Search results for: bi-directional long and short-term memory networks

Authors: Md Al Masum Bhuiyan, Maria C. Mariani, Osei K. Tweneboah

Abstract:

In the present work, we develop a technique for estimating the volatility of financial time series by using stochastic differential equation. Taking the daily closing prices from developed and emergent stock markets as the basis, we argue that the incorporation of stochastic volatility into the time-varying parameter estimation significantly improves the forecasting performance via Maximum Likelihood Estimation. While using the technique, we see the long-memory behavior of data sets and one-step-ahead-predicted log-volatility with ±2 standard errors despite the variation of the observed noise from a Normal mixture distribution, because the financial data studied is not fully Gaussian. Also, the Ornstein-Uhlenbeck process followed in this work simulates well the financial time series, which aligns our estimation algorithm with large data sets due to the fact that this algorithm has good convergence properties.

Keywords: financial time series, maximum likelihood estimation, Ornstein-Uhlenbeck type models, stochastic volatility model

Procedia PDF Downloads 241

Authors: Tiziana Biasutti, Daniela Rigamonti, Lorenzo Palmiotti, Adelaide Nespoli, Paolo Bettini

Abstract:

Aerospace industry is based on the continuous development of new technologies and solutions that allows constant improvement of the systems. Shape Memory Alloys are smart materials that can be used as dampers due to their pseudoelastic effect. The purpose of the research was to design a passive damper in Nitinol, manufactured by Selective Laser Melting, for space applications to reduce vibration between different structural parts in space structures. The powder is NiTi (50.2 at.% of Ni). The structure manufactured by additive technology allows us to eliminate the presence of joint and moving parts and to have a compact solution with high structural strength. The designed dampers had single or double cell structures with three different internal angles (30°, 45° and 60°). This particular shape has damping properties also without the pseudoelastic effect. For this reason, the geometries were reproduced in different materials, SS316L and Ti6Al4V, to test the geometry loss factor. The mechanical performances of these specimens were compared to the ones of NiTi structures, pointing out good damping properties of the designed structure and the highest performances of the NiTi pseudoelastic effect. The NiTi damper was mechanically characterized by static and dynamic tests and with DSC and microscope observations. The experimental results were verified with numerical models and with some scaled steel specimens in which optical fibers were embedded. The realized structure presented good mechanical and damping properties. It was observed that the loss factor and the dissipated energy increased with the angles of the cells.

Keywords: additive manufacturing, damper, nitinol, pseudo elastic effect, selective laser melting, shape memory alloys

Procedia PDF Downloads 107

Authors: Gaurav Bansod, Swapnil Sutar, Abhijit Patil, Jagdish Patil

Abstract:

This paper proposes an ultra-lightweight cipher NUX. NUX is a generalized Feistel network. It supports 128/80 bit key length and block length of 64 bit. For 128 bit key length, NUX needs only 1022 GEs which is less as compared to all existing cipher design. NUX design results into less footprint area and minimal memory size. This paper presents security analysis of NUX cipher design which shows cipher’s resistance against basic attacks like Linear and Differential Cryptanalysis. Advanced attacks like Biclique attack is also mounted on NUX cipher design. Two different F function in NUX cipher design results in high diffusion mechanism which generates large number of active S-boxes in minimum number of rounds. NUX cipher has total 31 rounds. NUX design will be best-suited design for critical application like smart grid, IoT, wireless sensor network, where memory size, footprint area and the power dissipation are the major constraints.

Keywords: lightweight cryptography, Feistel cipher, block cipher, IoT, encryption, embedded security, ubiquitous computing

Procedia PDF Downloads 372

Authors: Paramjit Mahey, Monica Sharma, Jasbinder Singh

Abstract:

Fiber based access networks can deliver performance that can support the increasing demands for high speed connections. One of the new technologies that have emerged in recent years is Passive Optical Networks. This paper is targeted to show the simultaneous delivery of triple play service (data, voice and video). The comparative investigation and suitability of various data rates is presented. It is demonstrated that as we increase the data rate, number of users to be accommodated decreases due to increase in bit error rate.

