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

Authors: Ksenia Meshkova

Abstract:

With increasing amount of multimedia data, it is very important to automate and speed up the process of obtaining meta. This process means not just recognition of some object or its movement, but recognition of the entire scene versus separate frames and having timeline segmentation as a final result. Labeling datasets is time consuming, besides, attributing characteristics to particular scenes is clearly difficult due to their nature. In this article, we will consider autoencoders application to unsupervised scene recognition and clusterization based on interpretable features. Further, we will focus on particular types of auto encoders that relevant to our study. We will take a look at the specificity of deep learning related to information theory and rate-distortion theory and describe the solutions empowering poor interpretability of deep learning in media content processing. As a conclusion, we will present the results of the work of custom framework, based on autoencoders, capable of scene recognition as was deeply studied above, with highlights generation resulted out of this recognition. We will not describe in detail the mathematical description of neural networks work but will clarify the necessary concepts and pay attention to important nuances.

Keywords: neural networks, computer vision, representation learning, autoencoders

Procedia PDF Downloads 116

Authors: William Li

Abstract:

Lane-change path planning is a crucial and yet complex task in autonomous driving. The traditional path planning approach based on a system of carefully-crafted rules to cover various driving scenarios becomes unwieldy as more and more rules are added to deal with exceptions and corner cases. This paper proposes to divide the entire path planning to two stages. In the first stage the ego vehicle travels longitudinally in the source lane to reach a safe state. In the second stage the ego vehicle makes lateral lane-change maneuver to the target lane. The paper derives the safe state conditions based on lateral lane-change maneuver calculation to ensure collision free in the second stage. To determine the acceleration sequence that minimizes the time to reach a safe state in the first stage, the paper proposes three schemes, namely, kinetic model based optimization, deep reinforcement learning, and 5G vehicle-to-vehicle (V2V) communications. The paper investigates these schemes via simulation. The model-based optimization is sensitive to the model assumptions. The deep reinforcement learning is more flexible in handling scenarios beyond the model assumed by the optimization. The 5G V2V eliminates uncertainty in predicting future behaviors of surrounding vehicles by sharing driving intents and enabling cooperative driving.

Keywords: lane change, path planning, autonomous driving, deep reinforcement learning, 5G, V2V communications, connected vehicles

Procedia PDF Downloads 229

Authors: Snowie Jane Galgo, Victor Asio

Abstract:

Geochemical composition of soils provides vital information about their origin and development. Highly weathered soils are widespread in the islands of Leyte and Samar but limited data have been published in terms of their nature, characteristics and nutrient status. This study evaluated the total elemental composition, properties and nutrient status of eight (8) deep and highly weathered soils in various parts of Leyte and Samar. Sampling was done down to 3 to 4 meters deep. Total amounts of Al₂O₃, As₂O₃, CaO, CdO, Cr₂O₃, CuO, Fe₂O₃, K₂O, MgO, MnO, Na₂O, NiO, P₂O₅, PbO, SO₃, SiO₂, TiO₂, ZnO and ZrO₂ were analyzed using an X-ray analytical microscope for eight soil profiles. Most of the deep and highly weathered soils have probably developed from homogenous parent materials based on the regular distribution with depth of TiO₂ and ZrO₂. Two of the soils indicated high variability with depth of TiO₂ and ZrO₂ suggesting that these soils developed from heterogeneous parent material. Most soils have K₂O and CaO values below those of MgO and Na₂O. This suggests more losses of K₂O and CaO have occurred since they are more mobile in the weathering environment. Most of the soils contain low amounts of other elements such as CuO, ZnO, PbO, NiO, CrO and SO₂. Basic elements such as K₂O and CaO are more mobile in the weathering environment than MgO and Na₂O resulting in higher losses of the former than the latter. Other elements also show small amounts in all soil profile. Thus, this study is very useful for sustainable crop production and environmental conservation in the study area specifically for highly weathered soils which are widespread in the Philippines.

