Search results for: adaptive neuro-fuzzy network

Authors: Hanwei Gao, Louis Jezequel, Eric Cabrol, Bernard Vitry

Abstract:

The chassis system is composed of complex elements that take up all the loads from the tire-ground contact area and thus it plays an important role in numerous specifications such as durability, comfort, crash, etc. During the development of new vehicle projects in Renault, durability validation is always the main focus while deployment of comfort comes later in the project. Therefore, sometimes design choices have to be reconsidered because of the natural incompatibility between these two specifications. Besides, robustness is also an important point of concern as it is related to manufacturing costs as well as the performance after the ageing of components like shock absorbers. In this paper an approach is proposed aiming to realize a multi-objective optimization between chassis endurance and comfort while taking the random factors into consideration. The adaptive-sparse polynomial chaos expansion method (PCE) with Chebyshev polynomial series has been applied to predict responses’ uncertainty intervals of a system according to its uncertain-but-bounded parameters. The approach can be divided into three steps. First an initial design of experiments is realized to build the response surfaces which represent statistically a black-box system. Secondly within several iterations an optimum set is proposed and validated which will form a Pareto front. At the same time the robustness of each response, served as additional objectives, is calculated from the pre-defined parameter intervals and the response surfaces obtained in the first step. Finally an inverse strategy is carried out to determine the parameters’ tolerance combination with a maximally acceptable degradation of the responses in terms of manufacturing costs. A quarter car model has been tested as an example by applying the road excitations from the actual road measurements for both endurance and comfort calculations. One indicator based on the Basquin’s law is defined to compare the global chassis durability of different parameter settings. Another indicator related to comfort is obtained from the vertical acceleration of the sprung mass. An optimum set with best robustness has been finally obtained and the reference tests prove a good robustness prediction of Chebyshev PCE method. This example demonstrates the effectiveness and reliability of the approach, in particular its ability to save computational costs for a complex system.

Keywords: chassis durability, Chebyshev polynomials, multi-objective optimization, polynomial chaos expansion, ride comfort, robust design

Procedia PDF Downloads 148

Authors: Kavyadevi N., Kaviya G., Gowsalya P., Janani M., Mohanraj S.

Abstract:

Hevea brasiliensis, also known as the rubber tree, is one of the foremost assets of crops in the world. One of the most significant advantages of the Rubber Plant in terms of air oxygenation is its capacity to reduce the likelihood of an individual developing respiratory allergies like asthma. To construct such a system that can properly identify crop diseases and pests and then create a database of insecticides for each pest and disease, we must first give treatment for the illness that has been detected. We shall primarily examine three major leaf diseases since they are economically deficient in this article, which is Bird's eye spot, algal spot and powdery mildew. And the recommended work focuses on disease identification on rubber tree leaves. It will be accomplished by employing one of the superior algorithms. Input, Preprocessing, Image Segmentation, Extraction Feature, and Classification will be followed by the processing technique. We will use time-consuming procedures that they use to detect the sickness. As a consequence, the main ailments, underlying causes, and signs and symptoms of diseases that harm the rubber tree are covered in this study.

Keywords: image processing, python, convolution neural network (CNN), machine learning

Procedia PDF Downloads 70

Authors: Provides Ng

Abstract:

Platform economy is a peer-to-peer model of distributing resources facilitated by community-based digital platforms. In recent years, digital platforms are rapidly reconfiguring the public realm using hyper-personalisation techniques. This paper aims at investigating how urban planning can leapfrog into the digital age to help relieve the rising tension of the global issue of labour flow; it discusses the means to transfer techniques of hyper-personalisation into urban planning for plasticity using platform technologies. This research first denotes the limitations of the current system of urban residency, where the system maintains itself on the circulation of documents, which are data on paper. Then, this paper tabulates how some of the institutions around the world, both public and private, digitise data, and streamline communications between a network of systems and citizens using platform technologies. Subsequently, this paper proposes ways in which hyper-personalisation can be utilised to form a digital planning platform. Finally, this paper concludes by reviewing how the proposed strategy may help to open up new ways of thinking about how we affiliate ourselves with cities.

Keywords: platform urbanism, hyper-personalisation, digital inventory, urban accessibility

Procedia PDF Downloads 107

Authors: Tomas Menard

Abstract:

The design of control-law for engineering systems has been investigated for many decades. While many results are concerned with continuous systems with continuous output, nowadays, many controlled systems have to transmit their output measurements through network, hence making it discrete-time. But it is well known that the sampling of a system whose control-law is based on the continuous output may render the system unstable, especially when this sampling period is long compared to the system dynamics. The control design then has to be adapted in order to cope with this issue. In this paper, we consider systems which can be modeled as double integrator with uncertainty on the input since many mechanical systems can be put under such form. We present a control scheme based on an observer using only discrete time measurement and which provides continuous time estimation of the state, combined with a continuous control law, which stabilized a system with second-order dynamics even in the presence of uncertainty. It is further shown that arbitrarily long sampling periods can be dealt with properly setting the control scheme parameters.

