Search results for: failure detection and prediction

Authors: Sonali Banrjee, Swarup Kumar Mitra, Aritra Acharyya

Abstract:

A piano note recognition method has been proposed by the authors in this paper. The authors have used a comprehensive method for onset detection of each note present in a piano piece followed by segmented short-time Fourier transform (STFT) for the identification of piano notes. The performance evaluation of the proposed method has been carried out in different harsh noisy environments by adding different levels of additive white Gaussian noise (AWGN) having different signal-to-noise ratio (SNR) in the original signal and evaluating the note detection error rate (NDER) of different piano pieces consisting of different number of notes at different SNR levels. The NDER is found to be remained within 15% for all piano pieces under consideration when the SNR is kept above 8 dB.

Keywords: AWGN, onset detection, piano note, STFT

Procedia PDF Downloads 160

Authors: Beng Yew Low, Cher Liang Cha, Cheng Yong Teoh

Abstract:

Due to a lack of continual assessment or grade related data, identifying first-year engineering students in a polytechnic education at risk of failing is challenging. Our experience over the years tells us that there is no strong correlation between having good entry grades in Mathematics and the Sciences and excelling in hardcore engineering subjects. Hence, identifying students at risk of failure cannot be on the basis of entry grades in Mathematics and the Sciences alone. These factors compound the difficulty of early identification and intervention. This paper describes the development of a predictive analytics model in the early detection of students at risk of failing and evaluates its effectiveness. Data from continual assessments conducted in term one, supplemented by data of student psychological profiles such as interests and study habits, were used. Three classification techniques, namely Logistic Regression, K Nearest Neighbour, and Random Forest, were used in our predictive model. Based on our findings, Random Forest was determined to be the strongest predictor with an Area Under the Curve (AUC) value of 0.994. Correspondingly, the Accuracy, Precision, Recall, and F-Score were also highest among these three classifiers. Using this Random Forest Classification technique, students at risk of failure could be identified at the end of term one. They could then be assigned to a Learning Support Programme at the beginning of term two. This paper gathers the results of our findings. It also proposes further improvements that can be made to the model.

Keywords: continual assessment, predictive analytics, random forest, student psychological profile

Procedia PDF Downloads 136

Authors: S. Jagadeesh Kumar

Abstract:

Face detection and recognition is an authoritative technology for image database management, video surveillance, and human computer interface (HCI). Face recognition is a rapidly nascent method, which has been extensively discarded in forensics such as felonious identification, tenable entree, and custodial security. This paper recommends an erudite technique using curvature analysis (CA) that has less false positives incidence, operative in different light environments and confiscates the artifacts that are introduced during image acquisition by ring correction in polar coordinate (RCP) method. This technique affronts mean and median filtering technique to remove the artifacts but it works in polar coordinate during image acquisition. Investigational fallouts for face detection and recognition confirms decent recitation even in diagonal orientation and stance variation.

Keywords: curvature analysis, ring correction in polar coordinate method, face detection, face recognition, human computer interaction

Procedia PDF Downloads 287

Authors: Caroline Lindlar, Eva Jakob

Abstract:

Female entrepreneurs often face significant barriers in accessing funding due to biases from business angels, venture capitalists, and financial institutions, which tend to favor male entrepreneurs. These biases contribute to persistent funding disparities, with female entrepreneurs receiving less financial support than their male counterparts. The situation worsens when female entrepreneurs have prior experiences with venture failure, which diminishes their attractiveness to traditional investors. Venture failure, defined as the cessation of operations due to declining revenues, rising costs, or ownership changes, plays a substantial role in shaping funding opportunities. In response, female entrepreneurs frequently turn to alternative funding sources such as crowdlending, where gender biases are often reversed in favor of women, particularly when their ventures emphasize social value creation. While existing research highlights the positive impact of gender on crowdfunding success, it remains unclear how venture failure, known to negatively bias female entrepreneurs in traditional funding contexts, interacts with the positive effects of gender in crowdlending. This interaction is particularly relevant because crowdlending often involves non-professional funders who make repeated investment decisions under uncertainty, based on limited information and past experiences. Given that approximately one-third of ventures fail to deliver promised returns, the role of gender bias after failure in crowdlending is an important area of investigation. This study addresses How failure affects crowd funders’ gender bias in future funding decisions? Drawing on social role and role congruity theory, we posit that societal perceptions of women as more communal conflict with the agentic qualities traditionally associated with entrepreneurship. This incongruence may result in reduced confidence in the success of female entrepreneurs after failure, limiting their access to future funding. However, we also hypothesize that social framing may mitigate this bias by aligning perceptions of female entrepreneurs with traits such as warmth and caring, enhancing their appeal after failure. To test these assertions, it conducted a between-subject audio vignette experiment with 155 participants who listened to entrepreneur pitches manipulated by gender (male vs. female) and venture framing (social vs. commercial). Participants made initial investment decisions, received failure-related news about the venture, and then made subsequent investment decisions. Pre-tests with 159 participants ensured the validity and reliability of the experimental manipulations. Moreover, we did a metric conjoint analysis with 100 participants, and they had to decide between different crowdfunding campaigns based on the attributes of previous failure, gender, and venture mission. it findings reveal that failure activates gender biases in crowdlending. Female-led ventures receive significantly less funding after failure compared to male-led ventures, suggesting the positive bias toward female entrepreneurs in the pre-funding phase does not persist post-failure. Moreover, framing a venture as socially oriented exacerbates the negative effect of failure for female entrepreneurs, as they secure fewer funds after failure compared to male entrepreneurs leading similar social ventures. This indicates that role-congruent framing does not mitigate gender bias after failure. This study contributes to research on gender in entrepreneurship by exploring how failure impacts future funding for female entrepreneurs. It also expands social crowdfunding literature by examining social value framing and adds to the entrepreneurial failure literature by focusing on crowd funders’ post-failure behavior.

Keywords: gender bias, crowdfunding, investment failure, investment behavior, social entrepreneurship

Procedia PDF Downloads 19

Authors: Maysoon Khalil Askar

Abstract:

The delineation of possible areas of corrosion along the external face of an underground oil pipeline in Trunk line of Al- Garraf oil field was investigated using the horizontal electrical resistivity profiling technique and study the contribution of pH, Moisture Content in Soil and Presence chlorides, sulfates and total dissolve salts in soil and water. The test sites represent a physical and chemical properties of soils. The hydrogen-ion concentration of soil and groundwater range from 7.2 to 9.6, and the resistivity values of the soil along the pipeline were obtained using the YH302B model resistivity meter having values between 1588 and 720 Ohm-cm. the chloride concentration in soil and groundwater is high (more than 1000 ppm), total soulable salt is more than 5000 ppm, and sulphate range from 0.17% and 0.98% in soil and more than 600 ppm in groundwater. The soil is poor aeration, the soil texture is fine (clay and silt soil), the water content is high (the groundwater is close to surface), the chloride and sulphate is high in the soil and groundwater, the total soulable salt is high in ground water and finally the soil electric resistivity is low that the soil is very corrosive and there is the possibility of the pipeline failure. These methods applied in the study are quick, economic and efficient for detecting along buried pipelines which need to be protected. Routine electrical geophysical investigations along buried oil pipelines should be undertaken for the early detection and prevention of pipeline failure with its attendant environmental, human and economic consequences.

Keywords: soil resistivity, corrosion, cathodic protection, chloride concentration, water content

Procedia PDF Downloads 438

Authors: Aboozar Aghaei, Kamran Dehghani

Abstract:

In the present work, the dissimilar Monel400 and SS316 were joined by friction stir welding (FSW). The applied rotating speed was 400 rpm, whereas the traverse speed varied between 50 and 150 mm/min. At a constant rotating speed, the sound welds were obtained at the welding speeds of 50 and 100 mm/min. However, a groove-like defect was formed when the welding speed exceeded 100 mm/min. The mechanical properties of the joints were evaluated using tensile and fatigue tests. The fatigue strength of dissimilar FSWed specimens was higher than that of both Monel400 and SS316. To study the failure behavior of FSWed specimens, the fracture surfaces were analyzed using a scanning electron microscope (SEM). The failure analysis indicates that different mechanisms may contribute to the fracture of welds. This was attributed to the dissimilar characteristics of dissimilar materials exhibiting different failure behaviors.

Keywords: frictions stir welding, stainless steel, Monel400, mechanical properties

Procedia PDF Downloads 88

Authors: Nomfundo Ngombane, Topside E. Mathonsi

Abstract:

Remote sensing and satellite imaging have been widely used to detect wildfires; nevertheless, the technologies present some limitations in terms of early wildfire detection as the technologies are greatly influenced by weather conditions and can miss small fires. The fires need to have spread a few kilometers for the technologies to provide accurate detection. The South African Advanced Fire Information System uses MODIS (Moderate Resolution Imaging Spectroradiometer) as satellite imaging. MODIS has limitations as it can exclude small fires and can fall short in validating fire vulnerability. Thus in the future, a Machine Learning algorithm will be designed and implemented for the early detection of wildfires. A simulator will be used to evaluate the effectiveness of the proposed solution, and the results of the simulation will be presented.

