Search results for: Wireless Sensor Networks (WSN)

Authors: Haiyan Wu, Ying Liu, Shaoyun Shi

Abstract:

Authorship attribution is to extract features to identify authors of anonymous documents. Many previous works on authorship attribution focus on statistical style features (e.g., sentence/word length), content features (e.g., frequent words, n-grams). Modeling these features by regression or some transparent machine learning methods gives a portrait of the authors' writing style. But these methods do not capture the syntactic (e.g., dependency relationship) or semantic (e.g., topics) information. In recent years, some researchers model syntactic trees or latent semantic information by neural networks. However, few works take them together. Besides, predictions by neural networks are difficult to explain, which is vital in authorship attribution tasks. In this paper, we not only utilize the statistical style and content features but also take advantage of both syntactic and semantic features. Different from an end-to-end neural model, feature selection and prediction are two steps in our method. An attentive n-gram network is utilized to select useful features, and logistic regression is applied to give prediction and understandable representation of writing style. Experiments show that our extracted features can improve the state-of-the-art methods on three benchmark datasets.

Keywords: authorship attribution, attention mechanism, syntactic feature, feature extraction

Procedia PDF Downloads 140

Authors: Yong-Jun Kim, Jae-Hyun Ro, Chang-Bin Ha, Hyoung-Kyu Song

Abstract:

Because current wireless communication requires high reliability in a limited bandwidth environment, this paper proposes the variable modulation scheme based on the codebook. The variable modulation scheme adjusts transmission power using the codebook in accordance with hannel state. Also, if the codebook is composed of many bits, the reliability is more improved by the proposed scheme. The simulation results show that the performance of proposed scheme has better reliability than the the performance of conventional scheme.

Keywords: MIMO-OFDM, variable modulation, codebook, channel state

Procedia PDF Downloads 590

Authors: Won Hyuck Kim, Chang Hwan Kim, Hyun Wook Kim, Myoung Hoon Lee, Chan Hong Park, Hyeon Yeong Park

Abstract:

We conducted submarine topography & beach survey from December 2015 and January 2016 using multi-beam echo sounder EM3001(Kongsberg corporation) & Shipborne Mobile LiDAR System. Our survey area were the Anmok beach in Gangneung, South Korea. We made Shipborne Mobile LiDAR System for these survey. Shipborne Mobile LiDAR System includes LiDAR (RIEGL LMS-420i), IMU ((Inertial Measurement Unit, MAGUS Inertial+) and RTKGNSS (Real Time Kinematic Global Navigation Satellite System, LEIAC GS 15 GS25) for beach's measurement, LiDAR's motion compensation & precise position. Shipborne Mobile LiDAR System scans beach on the movable vessel using the laser. We mounted Shipborne Mobile LiDAR System on the top of the vessel. Before beach survey, we conducted eight circles IMU calibration survey for stabilizing heading of IMU. This exploration should be as close as possible to the beach. But our vessel could not come closer to the beach because of latency objects in the water. At the same time, we conduct submarine topography survey using multi-beam echo sounder EM3001. A multi-beam echo sounder is a device observing and recording the submarine topography using sound wave. We mounted multi-beam echo sounder on left side of the vessel. We were equipped with a motion sensor, DGNSS (Differential Global Navigation Satellite System), and SV (Sound velocity) sensor for the vessel's motion compensation, vessel's position, and the velocity of sound of seawater. Shipborne Mobile LiDAR System was able to reduce the consuming time of beach survey rather than previous conventional methods of beach survey.

Keywords: Anmok, beach survey, Shipborne Mobile LiDAR System, submarine topography

Procedia PDF Downloads 433

Authors: Ching Louis Liu, Edmund Kazmierczak, Tim Miller

Abstract:

Safety analysis for multi-agent systems is complicated by the, potentially nonlinear, interactions between agents. This paper proposes a method for analyzing the safety of multi-agent systems by explicitly focusing on interactions and the accident data of systems that are similar in structure and function to the system being analyzed. The method creates a Bayesian network using the accident data from similar systems. A feature of our method is that the events in accident data are labeled with HAZOP guide words. Our method uses an Ontology to abstract away from the details of a multi-agent implementation. Using the ontology, our methods then constructs an “Interaction Map,” a graphical representation of the patterns of interactions between agents and other artifacts. Interaction maps combined with statistical data from accidents and the HAZOP classifications of events can be converted into a Bayesian Network. Bayesian networks allow designers to explore “what it” scenarios and make design trade-offs that maintain safety. We show how to use the Bayesian networks, and the interaction maps to improve multi-agent system designs.

