Search results for: input–output analysis

Authors: Georgios Charizanos, Haydar Demirhan, Duygu Icen

Abstract:

Two of the most impactful issues in classical logistic regression are class imbalance and complete separation. These can result in model predictions heavily leaning towards the imbalanced class on the binary response variable or over-fitting issues. Fuzzy methodology offers key solutions for handling these problems. However, most studies propose the transformation of the binary responses into a continuous format limited within [0,1]. This is called the possibilistic approach within fuzzy logistic regression. Following this approach is more aligned with straightforward regression since a logit-link function is not utilized, and fuzzy probabilities are not generated. In contrast, we propose a method of fuzzifying binary response variables that allows for the use of the logit-link function; hence, a probabilistic fuzzy logistic regression model with the Monte Carlo method. The fuzzy probabilities are then classified by selecting a fuzzy threshold. Different combinations of fuzzy and crisp input, output, and coefficients are explored, aiming to understand which of these perform better under different conditions of imbalance and separation. We conduct numerical experiments using both synthetic and real datasets to demonstrate the performance of the fuzzy logistic regression framework against seven crisp machine learning methods. The proposed framework shows better performance irrespective of the degree of imbalance and presence of separation in the data, while the considered machine learning methods are significantly impacted.

Keywords: fuzzy logistic regression, fuzzy, logistic, machine learning

Procedia PDF Downloads 66

Authors: Ş. Karabulut, A. Güllü, A. Güldaş, R. Gürbüz

Abstract:

This study investigates the effects of the lead angle and chip thickness variation on surface roughness during the machining of compacted graphite iron using ceramic cutting tools under dry cutting conditions. Analytical models were developed for predicting the surface roughness values of the specimens after the face milling process. Experimental data was collected and imported to the artificial neural network model. A multilayer perceptron model was used with the back propagation algorithm employing the input parameters of lead angle, cutting speed and feed rate in connection with chip thickness. Furthermore, analysis of variance was employed to determine the effects of the cutting parameters on surface roughness. Artificial neural network and regression analysis were used to predict surface roughness. The values thus predicted were compared with the collected experimental data, and the corresponding percentage error was computed. Analysis results revealed that the lead angle is the dominant factor affecting surface roughness. Experimental results indicated an improvement in the surface roughness value with decreasing lead angle value from 88° to 45°.

Keywords: CGI, milling, surface roughness, ANN, regression, modeling, analysis

Procedia PDF Downloads 445

Authors: Kaushal Kishore, Suman Mukhopadhyay, Susovan Das, Manashi Adhikary, Sandip Bhattacharyya

Abstract:

In integrated steel plants, conveyor belts are widely used for transferring raw materials from one location to another. An output pin bush coupling attached with a conveyor transferring iron ore fines and fluxes failed after two years of service life. This led to an operational delay of approximately 15 hours. This study is focused on failure analysis of the coupling and recommending counter-measures to prevent any such failures in the future. Investigation consisted of careful visual observation, checking of operating parameters, stress calculation and analysis, macro and micro-fractography, material characterizations like chemical and metallurgical analysis and tensile and impact testings. The fracture occurred from an unusually sharp double step. There were multiple corrosion pits near the step that aggravated the situation. Inner contact surface of the coupling revealed differential abrasion that created a macroscopic difference in the height of the component. This pointed towards misalignment of the coupling beyond a threshold limit. In addition to these design and installation issues, material of the coupling did not meet the quality standards. These were made up of grey cast iron having graphite morphology intermediate between random distribution (Type A) and rosette pattern (Type B). This manifested as a marked reduction in impact toughness and tensile strength of the component. These findings corroborated well with the brittle mode of fracture that might have occurred during minor impact loading while loading of conveyor belt with raw materials from height. Simulated study was conducted to examine the effect of corrosion pits on tensile and impact toughness of grey cast iron. It was observed that pitting marginally reduced tensile strength and ductility. However, there was marked (up to 45%) reduction in impact toughness due to pitting. Thus, it became evident that failure of the coupling occurred due to combination of factors like inferior material, misalignment, poor step design and corrosion pitting. Recommendation for life enhancement of coupling included the use of tougher SG 500/7 grade, incorporation of proper fillet radius for the step, correction of alignment and application of corrosion resistant organic coating to prevent pitting.