Keywords: moderate resolution imaging spectroradiometer, advanced fire information system, machine learning algorithm, detection of wildfires

Procedia PDF Downloads 80

Authors: In-Geun Lim, Sung-Woong Ra

Abstract:

As high resolution satellite images can be used, lots of studies are carried out for exploiting these images in various fields. This paper proposes the method based on mathematical morphology for extracting the ‘horse's hoof shaped object’. This proposed method can make an automatic object detection system to track the meaningful object in a large satellite image rapidly. Mathematical morphology process can apply in binary image, so this method is very simple. Therefore this method can easily extract the ‘horse's hoof shaped object’ from any images which have indistinct edges of the tracking object and have different image qualities depending on filming location, filming time, and filming environment. Using the proposed method by which ‘horse's hoof shaped object’ can be rapidly extracted, the performance of the automatic object detection system can be improved dramatically.

Keywords: facility detection, satellite image, object, mathematical morphology

Procedia PDF Downloads 382

Authors: Abdulrahman S. Alturki, John S. Loomis

Abstract:

This paper discusses a corner detection algorithm for camera calibration. Calibration is a necessary step in many computer vision and image processing applications. Robust corner detection for an image of a checkerboard is required to determine intrinsic and extrinsic parameters. In this paper, an algorithm for fully automatic and robust X-corner detection is presented. Checkerboard corner points are automatically found in each image without user interaction or any prior information regarding the number of rows or columns. The approach represents each X-corner with a quadratic fitting function. Using the fact that the X-corners are saddle points, the coefficients in the fitting function are used to identify each corner location. The automation of this process greatly simplifies calibration. Our method is robust against noise and different camera orientations. Experimental analysis shows the accuracy of our method using actual images acquired at different camera locations and orientations.

Keywords: camera calibration, corner detector, edge detector, saddle points

Procedia PDF Downloads 409

Authors: Tanu Aneja, Harsha Malaviya

Abstract:

Capturing pose information in cricket shots poses several challenges, such as low-resolution videos, noisy data, and joint occlusions caused by the nature of the shots. In response to these challenges, we propose a CondDGConv-based framework specifically for cricket shot prediction. By analyzing the spatial-temporal relationships in batsman shot sequences from an annotated 2D cricket dataset, our model achieves a 97% accuracy in predicting shot types. This performance is made possible by conditioning the graph network on batsman 2D poses, allowing for precise prediction of shot outcomes based on pose dynamics. Our approach highlights the potential for enhancing shot prediction in cricket analytics, offering a robust solution for overcoming pose-related challenges in sports analysis.

Keywords: action recognition, cricket. sports video analytics, computer vision, graph convolutional networks

Procedia PDF Downloads 21

Authors: H. Hotait, X. Chiementin, L. Rasolofondraibe

Abstract:

This paper presents a continuous work to detect the abnormal state in the rolling bearing by studying the vibration signature analysis and calculation of the remaining useful life. To achieve these aims, two methods; the first method is the classification to detect the degradation state by the AOM-OPTICS (Acousto-Optic Modulator) method. The second one is the prediction of the degradation state using least-squares support vector regression and then compared with the linear degradation model. An experimental investigation on ball-bearing was conducted to see the effectiveness of the used method by applying the acquired vibration signals. The proposed model for predicting the state of bearing gives us accurate results with the experimental and numerical data.

Keywords: bearings, automatization, optimization, prognosis, classification, defect detection

Procedia PDF Downloads 121

Authors: Kashika P. H.

Abstract:

The development of computer vision systems has been greatly aided by the efficient and precise detection of images and videos. Although the ability to recognize and comprehend images is a strength of the human brain, employing technology to tackle this issue is exceedingly challenging. In the past few years, the use of Deep Learning algorithms to treat object detection has dramatically expanded. One of the key issues in the realm of image recognition is the recognition and detection of certain notable people from randomly acquired photographs. Face recognition uses a way to identify, assess, and compare faces for a variety of purposes, including user identification, user counting, and classification. With the aid of an accessible deep learning-based API, this article intends to recognize various faces of people and their facial descriptors more accurately. The purpose of this study is to locate suitable individuals and deliver accurate information about them by using the Amazon Rekognition system to identify a specific human from a vast image dataset. We have chosen the Amazon Rekognition system, which allows for more accurate face analysis, face comparison, and face search, to tackle this difficulty.