Keywords: BER, PON, TDMPON, GPON, CWDM, OLT, ONT

Procedia PDF Downloads 541

Authors: Danilo López, Edwin Rivas, Leyla López

Abstract:

This paper presents the development of an algorithm that predicts the arrival of a secondary user (SU) to a base station (BS) in a cognitive network based on infrastructure, requesting a Best Effort (BE) or Real Time (RT) type of service with a determined bandwidth (BW) implementing neural networks. The algorithm dynamically uses a neural network construction technique using the geometric pyramid topology and trains a Multilayer Perceptron Neural Networks (MLPNN) based on the historical arrival of an SU to estimate future applications. This will allow efficiently managing the information in the BS, since it precedes the arrival of the SUs in the stage of selection of the best channel in CRN. As a result, the software application determines the probability of arrival at a future time point and calculates the performance metrics to measure the effectiveness of the predictions made.

Keywords: cognitive radio, base station, best effort, MLPNN, prediction, real time

Procedia PDF Downloads 330

Authors: Vangmayee. V. Subban, Somashekara H. S, Shwetha Prabhu, Jayashree S. Bhat

Abstract:

Introduction and Need: Phonological processing is critical in learning to read alphabetical and non-alphabetical languages. However, its role in learning to read Kannada an alphasyllabary is equivocal. The literature has focused on the developmental role of phonological awareness on reading. To the best of authors knowledge, the role of phonological memory and phonological naming has not been addressed in alphasyllabary Kannada language. Therefore, there is a need to evaluate the comprehensive role of the phonological processing skills in Kannada on word decoding skills during the early years of schooling. Aim and Objectives: The present study aimed to explore the phonological processing abilities and their role in learning to decode pseudowords in children learning to read the Kannada language during initial years of formal schooling between 5.6 to 8.6 years. Method: In this cross sectional study, 60 typically developing Kannada speaking children, 20 each from Grade I, Grade II, and Grade III between the age range of 5.6 to 6.6 years, 6.7 to 7.6 years and 7.7 to 8.6 years respectively were selected from Kannada medium schools. Phonological processing abilities were assessed using an assessment tool specifically developed to address the objectives of the present research. The assessment tool was content validated by subject experts and had good inter and intra-subject reliability. Phonological awareness was assessed at syllable level using syllable segmentation, blending, and syllable stripping at initial, medial and final position. Phonological memory was assessed using pseudoword repetition task and phonological naming was assessed using rapid automatized naming of objects. Both phonological awareneness and phonological memory measures were scored for the accuracy of the response, whereas Rapid Automatized Naming (RAN) was scored for total naming speed. Results: The mean scores comparison using one-way ANOVA revealed a significant difference (p ≤ 0.05) between the groups on all the measures of phonological awareness, pseudoword repetition, rapid automatized naming, and pseudoword reading. Subsequent post-hoc grade wise comparison using Bonferroni test revealed significant differences (p ≤ 0.05) between each of the grades for all the tasks except (p ≥ 0.05) for syllable blending, syllable stripping, and pseudoword repetition between Grade II and Grade III. The Pearson correlations revealed a highly significant positive correlation (p=0.000) between all the variables except phonological naming which had significant negative correlations. However, the correlation co-efficient was higher for phonological awareness measures compared to others. Hence, phonological awareness was chosen a first independent variable to enter in the hierarchical regression equation followed by rapid automatized naming and finally, pseudoword repetition. The regression analysis revealed syllable awareness as a single most significant predictor of pseudoword reading by explaining the unique variance of 74% and there was no significant change in R² when RAN and pseudoword repetition were added subsequently to the regression equation. Conclusion: Present study concluded that syllable awareness matures completely by Grade II, whereas the phonological memory and phonological naming continue to develop beyond Grade III. Amongst phonological processing skills, phonological awareness, especially syllable awareness is crucial for word decoding than phonological memory and naming during initial years of schooling.

Keywords: phonological awareness, phonological memory, phonological naming, phonological processing, pseudo-word decoding

Procedia PDF Downloads 175

Authors: Kensho Takahashi, Ko Watanabe, Takashi Kaburagi, Hiroshi Tanaka, Kajiro Watanabe, Yosuke Kurihara

Abstract:

Near-infrared spectroscopy (NIRS) has been widely used as a non-invasive method to measure brain activity, but it is corrupted by baseline drift noise. Here we present a method to measure regional cerebral blood flow as a derivative of NIRS output. We investigate whether, when listening to languages, blood flow can reasonably localize and represent regional brain activity or not. The prefrontal blood flow distribution pattern when advanced second-language listeners listened to a second language (L2) was most similar to that when listening to their first language (L1) among the patterns of mean and standard deviation. In experiments with 25 healthy subjects, the maximum blood flow was localized to the left BA46 of advanced listeners. The blood flow presented is robust to baseline drift and stably localizes regional brain activity.