Keywords: brittle fracture, cast iron, coupling, double step, pitting, simulated impact tests

Procedia PDF Downloads 130

Authors: Isao Tomita

Abstract:

The principle of all-silicon Raman lasers for an output wavelength of 1.3 μm is presented, which employs quasi-phase-matched structures and resonators to enhance the output power. 1.3-μm laser beams for GE-PONs in FTTH systems generated from a silicon device are very important because such a silicon device can be monolithically integrated with the silicon planar lightwave circuits (Si PLCs) used in the GE-PONs. This reduces the device fabrication processes and time and also optical losses at the junctions between optical waveguides of the Si PLCs and Si laser devices when compared with 1.3-μm III-V semiconductor lasers set on the Si PLCs employed at present. We show that the quasi-phase-matched Si Raman laser with resonators can produce about 174 times larger laser power at 1.3 μm (at maximum) than that without resonators for a Si waveguide of Raman gain 20 cm/GW and optical loss 1.2 dB/cm, pumped at power 10 mW, where the length of the waveguide is 3 mm and its cross-section is (1.5 μm)2.

Keywords: All-Silicon Raman Laser, FTTH, GE-PON, Quasi-Phase-Matched Structure, resonator

Procedia PDF Downloads 250

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 129

Authors: Kaleb Shiferaw, Berhanu Geberemedhin

Abstract:

Ethiopian farmers have a long tradition of beekeeping and the country has huge potential for honey production. However traditional mode of production still dominates the sub sector which negatively affect the total production and productivity. A number of studies have been conducted to better understand the working honey production, however, none of them systematically investigate the extent of technical efficiency of the sub-sector. This paper uses Stochastic Frontier production model to quantifying the extent of technical efficiency and identify exogenous determinant of inefficiency. The result showed that consistent with other studies traditional practice dominate small scale honey production in Ethiopia. The finding also revealed that use of purchased inputs such as bee forage and other supplement is very limited among honey producers indicating that natural bee forage is the primary source of bee forage. The immediate consequence of all these is low production and productivity. The number of hives the household owns, whether the household used improved apiculture technologies, availability of natural forest which is the primary sources of nectar for bees and amount of land owned by the households were found to have a significant influence on the amount of honey produced by beekeeper. Our result further showed that the mean technical efficiency of honey producers is 0.79 implying that, on average honey producer produce 80 percent of the maximum output. The implication is that 20 percent of the potential output is lost due to technical inefficiency. Number of hives owned by a honey produces, distance to district town-a proxy to market access, household wealth, and whether the household head has a leadership role in the PA affect the technical efficiency of honey producers. The finding suggest that policies that aim to expand the use of improved hives is expected to increase the honey production at household level. The result also suggest that investment on rural infrastructure would be instrumental in improving technical efficiency of honey producer.

Keywords: small-scale honey producer, Ethiopia, technical efficiency in apiculture, stochastic frontier analysis

Procedia PDF Downloads 230

Authors: Wan-Hsin Hsieh, Chieh-Fu Chang, Ming-Seng Kao

Abstract:

In this paper, a novel method termed the Phase Coherence Acquisition (PCA) is proposed for pseudo-random (PN) sequence acquisition. By employing complex phasors, the PCA requires only complex additions in the order of N, the length of the sequence, whereas the conventional method utilizing fast Fourier transform (FFT) requires complex multiplications and additions both in the order of Nlog2N . In order to combat noise, the input and local sequences are partitioned and mapped into complex phasors in PCA. The phase differences between pairs of input and local phasors are utilized for acquisition, and thus complex multiplications are avoided. For more noise-robustness capability, the multi-layer PCA is developed to extract the code phase step by step. The significant reduction of computational loads makes the PCA an attractive method, especially when the sequence length of is extremely large which becomes intractable for the FFT-based acquisition.

Keywords: FFT, PCA, PN sequence, convolution theory

Procedia PDF Downloads 474

Authors: Yassa Nacera, Badji Abderrezak, Saidoune Abdelmalek, Houassine Hamza

Abstract:

Several kinds of faults can occur in a permanent magnet synchronous machine (PMSM) systems: bearing faults, electrically short/open faults, eccentricity faults, and demagnetization faults. Demagnetization fault means that the strengths of permanent magnets (PM) in PMSM decrease, and it causes low output torque, which is undesirable for EVs. The fault is caused by physical damage, high-temperature stress, inverse magnetic field, and aging. Motor current signature analysis (MCSA) is a conventional motor fault detection method based on the extraction of signal features from stator current. a simulation model of the PMSM under partial demagnetization and uniform demagnetization fault was established, and different degrees of demagnetization fault were simulated. The harmonic analyses using the Fast Fourier Transform (FFT) show that the fault diagnosis method based on the harmonic wave analysis is only suitable for partial demagnetization fault of the PMSM and does not apply to uniform demagnetization fault of the PMSM.