Keywords: Amazon rekognition, API, deep learning, computer vision, face detection, text detection

Procedia PDF Downloads 107

Authors: Ramzi Rihane, Yassine Benayed

Abstract:

Epilepsy is a chronic neurological disorder characterized by recurrent, unprovoked seizures resulting from abnormal electrical activity in the brain. Timely and accurate detection of these seizures is essential for improving patient care. In this study, we leverage the UK Bonn University open-source EEG dataset and employ advanced deep-learning techniques to automate the detection of epileptic seizures. By extracting key features from both time and frequency domains, as well as Spectrogram features, we enhance the performance of various deep learning models. Our investigation includes architectures such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), 1D Convolutional Neural Networks (1D-CNN), and hybrid CNN-LSTM and CNN-BiLSTM models. The models achieved impressive accuracies: LSTM (98.52%), Bi-LSTM (98.61%), CNN-LSTM (98.91%), CNN-BiLSTM (98.83%), and CNN (98.73%). Additionally, we utilized a data augmentation technique called SMOTE, which yielded the following results: CNN (97.36%), LSTM (97.01%), Bi-LSTM (97.23%), CNN-LSTM (97.45%), and CNN-BiLSTM (97.34%). These findings demonstrate the effectiveness of deep learning in capturing complex patterns in EEG signals, providing a reliable and scalable solution for real-time seizure detection in clinical environments.

Keywords: electroencephalogram, epileptic seizure, deep learning, LSTM, CNN, BI-LSTM, seizure detection

Procedia PDF Downloads 15

Authors: Richard O’Riordan, Saritha Unnikrishnan

Abstract:

Autonomous Vehicles (AVs) are incorporating an increasing number of ADAS features, including automated lane-keeping systems. In recent years, many research papers into lane detection algorithms have been published, varying from computer vision techniques to deep learning methods. The transition from lower levels of autonomy defined in the SAE framework and the progression to higher autonomy levels requires increasingly complex models and algorithms that must be highly reliable in their operation and functionality capacities. Furthermore, these algorithms have no room for error when operating at high levels of autonomy. Although the current research details existing computer vision and deep learning algorithms and their methodologies and individual results, the research also details challenges faced by the algorithms and the resources needed to operate, along with shortcomings experienced during their detection of lanes in certain weather and lighting conditions. This paper will explore these shortcomings and attempt to implement a lane detection algorithm that could be used to achieve improvements in AV lane detection systems. This paper uses a pre-trained LaneNet model to detect lane or non-lane pixels using binary segmentation as the base detection method using an existing dataset BDD100k followed by a custom dataset generated locally. The selected roads will be modern well-laid roads with up-to-date infrastructure and lane markings, while the second road network will be an older road with infrastructure and lane markings reflecting the road network's age. The performance of the proposed method will be evaluated on the custom dataset to compare its performance to the BDD100k dataset. In summary, this paper will use Transfer Learning to provide a fast and robust lane detection algorithm that can handle various road conditions and provide accurate lane detection.

Keywords: ADAS, autonomous vehicles, deep learning, LaneNet, lane detection

Procedia PDF Downloads 106

Authors: Xinghang Lv, Tao Peng, Jia Chen, Junping Liu, Xinrong Hu, Ruhan He, Minghua Jiang, Wenli Cao

Abstract:

As one of the most dangerous vulnerabilities, effective detection of buffer overflow vulnerabilities is extremely necessary. Traditional detection methods are not accurate enough and consume more resources to meet complex and enormous code environment at present. In order to resolve the above problems, we propose the method for Buffer overflow detection based on Abstract syntax tree, Control flow graph, and Data dependency graph (BodeACD) in C/C++ programs with source code. Firstly, BodeACD constructs the function samples of buffer overflow that are available on Github, then represents them as code representation sequences, which fuse control flow, data dependency, and syntax structure of source code to reduce information loss during code representation. Finally, BodeACD learns vulnerability patterns for vulnerability detection through deep learning. The results of the experiments show that BodeACD has increased the precision and recall by 6.3% and 8.5% respectively compared with the latest methods, which can effectively improve vulnerability detection and reduce False-positive rate and False-negative rate.