Keywords: multi-agent system, safety analysis, safety model, integration map

Procedia PDF Downloads 422

Authors: Wissal Ben Arfi, Lubica Hikkerova, Jean-Michel Sahut

Abstract:

This study examines interfirm networks in the digital transformation era, and in particular, how tacit knowledge codification affects innovation success within digital platforms. Hence, one of the most important features of digital transformation and innovation process outcomes is the emergence of digital platforms, as an interfirm network, at the heart of open innovation. This research aims to illuminate how digital platforms influence inter-organizational innovation through virtual team interactions and knowledge sharing practices within an interfirm network. Consequently, it contributes to the respective strategic management literature on new product development (NPD), open innovation, industrial management, and its emerging interfirm networks’ management. The empirical findings show, on the one hand, that knowledge conversion may be enhanced, especially by the socialization which seems to be the most important phase as it has played a crucial role to hold the virtual team members together. On the other hand, in the process of socialization, the tacit knowledge codification is crucial because it provides the structure needed for the interfirm network actors to interact and act to reach common goals which favor the emergence of open innovation. Finally, our results offer several conditions necessary, but not always sufficient, for interfirm managers involved in NPD and innovation concerning strategies to increasingly shape interconnected and borderless markets and business collaborations. In the digital transformation era, the need for adaptive and innovative business models as well as new and flexible network forms is becoming more significant than ever. Supported by technological advancements and digital platforms, companies could benefit from increased market opportunities and creating new markets for their innovations through alliances and collaborative strategies, as a mode of reducing or eliminating uncertainty environments or entry barriers. Consequently, an efficient and well-structured interfirm network is essential to create network capabilities, to ensure tacit knowledge sharing, to enhance organizational learning and to foster open innovation success within digital platforms.

Keywords: interfirm networks, digital platform, virtual teams, open innovation, knowledge sharing

Procedia PDF Downloads 135

Authors: Fengqing Li, Petra Schneider

Abstract:

Failure of tailings management facilities (TMF) of radioactive residues is an enormous challenge worldwide and can result in major catastrophes. Particularly in transboundary regions, such failure is most likely to lead to international conflict. This risk occurs in Kyrgyzstan and Uzbekistan, where the current major challenge is the quantification of impacts due to pollution from uranium legacy sites and especially the impact on river basins after natural hazards (i.e., landslides). By means of GoldSim, a probabilistic simulation model, the amount of tailing material that flows into the river networks of Mailuu Suu in Kyrgyzstan after pond failure was simulated for three scenarios, namely 10%, 20%, and 30% of material inputs. Based on Muskingum-Cunge flood routing procedure, the peak value of uranium flood wave along the river network was simulated. Among the 23 TMF, 19 ponds are close to the river networks. The spatiotemporal distributions of uranium along the river networks were then simulated for all the 19 ponds under three scenarios. Taking the TP7 which is 30 km far from the Kyrgyzstan-Uzbekistan border as one example, the uranium concentration decreased continuously along the longitudinal gradient of the river network, the concentration of uranium was observed at the border after 45 min of the pond failure and the highest value was detected after 69 min. The highest concentration of uranium at the border were 16.5, 33, and 47.5 mg/L under scenarios of 10%, 20%, and 30% of material inputs, respectively. In comparison to the guideline value of uranium in drinking water (i.e., 30 µg/L) provided by the World Health Organization, the observed concentrations of uranium at the border were 550‒1583 times higher. In order to mitigate the transboundary impact of a radioactive pollutant release, an integrated framework consisting of three major strategies were proposed. Among, the short-term strategy can be used in case of emergency event, the medium-term strategy allows both countries handling the TMF efficiently based on the benefit-sharing concept, and the long-term strategy intends to rehabilitate the site through the relocation of all TMF.

Keywords: Central Asia, contaminant transport modelling, radioactive residue, transboundary conflict

Procedia PDF Downloads 122

Authors: Mustafa Elfituri, Jonathan Cook

Abstract:

Recently, graph-based computations have become more important in large-scale scientific computing as they can provide a methodology to model many types of relations between independent objects. They are being actively used in fields as varied as biology, social networks, cybersecurity, and computer networks. At the same time, graph problems have some properties such as irregularity and poor locality that make their performance different than regular applications performance. Therefore, parallelizing graph algorithms is a hard and challenging task. Initial evidence is that standard computer architectures do not perform very well on graph algorithms. Little is known exactly what causes this. The Graph500 benchmark is a representative application for parallel graph-based computations, which have highly irregular data access and are driven more by traversing connected data than by computation. In this paper, we present results from analyzing the performance of various example implementations of Graph500, including a shared memory (OpenMP) version, a distributed (MPI) version, and a hybrid version. We measured and analyzed all the factors that affect its performance in order to identify possible changes that would improve its performance. Results are discussed in relation to what factors contribute to performance degradation.

Keywords: graph computation, graph500 benchmark, parallel architectures, parallel programming, workload characterization.