Keywords: permanent magnet, diagnosis, demagnetization, modelling

Procedia PDF Downloads 62

Authors: S. A. Hashemi, A. Khoshraftar

Abstract:

This paper presents the influence of the vertical seismic component on the non-linear dynamics analysis of three different structures. The subject structures were analyzed and designed according to recent codes. This paper considers three types of buildings: 5-, 10-, and 15-story buildings. The non-linear dynamics analysis of the structures with assuming elastic-perfectly-plastic behavior was performed using Ram Perform-3D software; the horizontal component was taken into consideration with and without the incorporation of the corresponding vertical component. Dynamic responses obtained for the horizontal component acting alone were compared with those obtained from the simultaneous application of both seismic components. The results show that the effect of the vertical component of the ground motion may increase the axial load significantly in the interior columns and consequently, the stories. The plastic mechanisms would be changed. The P-Delta effect is expected to increase. The punching base plate shear of the columns should be considered. Moreover, the vertical component increases the input energy when the structures exhibit inelastic behavior and are taller.

Keywords: inelastic behavior, non-linear dynamic analysis, steel structure, vertical component

Procedia PDF Downloads 312

Authors: Bauer Peter, Murillo Jenny

Abstract:

This paper investigates the bounds of achievable fuel efficiency improvements in engines due to cycling between two operating points assuming a series hybrid configuration . It is shown that for linear bsfc dependencies (as a function of power), cycling is only beneficial if the average power needs are smaller than the power at the optimal bsfc value. Exact expressions for the fuel efficiency gains relative to the constant output power case are derived. This asymptotic analysis is then extended to the case where transient losses due to a change in the operating point are also considered. The case of the boundary bsfc trajectory where constant power application and cycling yield the same fuel consumption.is investigated. It is shown that the boundary bsfc locations of the second non-optimal operating points is hyperbolic. The analysis of the boundary case allows to evaluate whether for a particular engine, cycling can be beneficial. The introduced concepts are illustrated through a number of real world examples, i.e. large production Diesel engines in series hybrid configurations.

Keywords: cycling, efficiency, bsfc, series hybrid, diesel, operating point

Procedia PDF Downloads 502

Authors: Muhammad Farooq, Ahtasham Gul

Abstract:

To meet the desired standard, it is important to monitor and analyze different engineering processes to get desired output. The bivariate distributions got a lot of attention in recent years to describe the randomness of natural as well as artificial mechanisms. In this article, a bivariate model is constructed using two independent models developed by the nesting approach to study the effect of each component on reliability for better understanding. Further, the Bayes analysis of system availability is studied by considering prior parametric variations in the failure time and repair time distributions. Basic statistical characteristics of marginal distribution, like mean median and quantile function, are discussed. We use inverse Gamma prior to study its frequentist properties by conducting Monte Carlo Markov Chain (MCMC) sampling scheme.

Keywords: reliability, system availability Weibull, inverse Lomax, Monte Carlo Markov Chain, Bayesian

Procedia PDF Downloads 69

Authors: Ajai Singh

Abstract:

Simulation of hydrological processes at the watershed outlet through modelling approach is essential for proper planning and implementation of appropriate soil conservation measures in Damodar Barakar catchment, Hazaribagh, India where soil erosion is a dominant problem. This study quantifies the parametric uncertainty involved in simulation of stream flow using Soil and Water Assessment Tool (SWAT), a watershed scale model and Radial Basis Neural Network (RBNN), an artificial neural network model. Both the models were calibrated and validated based on measured stream flow and quantification of the uncertainty in SWAT model output was assessed using ‘‘Sequential Uncertainty Fitting Algorithm’’ (SUFI-2). Though both the model predicted satisfactorily, but RBNN model performed better than SWAT with R2 and NSE values of 0.92 and 0.92 during training, and 0.71 and 0.70 during validation period, respectively. Comparison of the results of the two models also indicates a wider prediction interval for the results of the SWAT model. The values of P-factor related to each model shows that the percentage of observed stream flow values bracketed by the 95PPU in the RBNN model as 91% is higher than the P-factor in SWAT as 87%. In other words the RBNN model estimates the stream flow values more accurately and with less uncertainty. It could be stated that RBNN model based on simple input could be used for estimation of monthly stream flow, missing data, and testing the accuracy and performance of other models.