Keywords: vulnerability detection, abstract syntax tree, control flow graph, data dependency graph, code representation, deep learning

Procedia PDF Downloads 170

Authors: Atinkut Atinafu Yilma, Eyob Messele Sefene

Abstract:

Anomaly detection is one of the essential mechanisms to control and reduce production loss, especially in today's smart manufacturing. Quick anomaly detection aids in reducing the cost of production by minimizing the possibility of producing defective products. However, developing an anomaly detection model that can rapidly detect a production change is challenging. This paper proposes Gated Recurrent Unit (GRU) combined with Random Forest (RF) to detect anomalies in the production process in real-time quickly. The GRU is used as a feature detector, and RF as a classifier using the input features from GRU. The model was tested using various synthesis and real-world datasets against benchmark methods. The results show that the proposed GRU-RF outperforms the benchmark methods with the shortest time taken to detect anomalies in the production process. Based on the investigation from the study, this proposed model can eliminate or reduce unnecessary production costs and bring a competitive advantage to manufacturing industries.

Keywords: anomaly detection, multivariate time series data, smart manufacturing, gated recurrent unit network, random forest

Procedia PDF Downloads 122

Authors: Belén Vinaixa Kinnear, Arturo Hidalgo López, Bernardo Elembo Wilasi, Pablo Fernández Pérez, Cecilia Hernández Fuentealba

Abstract:

The expanded use of risk assessment in legislative and corporate decision-making has increased the role of expert judgement in giving data for security-related decision-making. Expert judgements are required in most steps of risk assessment: danger recognizable proof, hazard estimation, risk evaluation, and examination of choices. This paper presents a fault tree analysis (FTA), which implies a probabilistic failure analysis applied to leakage of oil in a subsea production system. In standard FTA, the failure probabilities of items of a framework are treated as exact values while evaluating the failure probability of the top event. There is continuously insufficiency of data for calculating the failure estimation of components within the drilling industry. Therefore, fuzzy hypothesis can be used as a solution to solve the issue. The aim of this paper is to examine the leaks from the Zafiro West subsea oil facility by using fuzzy fault tree analysis (FFTA). As a result, the research has given theoretical and practical contributions to maritime safety and environmental protection. It has been also an effective strategy used traditionally in identifying hazards in nuclear installations and power industries.

Keywords: expert judgment, probability assessment, fault tree analysis, risk analysis, oil pipelines, subsea production system, drilling, quantitative risk analysis, leakage failure, top event, off-shore industry

Procedia PDF Downloads 192

Authors: Maryam Heidari, James H. Jones Jr.

Abstract:

Millions of online posts about different topics and products are shared on popular social media platforms. One use of this content is to provide crowd-sourced information about a specific topic, event or product. However, this use raises an important question: what percentage of information available through these services is trustworthy? In particular, might some of this information be generated by a machine, i.e., a bot, instead of a human? Bots can be, and often are, purposely designed to generate enough volume to skew an apparent trend or position on a topic, yet the consumer of such content cannot easily distinguish a bot post from a human post. In this paper, we introduce a model for social media bot detection which uses Bidirectional Encoder Representations from Transformers (Google Bert) for sentiment classification of tweets to identify topic-independent features. Our use of a Natural Language Processing approach to derive topic-independent features for our new bot detection model distinguishes this work from previous bot detection models. We achieve 94\% accuracy classifying the contents of data as generated by a bot or a human, where the most accurate prior work achieved accuracy of 92\%.

Keywords: bot detection, natural language processing, neural network, social media

Procedia PDF Downloads 116

Authors: Shivahari Revathi Venkateswaran

Abstract:

Segmenting customers plays a significant role in churn prediction. It helps the marketing team with proactive and reactive customer retention. For the reactive retention, the retention team reaches out to customers who already showed intent to disconnect by giving some special offers. When coming to proactive retention, the marketing team uses churn prediction model, which ranks each customer from rank 1 to 100, where 1 being more risk to churn/disconnect (high ranks have high propensity to churn). The churn prediction model is built by using XGBoost model. However, with the churn rank, the marketing team can only reach out to the customers based on their individual ranks. To profile different groups of customers and to frame different marketing strategies for targeted groups of customers are not possible with the churn ranks. For this, the customers must be grouped in different segments based on their profiles, like demographics and other non-controllable attributes. This helps the marketing team to frame different offer groups for the targeted audience and prevent them from disconnecting (proactive retention). For segmentation, machine learning approaches like k-mean clustering will not form unique customer segments that have customers with same attributes. This paper finds an alternate approach to find all the combination of unique segments that can be formed from the user attributes and then finds the segments who have uplift (churn rate higher than the baseline churn rate). For this, search algorithms like fast search and recursive search are used. Further, for each segment, all customers can be targeted using individual churn ranks from the churn prediction model. Finally, a UI (User Interface) is developed for the marketing team to interactively search for the meaningful segments that are formed and target the right set of audience for future marketing campaigns and prevent them from disconnecting.

