Search results for: deep machine learning

Authors: Dachuan Shi, M. Hecht, Y. Ye

Abstract:

With the trend of digitalization in railway freight transport, a large number of freight wagons in Germany have been equipped with telematics devices, commonly placed on the wagon body. A telematics device contains a GPS module for tracking and a 3-axis accelerometer for shock detection. Besides these basic functions, it is desired to use the integrated accelerometer for condition monitoring without any additional sensors. Wheel flats as a common type of failure on wheel tread cause large impacts on wagons and infrastructure as well as impulsive noise. A large wheel flat may even cause safety issues such as derailments. In this sense, this paper proposes a machine learning approach for wheel flat detection by using car body accelerations. Due to suspension systems, impulsive signals caused by wheel flats are damped significantly and thus could be buried in signal noise and disturbances. Therefore, it is very challenging to detect wheel flats using car body accelerations. The proposed algorithm considers the envelope spectrum of car body accelerations to eliminate the effect of noise and disturbances. Subsequently, a 1-D convolutional neural network (CNN), which is well known as a deep learning method, is constructed to automatically extract features in the envelope-frequency domain and conduct classification. The constructed CNN is trained and tested on field test data, which are measured on the underframe of a tank wagon with a wheel flat of 20 mm length in the operational condition. The test results demonstrate the good performance of the proposed algorithm for real-time fault detection.

Keywords: fault detection, wheel flat, convolutional neural network, machine learning

Procedia PDF Downloads 108

Authors: Md Rafiqul Islam, Ashir Ahmed, Anwaar Ulhaq, Abu Raihan M. Kamal, Yuan Miao, Hua Wang

Abstract:

Mental health of people is equally important as of their physical health. Mental health and well-being are influenced not only by individual attributes but also by the social circumstances in which people find themselves and the environment in which they live. Like physical health, there is a number of internal and external factors such as biological, social and occupational factors that could influence the mental health of people. People living in poverty, suffering from chronic health conditions, minority groups, and those who exposed to/or displaced by war or conflict are generally more likely to develop mental health conditions. However, to authors’ best knowledge, there is dearth of knowledge on the impact of workplace (especially the highly stressed IT/Tech workplace) on the mental health of its workers. This study attempts to examine the factors influencing the mental health of tech workers. A publicly available dataset containing more than 65,000 cells and 100 attributes is examined for this purpose. Number of machine learning techniques such as ‘Decision Tree’, ‘K nearest neighbor’ ‘Support Vector Machine’ and ‘Ensemble’, are then applied to the selected dataset to draw the findings. It is anticipated that the analysis reported in this study would contribute in presenting useful insights on the attributes contributing in the mental health of tech workers using relevant machine learning techniques.

Keywords: mental disorder, diagnosis, occupational stress, IT workplace

Procedia PDF Downloads 269

Authors: Bliss Singhal

Abstract:

Machine learning (ML) is a branch of Artificial Intelligence (AI) where computers analyze data and find patterns in the data. The study focuses on the detection of metastatic cancer using ML. Metastatic cancer is the stage where cancer has spread to other parts of the body and is the cause of approximately 90% of cancer-related deaths. Normally, pathologists spend hours each day to manually classifying whether tumors are benign or malignant. This tedious task contributes to mislabeling metastasis being over 60% of the time and emphasizes the importance of being aware of human error and other inefficiencies. ML is a good candidate to improve the correct identification of metastatic cancer, saving thousands of lives and can also improve the speed and efficiency of the process, thereby taking fewer resources and time. So far, the deep learning methodology of AI has been used in research to detect cancer. This study is a novel approach to determining the potential of using preprocessing algorithms combined with classification algorithms in detecting metastatic cancer. The study used two preprocessing algorithms: principal component analysis (PCA) and the genetic algorithm, to reduce the dimensionality of the dataset and then used three classification algorithms: logistic regression, decision tree classifier, and k-nearest neighbors to detect metastatic cancer in the pathology scans. The highest accuracy of 71.14% was produced by the ML pipeline comprising of PCA, the genetic algorithm, and the k-nearest neighbor algorithm, suggesting that preprocessing and classification algorithms have great potential for detecting metastatic cancer.

Keywords: breast cancer, principal component analysis, genetic algorithm, k-nearest neighbors, decision tree classifier, logistic regression

Procedia PDF Downloads 64

Authors: Edward W. Staley, Corban G. Rivera, Ashley J. Llorens

Abstract:

Advances in reinforcement learning (RL) have resulted in recent breakthroughs in the application of artificial intelligence (AI) across many different domains. An emerging landscape of development environments is making powerful RL techniques more accessible for a growing community of researchers. However, most existing frameworks do not directly address the problem of learning in complex operating environments, such as dense urban settings or defense-related scenarios, that incorporate distributed, heterogeneous teams of agents. To help enable AI research for this important class of applications, we introduce the AI Arena: a scalable framework with flexible abstractions for distributed multi-agent reinforcement learning. The AI Arena extends the OpenAI Gym interface to allow greater flexibility in learning control policies across multiple agents with heterogeneous learning strategies and localized views of the environment. To illustrate the utility of our framework, we present experimental results that demonstrate performance gains due to a distributed multi-agent learning approach over commonly-used RL techniques in several different learning environments.

