Search results for: Radial basis functionsneural networks

Authors: Iqra Noor, Ihtzaz Qamar

Abstract:

Pitot-tube Jet pump, single-stage pump with low flow rate and high head, consists of a radial impeller that feeds water to rotating cavity. Water then enters stationary pitot-tube collector (diffuser), which discharges to the outside. By means of ANSYS Fluent 15.0, the internal flow characteristics for Pitot-tube Jet pump with standard pitot and curved pitot are studied. Under design condition, realizable k-e turbulence model and SIMPLEC algorithm are used to calculate 3D flow field inside both pumps. The simulation results reveal that energy is imparted to the flow by impeller and inside the rotor, forced vortex type flow is observed. Total pressure decreases inside pitot-tube whereas static pressure increases. Changing pitot-tube from standard to curved shape results in minimum flow circulation inside pitot-tube and leads to a higher pump performance.

Keywords: CFD, flow circulation, high pressure pump, impeller, internal flow, pickup tube pump, rectangle channels, rotating casing, turbulence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 754

Authors: Yong W. Foo, Lai M. Tang

Abstract:

Artificial Intelligence (AI), particularly the usage of deep neural networks for hierarchical representations from data, has found numerous complex applications across various domains, including computer vision, robotics, autonomous vehicles, and other scientific fields. However, their inherent “black box” nature can sometimes make it challenging for early researchers or school students of various levels to comprehend and trust the results they produce. Consequently, there has been a growing demand for reliable visualization tools in engineering and science education to help learners understand, trust, and explain a deep learning network. This has led to a notable emphasis on the visualization of AI in the research community in recent years. AI visualization tools are increasingly being adopted to significantly improve the comprehension of complex topics in deep learning. This paper presents an approach to empower students to actively explore the inner workings of deep neural networks by integrating the student-centered learning approach of flipped classroom models with the investigative capabilities of AI visualization tools, namely, the TensorFlow Playground, the Local Interpretable Model-agnostic Explanations (LIME), and the SHapley Additive exPlanations (SHAP), for delivering an AI education curriculum. Integrating these two factors is crucial for fostering ownership, responsibility, and critical thinking skills in the age of AI.

Keywords: Deep Learning, Explainable AI, AI Visualization, Representation Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27

Authors: Olimpia Matarazzo, Ivana Baldassarre

Abstract:

The main aim of this study was to examine whether people understand indicative conditionals on the basis of syntactic factors or on the basis of subjective conditional probability. The second aim was to investigate whether the conditional probability of q given p depends on the antecedent and consequent sizes or derives from inductive processes leading to establish a link of plausible cooccurrence between events semantically or experientially associated. These competing hypotheses have been tested through a 3 x 2 x 2 x 2 mixed design involving the manipulation of four variables: type of instructions (“Consider the following statement to be true", “Read the following statement" and condition with no conditional statement); antecedent size (high/low); consequent size (high/low); statement probability (high/low). The first variable was between-subjects, the others were within-subjects. The inferences investigated were Modus Ponens and Modus Tollens. Ninety undergraduates of the Second University of Naples, without any prior knowledge of logic or conditional reasoning, participated in this study. Results suggest that people understand conditionals in a syntactic way rather than in a probabilistic way, even though the perception of the conditional probability of q given p is at least partially involved in the conditionals- comprehension. They also showed that, in presence of a conditional syllogism, inferences are not affected by the antecedent or consequent sizes. From a theoretical point of view these findings suggest that it would be inappropriate to abandon the idea that conditionals are naturally understood in a syntactic way for the idea that they are understood in a probabilistic way.

Keywords: Conditionals, conditional probability, conditional syllogism, inferential task.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1562

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: Artificial Intelligence, machine learning, deep learning, convolutional neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1257

Authors: Prakash G L, Chaitra K Meti, Poojitha K, Divya R.K.