Keywords: churn prediction modeling, XGBoost model, uplift segments, proactive marketing, search algorithms, retention, k-mean clustering

Procedia PDF Downloads 71

Authors: H. Bakhshi, E. Khayyamian

Abstract:

Cognitive radios have been recognized as one of the most promising technologies dealing with the scarcity of the radio spectrum. In cognitive radio systems, secondary users are allowed to utilize the frequency bands of primary users when the bands are idle. Hence, how to accurately detect the idle frequency bands has attracted many researchers’ interest. Detection performance is sensitive toward noise power and gain fluctuation. Since signal to noise ratio (SNR) between primary user and secondary users are not the same and change over the time, SNR and noise power estimation is essential. In this paper, we present a cooperative spectrum sensing algorithm using SNR estimation to improve detection performance in the real situation.

Keywords: cognitive radio, cooperative spectrum sensing, energy detection, SNR estimation, spectrum sensing, rayleigh fading channel

Procedia PDF Downloads 451

Authors: Matthew Scott Lau

Abstract:

This study addresses the research question: How effective has the Community Health Assist Scheme (CHAS) been in reducing market failure in Singapore’s healthcare sector? The CHAS policy, introduced in 2012 in Singapore, aims to improve accessibility and affordability of healthcare by offering subsidies to low and middle-income groups and elderly individuals for general practice consultations and healthcare. The investigation was undertaken by acquiring and analysing primary and secondary research data from 3 main sources, including handwritten survey responses of 334 individuals who were valid CHAS subsidy recipients (CHAS cardholders) from 5 different locations in Singapore, interview responses from two established general practitioner doctors with working knowledge of the scheme, and information from literature available online. Survey responses were analysed to determine how CHAS has affected the affordability and consumption of healthcare, and other benefits or drawbacks for CHAS users. The interview responses were used to explain the benefits of healthcare consumption and provide different perspectives on the impacts of CHAS on the various parties involved. Online sources provided useful information on changes in healthcare consumerism and Singapore’s government policies. The study revealed that CHAS has been largely effective in reducing market failure as the subsidies granted to consumers have improved the consumption of healthcare. This has allowed for the external benefits of healthcare consumption to be realized, thus reducing market failure. However, the study also revealed that CHAS cannot be fully effective in reducing market failure as the scope of CHAS prevents healthcare consumption from fully reaching the socially optimal level. Hence, the study concluded that CHAS has been effective to a large extent in reducing market failure in Singapore’s healthcare sector, albeit with some benefits to third parties yet to be realised. There are certain elements of the investigation, which may limit the validity of the conclusion, such as the means used to determine the socially optimal level of healthcare consumption, and the survey sample size.

Keywords: healthcare consumption, health economics, market failure, subsidies

Procedia PDF Downloads 159

Authors: Kosuri Harshitha Durga, Ritesh Yaduwanshi

Abstract:

Potholes are one of the most significant problems that affect road safety and the quality of infrastructure. The aim of pothole detection using OpenCV is to design an automated system that will detect and create a map of potholes on the road surfaces to improve the safety of roads and ease the maintenance process. This system is based on high-powered computer vision methods that use still images or video footage taken by cameras located in cars or drones. This paper presents an analysis of the implementation of the YOLOv11 model in pedestrian detection and demonstrates greater effectiveness of this method in regards to accuracy, speed, and efficiency of inference. The improved system now supports enhanced prompt diagnosis and timely repair leaving little or no damage on the infrastructure and also ensuring that enhanced road safety is achieved. This technology can also be used as a safety feature for the car itself by being installed in ADAS systems that would alert drivers in real-time while driving to avoid driving over potholes.