Keywords: SWAT, RBNN, SUFI 2, bootstrap technique, stream flow, simulation

Procedia PDF Downloads 364

Authors: Tian-Wei Huang, Wei-Ting Bai, Yu-Tung Cheng, Jeng-Han Tsai

Abstract:

In this paper, a 1-stage 6-section conventional distributed amplifier (CDA) structure distributed power amplifier (DPA) fabricated in a 28-nm HPC+ 1P9M CMOS process is proposed. The transistor size selection is introduced to achieve broadband power matching and thus remains a high flatness output power and power added efficiency (PAE) within the bandwidth. With the inductive peaking technique, the high-frequency pole appears and the high-frequency gain is increased; the gain flatness becomes better as well. The inductive elements used to form an artificial transmission line are built up with a floating ground coplanar waveguide plane (CPWFG) rather than a microstrip line, coplanar waveguide (CPW), or spiral inductor to get better performance. The DPA achieves 12.6 dB peak gain at 52.5 GHz with 2.9 to 64.9 GHz 3-dB bandwidth. The Psat is 11.4 dBm with PAEMAX of 10.6 % at 25 GHz. The output 1-dB compression point power is 9.8 dBm.

Keywords: distributed power amplifier (DPA), gain bandwidth (GBW), floating ground CPW, inductive peaking, 28-nm, CMOS, 5G.

Procedia PDF Downloads 75

Authors: M. Otrusinova, E. Pastuszkova

Abstract:

The article is addressing the currently ongoing reform processes of transforming the public finance accounting based on cash flow principle to accrual principle. The presented analysis concerns the issues associated with the introduction of the state accounting from the perspective of municipal employees in compiling the opinions of financial experts in conditions of the Czech Republic. The aim of this paper is to present outcomes of analysis focused on currently discussed topics which are related to introducing the accrual principle into accounting of selected entities, especially municipalities and municipality-funded institutions. The output of the paper consists of comparing the application of the accrual principle in the financial reporting of municipalities in the Czech Republic and Slovakia. In conclusion and based on the survey, respondents from Slovak municipalities that have already adopted the accrual accounting principle show better opinion than Czech municipalities.

Keywords: accrual principle, accounting, accounting reform, Czech Republic, municipalities, public finance

Procedia PDF Downloads 255

Authors: Sidharth Talan, Sanjay Kumar Sharma, Eoin Joseph Wallace, Nikita Agrawal

Abstract:

Underground mining is at the core of rapidly evolving metals and minerals sector due to the increasing mineral consumption globally. Even though the surface mines are still more abundant on earth, the scales of industry are slowly tipping towards underground mining due to rising depth and complexities of orebodies. Thus, the efficient and productive functioning of underground operations depends significantly on the synchronized performance of key elements such as operating site, mining equipment, manpower and mine services. Production drilling is the process of conducting long hole drilling for the purpose of charging and blasting these holes for the production of ore in underground metal mines. Thus, production drilling is the crucial segment in the underground metal mining value chain. This paper presents the process mapping tool to evaluate the production drilling process in the underground metal mining operation by dividing the given process into three segments namely Input, Process and Output. The three segments are further segregated into factors and sub-factors. As per the study, the major input factors crucial for the efficient functioning of production drilling process are power, drilling water, geotechnical support of the drilling site, skilled drilling operators, services installation crew, oils and drill accessories for drilling machine, survey markings at drill site, proper housekeeping, regular maintenance of drill machine, suitable transportation for reaching the drilling site and finally proper ventilation. The major outputs for the production drilling process are ore, waste as a result of dilution, timely reporting and investigation of unsafe practices, optimized process time and finally well fragmented blasted material within specifications set by the mining company. The paper also exhibits the drilling loss matrix, which is utilized to appraise the loss in planned production meters per day in a mine on account of availability loss in the machine due to breakdowns, underutilization of the machine and productivity loss in the machine measured in drilling meters per unit of percussion hour with respect to its planned productivity for the day. The given three losses would be essential to detect the bottlenecks in the process map of production drilling operation so as to instigate the action plan to suppress or prevent the causes leading to the operational performance deficiency. The given tool is beneficial to mine management to focus on the critical factors negatively impacting the production drilling operation and design necessary operational and maintenance strategies to mitigate them. 