Abstract:

Wireless Sensor Network is Multi hop Self-configuring Wireless Network consisting of sensor nodes. The deployment of wireless sensor networks in many application areas, e.g., aggregation services, requires self-organization of the network nodes into clusters. Efficient way to enhance the lifetime of the system is to partition the network into distinct clusters with a high energy node as cluster head. The different methods of node clustering techniques have appeared in the literature, and roughly fall into two families; those based on the construction of a dominating set and those which are based solely on energy considerations. Energy optimized cluster formation for a set of randomly scattered wireless sensors is presented. Sensors within a cluster are expected to be communicating with cluster head only. The energy constraint and limited computing resources of the sensor nodes present the major challenges in gathering the data. In this paper we propose a framework to study how partially correlated data affect the performance of clustering algorithms. The total energy consumption and network lifetime can be analyzed by combining random geometry techniques and rate distortion theory. We also present the relation between compression distortion and data correlation.

Keywords: Clusters, multi hop, random geometry, rate distortion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1637

Authors: Chen Faxin, Feng Jinghua, Yang Jianlun, Li Linbo, Zhou Lin

Abstract:

In order to obtaining the dynamic evolution image of Tungsten array for foam padding, and to research the form of interaction between Tungsten plasma and foam column, a shadow imaging system of four-frame ultraviolet probe laser (266nm)has been designed on 1MA pulse power device. The time resolution of the system is 2.5ns, and static space resolution is superior to 70μm. The radial shadowgraphy image reveals the whole process from the melting and expansion of solid wire to the interaction of the precursor plasma and the foam, from the pinch to rebound inflation. The image shows the continuous interaction of Tungsten plasma and foam in a form of “Raining" within a time of about 50ns, the plasma shell structure has not been found in the whole period of pinch. The quantitative analysis indicates the minimum pinching speed of the foam column is 1.0×106cm/s, and maximum pinching speed is 6.0×106cm/s, and the axial stagnation diameter is approx 1mm.

Keywords: Dynamic hohlraum, Shadowgraphy image, Foam evolution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1919

Authors: Mohd Fairuz Iskandar Othman, Nazrulazhar Bahaman, Zulkiflee Muslim, Faizal Abdollah

Abstract:

This paper discusses a curriculum approach that will give emphasis on practical portions of teaching network security subjects in information and communication technology courses. As we are well aware, the need to use a practice and application oriented approach in education is paramount. Research on active learning and cooperative groups have shown that students grasps more and have more tendency towards obtaining and realizing soft skills like leadership, communication and team work as opposed to the more traditional theory and exam based teaching and learning. While this teaching and learning paradigm is relatively new in Malaysia, it has been practiced widely in the West. This paper examines a certain approach whereby students learning wireless security are divided into and work in small and manageable groups where there will be 2 teams which consist of black hat and white hat teams. The former will try to find and expose vulnerabilities in a wireless network while the latter will try their best to prevent such attacks on their wireless networks using hardware, software, design and enforcement of security policy and etc. This paper will try to show that the approach taken plus the use of relevant and up to date software and hardware and with suitable environment setting will hopefully expose students to a more fruitful outcome in terms of understanding of concepts, theories and their motivation to learn.

Keywords: Curriculum approach, wireless networks, wirelesssecurity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1701

Authors: Axay J Mehta, Hema A Mehta, T.C.Manjunath, C. Ardil

Abstract:

In this paper, the modelling and design of artificial neural network architecture for load forecasting purposes is investigated. The primary pre-requisite for power system planning is to arrive at realistic estimates of future demand of power, which is known as Load Forecasting. Short Term Load Forecasting (STLF) helps in determining the economic, reliable and secure operating strategies for power system. The dependence of load on several factors makes the load forecasting a very challenging job. An over estimation of the load may cause premature investment and unnecessary blocking of the capital where as under estimation of load may result in shortage of equipment and circuits. It is always better to plan the system for the load slightly higher than expected one so that no exigency may arise. In this paper, a load-forecasting model is proposed using a multilayer neural network with an appropriately modified back propagation learning algorithm. Once the neural network model is designed and trained, it can forecast the load of the power system 24 hours ahead on daily basis and can also forecast the cumulative load on daily basis. The real load data that is used for the Artificial Neural Network training was taken from LDC, Gujarat Electricity Board, Jambuva, Gujarat, India. The results show that the load forecasting of the ANN model follows the actual load pattern more accurately throughout the forecasted period.