Keywords: deep learning, Potholes, segmentation, object detection, YOLO

Procedia PDF Downloads 6

Authors: Niloufar Khoshbakht, Peggi L. Clouston, Sanjay R. Arwade, Alexander C. Schreyer

Abstract:

Laminated veneer bamboo (LVB) is a structural engineered composite made from glued layers of bamboo. A relatively new building product, LVB is currently employed in similar sizes and applications as dimensional lumber. This study describes the results of a 3D elastic Finite Element model for halfhole specimens when loaded in compression parallel-to-grain per ASTM 5764. The model simulates LVB fracture initiation due to shear stresses in the dowel joint and predicts displacement at failure validated through comparison with experimental results. The material fails at 1mm displacement due to in-plane shear stresses. The paper clarifies the complex interactive state of in-plane shear, tension perpendicular-to-grain, and compression parallel-to-grain stresses that form different distributions in the critical zone beneath the bolt hole for half-hole specimens. These findings are instrumental in understanding key factors and fundamental failure mechanisms that occur in LVB dowel connections to help devise safe standards and further LVB product adoption and design.

Keywords: composite, dowel connection, embedment strength, failure behavior, finite element analysis, Moso bamboo

Procedia PDF Downloads 266

Authors: Mustapha Kamel Mihoubi, Mohamed Essadik Kerkar

Abstract:

Probabilistic risk analysis models are used to provide a better understanding of the reliability and structural failure of works, including when calculating the stability of large structures to a major risk in the event of an accident or breakdown. This work is interested in the study of the probability of failure of concrete dams through the application of reliability analysis methods including the methods used in engineering. It is in our case, the use of level 2 methods via the study limit state. Hence, the probability of product failures is estimated by analytical methods of the type first order risk method (FORM) and the second order risk method (SORM). By way of comparison, a level three method was used which generates a full analysis of the problem and involves an integration of the probability density function of random variables extended to the field of security using the Monte Carlo simulation method. Taking into account the change in stress following load combinations: normal, exceptional and extreme acting on the dam, calculation of the results obtained have provided acceptable failure probability values which largely corroborate the theory, in fact, the probability of failure tends to increase with increasing load intensities, thus causing a significant decrease in strength, shear forces then induce a shift that threatens the reliability of the structure by intolerable values of the probability of product failures. Especially, in case the increase of uplift in a hypothetical default of the drainage system.

Keywords: dam, failure, limit-state, monte-carlo, reliability, probability, simulation, sliding, taylor

Procedia PDF Downloads 326

Authors: Haidy S. Ghali, Engy Serag, A. Samer Ezeldin

Abstract:

Copper is an essential raw material used in the construction industry. During the year 2021 and the first half of 2022, the global market suffered from a significant fluctuation in copper raw material prices due to the aftermath of both the COVID-19 pandemic and the Russia-Ukraine war, which exposed its consumers to an unexpected financial risk. Thereto, this paper aims to develop two ANN-LSTM price prediction models, using Python, that can forecast the average monthly copper prices traded in the London Metal Exchange; the first model is a multivariate model that forecasts the copper price of the next 1-month and the second is a univariate model that predicts the copper prices of the upcoming three months. Historical data of average monthly London Metal Exchange copper prices are collected from January 2009 till July 2022, and potential external factors are identified and employed in the multivariate model. These factors lie under three main categories: energy prices and economic indicators of the three major exporting countries of copper, depending on the data availability. Before developing the LSTM models, the collected external parameters are analyzed with respect to the copper prices using correlation and multicollinearity tests in R software; then, the parameters are further screened to select the parameters that influence the copper prices. Then, the two LSTM models are developed, and the dataset is divided into training, validation, and testing sets. The results show that the performance of the 3-Month prediction model is better than the 1-Month prediction model, but still, both models can act as predicting tools for diverse economic situations.

Keywords: copper prices, prediction model, neural network, time series forecasting

Procedia PDF Downloads 114

Authors: Sheldon Liu, Gordon Wang, Lei Liu, Xuefeng Liu

Abstract:

Anomaly detection, also referred to as one-class classification, plays a crucial role in identifying product images that deviate from the expected distribution. This study introduces Data-centric Anomaly Detection with Diffusion Models (DCADDM), presenting a systematic strategy for data collection and further diversifying the data with image generation via diffusion models. The algorithm addresses data collection challenges in real-world scenarios and points toward data augmentation with the integration of generative AI capabilities. The paper explores the generation of normal images using diffusion models. The experiments demonstrate that with 30% of the original normal image size, modeling in an unsupervised setting with state-of-the-art approaches can achieve equivalent performances. With the addition of generated images via diffusion models (10% equivalence of the original dataset size), the proposed algorithm achieves better or equivalent anomaly localization performance.