Keywords: NIRS, oxy-hemoglobin, baseline drift, blood flow, working memory, BA46, first language, second language

Procedia PDF Downloads 558

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 198

Authors: Yang Zhang, Jian He

Abstract:

Heart disease is one of the leading causes of death in the world, and coronary heart disease (CHD) is one of the major heart diseases. Electrocardiogram (ECG) is widely used in the detection of heart diseases, but the traditional manual method for CHD prediction by analyzing ECG requires lots of professional knowledge for doctors. This paper introduces sliding window and continuous wavelet transform (CWT) to transform ECG signals into images, and then ResNet and Bi-LSTM are introduced to build the ECG feature extraction network (namely ECGNet). At last, an auxiliary system for coronary heart disease prediction was developed based on modified ResNet18 and Bi-LSTM, and the public ECG dataset of CHD from MIMIC-3 was used to train and test the system. The experimental results show that the accuracy of the method is 83%, and the F1-score is 83%. Compared with the available methods for CHD prediction based on ECG, such as kNN, decision tree, VGGNet, etc., this method not only improves the prediction accuracy but also could avoid the degradation phenomenon of the deep learning network.

Keywords: Bi-LSTM, CHD, ECG, ResNet, sliding window

Procedia PDF Downloads 89

Authors: Seyed Mohsen Jameii

Abstract:

Wireless underwater sensor networks are a type of sensor networks that are located in underwater environments and linked together by acoustic waves. The application of these kinds of network includes monitoring of pollutants (chemical, biological, and nuclear), oil fields detection, prediction of the likelihood of a tsunami in coastal areas, the use of wireless sensor nodes to monitor the passing submarines, and determination of appropriate locations for anchoring ships. This paper proposes a boundary coverage algorithm for intrusion detection in underwater sensor networks. In the first phase of the proposed algorithm, optimal deployment of nodes is done in the water. In the second phase, after the employment of nodes at the proper depth, clustering is executed to reduce the exchanges of messages between the sensors. In the third phase, the algorithm of "divide and conquer" is used to save energy and increase network efficiency. The simulation results demonstrate the efficiency of the proposed algorithm.

Keywords: boundary coverage, clustering, divide and ‎conquer, underwater sensor nodes

Procedia PDF Downloads 341

Authors: Ruiyuan Wang, Jing Han, Bruno Di Biase, Mark Antoniou

Abstract:

The purpose of this study is to explore the relationship between working memory (WM) capacity and Chinese-English consecutive interpreting (CI) performance in interpreting learners with different study abroad experience (SAE). Such relationship is not well understood. This study also examines whether Chinese interpreting learners with SAE in English-speaking countries, demonstrate a better performance in inflectional morphology and agreement, notoriously unstable in Chinese speakers of English L2, in their interpreting output than learners without SAE. Fifty Chinese university students, majoring in Chinese-English Interpreting, were recruited in Australia (n=25) and China (n=25). The two groups matched in age, language proficiency, and interpreting training period. Study abroad (SA) group has been studying in an English-speaking country (Australia) for over 12 months, and none of the students recruited in China (the no study abroad = NSA group) had ever studied or lived in an English-speaking country. Data on language proficiency and training background were collected via a questionnaire. Lexical retrieval performance and working memory (WM) capacity data were collected experimentally, and finally, interpreting data was elicited via a direct CI task. Main results of the study show that WM significantly correlated with participants' CI performance independently of learning context. Moreover, SA outperformed NSA learners in terms of subject-verb number agreement. Apart from that, WM capacity was also found to correlate significantly with their morphosyntactic accuracy. This paper sheds some light on the relationship between study abroad, WM capacity, and CI performance. Exploring the effect of study abroad on interpreting trainees and how various important factors correlate may help interpreting educators bring forward more targeted teaching paradigms for participants with different learning experiences.

