Search results for: sensor networks

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 417

Authors: Manon Giraud, Francois-Damien Delapierre, Guenaelle Jasmin-Lebras, Cecile Feraudet-Tarisse, Stephanie Simon, Claude Fermon

Abstract:

Early diagnosis or detection of harmful substances at low level is a growing field of high interest. The ideal test should be cheap, easy to use, quick, reliable, specific, and with very low detection limit. Combining the high specificity of antibodies-functionalized magnetic beads used to immune-capture biologic objects and the high sensitivity of a GMR-based sensors, it is possible to even detect these biologic objects one by one, such as a cancerous cell, a bacteria or a disease biomarker. The simplicity of the detection process makes its use possible even for untrained staff. Giant Magneto Resistance (GMR) is a recently discovered effect consisting in the electrical resistance modification of some conductive layers when exposed to a magnetic field. This effect allows the detection of very low variations of magnetic field (typically a few tens of nanoTesla). Magnetic nanobeads coated with antibodies targeting the analytes are mixed with a biological sample (blood, saliva) and incubated for 45 min. Then the mixture is injected in a very simple microfluidic chip and circulates above a GMR sensor that detects changes in the surrounding magnetic field. Magnetic particles do not create a field sufficient to be detected. Therefore, only the biological objects surrounded by several antibodies-functionalized magnetic beads (that have been captured by the complementary antigens) are detected when they move above the sensor. Proof of concept has been carried out on NS1 mouse cancerous cells diluted in PBS which have been bonded to magnetic 200nm particles. Signals were detected in cells-containing samples while none were recorded for negative controls. Binary response was hence assessed for this first biological model. The precise quantification of the analytes and its detection in highly diluted solution is the step now in progress.

Keywords: early diagnosis, giant magnetoresistance, lab-on-a-chip, submicron particle

Procedia PDF Downloads 247

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 127

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 117

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 146

Authors: Seong-Jin Cho, Jin Ho Kim

Abstract:

Energy harvesting is the technology which gathers and converts external energies such as light, vibration and heat which are disposed into reusable electrical energy and uses such electrical energy. The vibration energy harvesting is very interesting technology because it produces very high density of energy and unaffected by the climate. Vibration energy can be harvested by the electrostatic, electromagnetic and piezoelectric systems. The electrostatic system has low energy conversion efficiency, and the piezoelectric system is expensive and needs the frequent maintenance because it is made of piezoelectric ceramic. On the other hand, the electromagnetic system has a long life time and high harvesting efficiency, and it is relatively cheap. The electromagnetic harvesting system includes the linear generator and the rotary-type generator. The rotary-type generators require the additional mechanical conversion device if it uses linear motion of vibration. But, the linear generator uses directly linear motion of vibration without a mechanical conversion device, and it has uncomplicated structure and light weight compared with the rotary-type generator. Therefore, the linear electromagnetic generator can be useful in using vibration energy harvesting. The pole transformer systems need electricity sensor system for sending voltage and power information to administrator. Therefore, the battery is essential, and its regular maintenance of replacement is required. In case of the transformer of high location in mountainous areas, the person can’t easily access it resulting in high maintenance cost. To overcome these problems, we designed and developed the linear electromagnetic generator which can replace battery in electricity sensor system for sending voltage and power information of the pole transformer. And, it uses vibration energy of frequency more than 50 Hz by the pole transformer. In order to analyze the electromagnetic characteristics of small linear electric generator, a commercial electromagnetic finite element analysis program "MAXWELL" was used. Then, through the actual production and experiment of linear generator, we confirmed output power of linear generator.

Keywords: energy harvesting, frequency, linear generator, experiment

Procedia PDF Downloads 257

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 138

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 188

Authors: Angelo Lerro, Manuela Battipede, Piero Gili, Alberto Brandl

Abstract:

Redundancy requirements for UAV (Unmanned Aerial Vehicle) are hardly faced due to the generally restricted amount of available space and allowable weight for the aircraft systems, limiting their exploitation. Essential equipment as the Air Data, Attitude and Heading Reference Systems (ADAHRS) require several external probes to measure significant data as the Angle of Attack or the Sideslip Angle. Previous research focused on the analysis of a patented technology named Smart-ADAHRS (Smart Air Data, Attitude and Heading Reference System) as an alternative method to obtain reliable and accurate estimates of the aerodynamic angles. This solution is based on an innovative sensor fusion algorithm implementing soft computing techniques and it allows to obtain a simplified inertial and air data system reducing external devices. In fact, only one external source of dynamic and static pressures is needed. This paper focuses on the benefits which would be gained by the implementation of this system in UAV applications. A simplification of the entire ADAHRS architecture will bring to reduce the overall cost together with improved safety performance. Smart-ADAHRS has currently reached Technology Readiness Level (TRL) 6. Real flight tests took place on ultralight aircraft equipped with a suitable Flight Test Instrumentation (FTI). The output of the algorithm using the flight test measurements demonstrates the capability for this fusion algorithm to embed in a single device multiple physical and virtual sensors. Any source of dynamic and static pressure can be integrated with this system gaining a significant improvement in terms of versatility.