Keywords: depth function, geochemical composition, highly weathered soils, total elemental composition

Procedia PDF Downloads 256

Authors: Youji Miyake

Abstract:

In aircraft assembly, a large number of preparatory holes are required for screw and rivet joints. Currently, many holes are drilled manually because it is difficult to machine the holes using conventional computerized numerical control(CNC) machines. The application of industrial robots to drill the hole has been considered as an alternative to the CNC machines. However, the rigidity of robot arms is so low that vibration is likely to occur during drilling. In this study, it is proposed constant-load feed machining as a method to perform high-precision drilling while minimizing the thrust force, which is considered to be the cause of vibration. In this method, the drill feed is realized by a constant load applied onto the tool so that the thrust force is theoretically kept below the applied load. The performance of the proposed method was experimentally examined through the deep hole drilling of plastic and simultaneous drilling of metal/plastic stack plates. It was confirmed that the deep hole drilling and simultaneous drilling could be performed without generating vibration by controlling the tool feed rate in the appropriate range.

Keywords: constant load feed machining, robotic drilling, deep hole, simultaneous drilling

Procedia PDF Downloads 188

Authors: Mulugeta Fola, Mengistu Ketema, Kumilachew Alamerie

Abstract:

Watershed provides vast economic benefits within and beyond the management area of interest. But most watersheds in Ethiopia are increasingly facing the threats of degradation due to both natural and man-made causes. To reverse these problems, communities’ participation in sustainable management programs is among the necessary measures. Hence, this study assessed the households’ willingness to pay for watershed management practices through a contingent valuation study approach. Double bounded dichotomous choice with open-ended follow-up format was used to elicit the households’ willingness to pay. Based on data collected from 275 randomly selected households, descriptive statistics results indicated that most households (79.64%) were willing to pay for watershed management practices. A bivariate Probit model was employed to identify determinants of households’ willingness to pay and estimate mean willingness to pay. Its result shows that age, gender, income, livestock size, perception of watershed degradation, social position, and offered bids were important variables affecting willingness to pay for watershed management practices. The study also revealed that the mean willingness to pay for watershed management practices was calculated to be 58.41 Birr and 47.27 Birr per year from the double bounded and open-ended format, respectively. The study revealed that the aggregate welfare gains from watershed management practices were calculated to be 931581.09 Birr and 753909.23 Birr per year from double bounded dichotomous choice and open-ended format, respectively. Therefore, the policymakers should make households to pay for the services of watershed management practices in the study area.

Keywords: bivariate probit model, contingent valuation, watershed management practices, willingness to pay

Procedia PDF Downloads 216

Authors: Atakan Aral Ormancı, Tuğçe Arslantaş, Murat Özcü

Abstract:

This study presents the design and implementation of an experimental chassis-level system for various control applications. Specifically, the height level of the chassis is controlled using proportional integrated derivative, fuzzy logic, and deep learning control methods. Real-time data obtained from height and pressure sensors installed in a 6x2 truck chassis, in combination with pulse-width modulation signal values, are utilized during the tests. A prototype pneumatic system of a 6x2 truck is added to the setup, which enables the Smart Pneumatic Actuators to function as if they were in a real-world setting. To obtain real-time signal data from height sensors, an Arduino Nano is utilized, while a Raspberry Pi processes the data using Matlab/Simulink and provides the correct output signals to control the Smart Pneumatic Actuator in the truck chassis. The objective of this research is to optimize the time it takes for the chassis to level down and up under various loads. To achieve this, proportional integrated derivative control, fuzzy logic control, and deep learning techniques are applied to the system. The results show that the deep learning method is superior in optimizing time for a non-linear system. Fuzzy logic control with a triangular membership function as the rule base achieves better outcomes than proportional integrated derivative control. Traditional proportional integrated derivative control improves the time it takes to level the chassis down and up compared to an uncontrolled system. The findings highlight the superiority of deep learning techniques in optimizing the time for a non-linear system, and the potential of fuzzy logic control. The proposed approach and the experimental results provide a valuable contribution to the field of control, automation, and systems engineering.