Keywords: study abroad experience, consecutive interpreting, working memory, inflectional agreement

Procedia PDF Downloads 100

Authors: Birge Yildirim Okta

Abstract:

This paper aims to narrate the story of Atatürk Cultural Center in Taksim Square, which was demolished in 2018, and discuss its architectonic as a social place of memory and its existence and demolishment as the space of politics. Focusing on the timeline starting from early republican period till today, the paper uses narrative discourse analysis to research Atatürk Cultural Center as a place of memory and a space of politics in its existence. After the establishment of Turkish Republic, one of most important implementation in Taksim Square, reflecting the internationalist style, was the construction of Opera Building in Prost Plan. The first design of the opera building belonged to Aguste Perret, which could not be implemented due to economic hardship during World War II. Later the project was designed by architects Feridun Kip and Rüknettin Güney in 1946 but could not be completed due to 1960 military coup. Later the project was shifted to another architect Hayati Tabanlıoglu, with a change in its function as a cultural center. Eventually, the construction of the building was completed in 1969 in a completely different design. AKM became a symbol of republican modernism not only with its modern architectural style but also with it is function as the first opera building of the republic, reflecting the western, modern cultural heritage by professional groups, artists and the intelligentsia. In 2005, Istanbul’s council for the protection of cultural heritage decided to list AKM as a grade 1 cultural heritage, ending a period of controversy which saw calls for the demolition of the center as it was claimed it ended its useful lifespan. In 2008 the building was announced to be closed for repairs and restoration. Over the following years, the building was demolished piece by piece silently while Taksim mosque has been built just in front of Atatürk Cultural Center. Belonging to the early republican period, AKM was a representation of a cultural production of a modern society for the emergence and westward looking, secular public space in Turkey. Its erasure from Taksim scene under the rule of the conservative government, Justice and Development Party and the construction of Taksim mosque in front of AKM’s parcel is also representational. The question of governing the city through space has always been an important aspect for governments, those holding political power since cities are the chaotic environments that are seen as a threat for the governments, carrying the tensions of proletariat or the contradictory groups. The story of AKM as a dispositive or a regulatory apparatus demonstrates how space itself is becoming a political medium, to transform the socio-political condition. The article aims to discuss the existence and demolishment of Atatürk Cultural Center by discussing the constructed and demolished building as a place of memory and a space of politics.

Keywords: space of politics, place of memory, atatürk cultural center, taksim square

Procedia PDF Downloads 82

Authors: Samia Dardouri, Ridha Bouallegue

Abstract:

Scheduling is the process of dynamically allocating physical resources to User Equipment (UE) based on scheduling algorithms implemented at the LTE base station. Various algorithms have been proposed by network researchers as the implementation of scheduling algorithm which represents an open issue in Long Term Evolution (LTE) standard. This paper makes an attempt to study and compare the performance of PF, MLWDF and EXP/PF scheduling algorithms. The evaluation is considered for a single cell with interference scenario for different flows such as Best effort, Video and VoIP in a pedestrian and vehicular environment using the LTE-Sim network simulator. The comparative study is conducted in terms of system throughput, fairness index, delay, packet loss ratio (PLR) and total cell spectral efficiency.

Keywords: LTE, multimedia flows, scheduling algorithms, mobile computing

Procedia PDF Downloads 383

Authors: Mohammed Affanuddin H. Siddique, Jayesh S. Shukla, Chetan B. Meshram

Abstract:

The neural networks are one of the power tools of machine learning. After the invention of perceptron in early 1980's, the neural networks and its application have grown rapidly. Neural networks are a technique originally developed for pattern investigation. The structure of a neural network consists of neurons connected through synapse. Here, we have investigated the different algorithms and cost function reduction techniques for optimization of vertical axis wind turbine (VAWT) rotor blades. The aerodynamic force coefficients corresponding to the airfoils are stored in a database along with the airfoil coordinates. A forward propagation neural network is created with the input as aerodynamic coefficients and output as the airfoil co-ordinates. In the proposed algorithm, the hidden layer is incorporated into cost function having linear and non-linear error terms. In this article, it is observed that the ANNs (Artificial Neural Network) can be used for the VAWT’s optimization.