Keywords: Power system, Load forecasting, Neural Network, Neuron, Stabilization, Network structure, Load.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3423

Authors: Loke Kean Koay, Mani Maran Ratnam

Abstract:

A mechanically-resonant torsional spring scanner was developed in a recent study. Various methods were developed to improve the angular displacement of the scanner while maintaining the scanner frequency. However the effects of rotor magnet radial position on scanner characteristics were not well investigated. In this study, the relationships between the magnet position and the scanner characteristics such as natural frequency, angular displacement and stress level were studied. A finite element model was created and an average deviation of 3.18% was found between the simulation and experimental results, qualifying the simulation results as a guide for further investigations. Three magnet positions on the transverse oscillating suspended plate were investigated by finite element analysis (FEA) and one of the positions were selected as the design position. The magnet position with the longest distance from the twist axis of mirror was selected since it attains minimum stress level, while exceeding the minimum critical flicker frequency and delivering the targeted angular displacement to the scanner.

Keywords: Computer-aided design, design optimization, torsional scanner.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1966

Authors: Gizelle K. Vianna, Gabriel V. Cunha, Gustavo S. Oliveira

Abstract:

Foliage diseases in plants can cause a reduction in both quality and quantity of agricultural production. Intelligent detection of plant diseases is an essential research topic as it may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. This work investigates ways to recognize the late blight disease from the analysis of tomato digital images, collected directly from the field. A pair of multilayer perceptron neural network analyzes the digital images, using data from both RGB and HSL color models, and classifies each image pixel. One neural network is responsible for the identification of healthy regions of the tomato leaf, while the other identifies the injured regions. The outputs of both networks are combined to generate the final classification of each pixel from the image and the pixel classes are used to repaint the original tomato images by using a color representation that highlights the injuries on the plant. The new images will have only green, red or black pixels, if they came from healthy or injured portions of the leaf, or from the background of the image, respectively. The system presented an accuracy of 97% in detection and estimation of the level of damage on the tomato leaves caused by late blight.

Keywords: Artificial neural networks, digital image processing, pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2553

Authors: K. Bommanna Raja, M.Madheswaran, K.Thyagarajah

Abstract:

A higher order spline interpolated contour obtained with up-sampling of homogenously distributed coordinates for segmentation of kidney region in different classes of ultrasound kidney images has been developed and presented in this paper. The performance of the proposed method is measured and compared with modified snake model contour, Markov random field contour and expert outlined contour. The validation of the method is made in correspondence with expert outlined contour using maximum coordinate distance, Hausdorff distance and mean radial distance metrics. The results obtained reveal that proposed scheme provides optimum contour that agrees well with expert outlined contour. Moreover this technique helps to preserve the pixels-of-interest which in specific defines the functional characteristic of kidney. This explores various possibilities in implementing computer-aided diagnosis system exclusively for US kidney images.

Keywords: Ultrasound Kidney Image – Kidney Segmentation –Active Contour – Markov Random Field – Higher Order SplineInterpolation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1747

Authors: Valentina L. Kouznetsova, Jonathan W. Wang, Igor F. Tsigelny

Abstract:

Metabolomics has become a rising field of research for various diseases, particularly cancer. Increases or decreases in metabolite concentrations in the human body are indicative of various cancers. Further elucidation of metabolic pathways and their significance in cancer research may greatly spur medicinal discovery. We analyzed the metabolomics profiles of lung cancer. Thirty-three metabolites were selected as significant. These metabolites are involved in 37 metabolic pathways delivered by MetaboAnalyst software. The top pathways are glyoxylate and dicarboxylate pathway (its hubs are formic acid and glyoxylic acid) along with Citrate cycle pathway followed by Taurine and hypotaurine pathway (the hubs in the latter are taurine and sulfoacetaldehyde) and Glycine, serine, and threonine pathway (the hubs are glycine and L-serine). We studied interactions of the metabolites with the proteins involved in cancer-related signaling networks, and developed an approach to metabolomics biomarker use in cancer diagnostics. Our analysis showed that a significant part of lung-cancer-related metabolites interacts with main cancer-related signaling pathways present in this network: PI3K–mTOR–AKT pathway, RAS–RAF–ERK1/2 pathway, and NFKB pathway. These results can be employed for use of metabolomics profiles in elucidation of the related cancer proteins signaling networks.