Keywords: process map, drilling loss matrix, SIPOC, productivity, percussion rate

Procedia PDF Downloads 212

Authors: Pingping Zhang, Yanpeng Cai, Jianlong Wang

Abstract:

Stormwater storage tank (SST) is a popular low impact development technology for reducing stormwater runoff in the construction of sponge city. At present, it is difficult to perform the automatic control of SST for reducing peak flow. In this paper, fuzzy control was introduced into the peak control of SST to improve the efficiency of reducing stormwater runoff. Firstly, the design of SST was investigated. A catchment area and a return period were assumed, a SST model was manufactured, and then the storage capacity of the SST was verified. Secondly, the control parameters of the SST based on reducing stormwater runoff were analyzed, and a schematic diagram of real-time control (RTC) system based on peak control SST was established. Finally, fuzzy control system of a double input (flow and water level) and double output (inlet and outlet valve) was designed. The results showed that 1) under the different return periods (one year, three years, five years), the SST had the effect of delayed peak control and storage by increasing the detention time, 2) rainfall, pipeline flow, the influent time and the water level in the SST could be used as RTC parameters, and 3) the response curves of flow velocity and water level fluctuated very little and reached equilibrium in a short time. The combination of online monitoring and fuzzy control was feasible to control the SST automatically. This paper provides a theoretical reference for reducing stormwater runoff and improving the operation efficiency of SST.

Keywords: stormwater runoff, stormwater storage tank, real-time control, fuzzy control

Procedia PDF Downloads 198

Authors: Misbah Fatma, Anam Saiyeda

Abstract:

This analysis charts the introduction and expansion of research into the filter bubble phenomena over the last 10 years using a large dataset of academic publications. This bibliometric study demonstrates how interdisciplinary filter bubble research is. The identification of key authors and organizations leading the filter bubble study sheds information on collaborative networks and knowledge transfer. Relevant papers are organized based on themes including algorithmic bias, polarisation, social media, and ethical implications through a systematic examination of the literature. In order to shed light on how these patterns have changed over time, the study plots their historical history. The study also looks at how research is distributed globally, showing geographic patterns and discrepancies in scholarly output. The results of this bibliometric analysis let us fully comprehend the development and reach of filter bubble research. This study offers insights into the ongoing discussion surrounding information personalization and its implications for societal discourse, democratic participation, and the potential risks to an informed citizenry by exposing dominant themes, interdisciplinary collaborations, and geographic patterns. In order to solve the problems caused by filter bubbles and to advance a more diverse and inclusive information environment, this analysis is essential for scholars and researchers.

Keywords: bibliometric analysis, social media, social networking, algorithmic personalization, self-selection, content moderation policies and limited access to information, recommender system and polarization

Procedia PDF Downloads 115

Authors: Mustafa Albayrak, Mete Onur Kaman, Ilyas Bozkurt

Abstract:

In this study, the necessary material parameters were determined to be able to conduct progressive damage analysis of layered composites under low velocity impact by using the MAT162 material module in the LS-DYNA program. The material module MAT162 based on Hashin failure criterion requires 34 parameters in total. Some of these parameters were obtained directly as a result of dynamic and quasi-static mechanical tests, and the remaining part was calibrated and determined by comparing numerical and experimental results. Woven glass/epoxy was used as the composite material and it was produced by vacuum infusion method. In the numerical model, composites are modeled as three-dimensional and layered. As a result, the acquisition of MAT162 material module parameters, which will enable progressive damage analysis, is given in detail and step by step, and the selection methods of the parameters are explained. Numerical data consistent with the experimental results are given in graphics.

Keywords: Composite Impact, Finite Element Simulation, Progressive Damage Analyze, LS-DYNA, MAT162

Procedia PDF Downloads 102

Authors: Marlene Perez Villalpando, Kelly Joel Gurubel Tun

Abstract:

In this paper, we propose an optimal control strategy for a hydroelectric power plant subject to input disturbances like meteorological phenomena. The engineering characteristics of the system are described by a nonlinear model. The random availability of renewable sources is predicted by a high-order neural network trained with an extended Kalman filter, whereas the power generation is regulated by the optimal control law. The main advantage of the system is the stabilization of the amount of power generated in the plant. A control supervisor maintains stability and availability in hydropower reservoirs water levels for power generation. The proposed approach demonstrated a good performance to stabilize the reservoir level and the power generation along their desired trajectories in the presence of disturbances.

Keywords: hydropower, high order neural network, Kalman filter, optimal control

Procedia PDF Downloads 295

Authors: Subal Kar, Madhuja Ghosh, Soumik Das, Antara Saha

Abstract:

A novel technique has been developed to generate ultra-stable millimeter-wave signal by optical heterodyning of the output from two slave laser (SL) sources injection-locked to the sidebands of a frequency modulated (FM) master laser (ML). Precise thermal tuning of the SL sources is required to lock the particular slave laser frequency to the desired FM sidebands of the ML. The output signals from the injection-locked SL when coherently heterodyned in a fast response photo detector like high electron mobility transistor (HEMT), extremely stable millimeter-wave signal having very narrow line width can be generated. The scheme may also be used to generate ultra-stable sub-millimeter-wave/terahertz signal.