Keywords: aerodynamic angles, air data system, flight test, neural network, unmanned aerial vehicle, virtual sensor

Procedia PDF Downloads 219

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 197

Authors: Martin Arguelles Perez, Woosoon Yim, Alexander Barzilov

Abstract:

High-fidelity radiation monitoring is an essential component in the enhancement of the situational awareness capabilities of the Department of Energy’s Office of Environmental Management (DOE-EM) personnel. In this paper, multiple units of unmanned aerial vehicles (UAVs) each equipped with a cadmium zinc telluride (CZT) gamma-ray sensor are used for radiation source localization, which can provide vital real-time data for the EM tasks. To achieve this goal, a fully autonomous system of multicopter-based UAV swarm in 3D tetrahedron formation is used for surveying the area of interest and performing radiation source localization. The CZT sensor used in this study is suitable for small-size multicopter UAVs due to its small size and ease of interfacing with the UAV’s onboard electronics for high-resolution gamma spectroscopy enabling the characterization of radiation hazards. The multicopter platform with a fully autonomous flight feature is suitable for low-altitude applications such as radiation contamination sites. The conventional approach uses a single UAV mapping in a predefined waypoint path to predict the relative location and strength of the source, which can be time-consuming for radiation localization tasks. The proposed UAV swarm-based approach can significantly improve its ability to search for and track radiation sources. In this paper, two approaches are developed using (a) 2D planar circular (3 UAVs) and (b) 3D tetrahedron formation (4 UAVs). In both approaches, accurate estimation of the gradient vector is crucial for heading angle calculation. Each UAV carries the CZT sensor; the real-time radiation data are used for the calculation of a bulk heading vector for the swarm to achieve a UAV swarm’s source-seeking behavior. Also, a spinning formation is studied for both cases to improve gradient estimation near a radiation source. In the 3D tetrahedron formation, a UAV located closest to the source is designated as a lead unit to maintain the tetrahedron formation in space. Such a formation demonstrated a collective and coordinated movement for estimating a gradient vector for the radiation source and determining an optimal heading direction of the swarm. The proposed radiation localization technique is studied by computer simulation and validated experimentally in the indoor flight testbed using gamma sources. The technology presented in this paper provides the capability to readily add/replace radiation sensors to the UAV platforms in the field conditions enabling extensive condition measurement and greatly improving situational awareness and event management. Furthermore, the proposed radiation localization approach allows long-term measurements to be efficiently performed at wide areas of interest to prevent disasters and reduce dose risks to people and infrastructure.

Keywords: radiation, unmanned aerial system(UAV), source localization, UAV swarm, tetrahedron formation

Procedia PDF Downloads 97

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 160

Authors: Hamidreza Hoshyarmanesh, Sanju Lama, Garnette R. Sutherland

Abstract:

In tele-operative robotic surgery, an ideal haptic device should be equipped with an intuitive and smooth end-effector to cover the surgeon’s hand/wrist degrees of freedom (DOF) and translate the hand joint motions to the end-effector of the remote manipulator with low effort and high level of comfort. This research introduces the design and development of a microsurgery-specific end-effector, a gimbal mechanism possessing 4 passive and 1 active DOFs, equipped with a bipolar forceps and haptic feedback. The robust gimbal structure is comprised of three light-weight links/joint, pitch, yaw, and roll, each consisting of low-friction support and a 2-channel accurate optical position sensor. The third link, which provides the tool roll, was specifically designed to grip the tool prongs and accommodate a low mass geared actuator together with a miniaturized capstan-rope mechanism. The actuator is able to generate delicate torques, using a threaded cylindrical capstan, to emulate the sense of pinch/coagulation during conventional microsurgery. While the tool left prong is fixed to the rolling link, the right prong bears a miniaturized drum sector with a large diameter to expand the force scale and resolution. The drum transmits the actuator output torque to the right prong and generates haptic force feedback at the tool level. The tool is also equipped with a hall-effect sensor and magnet bar installed vis-à-vis on the inner side of the two prongs to measure the tooltip distance and provide an analogue signal to the control system. We believe that such a haptic end-effector could significantly increase the accuracy of telerobotic surgery and help avoid high forces that are known to cause bleeding/injury.

Keywords: end-effector, force generation, haptic interface, robotic surgery, surgical tool, tele-operation

Procedia PDF Downloads 117

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 638

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 85

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 69

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 111

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 136

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 298

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 427

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 119

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 354

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 407

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 223

Authors: İsmail Kavdır, M. Burak Büyükcan, Ferhat Kurtulmuş

Abstract:

Table olive is a valuable product especially in Mediterranean countries. It is usually consumed after some fermentation process. Defects happened naturally or as a result of an impact while olives are still fresh may become more distinct after processing period. Defected olives are not desired both in table olive and olive oil industries as it will affect the final product quality and reduce market prices considerably. Therefore it is critical to sort table olives before processing or even after processing according to their quality and surface defects. However, doing manual sorting has many drawbacks such as high expenses, subjectivity, tediousness and inconsistency. Quality criterions for green olives were accepted as color and free of mechanical defects, wrinkling, surface blemishes and rotting. In this study, it was aimed to classify fresh table olives using different classifiers and NIR spectroscopy readings and also to compare the classifiers. For this purpose, green (Ayvalik variety) olives were classified based on their surface feature properties such as defect-free, with bruised defect and with fly defect using FT-NIR spectroscopy and classification algorithms such as artificial neural networks, ident and cluster. Bruker multi-purpose analyzer (MPA) FT-NIR spectrometer (Bruker Optik, GmbH, Ettlingen Germany) was used for spectral measurements. The spectrometer was equipped with InGaAs detectors (TE-InGaAs internal for reflectance and RT-InGaAs external for transmittance) and a 20-watt high intensity tungsten–halogen NIR light source. Reflectance measurements were performed with a fiber optic probe (type IN 261) which covered the wavelengths between 780–2500 nm, while transmittance measurements were performed between 800 and 1725 nm. Thirty-two scans were acquired for each reflectance spectrum in about 15.32 s while 128 scans were obtained for transmittance in about 62 s. Resolution was 8 cm⁻¹ for both spectral measurement modes. Instrument control was done using OPUS software (Bruker Optik, GmbH, Ettlingen Germany). Classification applications were performed using three classifiers; Backpropagation Neural Networks, ident and cluster classification algorithms. For these classification applications, Neural Network tool box in Matlab, ident and cluster modules in OPUS software were used. Classifications were performed considering different scenarios; two quality conditions at once (good vs bruised, good vs fly defect) and three quality conditions at once (good, bruised and fly defect). Two spectrometer readings were used in classification applications; reflectance and transmittance. Classification results obtained using artificial neural networks algorithm in discriminating good olives from bruised olives, from olives with fly defect and from the olive group including both bruised and fly defected olives with success rates respectively changing between 97 and 99%, 61 and 94% and between 58.67 and 92%. On the other hand, classification results obtained for discriminating good olives from bruised ones and also for discriminating good olives from fly defected olives using the ident method ranged between 75-97.5% and 32.5-57.5%, respectfully; results obtained for the same classification applications using the cluster method ranged between 52.5-97.5% and between 22.5-57.5%.

Keywords: artificial neural networks, statistical classifiers, NIR spectroscopy, reflectance, transmittance

Procedia PDF Downloads 244

Authors: Maciej Jedrzejczyk, Karolina Marzantowicz

Abstract:

Traditional utility value chain is being transformed during last few years into unbundled markets. Increased distributed generation of energy is one of considerable challenges faced by Smart Grid networks. New sources of energy introduce volatile demand response which has a considerable impact on traditional middlemen in E&U market. The purpose of this research is to search for ways to allow near-real-time electricity markets to transact with surplus energy based on accurate time synchronous measurements. A proposed framework evaluates the use of secure peer-2-peer (P2P) communication and distributed transaction ledgers to provide flat hierarchy, and allow real-time insights into present and forecasted grid operations, as well as state and health of the network. An objective is to achieve dynamic grid operations with more efficient resource usage, higher security of supply and longer grid infrastructure life cycle. Methods used for this study are based on comparative analysis of different distributed ledger technologies in terms of scalability, transaction performance, pluggability with external data sources, data transparency, privacy, end-to-end security and adaptability to various market topologies. An intended output of this research is a design of a framework for safer, more efficient and scalable Smart Grid network which is bridging a gap between traditional components of the energy network and individual energy producers. Results of this study are ready for detailed measurement testing, a likely follow-up in separate studies. New platforms for Smart Grid achieving measurable efficiencies will allow for development of new types of Grid KPI, multi-smart grid branches, markets, and businesses.

Keywords: autonomous agents, Distributed computing, distributed ledger technologies, large scale systems, micro grids, peer-to-peer networks, Self-organization, self-stabilization, smart grids

Procedia PDF Downloads 300

Authors: Agastya Pratap Singh

Abstract:

Generative Adversarial Networks (GANs) have emerged as powerful tools in the fields of image recognition and anomaly detection due to their ability to model complex data distributions and generate realistic images. This systematic review explores recent advancements and applications of GANs in both image recognition and anomaly detection tasks. We discuss various GAN architectures, such as DCGAN, CycleGAN, and StyleGAN, which have been tailored to improve accuracy, robustness, and efficiency in visual data analysis. In image recognition, GANs have been used to enhance data augmentation, improve classification models, and generate high-quality synthetic images. In anomaly detection, GANs have proven effective in identifying rare and subtle abnormalities across various domains, including medical imaging, cybersecurity, and industrial inspection. The review also highlights the challenges and limitations associated with GAN-based methods, such as instability during training and mode collapse, and suggests future research directions to overcome these issues. Through this review, we aim to provide researchers with a comprehensive understanding of the capabilities and potential of GANs in transforming image recognition and anomaly detection practices.

Keywords: generative adversarial networks, image recognition, anomaly detection, DCGAN, CycleGAN, StyleGAN, data augmentation

Procedia PDF Downloads 19

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 366

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 440

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 189