Keywords: dynamical system, control law design, sampled output, observer design

Procedia PDF Downloads 182

Authors: Mohd Zamri Osman, Mohd Aizaini Maarof, Mohd Foad Rohani

Abstract:

Human skin detection recognized as the primary step in most of the applications such as face detection, illicit image filtering, hand recognition and video surveillance. The performance of any skin detection applications greatly relies on the two components: feature extraction and classification method. Skin color is the most vital information used for skin detection purpose. However, color feature alone sometimes could not handle images with having same color distribution with skin color. A color feature of pixel-based does not eliminate the skin-like color due to the intensity of skin and skin-like color fall under the same distribution. Hence, the statistical color analysis will be exploited such mean and standard deviation as an additional feature to increase the reliability of skin detector. In this paper, we studied the effectiveness of statistical color feature for human skin detection. Furthermore, the paper analyzed the integrated color and texture using eight classifiers with three color spaces of RGB, YCbCr, and HSV. The experimental results show that the integrating statistical feature using Random Forest classifier achieved a significant performance with an F1-score 0.969.

Keywords: color space, neural network, random forest, skin detection, statistical feature

Procedia PDF Downloads 454

Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei

Abstract:

With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.

Keywords: document processing, framework, formal definition, machine learning

Procedia PDF Downloads 206

Authors: Z. Gharaee

Abstract:

Recognizing actions performed by others is important in our daily lives since it is necessary for communicating with others in a proper way. We perceive an action by observing the kinematics of motions involved in the performance. We use our experience and concepts to make a correct recognition of the actions. Although building the action concepts is a life-long process, which is repeated throughout life, we are very efficient in applying our learned concepts in analyzing motions and recognizing actions. Experiments on the subjects observing the actions performed by an actor show that an action is recognized after only about two hundred milliseconds of observation. In this study, hierarchical action recognition architecture is proposed by using growing grid layers. The first-layer growing grid receives the pre-processed data of consecutive 3D postures of joint positions and applies some heuristics during the growth phase to allocate areas of the map by inserting new neurons. As a result of training the first-layer growing grid, action pattern vectors are generated by connecting the elicited activations of the learned map. The ordered vector representation layer receives action pattern vectors to create time-invariant vectors of key elicited activations. Time-invariant vectors are sent to second-layer growing grid for categorization. This grid creates the clusters representing the actions. Finally, one-layer neural network developed by a delta rule labels the action categories in the last layer. System performance has been evaluated in an experiment with the publicly available MSR-Action3D dataset. There are actions performed by using different parts of human body: Hand Clap, Two Hands Wave, Side Boxing, Bend, Forward Kick, Side Kick, Jogging, Tennis Serve, Golf Swing, Pick Up and Throw. The growing grid architecture was trained by applying several random selections of generalization test data fed to the system during on average 100 epochs for each training of the first-layer growing grid and around 75 epochs for each training of the second-layer growing grid. The average generalization test accuracy is 92.6%. A comparison analysis between the performance of growing grid architecture and self-organizing map (SOM) architecture in terms of accuracy and learning speed show that the growing grid architecture is superior to the SOM architecture in action recognition task. The SOM architecture completes learning the same dataset of actions in around 150 epochs for each training of the first-layer SOM while it takes 1200 epochs for each training of the second-layer SOM and it achieves the average recognition accuracy of 90% for generalization test data. In summary, using the growing grid network preserves the fundamental features of SOMs, such as topographic organization of neurons, lateral interactions, the abilities of unsupervised learning and representing high dimensional input space in the lower dimensional maps. The architecture also benefits from an automatic size setting mechanism resulting in higher flexibility and robustness. Moreover, by utilizing growing grids the system automatically obtains a prior knowledge of input space during the growth phase and applies this information to expand the map by inserting new neurons wherever there is high representational demand.

Keywords: action recognition, growing grid, hierarchical architecture, neural networks, system performance

Procedia PDF Downloads 154

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 72

Authors: Yan Zhang

Abstract:

Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. Analytics-driven predictive maintenance is gaining increasing attention in many industries such as manufacturing, utilities, aerospace, etc., along with the emerging demand of Internet of Things (IoT) applications and the maturity of technologies that support Big Data storage and processing. This study aims to build an end-to-end analytics solution that includes both real-time machine condition monitoring and machine learning based predictive analytics capabilities. The goal is to showcase a general predictive maintenance solution architecture, which suggests how the data generated from field machines can be collected, transmitted, stored, and analyzed. We use a publicly available aircraft engine run-to-failure dataset to illustrate the streaming analytics component and the batch failure prediction component. We outline the contributions of this study from four aspects. First, we compare the predictive maintenance problems from the view of the traditional reliability centered maintenance field, and from the view of the IoT applications. When evolving to the IoT era, predictive maintenance has shifted its focus from ensuring reliable machine operations to improve production/maintenance efficiency via any maintenance related tasks. It covers a variety of topics, including but not limited to: failure prediction, fault forecasting, failure detection and diagnosis, and recommendation of maintenance actions after failure. Second, we review the state-of-art technologies that enable a machine/device to transmit data all the way through the Cloud for storage and advanced analytics. These technologies vary drastically mainly based on the power source and functionality of the devices. For example, a consumer machine such as an elevator uses completely different data transmission protocols comparing to the sensor units in an environmental sensor network. The former may transfer data into the Cloud via WiFi directly. The latter usually uses radio communication inherent the network, and the data is stored in a staging data node before it can be transmitted into the Cloud when necessary. Third, we illustrate show to formulate a machine learning problem to predict machine fault/failures. By showing a step-by-step process of data labeling, feature engineering, model construction and evaluation, we share following experiences: (1) what are the specific data quality issues that have crucial impact on predictive maintenance use cases; (2) how to train and evaluate a model when training data contains inter-dependent records. Four, we review the tools available to build such a data pipeline that digests the data and produce insights. We show the tools we use including data injection, streaming data processing, machine learning model training, and the tool that coordinates/schedules different jobs. In addition, we show the visualization tool that creates rich data visualizations for both real-time insights and prediction results. To conclude, there are two key takeaways from this study. (1) It summarizes the landscape and challenges of predictive maintenance applications. (2) It takes an example in aerospace with publicly available data to illustrate each component in the proposed data pipeline and showcases how the solution can be deployed as a live demo.

Keywords: Internet of Things, machine learning, predictive maintenance, streaming data

Procedia PDF Downloads 380

Authors: Azeddine El-Hassouny, Chandrashekhar Meshram, Geraldin Nanfack

Abstract:

In recent years, learning from data with noisy labels (Label Noise) has been a major concern in supervised learning. This problem has become even more worrying in Deep Learning, where the generalization capabilities have been questioned lately. Indeed, deep learning requires a large amount of data that is generally collected by search engines, which frequently return data with unreliable labels. In this paper, we investigate the Label Noise in Deep Learning using variational inference. Our contributions are : (1) exploiting Label Noise concept where the true labels are learnt using reparameterization variational inference, while observed labels are learnt discriminatively. (2) the noise transition matrix is learnt during the training without any particular process, neither heuristic nor preliminary phases. The theoretical results shows how true label distribution can be learned by variational inference in any discriminate neural network, and the effectiveness of our approach is proved in several target datasets, such as MNIST and CIFAR32.

Keywords: label noise, deep learning, discrete latent variable, variational inference, MNIST, CIFAR32

Procedia PDF Downloads 117

Authors: S. Raja, K. M. Parammasivam, V. Aghilesh

Abstract:

Fluid-structure interaction is a crucial consideration in the design of many engineering systems such as flight vehicles and bridges. Aircraft lifting surfaces and turbine blades can fail due to oscillations caused by fluid-structure interaction. Hence, it is focussed to study the fluid-structure interaction in the present research. First, the effect of free vibration over the panel is studied. It is well known that the deformation of a panel and flow induced forces affects one another. The selected panel has a span 300mm, chord 300mm and thickness 2 mm. The project is to study, the effect of cross-sectional area and the stiffener location is carried out for the same panel. The stiffener spacing is varied along both the chordwise and span-wise direction. Then for that optimal location the ideal stiffener length is identified. The effect of stiffener cross-section shapes (T, I, Hat, Z) over flutter velocity has been conducted. The flutter velocities of the selected panel with two rectangular stiffeners of cantilever configuration are estimated using MSC NASTRAN software package. As the flow passes over the panel, deformation takes place which further changes the flow structure over it. With increasing velocity, the deformation goes on increasing, but the stiffness of the system tries to dampen the excitation and maintain equilibrium. But beyond a critical velocity, the system damping suddenly becomes ineffective, so it loses its equilibrium. This estimated in NASTRAN using PK method. The first 10 modal frequencies of a simple panel and stiffened panel are estimated numerically and are validated with open literature. A grid independence study is also carried out and the modal frequency values remain the same for element lengths less than 20 mm. The current investigation concludes that the span-wise stiffener placement is more effective than the chord-wise placement. The maximum flutter velocity achieved for chord-wise placement is 204 m/s while for a span-wise arrangement it is augmented to 963 m/s for the stiffeners location of ¼ and ¾ of the chord from the panel edge (50% of chord from either side of the mid-chord line). The flutter velocity is directly proportional to the stiffener cross-sectional area. A significant increment in flutter velocity from 218m/s to 1024m/s is observed for the stiffener lengths varying from 50% to 60% of the span. The maximum flutter velocity above Mach 3 is achieved. It is also observed that for a stiffened panel, the full effect of stiffener can be achieved only when the stiffener end is clamped. Stiffeners with Z cross section incremented the flutter velocity from 142m/s (Panel with no stiffener) to 328 m/s, which is 2.3 times that of simple panel.