Keywords: VAWT, ANN, optimization, inverse design

Procedia PDF Downloads 323

Authors: Ghayah Alsaleem

Abstract:

This research project focussed on specific compounds, whereas a literature review was completed on the broader subject of long-lasting phosphorescence. For the review and subsequent laboratory work, long lasting phosphorescence compounds were defined as materials that have an afterglow decay time greater than a few minutes. The decay time is defined as the time between the end of excitation and the moment the light intensity drops below 0.32mcd/m2. This definition is widely used in industry and in most research studies. The experimental work focused on known long-lasting phosphorescence compounds – strontium aluminate (SrAl2O4: Eu2+, Dy3+). At first, preparation was similar to literary methods. Temperature, dopant levels and mixing methods were then varied in order to expose their effects on long-lasting phosphorescence. The effect of temperature was investigated for SrAl2O4: Eu2+, Dy3+, and resulted in the discovery that 1350°C was the only temperature that the compound could be heated to in the Differential scanning calorimetry (DSC) in order to achieve any phosphorescence. However, no temperatures above 1350°C were investigated. The variation of mixing method and co-dopant level in the strontium aluminate compounds resulted in the finding that the dry mixing method using a Turbula mixer resulted in the longest afterglow. It was also found that an increase of europium inclusion, from 1mol% to 2mol% in these compounds, increased the brightest of the phosphorescence. As this increased batch was mixed using sonication, the phosphorescent time was actually reduced which produced green long-lasting phosphorescence for up to 20 minutes following 30 minutes excitation and 50 minutes when the europium content was doubled and mixed using sonication.

Keywords: long lasting, phosphorescence, excitation, europium

Procedia PDF Downloads 181

Authors: B. Zerouali, M. Kara, B. Hamaidi, H. Mahdjoub, S. Rouabhia

Abstract:

In this paper, a safety analysis for crude oil tanks to prevent undesirable events that may cause catastrophic accidents. The estimation of the probability of damage to industrial systems is carried out through a series of steps, and in accordance with a specific methodology. In this context, this work involves developing an assessment tool and risk analysis at the level of crude oil tanks system, based primarily on identification of various potential causes of crude oil tanks fire and explosion by the use of Fault Tree Analysis (FTA), then improved risk modelling by Bayesian Networks (BNs). Bayesian approach in the evaluation of failure and quantification of risks is a dynamic analysis approach. For this reason, have been selected as an analytical tool in this study. Research concludes that the Bayesian networks have a distinct and effective method in the safety analysis because of the flexibility of its structure; it is suitable for a wide variety of accident scenarios.

Keywords: bayesian networks, crude oil tank, fault tree, prediction, safety

Procedia PDF Downloads 660

Authors: A. Baloglu, A. Çınar

Abstract:

Different tools and technologies were implemented for Crisis Response and Management (CRM) which is generally using available network infrastructure for information exchange. Depending on type of disaster or crisis, network infrastructure could be affected and it could not be able to provide reliable connectivity. Thus any tool or technology that depends on the connectivity could not be able to fulfill its functionalities. As a solution, a new message exchange framework has been developed. Framework provides offline/online information exchange platform for CRM Information Systems (CRMIS) and it uses XML compression and packet prioritization algorithms and is based on open source web technologies. By introducing offline capabilities to the web technologies, framework will be able to perform message exchange on unreliable networks. The experiments done on the simulation environment provide promising results on low bandwidth networks (56kbps and 28.8 kbps) with up to 50% packet loss and the solution is to successfully transfer all the information on these low quality networks where the traditional 2 and 3 tier applications failed.

Keywords: crisis response and management, XML messaging, web services, XML compression, mining

Procedia PDF Downloads 339

Authors: Jiaqi Huang, Yuheng Wang

Abstract:

Premises selection, the task of selecting a set of axioms for proving a given conjecture, is a major bottleneck in automated theorem proving. An array of deep-learning-based methods has been established for premises selection, but a perfect performance remains challenging. Our study examines the inaccuracy of deep neural networks in premises selection. Through training network models using encoded conjecture and axiom pairs from the Mizar Mathematical Library, two potential biases are found: the network models classify more premises as necessary than unnecessary, referred to as the ‘positive bias’, and the network models perform better in proving conjectures that paired with more axioms, referred to as ‘length bias’. The ‘positive bias’ and ‘length bias’ discovered could inform the limitation of existing deep neural networks.