Keywords: Cancer, metabolites, metabolic pathway, signaling pathway.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1391

Authors: Corneliu Sofronie, Roxana Zubcov

Abstract:

Cognitive Science appeared about 40 years ago, subsequent to the challenge of the Artificial Intelligence, as common territory for several scientific disciplines such as: IT, mathematics, psychology, neurology, philosophy, sociology, and linguistics. The new born science was justified by the complexity of the problems related to the human knowledge on one hand, and on the other by the fact that none of the above mentioned sciences could explain alone the mental phenomena. Based on the data supplied by the experimental sciences such as psychology or neurology, models of the human mind operation are built in the cognition science. These models are implemented in computer programs and/or electronic circuits (specific to the artificial intelligence) – cognitive systems – whose competences and performances are compared to the human ones, leading to the psychology and neurology data reinterpretation, respectively to the construction of new models. During these processes if psychology provides the experimental basis, philosophy and mathematics provides the abstraction level utterly necessary for the intermission of the mentioned sciences. The ongoing general problematic of the cognitive approach provides two important types of approach: the computational one, starting from the idea that the mental phenomenon can be reduced to 1 and 0 type calculus operations, and the connection one that considers the thinking products as being a result of the interaction between all the composing (included) systems. In the field of psychology measurements in the computational register use classical inquiries and psychometrical tests, generally based on calculus methods. Deeming things from both sides that are representing the cognitive science, we can notice a gap in psychological product measurement possibilities, regarded from the connectionist perspective, that requires the unitary understanding of the quality – quantity whole. In such approach measurement by calculus proves to be inefficient. Our researches, deployed for longer than 20 years, lead to the conclusion that measuring by forms properly fits to the connectionism laws and principles.

Keywords: complementary methodology, connection approach, networks without scaling, quantum psychology.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3670

Authors: D. Vijayakumar, R. K. Nema

Abstract:

Over Current Relays (OCRs) and Directional Over Current Relays (DOCRs) are widely used for the radial protection and ring sub transmission protection systems and for distribution systems. All previous work formulates the DOCR coordination problem either as a Non-Linear Programming (NLP) for TDS and Ip or as a Linear Programming (LP) for TDS using recently a social behavior (Particle Swarm Optimization techniques) introduced to the work. In this paper, a Modified Particle Swarm Optimization (MPSO) technique is discussed for the optimal settings of DOCRs in power systems as a Non-Linear Programming problem for finding Ip values of the relays and for finding the TDS setting as a linear programming problem. The calculation of the Time Dial Setting (TDS) and the pickup current (Ip) setting of the relays is the core of the coordination study. PSO technique is considered as realistic and powerful solution schemes to obtain the global or quasi global optimum in optimization problem.

Keywords: Directional over current relays, Optimization techniques, Particle swarm optimization, Power system protection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2755

Authors: Rhadinia Tayag-Relanes, Felina C. Young

Abstract:

This study was conducted to analyze the noodle production process at Yan Hu Food Manufacturing for the basis of production improvement. The study utilized the Plan, Do, Check, Act (PDCA) approach and record review in the gathering of data for the calendar year 2019, specifically from August to October, focusing on the noodle products miki, canton, and misua. A causal-comparative research design was employed to establish cause-effect relationships among the variables, using descriptive statistics and correlation to compute the data gathered. The findings indicate that miki, canton, and misua production have distinct cycle times and production outputs in every set of its production processes, as well as varying levels of wastage. The company has not yet established a formal allowable rejection rate for wastage; instead, this paper used a 1% wastage limit. We recommended the following: machines used for each process of the noodle product must be consistently maintained and monitored; an assessment of all the production operators should be conducted by assessing their performance statistically based on the output and the machine performance; a root cause analysis must be conducted to identify solutions to production issues; and, an improved recording system for input and output of the production process of each noodle product should be established to eliminate the poor recording of data.

