneously analyze multiple quantitative and qualitative features makes it suitable to predict radon with a high degree of precision. Using Canadian and Swedish long-term indoor air radon exposure data, we are using artificial deep neural network models with random weights and polynomial statistical models in MATLAB to assess and predict radon health risk to human as a function of geospatial, human behavioral, and built environmental metrics. Our initial artificial neural network with random weights model run by sigmoid activation tested different combinations of variables and showed the highest prediction accuracy (>96%) within the reasonable iterations. Here, we present details of these emerging methods and discuss strengths and weaknesses compared to the traditional artificial neural network and statistical methods commonly used to predict indoor air quality in different countries. We propose an artificial deep neural network with random weights as a highly effective method for assessing and predicting indoor radon.

Keywords: radon, radiation protection, lung cancer, aI-machine deep learnng, risk assessment, risk prediction, Europe, North America

Procedia PDF Downloads 86