Procedia PDF Downloads 153

Authors: Shwetha B. S., Sirisha M., Vachana U., Aditya Kadlimatti, Manjushree N. S.

Abstract:

Braille script holds significant importance in bridging the communication gap for visually impaired individuals. However, the challenge of interpreting Braille for non-experts creates barriers in education and day-to-day interactions. This paper aims to develop a system that translates Braille text into multilingual speech using advanced Convolutional Neural Networks (CNNs) and Google Text-to-Speech (GTTS) technology. The proposed system employs image recognition techniques powered by CNNs to accurately identify and decode Braille characters from captured images. The deep learning model undergoes training on a diverse dataset of Braille symbols to ensure high accuracy and robustness. Among the models evaluated, AlexNet demonstrated the highest accuracy in decoding Braille characters. Once recognized, the decoded text is converted into speech in the user’s preferred language using the GTTS API. This system possesses the ability to greatly improve inclusivity by enabling real-time Braille interpretation for visually impaired individuals, educators, and caregivers.

Keywords: convolutional neural networks, Braille image, image-to-speech, GTTS, AlexNet, VGG16, DenseNet121, ResNet50

Procedia PDF Downloads 8

Authors: Azam Abkhiz, Abolghasem Nasir

Abstract:

To achieve sustainable competitive advantage in the market, it is necessary to provide and improve customer satisfaction and Loyalty. To reach this objective, companies need to identify and analyze their customers. Thus, it is critical to measure the level of customer satisfaction and Loyalty very carefully. This study attempts to build a conceptual model to provide clear insights of customer loyalty. Using Bayesian networks (BNs), a model is proposed to evaluate customer loyalty and its consequences, such as repurchase and positive word-of-mouth. BN is a probabilistic approach that predicts the behavior of a system based on observed stochastic events. The most relevant determinants of customer loyalty are identified by the literature review. Perceived value, service quality, trust, corporate image, satisfaction, and switching costs are the most important variables that explain customer loyalty. The data are collected by use of a questionnaire-based survey from 1430 customers of a home appliances manufacturer in Iran. Four scenarios and sensitivity analyses are performed to run and analyze the impact of different determinants on customer loyalty. The proposed model allows businesses to not only set their targets but proactively manage their customer behaviors as well.

Keywords: customer satisfaction, customer loyalty, Bayesian networks, home appliances industry

Procedia PDF Downloads 148

Authors: Vethathirri Ramanujam Srinivasan, S. M. Shiva Nagendra

Abstract:

Air quality management in urban areas is a serious concern in both developed and developing countries. In this regard, more number of air quality monitoring stations are planned to mitigate air pollution in urban areas. In India, Central Pollution Control Board has set up 574 air quality monitoring stations across the country and proposed to set up another 500 stations in the next few years. The number of monitoring stations for each city has been decided based on population data. The setting up of ambient air quality monitoring stations and their operation and maintenance are highly expensive. Therefore, there is a need to optimize monitoring networks for air quality management. The present paper discusses the various methods such as Indian Standards (IS) method, US EPA method and European Union (EU) method to arrive at the minimum number of air quality monitoring stations. In addition, optimization of rain-gauge method and Inverse Distance Weighted (IDW) method using Geographical Information System (GIS) are also explored in the present work for the design of air quality network in Chennai city. In summary, additionally 18 stations are required for Chennai city, and the potential monitoring locations with their corresponding land use patterns are ranked and identified from the 1km x 1km sized grids.

Keywords: air quality monitoring network, inverse distance weighted method, population based method, spatial variation

Procedia PDF Downloads 194

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 208

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 166

Authors: Shih-Wen Hsiao, Yi-Cheng Tsao

Abstract:

In the field of reverse engineering and creative industries, applying 3D scanning process to obtain geometric forms of the objects is a mature and common technique. For instance, organic objects such as faces and nonorganic objects such as products could be scanned to acquire the geometric information for further application. However, although the data resolution of 3D scanning device is increasing and there are more and more abundant complementary applications, the penetration rate of 3D scanning for the public is still limited by the relative high price of the devices. On the other hand, Kinect, released by Microsoft, is known for its powerful functions, considerably low price, and complete technology and database support. Therefore, related studies can be done with the applying of Kinect under acceptable cost and data precision. Due to the fact that Kinect utilizes optical mechanism to extracting depth information, limitations are found due to the reason of the straight path of the light. Thus, various angles are required sequentially to obtain the complete 3D information of the object when applying a single Kinect for 3D scanning. The integration process which combines the 3D data from different angles by certain algorithms is also required. This sequential scanning process costs much time and the complex integration process often encounter some technical problems. Therefore, this paper aimed to apply multiple Kinects simultaneously on the field of developing a rapid 3D mannequin scan platform and proposed suggestions on the number and angles of Kinects. In the content, a method of establishing the coordination based on the relation between mannequin and the specifications of Kinect is proposed, and a suggestion of angles and number of Kinects is also described. An experiment of applying multiple Kinect on the scanning of 3D mannequin is constructed by Microsoft API, and the results show that the time required for scanning and technical threshold can be reduced in the industries of fashion and garment design.