Keywords: automotive, chassis level control, control systems, pneumatic system control

Procedia PDF Downloads 69

Authors: John Pomerat, Aviv Segev

Abstract:

Recently, deep learning has had many theoretical breakthroughs. For deep learning to be successful in the industry, however, there need to be practical algorithms capable of handling many real-world hiccups preventing the immediate application of a learning algorithm. Although AI promises to revolutionize the healthcare industry, getting access to patient data in order to train learning algorithms has not been easy. One proposed solution to this is data- sharing. In this paper, we propose an alternative protocol, based on multi-party computation, to train deep learning models while maintaining both the privacy and security of training data. We examine three methods of training neural networks in this way: Transfer learning, average ensemble learning, and series network learning. We compare these methods to the equivalent model obtained through data-sharing across two different experiments. Additionally, we address the security concerns of this protocol. While the motivating example is healthcare, our findings regarding multi-party computation of neural network training are purely theoretical and have use-cases outside the domain of healthcare.

Keywords: neural network aggregation, multi-party computation, transfer learning, average ensemble learning

Procedia PDF Downloads 154

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 138

Authors: B. Umaru Mohammed, Faris A. Al-Maziad, Mohammad Y. Numan

Abstract:

One of the most important factors affecting the energy performance within a building is a carefully and efficiently designed facade. The primary aim of this research was to identify and present the potentiality of utilising Double-Skin Facade (DSF) construction and critically examine its effect on the energy consumption of an office building located within a maritime desert climate as to the conventional single-skin curtain wall system. A comparative analysis of the effect on the overall energy consumption within an office building was investigated in which a combination of various Double-Skin Facade configurations, systems, and cavity depths, glazing types and orientations were utilised. A computer dynamic modelling was utilised in order to ensure accurate calculations and efficient simulations of the various DSF systems due to the complex nature of the various functions within the Facade cavity. Through the use of the dynamic thermal modelling simulations, the best cavity size glazed type and orientation were determined to lead to a detailed analysis of the efficiency of each respective combination of Double-Skin Facade construction. As such the optimal facade combination for use within an office building located in a maritime desert climate was identified. Results demonstrated that a multi-story Facade, depending on its configuration, save up to 5% on annual cooling loads respect to a Corridor Facade and while vented can save unto 12% when compared to the single skin façade, on annual cooling load in the maritime desert climate. The selected configuration of the DSF from SSF saves an overall annual cooling load of 32%.A comparative analysis of the effect on the overall energy consumption within an office building was investigated in which a combination of various Double-Skin Facade configurations, systems, and cavity depths, glazing types and orientations were utilized. A computer dynamic modelling was utilized in order to ensure accurate calculations and efficient simulations of the various DSF systems due to the complex nature of the various functions within the Facade cavity. Through the use of the dynamic thermal modelling simulations, the best cavity size glazed type and orientation were determined to lead to a detailed analysis of the efficiency of each respective combination of Double-Skin Facade construction. As such the optimal facade combination for use within an office building located in a maritime desert climate was identified. Results demonstrated that a multi-story Facade, depending on its configuration, save up to 5% on annual cooling loads respect to a Corridor Facade and while vented can save unto 12% when compared to the single skin facade, on annual cooling load in the maritime desert climate. The selected configuration of the DSF from SSF saves an overall annual cooling load of 32%.

Keywords: computer dynamics modelling, comparative analysis, energy computation, double skin facade, single skin curtain wall, maritime desert climate

Procedia PDF Downloads 338

Authors: Benjamin Legros, Jan Fransoo, Oualid Jouini

Abstract:

This study aims to evaluate street-turn strategies for empty container repositioning in the hinterland. Containers arrive over time at the (importer) consignee, while the demand for containers arises from the (exporter) shipper. A match can be operated between an empty container from the consignee and the load from the shipper. Therefore, we model the system as a double-ended queue with non-zero matching time and a limited number of resources in order to optimize the reposition- ing decisions. We determine the performance measures when the consignee operates using a fixed withholding threshold policy. We show that the matching time mainly plays a role in the matching proportion, while under a certain duration, it only marginally impacts the consignee’s inventory policy and cost per container. Also, the withholding level is mainly determined by the shipper’s production rate.