Keywords: Production, continuous improvement, process, operations, Plan, Do, Check, Act approach.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 29

Authors: Shahrinaz Ismail, Roslina Abdul Latif

Abstract:

Social media has led to paradigm shifts in ways people work and do business, interact and socialize, learn and obtain knowledge. So much so that social media has established itself as an important spatial extension of this nation-s historicity and challenges. Regardless of the enabling reputation and recommendation features through social networks embedded in the social media system, the overflow of broadcasted and publicized media contents turns the table around from engendering trust to doubting the trust system. When the trust is at doubt, the effects include deactivation of accounts and creation of multiple profiles, which lead to the overflow of 'ghost' contents (i.e. “the abundance of abandoned ships"). In most literature, the study of trust can be related to culture; hence the difference between Western-s “openness" and Eastern-s “blue-chip" concepts in networking and relationships. From a survey on issues and challenges among Malaysian social media users, 'authenticity' emerges as one of the main factors that causes and is caused by other factors. The other issue that has surfaced is credibility either in terms of message/content and source. Another is the quality of the knowledge that is shared. This paper explores the terrains of this critical space which in recent years has been dominated increasingly by, arguably, social networks embedded in the social media system, the overflow of broadcasted and publicized media content.

Keywords: Authenticity, credibility, knowledge quality and social media.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4549

Authors: Ali Reza Tahavvor, Saeed Hosseini, Nazli Jowkar, Afshin Karimzadeh Fard

Abstract:

Experimental & numeral study of temperature distribution during milling process, is important in milling quality and tools life aspects. In the present study the milling cross-section temperature is determined by using Artificial Neural Networks (ANN) according to the temperature of certain points of the work piece and the point specifications and the milling rotational speed of the blade. In the present work, at first three-dimensional model of the work piece is provided and then by using the Computational Heat Transfer (CHT) simulations, temperature in different nods of the work piece are specified in steady-state conditions. Results obtained from CHT are used for training and testing the ANN approach. Using reverse engineering and setting the desired x, y, z and the milling rotational speed of the blade as input data to the network, the milling surface temperature determined by neural network is presented as output data. The desired points temperature for different milling blade rotational speed are obtained experimentally and by extrapolation method for the milling surface temperature is obtained and a comparison is performed among the soft programming ANN, CHT results and experimental data and it is observed that ANN soft programming code can be used more efficiently to determine the temperature in a milling process.

Keywords: Milling process, rotational speed, Artificial Neural Networks, temperature.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2332

Authors: Israt Jahan Eshita

Abstract:

Flows developed between two parallel disks have many engineering applications. Two types of non-swirling flows can be generated in such a domain. One is purely source flow in disc type domain (outward flow). Other is purely sink flow in disc type domain (inward flow). This situation often appears in some turbo machinery components such as air bearings, heat exchanger, radial diffuser, vortex gyroscope, disc valves, and viscosity meters. The main goal of this paper is to show the mesh convergence, because mesh convergence saves time, and economical to run and increase the efficiency of modeling for both sink and source flow. Then flow field is resolved using a very fine mesh near-wall, using enhanced wall treatment. After that we are going to compare this flow using standard k-epsilon, RNG k-epsilon turbulence models. Lastly compare some experimental data with numerical solution for sink flow. The good agreement of numerical solution with the experimental works validates the current modeling.

Keywords: Hydraulic diameter, k-epsilon model, meshes convergence, Reynolds number, RNG model, sink flow, source flow and wall y+.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2535

Authors: Yao-Hong Tsai

Abstract:

Due to the sensor technology, video surveillance has become the main way for security control in every big city in the world. Surveillance is usually used by governments for intelligence gathering, the prevention of crime, the protection of a process, person, group or object, or the investigation of crime. Many surveillance systems based on computer vision technology have been developed in recent years. Moving target tracking is the most common task for Unmanned Aerial Vehicle (UAV) to find and track objects of interest in mobile aerial surveillance for civilian applications. The paper is focused on vision-based collision avoidance for UAVs by recurrent neural networks. First, images from cameras on UAV were fused based on deep convolutional neural network. Then, a recurrent neural network was constructed to obtain high-level image features for object tracking and extracting low-level image features for noise reducing. The system distributed the calculation of the whole system to local and cloud platform to efficiently perform object detection, tracking and collision avoidance based on multiple UAVs. The experiments on several challenging datasets showed that the proposed algorithm outperforms the state-of-the-art methods.