Keywords: stiffener placement, stiffener cross-sectional area, stiffener length, stiffener cross sectional area shape

Procedia PDF Downloads 285

Authors: Hossam Abdelrahman, Sama Rostom, Reem Yassein, Yara Mohamed, Salma Salah, Nour Awny

Abstract:

In today’s environment, people are becoming increasingly interested in their appearance. However, they are afraid of their unknown appearance after a plastic surgery or treatment. Accidents, burns and genetic problems such as bowing of body parts of people have a negative impact on their mental health with their appearance and this makes them feel uncomfortable and underestimated. The approach presents a revolutionary deep learning-based image inpainting method that analyses the various picture structures and corrects damaged images. In this study, A model is proposed based on the in-painting of medical images with Stable Diffusion Inpainting method. Reconstructing missing and damaged sections of an image is known as image inpainting is a key progress facilitated by deep neural networks. The system uses the input of the user of an image to indicate a problem, the system will then modify the image and output the fixed image, facilitating for the patient to see the final result.

Keywords: generative adversarial network, large mask inpainting, stable diffusion inpainting, plastic surgery

Procedia PDF Downloads 68

Authors: Brian Ceh, Alison Jackson-Holland

Abstract:

Food deserts are a reality in some cities. These deserts can be described as a shortage of healthy food options within close proximity of consumers. The shortage in this case is typically facilitated by a lack of stores in an urban area that provide adequate fruit and vegetable choices. This study explores new avenues to better understand food deserts by examining modes of transportation that are available to shoppers or consumers, e.g. walking, automobile, or public transit. Further, this study is unique in that it not only explores the location of large grocery stores, but small grocery and convenience stores too. In this study, the relationship between some socio-economic indicators, such as personal income, are also explored to determine any possible association with food deserts. In addition, to help facilitate our understanding of food deserts, complex network spatial models that are built on adequate algorithms are used to investigate the possibility of food deserts in the city of Hamilton, Canada. It is found that Hamilton, Canada is adequate serviced by retailers who provide healthy food choices and that the food desert phenomena is almost absent.

Keywords: Canada, desert, food, Hamilton, store

Procedia PDF Downloads 237

Authors: Andrea N. Ofori-Boadu

Abstract:

The purpose is to develop a conceptual model of subcontractor development practices and processes that strengthen the integration of subcontractors into construction supply chain systems for improved subcontractor performance on Leadership in Energy and Environmental Design (LEED) certified building projects. The construction management of a LEED project has an important objective of meeting sustainability certification requirements. This is in addition to the typical project management objectives of cost, time, quality, and safety for traditional projects; and, therefore increases the complexity of LEED projects. Considering that construction management organizations rely heavily on subcontractors, poor performance on complex projects such as LEED projects has been largely attributed to the unsatisfactory preparation of subcontractors. Furthermore, the extensive use of unique and non-repetitive short term contracts limits the full integration of subcontractors into construction supply chains and hinders long-term cooperation and benefits that could enhance performance on construction projects. Improved subcontractor development practices are needed to better prepare and manage subcontractors, so that complex objectives can be met or exceeded. While supplier development and supply chain theories and practices for the manufacturing sector have been extensively investigated to address similar challenges, investigations in the construction sector are not that obvious. Consequently, the objective of this research is to investigate effective subcontractor development practices and processes to guide construction management organizations in their development of a strong network of high performing subcontractors. Drawing from foundational supply chain and supplier development theories in the manufacturing sector, a mixed interpretivist and empirical methodology is utilized to assess the body of knowledge within literature for conceptual model development. A self-reporting survey with five-point Likert scale items and open-ended questions is administered to 30 construction professionals to estimate their perceptions of the effectiveness of 37 practices, classified into five subcontractor development categories. Data analysis includes descriptive statistics, weighted means, and t-tests that guide the effectiveness ranking of practices and categories. The results inform the proposed three-phased LEED subcontractor development program model which focuses on preparation, development and implementation, and monitoring. Highly ranked LEED subcontractor pre-qualification, commitment, incentives, evaluation, and feedback practices are perceived as more effective, when compared to practices requiring more direct involvement and linkages between subcontractors and construction management organizations. This is attributed to unfamiliarity, conflicting interests, lack of trust, and resource sharing challenges. With strategic modifications, the recommended practices can be extended to other non-LEED complex projects. Additional research is needed to guide the development of subcontractor development programs that strengthen direct involvement between construction management organizations and their network of high performing subcontractors. Insights from this present research strengthen theoretical foundations to support future research towards more integrated construction supply chains. In the long-term, this would lead to increased performance, profits and client satisfaction.