Keywords: container, double-ended queue, inventory, Markov decision process, non-zero matching time, street-turn

Procedia PDF Downloads 134

Authors: Seon Yeong Byeon, Hwa Sung Shin

Abstract:

Nanofibrous sheets are of interest in the beauty industries due to the properties of moisturizing, adhesion to skin and delivery of nutrient materials. The benefit and function of the cosmetic products should not be considered without safety thus a non-toxic manufacturing process is ideal when fabricating the products. In this study, we have developed cosmetic patches consisting of alginate and Spirulina extract, a marine resource which has antibacterial and antioxidant effects, without addition of harmful cross-linkers. The patches obtained their structural stabilities by layer-upon-layer electrospinning of an alginate layer on a formerly spread polycaprolactone (PCL) layer instead of crosslinking method. The morphological characteristics, release of Spirulina extract, water absorption, skin adhesiveness and cytotoxicity of the double-layered patches were assessed. The image of scanning electron microscopy (SEM) showed that the addition of Spirulina extract has made the fiber diameter of alginate layers thinner. Impregnation of Spirulina extract increased their hydrophilicity, moisture absorption ability and skin adhesive ability. In addition, wetting the pre-dried patches resulted in releasing the Spirulina extract within 30 min. The patches were detected to have no cytotoxicity in the human keratinocyte cell-based MTT assay, but rather showed increased cell viability. All the results indicate the bioactive and hydro-adhesive double-layered patches have an excellent applicability to bioproducts for personal skin care in the trend of ‘A mask pack a day’.

Keywords: alginate, cosmetic patch, electrospun nanofiber, polycaprolactone, Spirulina extract

Procedia PDF Downloads 341

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 258

Authors: Titus Wuyah Yunana

Abstract:

This study analyzed the impact of commercial agricultural credit scheme on income of beneficiary farmers in Kaduna State using the Net farm income and double difference method. A questionnaire was used to source the data from 306 farmers comprising of 153 beneficiaries and 153 non-beneficiaries. The results indicated that the net farm income of the commercial agricultural credit scheme beneficiaries increases from N15,006,352.00 before scheme to N24,862,585.00 after the first and the second phases of the scheme. There was also an increase in the net farm income of the non-beneficiaries from N9, 670,385.40 to N14, 391,469.00 during the scheme. The double difference method analysis indicated a positive mean income difference value between beneficiaries and nonbeneficiaries after the first and the second phases of the scheme. The study recommends expansion in the number of beneficiaries and efficient allocation and utilization of the resources. The government should also introduce more programs that will assist the farmers to increase their productivity, income and the economy as a whole.

Keywords: agriculture, credit scheme, farmers, income, beneficiary

Procedia PDF Downloads 327

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 262

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 86

Authors: Serap Pektas

Abstract:

Ataxia telangiectasia mutated (ATM) is a serine-threonine kinase, which is the major regulator of the DNA damage response. ATM is activated upon the formation of DNA double-strand breaks (DSBs) in the cells. ATM phosphorylates the proteins involved in apoptotic responses, cell cycle checkpoint control, DNA repair, etc. Tumor protein p53, known as p53 is one of these proteins that phosphorylated by ATM. Phosphorylation of p53 at Ser15 residue leads to p53 stabilization in the cells. Often enzymes activity is affected by hydrogen ion concentration (pH). In order to find the optimal pH range for ATM activity, steady-state kinetic assays were performed at acidic and basic pH ranges. Ser15 phosphorylation of p53 is determined by using ELISA. The results indicated that the phosphorylation rate was better at basic pH range compared with the acidic pH range. This could be due to enzyme stability, or enzyme-substrate interaction is pH dependent.