Keywords: automated theorem proving, premises selection, deep learning, interpreting deep learning

Procedia PDF Downloads 183

Authors: Abdelazziz Aouiche, El Moundher Aouiche, Mouhamed Salah Soudani

Abstract:

Renewable energy sources now significantly contribute to the replacement of traditional fossil fuel energy sources. One of the most potent types of renewable energy that has developed quickly in recent years is photovoltaic energy. We all know that solar energy, which is sustainable and non-depleting, is the best knowledge form of energy that we have at our disposal. Due to changing weather conditions, the primary drawback of conventional solar PV cells is their inability to track their maximum power point. In this study, we apply artificial neural networks (ANN) to automatically track and measure the maximum power point (MPP) of solar panels. In MATLAB, the complete system is simulated, and the results are adjusted for the external environment. The results are better performance than traditional MPPT methods and the results demonstrate the advantages of using neural networks in solar PV systems.

Keywords: modeling, photovoltaic panel, artificial neural networks, maximum power point tracking

Procedia PDF Downloads 88

Authors: A. A. Behroozpoor, M. M. Mazarei

Abstract:

In this paper, a fuzzy recurrent neural network is proposed for solving the classical quadratic control problem subject to linear equality and bound constraints. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed.

Keywords: REFERENCES [1] Xia, Y, A new neural network for solving linear and quadratic programming problems. IEEE Transactions on Neural Networks, 7(6), 1996, pp.1544–1548. [2] Xia, Y., & Wang, J, A recurrent neural network for solving nonlinear convex programs subject to linear constraints. IEEE Transactions on Neural Networks, 16(2), 2005, pp. 379–386. [3] Xia, Y., H, Leung, & J, Wang, A projection neural network and its application to constrained optimization problems. IEEE Transactions Circuits and Systems-I, 49(4), 2002, pp.447–458.B. [4] Q. Liu, Z. Guo, J. Wang, A one-layer recurrent neural network for constrained seudoconvex optimization and its application for dynamic portfolio optimization. Neural Networks, 26, 2012, pp. 99-109.

Procedia PDF Downloads 643

Authors: Tolulope Aremu

Abstract:

This paper is based on the idea of using deep learning methodology for optimizing production yield by tuning a few key process parameters in a manufacturing environment. The study was explicitly on how to maximize production yield and minimize operational costs by utilizing advanced neural network models, specifically Long Short-Term Memory and Convolutional Neural Networks. These models were implemented using Python-based frameworks—TensorFlow and Keras. The targets of the research are the precision molding processes in which temperature ranges between 150°C and 220°C, the pressure ranges between 5 and 15 bar, and the material flow rate ranges between 10 and 50 kg/h, which are critical parameters that have a great effect on yield. A dataset of 1 million production cycles has been considered for five continuous years, where detailed logs are present showing the exact setting of parameters and yield output. The LSTM model would model time-dependent trends in production data, while CNN analyzed the spatial correlations between parameters. Models are designed in a supervised learning manner. For the model's loss, an MSE loss function is used, optimized through the Adam optimizer. After running a total of 100 training epochs, 95% accuracy was achieved by the models recommending optimal parameter configurations. Results indicated that with the use of RSM and DOE traditional methods, there was an increase in production yield of 12%. Besides, the error margin was reduced by 8%, hence consistent quality products from the deep learning models. The monetary value was annually around $2.5 million, the cost saved from material waste, energy consumption, and equipment wear resulting from the implementation of optimized process parameters. This system was deployed in an industrial production environment with the help of a hybrid cloud system: Microsoft Azure, for data storage, and the training and deployment of their models were performed on Google Cloud AI. The functionality of real-time monitoring of the process and automatic tuning of parameters depends on cloud infrastructure. To put it into perspective, deep learning models, especially those employing LSTM and CNN, optimize the production yield by fine-tuning process parameters. Future research will consider reinforcement learning with a view to achieving further enhancement of system autonomy and scalability across various manufacturing sectors.