Keywords: Unmanned aerial vehicle, object tracking, deep learning, collision avoidance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 953

Authors: Nouri Sabrina, Benzeghiba Mohamed, Ghezal Abderrahmane

Abstract:

Numerical parametric study is conducted to study the effects of ampoule rotation on the flows and the dopant segregation in vertical bridgman (vb) crystal growth. Calculations were performed in unsteady state. The extended darcy model, which includes the time derivative and coriolis terms, has been employed in the momentum equation. It’s found that the convection, and dopant segregation can be affected significantly by ampoule rotation, and the effect is similar to that by an axial magnetic field. Ampoule rotation decreases the intensity of convection and stretches the flow cell axially. When the convection is weak, the flow can be suppressed almost completely by moderate ampoule rotation and the dopant segregation becomes diffusion-controlled. For stronger convection, the elongated flow cell by ampoule rotation may bring dopant mixing into the bulk melt reducing axial segregation at the early stage of the growth. However, if the cellular flow cannot be suppressed completely, ampoule rotation may induce larger radial segregation due to poor mixing.

Keywords: Numerical Simulation, Heat and mass transfer, vertical solidification, chemical segregation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1752

Authors: Rong-Terng Juang

Abstract:

Autonomous vehicles offer the possibility of significant benefits to social welfare. However, fully automated cars might not be going to happen in the near further. To speed the adoption of the self-driving technologies, many governments worldwide are passing laws requiring data recorders for the testing of autonomous vehicles. Currently, the self-driving vehicle, (e.g., shuttle bus) has to be monitored from a remote control center. When an autonomous vehicle encounters an unexpected driving environment, such as road construction or an obstruction, it should request assistance from a remote operator. Nevertheless, large amounts of data, including images, radar and lidar data, etc., have to be transmitted from the vehicle to the remote center. Therefore, this paper proposes a data compression method of in-vehicle networks for remote monitoring of autonomous vehicles. Firstly, the time-series data are rearranged into a multi-dimensional signal space. Upon the arrival, for controller area networks (CAN), the new data are mapped onto a time-data two-dimensional space associated with the specific CAN identity. Secondly, the data are sampled based on differential sampling. Finally, the whole set of data are encoded using existing algorithms such as Huffman, arithmetic and codebook encoding methods. To evaluate system performance, the proposed method was deployed on an in-house built autonomous vehicle. The testing results show that the amount of data can be reduced as much as 1/7 compared to the raw data.

Keywords: Autonomous vehicle, data recording, remote monitoring, controller area network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1352

Authors: Junko Hara, Yoshishige Kawabe, Takeshi Komai, Chihiro Inoue

Abstract:

The chemical degradation of dieldrin in ferric sulfide and iron powder aqueous suspension was investigated in laboratory batch type experiments. To identify the reaction mechanism, reduced copper was used as reductant. More than 90% of dieldrin was degraded using both reaction systems after 29 days. Initial degradation rate of the pesticide using ferric sulfide was superior to that using iron powder. The reaction schemes were completely dissimilar even though the ferric ion plays an important role in both reaction systems. In the case of metallic iron powder, dieldrin undergoes partial dechlorination. This reaction proceeded by reductive hydrodechlorination with the generation of H+, which arise by oxidation of ferric iron. This reductive reaction was accelerated by reductant but mono-dechlorination intermediates were accumulated. On the other hand, oxidative degradation was observed in the reaction with ferric sulfide, and the stable chemical structure of dieldrin was decomposed into water-soluble intermediates. These reaction intermediates have no chemical structure of drin class. This dehalogenation reaction assumes to occur via the adsorbed hydroxyl radial generated on the surface of ferric sulfide.

Keywords: Dieldrin, kinetics, pesticide residue, soil remediation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2491

Authors: Yeonjeong Lee, Kyoung-jae Kim, Youngtae Kim

Abstract:

This study proposes a novel recommender system that uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user’s preference. The proposed model consists of two steps. In the first step, this study uses logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. Then, this study combines the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. In the second step, this study uses the market basket analysis to extract association rules for co-purchased products. Finally, the system selects customers who have high likelihood to purchase products in each product group and recommends proper products from same or different product groups to them through above two steps. We test the usability of the proposed system by using prototype and real-world transaction and profile data. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The results also show that the proposed system may be useful in real-world online shopping store.