Keywords: ataxia telangiectasia mutated, DNA double strand breaks, DNA repair, tumor protein p53

Procedia PDF Downloads 122

Authors: Manjot Kaur, Harminder Singh, S. K. Jawandha

Abstract:

The present investigations were carried out at Fruit Research Farm, Department of Fruit Science, Punjab Agricultural University, Ludhiana during the years 2016 and 2017, with the aim of assessing the effect of amino acids on fruit development, shoot growth and yield of peach. The six-year-old peach trees of cv. Florida Prince were sprayed with 0.25 % and 0.50 % concentrations of amino acids (Peptone P1 023), 7 and 14 days after full bloom and the sprays were repeated after 15 and 30 days. Experimental findings showed that all the amino acid treatments increased fruit growth, shoot growth, fruit retention and yield and decreased fruit drop as compared to control during both the years. Maximum fruit retention (89.29 %) and minimum fruit drop (10.71 %) was observed in T8 (2 sprays @ 0.50%). Highest mean shoot growth (113.89 cm) was recorded in T12 (3 sprays @ 0.50%) while the minimum was in control plants (88.23 cm). Fruit yield was also found to be maximum (53.92 kg/tree) under double spray treatment T8 (2 sprays @ 0.50%) of amino acids and minimum in plants sprayed with triple spray of amino acids. Fruit maturity was advanced by 3-4 days by double spray treatments of amino acids as compared to control. In brief, the application of double spray of amino acids @ 0.50% (applied 14 days after full bloom and 15 days later), was found to be best to improve the fruit growth, fruit retention and yield of Florida Prince peach under Punjab conditions.

Keywords: amino acids, fruit growth, maturity, peach, shoot growth

Procedia PDF Downloads 177

Authors: David Rafetseder, Walter Bauer, Florian Poltschak, Wolfgang Amrhein

Abstract:

A flat double-stator linear induction machine (DSLIM) with a short squirrel-cage mover is designed for high thrust force at moderate speed < 5m/s. The performance and motor parameters are determined on the basis of a 2D time-transient simulation with the finite element (FE) software Maxwell 2015. Design guidelines and transformation rules for space vector theory of the LIM are presented. Resulting thrust calculated by flux and current vectors is compared with the FE results showing good coherence and reduced noise. The parameters of the equivalent circuit model are obtained.

Keywords: equivalent circuit model, finite element model, linear induction motor, space vector theory

Procedia PDF Downloads 559

Authors: Kwei Huan Liw, Sashi B. Darshan

Abstract:

Background: Double eyelid surgery has become one of the most sought-after aesthetic procedures among Asians. Many surgeons perform surgical blepharoplasty and various other methods of non-incisional blepharoplasty. Face-Q is a validated method of measuring patient satisfaction for facial aesthetic procedures. Here we have analyzed the overall eye satisfaction score, the upper eyelid appraisal score and the adverse effect on eyes score Methods: 274 patients (548 eyes), aged between 18 to 40 years old, were recruited from 2015-2018. Each patient underwent a non-incisional double-eyelid blepharoplasty using a single-knotted continuous buried suture. 3 – 5 stab incisions were made depending on the upper eyelid size. A needle loaded with 7-0 nylon is passed from the lateral most wound through the dermis and the conjunctiva in an alternate fashion into the remaining stab wounds. The suture is then tunneled back laterally in the deeper dermis and knotted securely with the suture end. The knot is then buried within the orbicularis oculi muscle. Each patient was required to fill the Face-Q questionnaire before the procedure and 2 weeks post procedure. The results are described based on the percentage of the maximum achievable score. Patients were reviewed after 12 to 18 months to assess the long-term outcome. Results: The overall eye satisfaction score demonstrated a high level of post-operative satisfaction (97.85%), compared to 27.32% pre-operatively. The appraisal of upper eyelid scores showed drastic improvement in perception post-operatively (95.31%) compared to 21.44% pre-operatively. Adverse effect on eyes score showed a very low post-operative complication rate (0.4%) The long-term follow-up showed 6 cases that had developed asymmetrical folds. Only 1 patient agreed for revision surgery. The other 5 patients were still satisfied with the outcome and were not keen for revision surgery. None of the cases had loosening of knots. Conclusion: Modified single-knot continuous buried suture technique is a simple and non-invasive method to create aesthetically pleasing non-surgical double-eyelids, which has long-term effects. Proper patient selection is crucial and good surgical technique is required to achieve a desirable outcome.