Keywords: 3D scan, depth sensor, fashion and garment design, mannequin, multiple Kinect sensor

Procedia PDF Downloads 370

Authors: Edwin Foo, Woei Wen, Lui, Meijun Zhao, Shigeru Kuchii, Chin Sai Wong, Chung Sern Goh, Yi Hao He

Abstract:

This presentation presents an elderly care and assistive social robot development work. We named this robot JOS and he is restricted to table top operation. JOS is designed to have a maximum volume of 3600 cm3 with its base restricted to 250 mm and his mission is to provide companion, assist and help the elderly. In order for JOS to accomplish his mission, he will be equipped with perception, reaction and cognition capability. His appearance will be not human like but more towards cute and approachable type. JOS will also be designed to be neutral gender. However, the robot will still have eyes, eyelid and a mouth. For his eyes and eyelids, they will be built entirely with Robotis Dynamixel AX18 motor. To realize this complex task, JOS will be also be equipped with micro-phone array, vision camera and Intel i5 NUC computer and a powered by a 12 V lithium battery that will be self-charging. His face is constructed using 1 motor each for the eyelid, 2 motors for the eyeballs, 3 motors for the neck mechanism and 1 motor for the lips movement. The vision senor will be house on JOS forehead and the microphone array will be somewhere below the mouth. For the vision system, Omron latest OKAO vision sensor is used. It is a compact and versatile sensor that is only 60mm by 40mm in size and operates with only 5V supply. In addition, OKAO vision sensor is capable of identifying the user and recognizing the expression of the user. With these functions, JOS is able to track and identify the user. If he cannot recognize the user, JOS will ask the user if he would want him to remember the user. If yes, JOS will store the user information together with the capture face image into a database. This will allow JOS to recognize the user the next time the user is with JOS. In addition, JOS is also able to interpret the mood of the user through the facial expression of the user. This will allow the robot to understand the user mood and behavior and react according. Machine learning will be later incorporated to learn the behavior of the user so as to understand the mood of the user and requirement better. For the speech system, Microsoft speech and grammar engine is used for the speech recognition. In order to use the speech engine, we need to build up a speech grammar database that captures the commonly used words by the elderly. This database is built from research journals and literature on elderly speech and also interviewing elderly what do they want to robot to assist them with. Using the result from the interview and research from journal, we are able to derive a set of common words the elderly frequently used to request for the help. It is from this set that we build up our grammar database. In situation where there is more than one person near JOS, he is able to identify the person who is talking to him through an in-house developed microphone array structure. In order to make the robot more interacting, we have also included the capability for the robot to express his emotion to the user through the facial expressions by changing the position and movement of the eyelids and mouth. All robot emotions will be in response to the user mood and request. Lastly, we are expecting to complete this phase of project and test it with elderly and also delirium patient by Feb 2015.

Keywords: social robot, vision, elderly care, machine learning

Procedia PDF Downloads 443

Authors: Libo Jiang, Huan Li, Rongling Wu

Abstract:

Ordinary differentiation equations (ODE) have proven to be powerful for reconstructing precise and informative gene regulatory networks (GRNs) from dynamic gene expression data. However, joint modeling and analysis of all genes, essential for the systematical characterization of genetic interactions, are challenging due to high dimensionality and a complex pattern of genetic regulation including activation, repression, and antitermination. Here, we address these challenges by unifying variable selection and game theory through ODE. Each gene within a GRN is co-expressed with its partner genes in a way like a game of multiple players, each of which tends to choose an optimal strategy to maximize its “fitness” across the whole network. Based on this unifying theory, we designed and conducted a real experiment to infer salt tolerance-related GRNs for Euphrates poplar, a hero tree that can grow in the saline desert. The pattern and magnitude of interactions between several hub genes within these GRNs were found to determine the capacity of Euphrates poplar to resist to saline stress.