Keywords: production yield optimization, deep learning, tuning of process parameters, LSTM, CNN, precision manufacturing, TensorFlow, Keras, cloud infrastructure, cost saving

Procedia PDF Downloads 29

Authors: Hamideh Marefat, Eskandar Samadi

Abstract:

This study examined the effect of semantics on processing ambiguous sentences containing Relative Clauses (RCs) preceded by a complex Determiner Phrase (DP) by Persian-speaking learners of L2 English with different proficiency and Working Memory Capacities (WMCs). The semantic relationship studied was one between the subject of the main clause and one of the DPs in the complex DP to see if, as predicted by Spreading Activation Model, priming one of the DPs through this semantic manipulation affects the L2ers’ preference. The results of a task using Rapid Serial Visual Processing (time-controlled paradigm) showed that manipulation of the relationship between the subject of the main clause and one of the DPs in the complex DP preceding RC has no effect on the choice of the antecedent; rather, the L2ers' processing is guided by the phrase structure information. Moreover, while proficiency did not have any effect on the participants’ preferences, WMC brought about a difference in their preferences, with a DP1 preference by those with a low WMC. This finding supports the chunking hypothesis and the predicate proximity principle, which is the strategy also used by monolingual Persian speakers.

Keywords: semantics, relative clause processing, ambiguity resolution, proficiency, working memory capacity

Procedia PDF Downloads 623

Authors: Saurabh Shukla, G. N. Pandey

Abstract:

The fires have become the most serious disasters to forest resources and the human environment. In recent years, due to climate change, human activities and other factors the frequency of forest fires has increased considerably. The monitoring and prevention of forest fires have now become a global concern for forest fire prevention organizations. Currently, the methods for forest fire prevention largely consist of patrols, observation from watch towers. Thus, software like deployment of the wireless sensor network to prevent forest fire is being developed to get a better estimate of the temperature and humidity prospects. Now days, wireless sensor networks are beginning to be deployed at an accelerated pace. It is not unrealistic to expect that in coming years the world will be covered with wireless sensor networks. This new technology has lots of unlimited potentials and can be used for numerous application areas including environmental, medical, military, transportation, entertainment, crisis management, homeland defense, and smart spaces.

Keywords: deployment, sensors, wireless sensor networks, forest fires

Procedia PDF Downloads 436

Authors: Mahsa Namvari, Kari Ullakko

Abstract:

It is well-known that the Co-doping of ferromagnetic shape memory alloys (FSMAs) is a crucial tool to control their multifunctional properties. The present work investigates the use of small quantities of Co to fine-tune the transformation, structure, microstructure, mechanical and magnetic properties of the polycrystalline Ni₄₉.₈Mn₂₈.₅Ga₂₁.₇ (at.%) alloy, At Co concentrations of 1-1.5 at.%, a microstructure with an average grain size of about 2.00 mm was formed with a twin structure, enabling the experimental observation of magnetic-field-induced twin variant rearrangement. At higher levels of Co-doping, the grain size was essentially reduced, and the crystal structure of the martensitic phase became 2M martensite. The decreasing grain size and changing crystal structure are attributed to the progress of γ-phase precipitates. Alongside the academic aspect, the results of the present work point to the commercial advantage of fabricating 10M Co-doped Ni-Mn-Ga actuating elements made from large grains of polycrystalline ingots obtained by a standard melting facility instead of grown single crystals.

Keywords: Ni-Mn-Ga, ferromagnetic shape memory, martensitic phase transformation, grain growth

Procedia PDF Downloads 95

Authors: Ruvaitha Banu, Amaladhithyan Krishnamoorthy

Abstract:

IoT networks today solve various consumer problems, from home automation systems to aiding in driving autonomous vehicles with the exploration of multiple devices. For example, in an autonomous vehicle environment, multiple sensors are available on roads to monitor weather and road conditions and interact with each other to aid the vehicle in reaching its destination safely and timely. IoT systems are predominantly dependent on the cloud environment for data storage, and computing needs that result in latency problems. With the advent of Fog networks, some of this storage and computing is pushed to the edge/fog nodes, saving the network bandwidth and reducing the latency proportionally. Managing the data stored in these fog nodes becomes crucial as it might also store sensitive information required for a certain application. Data management in fog nodes is strenuous because Fog networks are dynamic in terms of their availability and hardware capability. It becomes more challenging when the nodes in the network also live a short span, detaching and joining frequently. When an end-user or Fog Node wants to access, read, or write data stored in another Fog Node, then a new protocol becomes necessary to access/manage the data stored in the fog devices as a conventional static way of managing the data doesn’t work in Fog Networks. The proposed solution discusses a protocol that acts by defining sensitivity levels for the data being written and read. Additionally, a distinct data distribution and replication model among the Fog nodes is established to decentralize the access mechanism. In this paper, the proposed model implements stewardship towards the data stored in the Fog node using the application of Reinforcement Learning so that access to the data is determined dynamically based on the requests.