Keywords: blepharoplasty, double-eyelid, face-Q, non-incisional

Procedia PDF Downloads 114

Authors: Asmau Mukhtar Ahmed, Olga Duran

Abstract:

Hydrocarbon (HC) spills constitute a significant problem that causes great concern to the environment. With the latest technology (hyperspectral images) and state of the earth techniques (image processing tools), hydrocarbon spills can easily be detected at an early stage to mitigate the effects caused by such menace. In this study; a controlled laboratory experiment was used, and clay soil was mixed and homogenized with different hydrocarbon types (diesel, bio-diesel, and petrol). The different mixtures were scanned with HYSPEX hyperspectral camera under constant illumination to generate the hypersectral datasets used for this experiment. So far, the Short Wave Infrared Region (SWIR) has been exploited in detecting HC spills with excellent accuracy. However, the Near-Infrared Region (NIR) is somewhat unexplored with regards to HC contamination and how it affects the spectrum of soils. In this study, Deep Neural Network (DNN) was applied to the controlled datasets to detect and quantify the amount of HC spills in soils in the Near-Infrared Region. The initial results are extremely encouraging because it indicates that the DNN was able to identify features of HC in the Near-Infrared Region with a good level of accuracy.

Keywords: hydrocarbon, Deep Neural Network, short wave infrared region, near-infrared region, hyperspectral image

Procedia PDF Downloads 106

Authors: Balogun R. Ayodeji, Adefisan E. Adesanya, Adeyewa Z. Debo, E. C. Okogbue

Abstract:

Deep convective systems during active periods of the West African monsoon season have not been properly investigated over better temporal and spatial resolution in West Africa. Deep convective systems are investigated over seven climatic zones of the West African sub-region, which are; west-coast rainforest, dry rainforest, Nigeria-Cameroon rainforest, Nigeria savannah, Central African and South Sudan (CASS) Savannah, Sudano-Sahel, and Sahel, using data from Tropical Rainfall Measurement Mission (TRMM) Precipitation Feature (PF) database. The vertical structure of the convective systems indicated by the presence of at least one 40 dBZ and reaching (attaining) at least 1km in the atmosphere showed strong core (highest frequency (%)) of reflectivity values around 2 km which is below the freezing level (4-5km) for all the zones. Echoes are detected above the 15km altitude much more frequently in the rainforest and Savannah zones than the Sudano and Sahel zones during active periods in March-May (MAM), whereas during active periods in June-September (JJAS) the savannahs, Sudano and Sahel zones convections tend to reach higher altitude more frequently than the rainforest zones. The percentage frequencies of deep convection indicated that the occurrences of the systems are within the range of 2.3-2.8% during both March-May (MAM) and June-September (JJAS) active periods in the rainforest and savannah zones. On the contrary, the percentage frequencies were found to be less than 2% in the Sudano and Sahel zones, except during the active-JJAS period in the Sudano zone.

Keywords: active periods, convective system, frequency, reflectivity

Procedia PDF Downloads 144

Authors: Seyedeh Faranak Baniahmad, Soroor Yousefi

Abstract:

Osteoporosis is a bone disease which increases the bone fracture risk, reduces the bone mineral density (BMD) and alters the amount and variety of proteins in bones. Antiresorptive therapy is one the most popular Osteoporosis treatment methods. In this method the bisphosphonates, hormones, calcitonin or the selective estrogen receptor modulators is replaced. In order to reduce undesirable effects and to increase the bioavailability of drug agents, the controlled drug delivery systems have been utilized. In current study, the controlled release of Alendronate from LDH-PCL with (0, 5, 10, 15 % wt. of LDH) was investigated. The results showed that the release of alendronate from the lamellar LDH incorporated into the PCL matrix is much slower than the release of alendronate from the PCL. Therefore such systems are very promising, in which the antiresorptive drug has to remain in the matrix for longer time and can be released in controlled manner.