Keywords: gene regulatory network, ordinary differential equation, game theory, LASSO, saline resistance

Procedia PDF Downloads 644

Authors: Hritwik Ghosh, Irfan Sadiq Rahat, Sachi Nandan Mohanty, J. V. R. Ravindra

Abstract:

In the rapidly evolving landscape of medical diagnostics, the early detection and accurate classification of skin cancer remain paramount for effective treatment outcomes. This research delves into the transformative potential of Artificial Intelligence (AI), specifically Deep Learning (DL), as a tool for discerning and categorizing various skin conditions. Utilizing a diverse dataset of 3,000 images representing nine distinct skin conditions, we confront the inherent challenge of class imbalance. This imbalance, where conditions like melanomas are over-represented, is addressed by incorporating class weights during the model training phase, ensuring an equitable representation of all conditions in the learning process. Our pioneering approach introduces a hybrid model, amalgamating the strengths of two renowned Convolutional Neural Networks (CNNs), VGG16 and ResNet50. These networks, pre-trained on the ImageNet dataset, are adept at extracting intricate features from images. By synergizing these models, our research aims to capture a holistic set of features, thereby bolstering classification performance. Preliminary findings underscore the hybrid model's superiority over individual models, showcasing its prowess in feature extraction and classification. Moreover, the research emphasizes the significance of rigorous data pre-processing, including image resizing, color normalization, and segmentation, in ensuring data quality and model reliability. In essence, this study illuminates the promising role of AI and DL in revolutionizing skin cancer diagnostics, offering insights into its potential applications in broader medical domains.

Keywords: artificial intelligence, machine learning, deep learning, skin cancer, dermatology, convolutional neural networks, image classification, computer vision, healthcare technology, cancer detection, medical imaging

Procedia PDF Downloads 92

Authors: Kulkarni Rohini D.

Abstract:

While emerging as plausible sources of energy generation, new technologies, including photovoltaic (PV) solar panels, home battery energy storage systems, and electric vehicles (EVs), are exacerbating the operations of power distribution networks for distribution network operators (DNOs). Renewable energy production fluctuates, stemming in over- and under-generation energy, further complicating the issue of storing excess power and using it when necessary. Though renewable sources are non-exhausting and reoccurring, power storage of generated energy is almost as paramount as to its production process. Hence, to ensure smooth and efficient power storage at different levels, Grid balancing technologies are consequently the next theme to address in the sustainable space and growth sector. But, since hydrogen batteries were used in the earlier days to achieve this balance in power grids, new, recent advancements are more efficient and capable per unit of storage space while also being distinctive in terms of their underlying operating principles. The underlying technologies of "Flow batteries," "Gravity Solutions," and "Graphene Batteries" already have entered the market and are leading the race for efficient storage device solutions that will improve and stabilize Grid networks, followed by Grid balancing technologies.

Keywords: flow batteries, grid balancing, hydrogen batteries, power storage, solar

Procedia PDF Downloads 76

Authors: Sanjana S. Mallya, Roshan Arvind Sivakumar

Abstract:

Orthotics is the branch of medicine that deals with the provision and use of artificial casts or braces to alter the biomechanical structure of the limb and provide support for the limb. Custom-made orthoses provide more comfort and can correct issues better than those available over-the-counter. However, they are expensive and require intricate modelling of the limb. Traditional methods of modelling involve creating a plaster of Paris mould of the limb. Lately, CAD/CAM and 3D printing processes have improved the accuracy and reduced the production time. Ordinarily, digital cameras are used to capture the features of the limb from different views to create a 3D model. We propose a system to model the limb using Microsoft Kinect2 sensor. The Kinect can capture RGB and depth frames simultaneously up to 30 fps with sufficient accuracy. The region of interest is captured from three views, each shifted by 90 degrees. The RGB and depth data are fused into a single RGB-D frame. The resolution of the RGB frame is 1920px x 1080px while the resolution of the Depth frame is 512px x 424px. As the resolution of the frames is not equal, RGB pixels are mapped onto the Depth pixels to make sure data is not lost even if the resolution is lower. The resulting RGB-D frames are collected and using the depth coordinates, a three dimensional point cloud is generated for each view of the Kinect sensor. A common reference system was developed to merge the individual point clouds from the Kinect sensors. The reference system consisted of 8 coloured cubes, connected by rods to form a skeleton-cube with the coloured cubes at the corners. For each Kinect, the region of interest is the square formed by the centres of the four cubes facing the Kinect. The point clouds are merged by considering one of the cubes as the origin of a reference system. Depending on the relative distance from each cube, the three dimensional coordinate points from each point cloud is aligned to the reference frame to give a complete point cloud. The RGB data is used to correct for any errors in depth data for the point cloud. A triangular mesh is generated from the point cloud by applying Delaunay triangulation which generates the rough surface of the limb. This technique forms an approximation of the surface of the limb. The mesh is smoothened to obtain a smooth outer layer to give an accurate model of the limb. The model of the limb is used as a base for designing the custom orthotic brace or cast. It is transferred to a CAD/CAM design file to design of the brace above the surface of the limb. The proposed system would be more cost effective than current systems that use MRI or CT scans for generating 3D models and would be quicker than using traditional plaster of Paris cast modelling and the overall setup time is also low. Preliminary results indicate that the accuracy of the Kinect2 is satisfactory to perform modelling.