Keywords: construction management, general contractor, supply chain, sustainable construction

Procedia PDF Downloads 105

Authors: Sonia Bedhiaf-Romdhani

Abstract:

The sheep (Ovis aries) was domesticated, approximately 11,000 years ago (YBP), in the Fertile Crescent from Asian Mouflon (Ovis Orientalis). The Northern African (NA) sheep is 7,000 years old, represents a remarkable diversity of sheep populations reared under traditional and low input farming systems (LIFS) over millennia. The majority of small ruminants in developing countries are encountered in low input production systems and the resilience of local communities in rural areas is often linked to the wellbeing of small ruminants. Regardless of the rich biodiversity encountered in sheep ecotypes there are four main sheep breeds in the country with 61,6 and 35.4 percents of Barbarine (fat tail breed) and Queue Fine de l’Ouest (thin tail breed), respectively. Phoenicians introduced the Barbarine sheep from the steppes of Central Asia in the Carthaginian period, 3000 years ago. The Queue Fine de l’Ouest is a thin-tailed meat breed heavily concentrated in the Western and the central semi-arid regions. The Noire de Thibar breed, involving mutton-fine wool producing animals, has been on the verge of extinction, it’s a composite black coated sheep breed found in the northern sub-humid region because of its higher nutritional requirements and non-tolerance of the prevailing harsher condition. The D'Man breed, originated from Morocco, is mainly located in the southern oases of the extreme arid ecosystem. A genetic investigation of Tunisian sheep breeds using a genome-wide scan of approximately 50,000 SNPs was performed. Genetic analysis of relationship between breeds highlighted the genetic differentiation of Noire de Thibar breed from the other local breeds, reflecting the effect of past events of introgression of European gene pool. The Queue Fine de l’Ouest breed showed a genetic heterogeneity and was close to Barbarine. The D'Man breed shared a considerable gene flow with the thin-tailed Queue Fine de l'Ouest breed. Native small ruminants breeds, are capable to be efficiently productive if essential ingredients and coherent breeding schemes are implemented and followed. Assessing the status of genetic variability of native sheep breeds could provide important clues for research and policy makers to devise better strategies for the conservation and management of genetic resources.

Keywords: sheep, farming systems, diversity, SNPs.

Procedia PDF Downloads 141

Authors: Zheng Yuxun

Abstract:

This review critically assesses the advancements and prospective developments in defect detection methodologies within the semiconductor industry, an essential domain that significantly affects the operational efficiency and reliability of electronic components. As semiconductor devices continue to decrease in size and increase in complexity, the precision and efficacy of defect detection strategies become increasingly critical. Tracing the evolution from traditional manual inspections to the adoption of advanced technologies employing automated vision systems, artificial intelligence (AI), and machine learning (ML), the paper highlights the significance of precise defect detection in semiconductor manufacturing by discussing various defect types, such as crystallographic errors, surface anomalies, and chemical impurities, which profoundly influence the functionality and durability of semiconductor devices, underscoring the necessity for their precise identification. The narrative transitions to the technological evolution in defect detection, depicting a shift from rudimentary methods like optical microscopy and basic electronic tests to more sophisticated techniques including electron microscopy, X-ray imaging, and infrared spectroscopy. The incorporation of AI and ML marks a pivotal advancement towards more adaptive, accurate, and expedited defect detection mechanisms. The paper addresses current challenges, particularly the constraints imposed by the diminutive scale of contemporary semiconductor devices, the elevated costs associated with advanced imaging technologies, and the demand for rapid processing that aligns with mass production standards. A critical gap is identified between the capabilities of existing technologies and the industry's requirements, especially concerning scalability and processing velocities. Future research directions are proposed to bridge these gaps, suggesting enhancements in the computational efficiency of AI algorithms, the development of novel materials to improve imaging contrast in defect detection, and the seamless integration of these systems into semiconductor production lines. By offering a synthesis of existing technologies and forecasting upcoming trends, this review aims to foster the dialogue and development of more effective defect detection methods, thereby facilitating the production of more dependable and robust semiconductor devices. This thorough analysis not only elucidates the current technological landscape but also paves the way for forthcoming innovations in semiconductor defect detection.

Keywords: semiconductor defect detection, artificial intelligence in semiconductor manufacturing, machine learning applications, technological evolution in defect analysis

Procedia PDF Downloads 31

Authors: Adamu Mudi, Ibrahim Wahab Fawole, Abubakar Abba Kolo

Abstract:

In this research paper, we present a microcontroller-based liquid level controller that identifies the various levels of a liquid, carries out certain actions, and is capable of communicating with the human being and other devices through the GSM network. This project is useful in ensuring that a liquid is not wasted. It also contributes to the internet of things paradigm, which is the future of the internet. The method used in this work includes designing the circuit and simulating it. The circuit is then implemented on a solderless breadboard, after which it is implemented on a strip board. A C++ computer program is developed and uploaded into the microcontroller. This program instructs the microcontroller on how to carry out its actions. In other to determine levels of the liquid, an ultrasonic wave is sent to the surface of the liquid similar to radar or the method for detecting the level of sea bed. Message is sent to the phone of the user similar to the way computers send messages to phones of GSM users. It is concluded that the routine of observing the levels of a liquid in a tank, refilling the tank when the liquid level is too low can be entirely handled by a programmable device without wastage of the liquid or bothering a human being with such tasks.