Keywords: IoT, fog networks, data stewardship, dynamic access policy

Procedia PDF Downloads 59

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

Abstract:

The use of decision support systems in agriculture may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. In our work, we designed and implemented a decision support system for small tomatoes producers. This work investigates ways to recognize the late blight disease from the analysis of digital images of tomatoes, using a pair of multilayer perceptron neural networks. The networks outputs are used to generate repainted tomato images in which the injuries on the plant are highlighted, and to calculate the damage level of each plant. Those levels are then used to construct a situation map of a farm where a cellular automata simulates the outbreak evolution over the fields. The simulator can test different pesticides actions, helping in the decision on when to start the spraying and in the analysis of losses and gains of each choice of action.

Keywords: artificial neural networks, cellular automata, decision support system, pattern recognition

Procedia PDF Downloads 455

Authors: Salahud Din, Saima Masood, Hafsa Zaneb, Habib –ur- Rehman, Imad Khan, Muqader Shah

Abstract:

The objective of this study was to examine the osteomorphological differences between the long bones of adult Chinkara and an adult Beetal goat, using visual observation, which has still not studied. The osseous remains of these small-sized ungulates often encountered, but cannot distinguish, because of the lack of literature. Specimens of the adult Chinkara of known age and sex for osteomorphological studies are collected from the Manglot Wildlife Park and Ungulate Breeding Centre, Nizampur, Pakistan, while the bones of adult Beetal goats are obtained after slaughtering in a slaughterhouse. The research is carried out at the University of Veterinary and Animal Sciences, Lahore, Pakistan. In this research, the main morphological features recorded in the long bones of thoracic limb and pelvic limb of the adult Chinkara, by comparing them to those of the Beetal goat. The most important differences between the two species are noted in the scapula, the humerus, the radius and ulna, the metacarpal, femur, tibia metatarsal and phalanges. In conclusion, the present study suggests that the morphology of the long bones of adult Chinkara has different from the Beetal goat in various points of view. Based on these recorded points, long bones of these two species can easily be differentiated. The study is helpful in zooarcheological, comparative osteometric studies, for forensic specialists and veterinary anatomists.

Keywords: Beetal goat, Chinkara, comparative morphological features, long bones, osteology

Procedia PDF Downloads 133

Authors: Mami Nishida

Abstract:

This paper presented a study on the development and control of a small biped soft robot using shape memory alloys (SMAs). Author proposed a flexible flat plate (FFP) actuators consisting of a thin　polyethylene plate and SMAs. This actuator has a nail like an insect. This robot moves from the front to back and from left to right using two nails. The walking robot has two degrees of freedom and is controlled by switching the ON-OFF current signals to the SMA based FFPs. The resulting small biped soft robot weighs a mere 4.7 g (with a height of 67 mm). The small robot realizes biped walking by transferring the elastic potential energy (generated by deflections of the SMA based FFPs) to kinematic energy. Experimental results demonstrated the viability and utility of the small biped soft robot with the proposed SMA-based FFPs and the control strategy to achieve walking behavior.

Keywords: biped soft robot with nails, flexible flat plate (FFP) actuators, ON-OFF control strategy, shape memory alloys (SMA)

Procedia PDF Downloads 502

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 314

Authors: Sanaa Chafik, Imane Daoudi, Mounim A. El Yacoubi, Hamid El Ouardi

Abstract:

Locality Sensitive Hashing (LSH) is one of the most promising techniques for solving nearest neighbour search problem in high dimensional space. Euclidean LSH is the most popular variation of LSH that has been successfully applied in many multimedia applications. However, the Euclidean LSH presents limitations that affect structure and query performances. The main limitation of the Euclidean LSH is the large memory consumption. In order to achieve a good accuracy, a large number of hash tables is required. In this paper, we propose a new hashing algorithm to overcome the storage space problem and improve query time, while keeping a good accuracy as similar to that achieved by the original Euclidean LSH. The Experimental results on a real large-scale dataset show that the proposed approach achieves good performances and consumes less memory than the Euclidean LSH.

Keywords: approximate nearest neighbor search, content based image retrieval (CBIR), curse of dimensionality, locality sensitive hashing, multidimensional indexing, scalability

Procedia PDF Downloads 321