Keywords: 3d scanning, mesh generation, Microsoft kinect, orthotics, registration

Procedia PDF Downloads 191

Authors: Monish Sengupta, Benjamin Heydecker, Daniel Woodland

Abstract:

New train control systems rely mainly on Automatic Train Protection (ATP) and Automatic Train Operation (ATO) dynamically to control the speed and hence performance. The ATP and the ATO form the vital element within the CBTC (Communication Based Train Control) and within the ERTMS (European Rail Traffic Management System) system architectures. Reliable and accurate measurement of train location, speed and acceleration are vital to the operation of train control systems. In the past, all CBTC and ERTMS system have deployed a balise or equivalent to correct the uncertainty element of the train location. Typically a CBTC train is allowed to miss only one balise on the track, after which the Automatic Train Protection (ATP) system applies emergency brake to halt the service. This is because the location uncertainty, which grows within the train control system, cannot tolerate missing more than one balise. Balises contribute a significant amount towards wayside maintenance and studies have shown that balises on the track also forms a constraint for future track layout change and change in speed profile.This paper investigates the causes of the location uncertainty that is currently experienced and considers whether it is possible to identify an effective filter to ascertain, in conjunction with appropriate sensors, more accurate speed, distance and location for a CBTC driven train without the need of any external balises. An appropriate sensor fusion algorithm and intelligent sensor selection methodology will be deployed to ascertain the railway location and speed measurement at its highest precision. Similar techniques are already in use in aviation, satellite, submarine and other navigation systems. Developing a model for the speed control and the use of Kalman filter is a key element in this research. This paper will summarize the research undertaken and its significant findings, highlighting the potential for introducing alternative approaches to train positioning that would enable removal of all trackside location correction balises, leading to huge reduction in maintenances and more flexibility in future track design.

Keywords: ERTMS, CBTC, ATP, ATO

Procedia PDF Downloads 416

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 124

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 140

Authors: Kavian Khosravinia, Mohd Khair Hassan, Ribhan Zafira Abdul Rahman, Syed Abdul Rahman Al-Haddad

Abstract:

The CAN (controller area network) bus is introduced as a multi-master, message broadcast system. The messages sent on the CAN are used to communicate state information, referred as a signal between different ECUs, which provides data consistency in every node of the system. OBD-II Dongles that are based on request and response method is the wide-spread solution for extracting sensor data from cars among researchers. Unfortunately, most of the past researches do not consider resolution and quantity of their input data extracted through OBD-II technology. The maximum feasible scan rate is only 9 queries per second which provide 8 data points per second with using ELM327 as well-known OBD-II dongle. This study aims to develop and design a programmable, and latency-sensitive vehicle data acquisition system that improves the modularity and flexibility to extract exact, trustworthy, and fresh car sensor data with higher frequency rates. Furthermore, the researcher must break apart, thoroughly inspect, and observe the internal network of the vehicle, which may cause severe damages to the expensive ECUs of the vehicle due to intrinsic vulnerabilities of the CAN bus during initial research. Desired sensors data were collected from various vehicles utilizing Raspberry Pi3 as computing and processing unit with using OBD (request-response) and direct CAN method at the same time. Two types of data were collected for this study. The first, CAN bus frame data that illustrates data collected for each line of hex data sent from an ECU and the second type is the OBD data that represents some limited data that is requested from ECU under standard condition. The proposed system is reconfigurable, human-readable and multi-task telematics device that can be fitted into any vehicle with minimum effort and minimum time lag in the data extraction process. The standard operational procedure experimental vehicle network test bench is developed and can be used for future vehicle network testing experiment.

Keywords: CAN bus, OBD-II, vehicle data acquisition, connected cars, telemetry, Raspberry Pi3

Procedia PDF Downloads 212

Authors: Joanna Cabaj, Sylwia Baluta, Karol Malecha, Kamila Drzozga

Abstract:

Catecholamines are the principal neurotransmitters that mediate a variety of the central nervous system functions, such as motor control, cognition, emotion, memory processing, and endocrine modulation. Dysfunctions in catecholamine neurotransmission are induced in some neurologic and neuropsychiatric diseases. Changeable neurotransmitters level in biological fluids can be a marker of several neurological disorders. Because of its significance in analytical techniques and diagnostics, sensitive and selective detection of neurotransmitters is increasingly attracting a lot of attention in different areas of bio-analysis or biomedical research. Recently, fluorescent techniques for detection of catecholamines have attracted interests due to their reasonable cost, convenient control, as well as maneuverability in biological environments. Nevertheless, with the observed need for a sensitive and selective catecholamines sensor, the development of a convenient method for this neurotransmitter is still at its basic level. The manipulation of nanostructured materials in conjunction with biological molecules has led to the development of a new class of hybrid modified biosensors in which both enhancement of charge transport and biological activity preservation may be obtained. Immobilization of biomaterials on electrode surfaces is the crucial step in fabricating electrochemical as well as optical biosensors and bioelectronic devices. Continuing systematic investigation in the manufacturing of enzyme–conducting sensitive systems, here is presented a convenient fluorescence sensing strategy for catecholamines detection based on FRET (fluorescence resonance energy transfer) phenomena observed for, i.e., complexes of Fe²⁺ and epinephrine. The biosensor was constructed using low temperature co-fired ceramics technology (LTCC). This sensing system used the catalytical oxidation of catecholamines and quench of the strong luminescence of obtained complexes due to FRET. The detection process was based on the oxidation of substrate in the presence of the enzyme–laccase/tyrosinase.