Keywords: Arduino Uno, HC-SR04 ultrasonic sensor, internet of things, IoT, SIM900 GSM module

Procedia PDF Downloads 121

Authors: Sonal H. Singh, Bhaskar Bhowmick

Abstract:

The research hypothesis formulated in this paper examines the importance of microfinance provision for entrepreneurship development by engendering a high level of entrepreneurial orientation among the grassroots entrepreneurs. A theoretically well supported empirical framework is proposed to identify the influence of financial services and non-financial services provided by microfinance institutes in strengthening the impact of grassroots innovation on entrepreneurial orientation under resource constraints. In this paper, Grassroots innovation is perceived in three dimensions: new learning practice, localized solution, and network development. The study analyzes the moderating effect of microfinance provision on the relationship between grassroots innovation and entrepreneurial orientation. The paper employed structural equation modelling on 400 data entries from the grassroots entrepreneurs in India. The research intends to help policymakers, entrepreneurs and microfinance providers to promote the innovative design of microfinance services for the well-being of grassroots entrepreneurs and to foster sustainable entrepreneurship development.

Keywords: entrepreneurship development, grassroots innovation, India, structural equation model

Procedia PDF Downloads 258

Authors: Somayyeh Naeemi, Ezhar Tamam

Abstract:

In most of the countries, Facebook allocated high rank of usage among other social network sites. Several studies have examined the effect of Facebook intensity on individuals’ psychological well-being. However, few studies have investigated its effect on eudaimonic well-being. The current study explored how emotional dependency to Facebook relates to psychological well-being in terms of eudaimonic well-being. The number of 402 adolescents 13-16 years old who studied in upper secondary school in Malaysia participated in this study. It was expected to find out a negative association between emotional dependency to Facebook and time spent on Facebook and psychological well-being. It also was examined the moderation effects of self-efficacy on psychological well-being. The results by Structural Equation Modeling revealed that emotional dependency to Facebook has a negative effect on adolescents’ psychological well-being. Surprisingly self-efficacy did not have moderation effect on the relationship between emotional dependency to Facebook and psychological well-being. Lastly, the emotional dependency to Facebook and not the time spent on Facebook lessen adolescents’ psychological well-being, suggesting the value of investigating Facebook usage among college students in future studies.

Keywords: emotional dependency to facebook, psychological well-being, eudaimonic well-being, self-efficacy, adolescent

Procedia PDF Downloads 511

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

The design of adaptive systems that take advantage of financial markets while reducing the risk can bring more stagnant wealth into the global market. However, most efforts made to generate successful deals in trading financial assets rely on Supervised Learning (SL), which suffered from various limitations. Deep Reinforcement Learning (DRL) offers to solve these drawbacks of SL approaches by combining the financial assets price "prediction" step and the "allocation" step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. In this paper, a continuous action space approach is adopted to give the trading agent the ability to gradually adjust the portfolio's positions with each time step (dynamically re-allocate investments), resulting in better agent-environment interaction and faster convergence of the learning process. In addition, the approach supports the managing of a portfolio with several assets instead of a single one. This work represents a novel DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem, or what is referred to as The Agent Environment as Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. More specifically, we design an environment that simulates the real-world trading process by augmenting the state representation with ten different technical indicators and sentiment analysis of news articles for each stock. We then solve the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, which can learn policies in high-dimensional and continuous action spaces like those typically found in the stock market environment. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of deep reinforcement learning in financial markets over other types of machine learning such as supervised learning and proves its credibility and advantages of strategic decision-making.

Keywords: the stock market, deep reinforcement learning, MDP, twin delayed deep deterministic policy gradient, sentiment analysis, technical indicators, autonomous agent

Procedia PDF Downloads 174

Authors: Pankaj Negi

Abstract:

Nowadays the demand for receiving the high quality electrical energy is being increasing as consumer wants not only reliable but also quality power. Custom power instruments are of the most well-known compensators of power quality in distributed network. This paper present a comprehensive review of compensating custom power devices mainly DSTATCOM (distribution static compensator),DVR (dynamic voltage restorer), and UPQC (unified power quality compensator) and also deals with sliding mode control and its applications to custom power devices. The sliding mode control strategy provides robustness to custom power device and enhances the dynamic response for compensating voltage sag, swell, voltage flicker, and voltage harmonics. The aim of this paper is to provide a broad perspective on the status of compensating devices in electric power distribution system and sliding mode control strategies to researchers and application engineers who are dealing with power quality and stability issues.

Keywords: active power filters(APF), custom power device(CPD), DSTATCOM, DVR, UPQC, sliding mode control (SMC), power quality

Procedia PDF Downloads 434

Authors: Harshith Gowda K. S, Tejaskumar N, Shubhanga R. B, Gowtham N, Deekshith Gowda H. S

Abstract:

Phasor measurement units (PMU) are playing an important role in the current power system for state estimation. It is necessary to have complete observability of the power system while minimizing the cost. For this purpose, the optimal location of the phasor measurement units in the power system is essential. In a bus system, zero injection buses need to be evaluated to minimize the number of PMUs. In this paper, the optimization problem is formulated using mixed integer programming to obtain the optimal location of the PMUs with increased observability. The formulation consists of with and without zero injection bus as constraints. The formulated problem is simulated using a CPLEX solver in the GAMS software package. The proposed method is tested on IEEE 30, IEEE 39, IEEE 57, and IEEE 118 bus systems. The results obtained show that the number of PMUs required is minimal with increased observability.