Keywords: diffusion models, anomaly detection, data-centric, generative AI

Procedia PDF Downloads 84

Authors: Azim Khodadadi, Sahar Sadaat Vakili, Ebrahim Babaei

Abstract:

This study presents a numerical method to optimize the failure rate and repair time of a typical radial distribution system. Failure rate and repair time are effective parameters in customer and energy based indices of reliability. Decrease of these parameters improves reliability indices. Thus, system stability will be boost. The penalty functions indirectly reflect the cost of investment which spent to improve these indices. Constraints on customer and energy based indices, i.e. SAIFI, SAIDI, CAIDI and AENS have been considered by using a new method which reduces optimization algorithm controlling parameters. Imperialist Competitive Algorithm (ICA) used as main optimization technique and particle swarm optimization (PSO), simulated annealing (SA) and differential evolution (DE) has been applied for further investigation. These algorithms have been implemented on a test system by MATLAB. Obtained results have been compared with each other. The optimized values of repair time and failure rate are much lower than current values which this achievement reduced investment cost and also ICA gives better answer than the other used algorithms.

Keywords: imperialist competitive algorithm, failure rate, repair time, radial distribution network

Procedia PDF Downloads 669

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 114

Authors: Lina Pan

Abstract:

In non-Gaussian clutter of a spherically invariant random vector, in the cases that a certain estimated covariance matrix could become singular, the adaptive target detection of high-range-resolution radar is addressed. Firstly, the restricted maximum likelihood (RML) estimates of unknown covariance matrix and scatterer amplitudes are derived for non-Gaussian clutter. And then the RML estimate of texture is obtained. Finally, a novel detector is devised. It is showed that, without secondary data, the proposed detector outperforms the existing Kelly binary integrator.

Keywords: non-Gaussian clutter, covariance matrix estimation, target detection, maximum likelihood

Procedia PDF Downloads 465

Authors: Nir Nissim, Ran Yahalom, Tomer Lancewiki, Yuval Elovici, Boaz Lerner

Abstract:

Background: Attackers increasingly take advantage of innocent users who tend to use USB devices casually, assuming these devices benign when in fact they may carry an embedded malicious behavior or hidden malware. USB devices have many properties and capabilities that have become the subject of malicious operations. Many of the recent attacks targeting individuals, and especially organizations, utilize popular and widely used USB devices, such as mice, keyboards, flash drives, printers, and smartphones. However, current detection tools, techniques, and solutions generally fail to detect both the known and unknown attacks launched via USB devices. Significance: We propose USBWARE, a project that focuses on the vulnerabilities of USB devices and centers on the development of a comprehensive detection framework that relies upon a crucial attack repository. USBWARE will allow researchers and companies to better understand the vulnerabilities and attacks associated with USB devices as well as providing a comprehensive platform for developing detection solutions. Methodology: The framework of USBWARE is aimed at accurate detection of both known and unknown USB-based attacks by a process that efficiently enhances the framework's detection capabilities over time. The framework will integrate two main security approaches in order to enhance the detection of USB-based attacks associated with a variety of USB devices. The first approach is aimed at the detection of known attacks and their variants, whereas the second approach focuses on the detection of unknown attacks. USBWARE will consist of six independent but complimentary detection modules, each detecting attacks based on a different approach or discipline. These modules include novel ideas and algorithms inspired from or already developed within our team's domains of expertise, including cyber security, electrical and signal processing, machine learning, and computational biology. The establishment and maintenance of the USBWARE’s dynamic and up-to-date attack repository will strengthen the capabilities of the USBWARE detection framework. The attack repository’s infrastructure will enable researchers to record, document, create, and simulate existing and new USB-based attacks. This data will be used to maintain the detection framework’s updatability by incorporating knowledge regarding new attacks. Based on our experience in the cyber security domain, we aim to design the USBWARE framework so that it will have several characteristics that are crucial for this type of cyber-security detection solution. Specifically, the USBWARE framework should be: Novel, Multidisciplinary, Trusted, Lightweight, Extendable, Modular and Updatable and Adaptable. Major Findings: Based on our initial survey, we have already found more than 23 types of USB-based attacks, divided into six major categories. Our preliminary evaluation and proof of concepts showed that our detection modules can be used for efficient detection of several basic known USB attacks. Further research, development, and enhancements are required so that USBWARE will be capable to cover all of the major known USB attacks and to detect unknown attacks. Conclusion: USBWARE is a crucial detection framework that must be further enhanced and developed.

Keywords: USB, device, cyber security, attack, detection

Procedia PDF Downloads 398