Keywords: biosensor, conducting polymer, enzyme, FRET, LTCC

Procedia PDF Downloads 262

Authors: M. Khazini, M.Damou, Z. Souar

Abstract:

In this paper, octagon antenna ultra wideband (UWB) low band wearable antenna designs have been proposed for in-body to on-body communication channel of wireless. Single element antenna, dual elements, are designed and compared in free space and in body proximity. Conformal design has been focused. Liquid crystal polymer (LCP) is a material that has gained attention as a potential high-performance microwave substrate and packaging material. This investigation uses several methods to determine the electrical properties of LCP for millimeter-wave frequencies.

Keywords: ultra wideband, wearable antenna, slot antenna, liquid crystal polymer (LCP), CST studio

Procedia PDF Downloads 365

Authors: Hyeon Su Kim, Sungjin Park, Hae Ryung Chang, Hae Rim Jung, Young Zoo Ahn, Yon Hui Kim, Seungyoon Nam

Abstract:

Ependymoma, one of the most common parenchymal spinal cord tumor, represents 3-6% of all CNS tumor. Especially intracranial ependymomas, which are more frequent in childhood, have a more poor prognosis and more malignant than spinal ependymomas. Although there are growing needs to understand pathogenesis, detailed molecular understanding of pathogenesis remains to be explored. A cancer cell is composed of complex signaling pathway networks, and identifying interaction between genes and/or proteins are crucial for understanding these pathways. Therefore, we explored each ependymoma in terms of differential expressed genes and signaling networks. We used Microsoft Excel™ to manipulate microarray data gathered from NCBI’s GEO Database. To analyze and visualize signaling network, we used web-based PATHOME algorithm and Cytoscape. We show HOX family and NEFL are down-regulated but SCL family is up-regulated in cerebrum and posterior fossa cancers over a spinal cancer, and JAK/STAT signaling pathway and Chemokine signaling pathway are significantly different in the both intracranial ependymoma comparing to spinal ependymoma. We are considering there may be an age-dependent mechanism under different histological pathogenesis. We annotated mutation data of each gene subsequently in order to find potential target genes.

Keywords: systems biology, ependymoma, deg, network analysis

Procedia PDF Downloads 303

Authors: Sung-Jun Yoo, Kazuhide Ito

Abstract:

In this study, a comprehensive computer simulated person (CSP) that integrates computational human model (virtual manikin) and respiratory tract model (virtual airway), was applied for estimation of indoor environmental quality. Moreover, an inclusive prediction method was established by integrating computational fluid dynamics (CFD) analysis with advanced CSP which is combined with physiologically-based pharmacokinetic (PBPK) model, unsteady thermoregulation model for analysis targeting micro-climate around human body and respiratory area with high accuracy. This comprehensive method can estimate not only the contaminant inhalation but also constant interaction in the contaminant transfer between indoor spaces, i.e., a target area for indoor air quality (IAQ) assessment, and respiratory zone for health risk assessment. This study focused on the usage of the CSP as an air/thermal quality sensor in indoors, which means the application of comprehensive model for assessment of IAQ and thermal environmental quality. Demonstrative analysis was performed in order to examine the applicability of the comprehensive model to the heating, ventilation, air conditioning (HVAC) control scheme. CSP was located at the center of the simple model room which has dimension of 3m×3m×3m. Formaldehyde which is generated from floor material was assumed as a target contaminant, and flow field, sensible/latent heat and contaminant transfer analysis in indoor space were conducted by using CFD simulation coupled with CSP. In this analysis, thermal comfort was evaluated by thermoregulatory analysis, and respiratory exposure risks represented by adsorption flux/concentration at airway wall surface were estimated by PBPK-CFD hybrid analysis. These Analysis results concerning IAQ and thermal comfort will be fed back to the HVAC control and could be used to find a suitable ventilation rate and energy requirement for air conditioning system.