Keywords: PMU, observability, mixed integer programming (MIP), zero injection buses (ZIB)

Procedia PDF Downloads 157

Authors: Amhimmid Mohammed Saffour, Mustafa Mohamed Abdullah

Abstract:

The use of computers for handling image data in the healthcare is growing. However, the amount of data produced by modern image generating techniques is vast. This data might be a problem from a storage point of view or when the data is sent over a network. This paper using wavelet transform technique for medical images compression. MATLAB program, are designed to evaluate medical images storage and transmission time problem at Sebha Medical Center Libya. In this paper, three different Computed Tomography images which are abdomen, brain and chest have been selected and compressed using wavelet transform. Objective evaluation has been performed to measure the quality of the compressed images. For this evaluation, the results show that the Peak Signal to Noise Ratio (PSNR) which indicates the quality of the compressed image is ranging from (25.89db to 34.35db for abdomen images, 23.26db to 33.3db for brain images and 25.5db to 36.11db for chest images. These values shows that the compression ratio is nearly to 30:1 is acceptable.

Keywords: medical image, Matlab, image compression, wavelet's, objective evaluation

Procedia PDF Downloads 283

Authors: Tyng-Rong Roan, Fuji Foo, Wenwey Hseush

Abstract:

Recent development of AI and edge computing plays a critical role to capture meaningful events such as detection of an unattended bag. One of the core problems is re-identification across multiple CCTVs. Immediately following the detection of a meaningful event is to track and trace the objects related to the event. In an extensive environment, the challenge becomes severe when the number of CCTVs increases substantially, imposing difficulties in achieving high accuracy while maintaining real-time performance. The algorithm that re-identifies cross-boundary objects for extensive tracking is referred to Extensive Re-Identification, which emphasizes the issues related to the complexity behind a great number of CCTVs. The Spatial-Temporal Awareness approach challenges the conventional thinking and concept of operations which is labor intensive and time consuming. The ability to perform Extensive Re-Identification through a multi-sensory network provides the next-level insights – creating value beyond traditional risk management.

Keywords: long-short-term memory, re-identification, security critical application, spatial-temporal awareness

Procedia PDF Downloads 108

Authors: Vuk M. Popovic, Dunja D. Popovic

Abstract:

Software maintenance phase is started once a software project has been developed and delivered. After that, any modification to it corresponds to maintenance. Software maintenance involves modifications to keep a software project usable in a changed or a changing environment, to correct discovered faults, and modifications, and to improve performance or maintainability. Software maintenance and management of software maintenance are recognized as two most important and most expensive processes in a life of a software product. This research is basing the prediction of maintenance, on risks and time evaluation, and using them as data sets for working with neural networks. The aim of this paper is to provide support to project maintenance managers. They will be able to pass the issues planned for the next software-service-patch to the experts, for risk and working time evaluation, and afterward to put all data to neural networks in order to get software maintenance prediction. This process will lead to the more accurate prediction of the working hours needed for the software-service-patch, which will eventually lead to better planning of budget for the software maintenance projects.

Keywords: laboratory information system, maintenance engineering, neural networks, software maintenance, software maintenance costs

Procedia PDF Downloads 348

Authors: Ashiraliyev SHavkat

Abstract:

Relevance of the topic: Diabetes mellitus in overweight people development and absence of treatment measures. Objective: to give patients the correct instructions on proper nutrition, to organize a network of preventive and therapeutic measures. Materials and methods: Multidisciplinary Tashkent Medical Academy. As a result of objective observations in patients who applied to the clinic, 28 11 overweight patients had to type 2 diabetes. Diabetesmellituswasdiagnosed. Results: 11.5 mmol / L on an empty stomach in the morning. EDT yes. Pathogenesis: fat content in the diet of patients with diabetes mellitus. Carbohydrate foods make up 60%. Eating disorders and physical inactivity As a result, the accumulation of glucose in the form of fat increases, and this is constantly in the blood, which led to an increase in the number of fatty acids. Clinic: Frequent fasting in 11 patients (hypothalamus). Associated with glucose deficiency), drinking 8-9 liters of water per day of blood in 7 people Systolic pressure 150 diastolic pressures 100. Sensation of ants in 3 people and poor eyesight in 5 people. Conclusion: Explain to patients that nutritional guidelines should be followed. Assign active movement in accordance with the energy entering the body.

Keywords: mellitus, diabetes, pathogenesis, clinic

Procedia PDF Downloads 83

Authors: Mobarok Hossain Bhuyain

Abstract:

Video surveillance processing has attracted various security fields transforming it into one of the leading research fields. Today's demand for detection and tracking of human mobility for security is very useful for human security, such as in crowded areas. Accordingly, video surveillance technology has seen a rapid advancement in recent years, with algorithms analyzing the behavior of people under surveillance automatically. The main motivation of this research focuses on the detection and tracking of the elderly and socially vulnerable people in crowded areas. Degenerate people are a major health concern, especially for elderly people and socially vulnerable people. One major disadvantage of video surveillance is the need for continuous monitoring, especially in crowded areas. To assist the security monitoring live surveillance video, image processing, and artificial intelligence methods can be used to automatically send warning signals to the monitoring officers about elderly people and socially vulnerable people.