Keywords: Product recommender system, Ensemble technique, Association rules, Decision tree, Artificial neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4222

Authors: Fatma El-zahraa El-taher, Ayman Taha, Jane Courtney, Susan Mckeever

Abstract:

Understanding road networks plays an important role in navigation applications such as self-driving vehicles and route planning for individual journeys. Intersections of roads are essential components of road networks. Understanding the features of an intersection, from a simple T-junction to larger multi-road junctions is critical to decisions such as crossing roads or selecting safest routes. The identification and profiling of intersections from satellite images is a challenging task. While deep learning approaches offer state-of-the-art in image classification and detection, the availability of training datasets is a bottleneck in this approach. In this paper, a labelled satellite image dataset for the intersection recognition  problem is presented. It consists of 14,692 satellite images of Washington DC, USA. To support other users of the dataset, an automated download and labelling script is provided for dataset replication. The challenges of construction and fine-grained feature labelling of a satellite image dataset are examined, including the issue of how to address features that are spread across multiple images. Finally, the accuracy of detection of intersections in satellite images is evaluated.

Keywords: Satellite images, remote sensing images, data acquisition, autonomous vehicles, robot navigation, route planning, road intersections.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 757

Authors: J. P. Dubois, H. M. Chiu

Abstract:

In this paper, we study statistical multiplexing of VBR video in ATM networks. ATM promises to provide high speed realtime multi-point to central video transmission for telemedicine applications in rural hospitals and in emergency medical services. Video coders are known to produce variable bit rate (VBR) signals and the effects of aggregating these VBR signals need to be determined in order to design a telemedicine network infrastructure capable of carrying these signals. We first model the VBR video signal and simulate it using a generic continuous-data autoregressive (AR) scheme. We carry out the queueing analysis by the Fluid Approximation Model (FAM) and the Markov Modulated Poisson Process (MMPP). The study has shown a trade off: multiplexing VBR signals reduces burstiness and improves resource utilization, however, the buffer size needs to be increased with an associated economic cost. We also show that the MMPP model and the Fluid Approximation model fit best, respectively, the cell region and the burst region. Therefore, a hybrid MMPP and FAM completely characterizes the overall performance of the ATM statistical multiplexer. The ramifications of this technology are clear: speed, reliability (lower loss rate and jitter), and increased capacity in video transmission for telemedicine. With migration to full IP-based networks still a long way to achieving both high speed and high quality of service, the proposed ATM architecture will remain of significant use for telemedicine.

Keywords: ATM, multiplexing, queueing, telemedicine, VBR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1744

Authors: Malinwo Estone Ayikpa

Abstract:

Electric power systems are likely to operate with minimum losses and voltage meeting international standards. This is made possible generally by control actions provide by automatic voltage regulators, capacitors and transformers with on-load tap changer (OLTC). With the development of photovoltaic (PV) systems technology, their integration on distribution networks has increased over the last years to the extent of replacing the above mentioned techniques. The conventional analysis and simulation tools used for electrical networks are no longer able to take into account control actions necessary for studying distributed PV generation impact. This paper presents an unbalanced optimal power flow (OPF) model that minimizes losses with association of active power generation and reactive power control of single-phase and three-phase PV systems. Reactive power can be generated or absorbed using the available capacity and the adjustable power factor of the inverter. The unbalance OPF is formulated by current balance equations and solved by primal-dual interior point method. Several simulation cases have been carried out varying the size and location of PV systems and the results show a detailed view of the impact of PV distributed generation on distribution systems.

Keywords: Distribution system, losses, photovoltaic generation, primal-dual interior point method, reactive power control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1080

Authors: B. Malarkodi, S. K. Riyaz Hussain, B. Venkataramani

Abstract:

Power consumption of nodes in ad hoc networks is a critical issue as they predominantly operate on batteries. In order to improve the lifetime of an ad hoc network, all the nodes must be utilized evenly and the power required for connections must be minimized. In this project a link layer algorithm known as Power Aware medium Access Control (PAMAC) protocol is proposed which enables the network layer to select a route with minimum total power requirement among the possible routes between a source and a destination provided all nodes in the routes have battery capacity above a threshold. When the battery capacity goes below a predefined threshold, routes going through these nodes will be avoided and these nodes will act only as source and destination. Further, the first few nodes whose battery power drained to the set threshold value are pushed to the exterior part of the network and the nodes in the exterior are brought to the interior. Since less total power is required to forward packets for each connection. The network layer protocol AOMDV is basically an extension to the AODV routing protocol. AOMDV is designed to form multiple routes to the destination and it also avoid the loop formation so that it reduces the unnecessary congestion to the channel. In this project, the performance of AOMDV is evaluated using PAMAC as a MAC layer protocol and the average power consumption, throughput and average end to end delay of the network are calculated and the results are compared with that of the other network layer protocol AODV.