Keywords: FM sideband injection locking, master-slave injection locking, millimetre-wave signal generation, optical heterodyning

Procedia PDF Downloads 390

Authors: Abobaker Mohammed Qasem Farhan, Shangming Yang, Mohammed Al-Nehari

Abstract:

Pneumonia is a kind of lung disease that creates congestion in the chest. Such pneumonic conditions lead to loss of life of the severity of high congestion. Pneumonic lung disease is caused by viral pneumonia, bacterial pneumonia, or Covidi-19 induced pneumonia. The early prediction and classification of such lung diseases help to reduce the mortality rate. We propose the automatic Computer-Aided Diagnosis (CAD) system in this paper using the deep learning approach. The proposed CAD system takes input from raw computerized tomography (CT) scans of the patient's chest and automatically predicts disease classification. We designed the Hybrid Deep Learning Algorithm (HDLA) to improve accuracy and reduce processing requirements. The raw CT scans have pre-processed first to enhance their quality for further analysis. We then applied a hybrid model that consists of automatic feature extraction and classification. We propose the robust 2D Convolutional Neural Network (CNN) model to extract the automatic features from the pre-processed CT image. This CNN model assures feature learning with extremely effective 1D feature extraction for each input CT image. The outcome of the 2D CNN model is then normalized using the Min-Max technique. The second step of the proposed hybrid model is related to training and classification using different classifiers. The simulation outcomes using the publically available dataset prove the robustness and efficiency of the proposed model compared to state-of-art algorithms.

Keywords: CT scan, Covid-19, deep learning, image processing, lung disease classification

Procedia PDF Downloads 149

Authors: Khyamling Parane, B. M. Prabhu Prasad, Basavaraj Talawar

Abstract:

Fast simulations are critical in reducing time to market in CMPs and SoCs. Several simulators have been used to evaluate the performance and power consumed by Network-on-Chips. Researchers and designers rely upon these simulators for design space exploration of NoC architectures. Our experiments show that simulating large NoC topologies take hours to several days for completion. To speed up the simulations, it is necessary to investigate and optimize the hotspots in simulator source code. Among several simulators available, we choose Booksim2.0, as it is being extensively used in the NoC community. In this paper, we analyze the cache and memory system behaviour of Booksim2.0 to accurately monitor input dependent performance bottlenecks. Our measurements show that cache and memory usage patterns vary widely based on the input parameters given to Booksim2.0. Based on these measurements, the cache configuration having least misses has been identified. To further reduce the cache misses, we use software optimization techniques such as removal of unused functions, loop interchanging and replacing post-increment operator with pre-increment operator for non-primitive data types. The cache misses were reduced by 18.52%, 5.34% and 3.91% by employing above technology respectively. We also employ thread parallelization and vectorization to improve the overall performance of Booksim2.0. The OpenMP programming model and SIMD are used for parallelizing and vectorizing the more time-consuming portions of Booksim2.0. Speedups of 2.93x and 3.97x were observed for the Mesh topology with 30 × 30 network size by employing thread parallelization and vectorization respectively.

Keywords: cache behaviour, network-on-chip, performance profiling, vectorization

Procedia PDF Downloads 193

Authors: Ziad M. Hejazi, Hani F. Mokhtar, Mohammed S. Bahabri, Mohammed H. Ghafouri, Ahmed S. Bahaitham

Abstract:

This paper demonstrates the efforts taken by an Information Technology (IT) organization at Saudi Aramco to establish Operations Guide in a practical manner. Review of related work and literature revealed several important aspects to be considered when implementing the operation guide including Identify supporting IT groups, specify each group roles and responsibilities, formulate the IT operations in terms of processes (input/output), list each process main steps, provide the details of each process main step, develop the RACI (Responsible, Accountable, Consulted, and Informed) chart, highlight the process KPI’s, utilized systems, and forms. Identified aspects were then addressed in the actual implementation via several practices, including developing the operation guide for all IT supported operations, creating a shared folder for the operations guide, and announcing the implementation to all IT staff. The implementation of the mentioned practice was benchmarked, identified as best in class, and adopted by other internal organizations. Moreover, it was evident and appreciated by IT management. The significance of this study stems from the fact that it might be among the first studies in Saudi Arabia that propose a practical guideline to implement IT operations guide by IT organizations. Additional research significance comes from the study being conducted in Saudi Aramco, one of the world’s biggest integrated energy and petrochemical companies.