Keywords: human detection, target tracking, neural network, particle filter

Procedia PDF Downloads 157

Authors: Nesrine Bougarech, Habib Affes

Abstract:

This research lays the emphasis on the business process reengineering (BPR) which consists in radically altering the organizational processes through the optimal use of information technology (IT) to attain major enhancements in terms of quality, performance and productivity. A survey of the business process reengineering (BPR) was carried out in three French groups and their subsidiaries in Tunisia. The data collected were qualitatively analyzed in an attempt to test the main indicators of the success of a business process reengineering project (BPR) and to compare the importance of these indicators in the context of France versus Tunisia. The study corroborates that the respect of the inherent principles of the business process reengineering (BPR) and the diversity of the human resources involved in the project can lead to better productivity, higher quality of the goods or services and lower cost. Additionally, our results mirror the extent to which the respect of the principles and the diversity of resources are more important in the French companies than in their Tunisian subsidiaries.

Keywords: business process reengineering (BPR), human resources management (HRM), information technology (IT), management

Procedia PDF Downloads 400

Authors: Apurva Gupta, Surendra Singh

Abstract:

Spirulina spp., as a promising source of many commercially valuable products, is grown photo autotrophically in open ponds and raceways on a large scale. However, the economic exploitation in an open system seems to have been limited because of lack of multiple stress-tolerant strains. The present study aims to isolate a stable stress tolerant mutant of Spirulina platensis with improved growth rate and enhanced potential to produce its commercially valuable bioactive compounds. N-methyl-n'-nitro-n-nitrosoguanidine (NTG) at 250 μg/mL (concentration permitted 1% survival) was employed for chemical mutagenesis to generate random mutants and screened against NaCl. In a preliminary experiment, wild type S. platensis was treated with NaCl concentrations from 0.5-1.5 M to calculate its LC₅₀. Mutagenized colonies were then screened for tolerance at 0.8 M NaCl (LC₅₀), and the surviving colonies were designated as NaCl tolerant mutants of S. platensis. The mutant cells exhibited 1.5 times improved growth against NaCl stress as compared to the wild type strain in control conditions. This might be due to the ability of the mutant cells to protect its metabolic machinery against inhibitory effects of salt stress. Salt stress is known to adversely affect the rate of photosynthesis in cyanobacteria by causing degradation of the pigments. Interestingly, the mutant cells were able to protect its photosynthetic machinery and exhibited 4.23 and 1.72 times enhanced accumulation of Chl a and phycobiliproteins, respectively, which resulted in enhanced rate of photosynthesis (2.43 times) and respiration (1.38 times) against salt stress. Phycocyanin production in mutant cells was observed to enhance by 1.63 fold. Nitrogen metabolism plays a vital role in conferring halotolerance to cyanobacterial cells by influx of nitrate and efflux of Na+ ions from the cell. The NaCl tolerant mutant cells took up 2.29 times more nitrate as compared to the wild type and efficiently reduce it. Nitrate reductase and nitrite reductase activity in the mutant cells also improved by 2.45 and 2.31 times, respectively against salt stress. From these preliminary results, it could be deduced that enhanced nitrogen uptake and its efficient reduction might be a reason for adaptive and halotolerant behavior of the S. platensis mutant cells. Also, the NaCl tolerant mutant of S. platensis with significant improved growth and phycocyanin accumulation compared to the wild type can be commercially promising.

Keywords: chemical mutagenesis, NaCl tolerant mutant, nitrogen metabolism, photosynthetic machinery, phycocyanin

Procedia PDF Downloads 162

Authors: Abdessalam Hijab, Hafida Boulekbache, Eric Henry

Abstract:

The objective of this article is to explain the use of geographic information system (GIS) and information and communication technologies (ICTs) in the real-time processing and analysis of data on the status of an urban sanitation network by integrating professional actors in sanitation for sustainable management in urban areas. Indeed, it is a smart geo-collaboration based on the complementarity of ICTs and GIS. This multi-actor reflection was built with the objective of contributing to the development of complementary solutions to the existing technologies to better protect the urban environment, with the help of a checklist with the spatial reference "E-Géo-LD" dedicated to the "professional/professional" actors in sanitation, for intelligent monitoring of liquid sanitation networks in urban areas. In addition, this research provides a good understanding and assimilation of liquid sanitation schemes in the "Lamkansa" sampling area of the city of Casablanca, and spatially evaluates these schemes. Downstream, it represents a guide to assess the environmental impacts of the liquid sanitation scheme.

Keywords: ICT, GIS, spatial checklist, liquid sanitation, environment

Procedia PDF Downloads 224