Keywords: AODV, PAMAC, AOMDV, Power consumption.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1825

Authors: Moneeb Gohar, Seok Joo Koh, Tae-Won Um, Hyun-Woo Lee

Abstract:

This paper proposes a fast tree join scheme to provide seamless multicast handover in the mobile networks based on the Fast Mobile IPv6 (FMIPv6). In the existing FMIPv6-based multicast handover scheme, the bi-directional tunnelling or the remote subscription is employed with the packet forwarding from the previous access router (AR) to the new AR. In general, the remote subscription approach is preferred to the bi-directional tunnelling one, since in the remote subscription scheme we can exploit an optimized multicast path from a multicast source to many mobile receivers. However, in the remote subscription scheme, if the tree joining operation takes a long time, the amount of data packets to be forwarded and buffered for multicast handover will increase, and thus the corresponding buffer may overflow, which results in severe packet losses. In order to reduce these costs associated with packet forwarding and buffering, this paper proposes the fast join to multicast tree, in which the new AR will join the multicast tree as fast as possible, so that the new multicast data packets can also arrive at the new AR, by which the packet forwarding and buffering costs can be reduced. From numerical analysis, it is shown that the proposed scheme can give better performance than the existing FMIPv6-based multicast handover schemes in terms of the multicast packet delivery costs.

Keywords: Mobile Multicast, FMIPv6, Seamless Handover, Fast Tree Join.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1426

Authors: Yong Zhao, Jian He, Cheng Zhang

Abstract:

Cardiovascular disease resulting from hypertension poses a significant threat to human health, and early detection of hypertension can potentially save numerous lives. Traditional methods for detecting hypertension require specialized equipment and are often incapable of capturing continuous blood pressure fluctuations. To address this issue, this study starts by analyzing the principle of heart rate variability (HRV) and introduces the utilization of sliding window and power spectral density (PSD) techniques to analyze both temporal and frequency domain features of HRV. Subsequently, a hypertension prediction network that relies on HRV is proposed, combining Resnet, attention mechanisms, and a multi-layer perceptron. The network leverages a modified ResNet18 to extract frequency domain features, while employing an attention mechanism to integrate temporal domain features, thus enabling auxiliary hypertension prediction through the multi-layer perceptron. The proposed network is trained and tested using the publicly available SHAREE dataset from PhysioNet. The results demonstrate that the network achieves a high prediction accuracy of 92.06% for hypertension, surpassing traditional models such as K Near Neighbor (KNN), Bayes, Logistic regression, and traditional Convolutional Neural Network (CNN).

Keywords: Feature extraction, heart rate variability, hypertension, residual networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 195

Authors: Y. Harold Robinson, M. Rajaram, E. Golden Julie, S. Balaji

Abstract:

In wireless sensor networks, locality and positioning information can be captured using Global Positioning System (GPS). This message can be congregated initially from spot to identify the system. Users can retrieve information of interest from a wireless sensor network (WSN) by injecting queries and gathering results from the mobile sink nodes. Routing is the progression of choosing optimal path in a mobile network. Intermediate node employs permutation of device nodes into teams and generating cluster heads that gather the data from entity cluster’s node and encourage the collective data to base station. WSNs are widely used for gathering data. Since sensors are power-constrained devices, it is quite vital for them to reduce the power utilization. A tree-based data fusion clustering routing algorithm (TBDFC) is used to reduce energy consumption in wireless device networks. Here, the nodes in a tree use the cluster formation, whereas the elevation of the tree is decided based on the distance of the member nodes to the cluster-head. Network simulation shows that this scheme improves the power utilization by the nodes, and thus considerably improves the lifetime.

Keywords: WSN, TBDFC, LEACH, PEGASIS, TREEPSI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1116