Keywords: osteoporosis, alendronate, poly (ε–caprolactone), layered double hydroxide

Procedia PDF Downloads 387

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 82

Authors: Venkata Narayana Chejarla, Nafisa Parvez Shaik, Gopi Vara Prasad Marabathula, Deva Kumar Bejjam

Abstract:

Yoga is an advanced, well-recognized method with roots in Indian philosophy. Yoga benefits both the body and the psyche. Yoga is a regular exercise that helps people relax and sleep better while also enhancing their balance, endurance, and concentration. Yoga can be learned in a variety of settings, including at home with the aid of books and the internet as well as in yoga studios with the guidance of an instructor. Self-learning does not teach the proper yoga poses, and doing them without the right instruction could result in significant injuries. We developed "Online Yoga Asana Trainer using Deep Learning" so that people could practice yoga without a teacher. Our project is developed using Tensorflow, Movenet, and Keras models. The system makes use of data from Kaggle that includes 25 different yoga poses. The first part of the process involves applying the movement model for extracting the 17 key points of the body from the dataset, and the next part involves preprocessing, which includes building a pose classification model using neural networks. The system scores a 98.3% accuracy rate. The system is developed to work with live videos.

Keywords: yoga, deep learning, movenet, tensorflow, keras, CNN

Procedia PDF Downloads 235

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 324

Authors: Keda Li, Hong Hu

Abstract:

Auxetic materials, as an emerging artificial designed metamaterial has attracted growing attention due to their promising negative Poisson’s ratio behaviors and tunable properties. The conventional auxetic lattice structures for which the deformation process is governed by a bending-dominated mechanism have faced the limitation of poor mechanical performance for many potential engineering applications. Recently, both load-bearing and energy absorption capabilities have become a crucial consideration in auxetic structure design. This study reports the finite element analysis of a class of hexagonal double-arrowhead auxetic structures with enhanced stiffness and energy absorption performance. The structure design was developed by extending the traditional double-arrowhead honeycomb to a hexagon frame, the stretching-dominated deformation mechanism was determined according to Maxwell’s stability criterion. The finite element (FE) models of 2D lattice structures established with stainless steel material were analyzed in ABAQUS/Standard for predicting in-plane structural deformation mechanism, failure process, and compressive elastic properties. Based on the computational simulation, the parametric analysis was studied to investigate the effect of the structural parameters on Poisson’s ratio and mechanical properties. The geometrical optimization was then implemented to achieve the optimal Poisson’s ratio for the maximum specific energy absorption. In addition, the optimized 2D lattice structure was correspondingly converted into a 3D geometry configuration by using the orthogonally splicing method. The numerical results of 2D and 3D structures under compressive quasi-static loading conditions were compared separately with the traditional double-arrowhead re-entrant honeycomb in terms of specific Young's moduli, Poisson's ratios, and specified energy absorption. As a result, the energy absorption capability and stiffness are significantly reinforced with a wide range of Poisson’s ratio compared to traditional double-arrowhead re-entrant honeycomb. The auxetic behaviors, energy absorption capability, and yield strength of the proposed structure are adjustable with different combinations of joint angle, struts thickness, and the length-width ratio of the representative unit cell. The numerical prediction in this study suggests the proposed concept of hexagonal double-arrowhead structure could be a suitable candidate for the energy absorption applications with a constant request of load-bearing capacity. For future research, experimental analysis is required for the validation of the numerical simulation.

Keywords: auxetic, energy absorption capacity, finite element analysis, negative Poisson's ratio, re-entrant hexagonal honeycomb

Procedia PDF Downloads 84

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 134

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 148

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 119

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 292