Keywords: CFD simulation, computer simulated person, HVAC control, indoor environmental quality

Procedia PDF Downloads 364

Authors: Mohanad Alhabo, Naveed Nawaz

Abstract:

The ongoing call or data session must be maintained to ensure a good quality of service. This can be accomplished by performing the handover procedure while the user is on the move. However, the dense deployment of small cells in 5G networks is a challenging issue due to the extensive number of handovers. In this paper, a neighbour cell list method is proposed to reduce the number of target small cells and hence minimizing the number of handovers. The neighbour cell list is built by omitting cells that could cause an unnecessary handover and handover failure because of short time of stay of the user in these cells. A multi-attribute decision making technique, simple additive weighting, is then applied to the optimized neighbour cell list. Multi-tier small cells network is considered in this work. The performance of the proposed method is analysed and compared with that of the existing methods. Results disclose that our method has decreased the candidate small cell list, unnecessary handovers, handover failure, and short time of stay cells compared to the competitive method.

Keywords: handover, HetNets, multi-attribute decision making, small cells

Procedia PDF Downloads 125

Authors: Talal Alsulaiman, Khaldoun Khashanah

Abstract:

In this paper, we provided a literature survey on the artificial stock problem (ASM). The paper began by exploring the complexity of the stock market and the needs for ASM. ASM aims to investigate the link between individual behaviors (micro level) and financial market dynamics (macro level). The variety of patterns at the macro level is a function of the AFM complexity. The financial market system is a complex system where the relationship between the micro and macro level cannot be captured analytically. Computational approaches, such as simulation, are expected to comprehend this connection. Agent-based simulation is a simulation technique commonly used to build AFMs. The paper proceeds by discussing the components of the ASM. We consider the roles of behavioral finance (BF) alongside the traditionally risk-averse assumption in the construction of agent's attributes. Also, the influence of social networks in the developing of agents’ interactions is addressed. Network topologies such as a small world, distance-based, and scale-free networks may be utilized to outline economic collaborations. In addition, the primary methods for developing agents learning and adaptive abilities have been summarized. These incorporated approach such as Genetic Algorithm, Genetic Programming, Artificial neural network and Reinforcement Learning. In addition, the most common statistical properties (the stylized facts) of stock that are used for calibration and validation of ASM are discussed. Besides, we have reviewed the major related previous studies and categorize the utilized approaches as a part of these studies. Finally, research directions and potential research questions are argued. The research directions of ASM may focus on the macro level by analyzing the market dynamic or on the micro level by investigating the wealth distributions of the agents.

Keywords: artificial stock markets, market dynamics, bounded rationality, agent based simulation, learning, interaction, social networks

Procedia PDF Downloads 357

Authors: Adel Sabry Eesa, Adnan Mohsin Abdulazeez Brifcani, Zeynep Orman

Abstract:

Feature selection has been used in many fields such as classification, data mining and object recognition and proven to be effective for removing irrelevant and redundant features from the original data set. In this paper, a new design of distributed intrusion detection system using a combination feature selection model based on bees and decision tree. Bees algorithm is used as the search strategy to find the optimal subset of features, whereas decision tree is used as a judgment for the selected features. Both the produced features and the generated rules are used by Decision Making Mobile Agent to decide whether there is an attack or not in the networks. Decision Making Mobile Agent will migrate through the networks, moving from node to another, if it found that there is an attack on one of the nodes, it then alerts the user through User Interface Agent or takes some action through Action Mobile Agent. The KDD Cup 99 data set is used to test the effectiveness of the proposed system. The results show that even if only four features are used, the proposed system gives a better performance when it is compared with the obtained results using all 41 features.

Keywords: distributed intrusion detection system, mobile agent, feature selection, bees algorithm, decision tree

Procedia PDF Downloads 412

Authors: Siddhant Rao

Abstract:

Studies estimate that there will be 266,120 new cases of invasive breast cancer and 40,920 breast cancer induced deaths in the year of 2018 alone. Despite the pervasiveness of this affliction, the current process to obtain an accurate breast cancer prognosis is tedious and time consuming. It usually requires a trained pathologist to manually examine histopathological images and identify the features that characterize various cancer severity levels. We propose MITOS-RCNN: a region based convolutional neural network (RCNN) geared for small object detection to accurately grade one of the three factors that characterize tumor belligerence described by the Nottingham Grading System: mitotic count. Other computational approaches to mitotic figure counting and detection do not demonstrate ample recall or precision to be clinically viable. Our models outperformed all previous participants in the ICPR 2012 challenge, the AMIDA 2013 challenge and the MITOS-ATYPIA-14 challenge along with recently published works. Our model achieved an F- measure score of 0.955, a 6.11% improvement in accuracy from the most accurate of the previously proposed models.

Keywords: breast cancer, mitotic count, machine learning, convolutional neural networks

Procedia PDF Downloads 226