Keywords: operations guide, process implementation, Saudi Aramco company, information technology, standard of procedure

Procedia PDF Downloads 91

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 178

Authors: Shubhakar Gupta, Dhruv Prakash, Apoorv Mehta

Abstract:

In this project, we design a modular robot capable of using and switching between multiple methods of propulsion and classifying terrain, based on an Inertial Measurement Unit (IMU) input. We wanted to make a robot that is not only intelligent in its functioning but also versatile in its physical design. The advantage of a modular robot is that it can be designed to hold several movement-apparatuses, such as wheels, legs for a hexapod or a quadpod setup, propellers for underwater locomotion, and any other solution that may be needed. The robot takes roughness input from a gyroscope and an accelerometer in the IMU, and based on the terrain classification from an artificial neural network; it decides which method of propulsion would best optimize its movement. This provides the bot with adaptability over a set of terrains, which means it can optimize its locomotion on a terrain based on its roughness. A feature like this would be a great asset to have in autonomous exploration or research drones.

Keywords: modular robotics, terrain detection, terrain classification, neural network

Procedia PDF Downloads 142

Authors: Shreya Thusoo, Karan Modi, Ankit Kumar Jha, Rajesh Kumar

Abstract:

Since the evolution of computational tools and simulation software, there has been considerable increase in research on Soil Structure Interaction (SSI) to decrease the computational time and increase accuracy in the results. To aid the designer with a proper understanding of the response of structure in different soil types, the presented paper compares the deformation, shear stress, acceleration and other parameters of multi-storey building for a specific input ground motion using Response-spectrum Analysis (RSA) method. The response of all the models of different heights have been compared in different soil types. Finite Element Simulation software, ANSYS, has been used for all the computational purposes. Overall, higher response is observed with SSI, while it increases with decreasing stiffness of soil.

Keywords: soil-structure interaction, response spectrum, analysis, finite element method, multi-storey buildings

Procedia PDF Downloads 475

Authors: Wu Peiqin

Abstract:

Flexible thermoelectric devices are light and flexible, which can be in close contact with any shape of heat source surfaces to minimize heat loss and achieve efficient energy conversion. Among the wide application fields, energy harvesting via flexible thermoelectric generators can adapt to a variety of curved heat sources (such as human body, circular tubes, and surfaces of different shapes) and can drive low-power electronic devices, exhibiting one of the most promising technologies in self-powered systems. The heat flux along the cross-section of the flexible thin-film generator is limited by the thickness, so the temperature difference decreases during the generation process, and the output power is low. At present, most of the heat flow directions of the thin film thermoelectric generator are along the thin-film plane; however, this method is not suitable for attaching to the human body surface to generate electricity. In order to make the film generator more suitable for thermoelectric generation, it is necessary to apply a flexible heatsink on the air sides with the film to maintain the temperature difference. In this paper, Bismuth telluride thermoelectric paste was deposited on polyimide flexible substrate by a screen printing method, and the flexible thermoelectric film was formed after drying. There are ten pairs of thermoelectric legs. The size of the thermoelectric leg is 20 x 2 x 0.1 mm, and adjacent thermoelectric legs are spaced 2 mm apart. A phase change material-based flexible heatsink was designed and fabricated. The flexible heatsink consists of n-octadecane, polystyrene, and expanded graphite. N-octadecane was used as the thermal storage material, polystyrene as the supporting material, and expanded graphite as the thermally conductive additive. The thickness of the flexible phase change material-based heatsink is 2mm. A thermoelectric performance testing platform was built, and its output performance was tested. The results show that the system can generate an open-circuit output voltage of 3.89 mV at a temperature difference of 10K, which is higher than the generator without a heatsink. Therefore, the flexible heatsink can increase the temperature difference between the two ends of the film and improve the output performance of the flexible film generator. This result promotes the application of the film thermoelectric generator in collecting human heat for power generation.

Keywords: flexible thermoelectric generator, screen printing, PCM, flexible heatsink

Procedia PDF Downloads 97

Authors: Abhisek Chakrabarty, Subhraprakash Mandal

Abstract:

Flash flood is one of the catastrophic natural hazards in the mountainous region of India. The recent flood in the Mandakini River in Kedarnath (14-17th June, 2013) is a classic example of flash floods that devastated Uttarakhand by killing thousands of people.The disaster was an integrated effect of high intensityrainfall, sudden breach of Chorabari Lake and very steep topography. Every year in Himalayan Region flash flood occur due to intense rainfall over a short period of time, cloud burst, glacial lake outburst and collapse of artificial check dam that cause high flow of river water. In Sikkim-Derjeeling Himalaya one of the probable flash flood occurrence zone is Teesta Watershed. The Teesta River is a right tributary of the Brahmaputra with draining mountain area of approximately 8600 Sq. km. It originates in the Pauhunri massif (7127 m). The total length of the mountain section of the river amounts to 182 km. The Teesta is characterized by a complex hydrological regime. The river is fed not only by precipitation, but also by melting glaciers and snow as well as groundwater. The present study describes an attempt to model surface runoff in upper Teesta basin, which is directly related to catastrophic flood events, by creating a system based on GIS technology. The main object was to construct a direct unit hydrograph for an excess rainfall by estimating the stream flow response at the outlet of a watershed. Specifically, the methodology was based on the creation of a spatial database in GIS environment and on data editing. Moreover, rainfall time-series data collected from Indian Meteorological Department and they were processed in order to calculate flow time and the runoff volume. Apart from the meteorological data, background data such as topography, drainage network, land cover and geological data were also collected. Clipping the watershed from the entire area and the streamline generation for Teesta watershed were done and cross-sectional profiles plotted across the river at various locations from Aster DEM data using the ERDAS IMAGINE 9.0 and Arc GIS 10.0 software. The analysis of different hydraulic model to detect flash flood probability ware done using HEC-RAS, Flow-2D, HEC-HMS Software, which were of great importance in order to achieve the final result. With an input rainfall intensity above 400 mm per day for three days the flood runoff simulation models shows outbursts of lakes and check dam individually or in combination with run-off causing severe damage to the downstream settlements. Model output shows that 313 Sq. km area were found to be most vulnerable to flash flood includes Melli, Jourthang, Chungthang, and Lachung and 655sq. km. as moderately vulnerable includes Rangpo,Yathang, Dambung,Bardang, Singtam, Teesta Bazarand Thangu Valley. The model was validated by inserting the rain fall data of a flood event took place in August 1968, and 78% of the actual area flooded reflected in the output of the model. Lastly preventive and curative measures were suggested to reduce the losses by probable flash flood event.

Keywords: flash flood, GIS, runoff, simulation model, Teesta river basin

Procedia PDF Downloads 313

Authors: Mohammad Beyki, Justus Pawlak, Robert Patzke, Franz Renz

Abstract:

In the context of planetary exploration, the MIMOS II (miniaturized Mössbauer spectrometer) serves as a proven and reliable measuring instrument. The transmission behaviour of the electronics in the Mössbauer spectroscopy is newly developed and optimized. For this purpose, the overall electronics is split into three parts. This elaboration deals exclusively with the first part of the signal chain for the evaluation of photons in experiments with gamma radiation. Parallel to the analysis of the electronics, a new method for the stability consideration of linear and non-linear systems is presented: The extended method of Lyapunov’s stability criteria. The design helps to weigh advantages and disadvantages against other simulated circuits in order to optimize the MIMOS II for the terestric and extraterestric measurment. Finally, after stability analysis, the controller design according to Ackermann is performed, achieving the best possible optimization of the output variable through a skillful pole assignment.

Keywords: Mössbauer spectroscopy, electronic signal amplifier, light processing technology, photocurrent, trans-impedance amplifier, extended Lyapunov method

Procedia PDF Downloads 98

Authors: Zahra Ahmadi, Fazlollah Adibnia

Abstract:

Scheduling of tasks and the optimal allocation of resources in the cloud are based on the dynamic nature of tasks and the heterogeneity of resources. Applications that are based on the scientific workflow are among the most widely used applications in this field, which are characterized by high processing power and storage capacity. In order to increase their efficiency, it is necessary to plan the tasks properly and select the best virtual machine in the cloud. The goals of the system are effective factors in scheduling tasks and resource selection, which depend on various criteria such as time, cost, current workload and processing power. Multi-criteria decision-making methods are a good choice in this field. In this research, a new method of work planning and resource allocation in a heterogeneous environment based on the modified AHP algorithm is proposed. In this method, the scheduling of input tasks is based on two criteria of execution time and size. Resource allocation is also a combination of the AHP algorithm and the first-input method of the first client. Resource prioritization is done with the criteria of main memory size, processor speed and bandwidth. What is considered in this system to modify the AHP algorithm Linear Max-Min and Linear Max normalization methods are the best choice for the mentioned algorithm, which have a great impact on the ranking. The simulation results show a decrease in the average response time, return time and execution time of input tasks in the proposed method compared to similar methods (basic methods).

Keywords: hierarchical analytical process, work prioritization, normalization, heterogeneous resource allocation, scientific workflow

Procedia PDF Downloads 140