Keywords: reinforcement learning, multi-agent, deep learning, artificial intelligence

Procedia PDF Downloads 137

Authors: Luther Ollier, Sylvie Thiria, Anastase Charantonis, Carlos E. Mejia, Michel Crépon

Abstract:

Sea Surface Height Anomaly (SLA) is a signature of the sub-mesoscale dynamics of the upper ocean. Sea Surface Temperature (SST) is driven by these dynamics and can be used to improve the spatial interpolation of SLA fields. In this study, we focused on the temporal evolution of SLA fields. We explored the capacity of deep learning (DL) methods to predict short-term SLA fields using SST fields. We used simulated daily SLA and SST data from the Mercator Global Analysis and Forecasting System, with a resolution of (1/12)◦ in the North Atlantic Ocean (26.5-44.42◦N, -64.25–41.83◦E), covering the period from 1993 to 2019. Using a slightly modified image-to-image convolutional DL architecture, we demonstrated that SST is a relevant variable for controlling the SLA prediction. With a learning process inspired by the teaching-forcing method, we managed to improve the SLA forecast at five days by using the SST fields as additional information. We obtained predictions of a 12 cm (20 cm) error of SLA evolution for scales smaller than mesoscales and at time scales of 5 days (20 days), respectively. Moreover, the information provided by the SST allows us to limit the SLA error to 16 cm at 20 days when learning the trajectory.

Keywords: deep-learning, altimetry, sea surface temperature, forecast

Procedia PDF Downloads 68

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 190

Authors: Hien Thi Dieu Truong, Mahmoud Al-Sarayreh, Pullanagari Reddy, Marlon M. Reis, Richard Archer

Abstract:

New Zealand mānuka honey is a honeybee product derived mainly from Leptospermum scoparium nectar. The potent antibacterial activity of mānuka honey derives principally from methylglyoxal (MGO), in addition to the hydrogen peroxide and other lesser activities present in all honey. MGO is formed from dihydroxyacetone (DHA) unique to L. scoparium nectar. Mānuka honey also has an idiosyncratic phenolic profile that is useful as a chemical maker. Authentic mānuka honey is highly valuable, but almost all honey is formed from natural mixtures of nectars harvested by a hive over a time period. Once diluted by other nectars, mānuka honey irrevocably loses value. We aimed to apply hyperspectral imaging to honey frames before bulk extraction to minimise the dilution of genuine mānuka by other honey and ensure authenticity at the source. This technology is non-destructive and suitable for an industrial setting. Chemometrics using linear Partial Least Squares (PLS) and Support Vector Machine (SVM) showed limited efficacy in interpreting chemical footprints due to large non-linear relationships between predictor and predictand in a large sample set, likely due to honey quality variability across geographic regions. Therefore, an advanced modelling approach, one-dimensional convolutional neural networks (1D-CNN), was investigated for analysing hyperspectral data for extraction of biochemical information from honey. The 1D-CNN model showed superior prediction of honey quality (R² = 0.73, RMSE = 2.346, RPD= 2.56) to PLS (R² = 0.66, RMSE = 2.607, RPD= 1.91) and SVM (R² = 0.67, RMSE = 2.559, RPD=1.98). Classification of mono-floral manuka honey from multi-floral and non-manuka honey exceeded 90% accuracy for all models tried. Overall, this study reveals the potential of HSI and deep learning modelling for automating the evaluation of honey quality in frames.

Keywords: mānuka honey, quality, purity, potency, deep learning, 1D-CNN, chemometrics

Procedia PDF Downloads 115

Authors: Aya Belal, Ahmed Maher Eltair, Maggie Ahmed Mashaly

Abstract:

Geopolymer concrete is gaining recognition as a sustainable alternative to conventional Portland Cement concrete due to its environmentally friendly nature, which is a key goal for Smart City initiatives. It has demonstrated its potential as a reliable material for the design of structural elements. However, the production of Geopolymer concrete is hindered by batch-to-batch variations, which presents a significant challenge to the widespread adoption of Geopolymer concrete. To date, Machine learning has had a profound impact on various fields by enabling models to learn from large datasets and predict outputs accurately. This paper proposes an integration between the current drift to Artificial Intelligence and the composition of Geopolymer mixtures to predict their mechanical properties. This study employs Python software to develop machine learning model in specific Decision Trees. The research uses the percentage oxides and the chemical composition of the Alkali Solution along with the curing conditions as the input independent parameters, irrespective of the waste products used in the mixture yielding the compressive strength of the mix as the output parameter. The results showed 90 % agreement of the predicted values to the actual values having the ratio of the Sodium Silicate to the Sodium Hydroxide solution being the dominant parameter in the mixture.

Keywords: decision trees, geopolymer concrete, machine learning, smart cities, sustainability

Procedia PDF Downloads 58

Authors: Kwaku Damoah

Abstract:

This paper presents a methodology and software application (App) designed to empower users in accessing, retrieving, and comparatively exploring data within the hierarchical network framework of the Government Finance Statistics (GFS) system. It explores the ease of navigating the GFS system and identifies the gaps filled by the new methodology and App. The GFS, embodies a complex Hierarchical Network Classification (HNC) structure, encapsulating institutional units, revenues, expenses, assets, liabilities, and economic activities. Navigating this structure demands specialized knowledge, experience, and skill, posing a significant challenge for effective analytics and fiscal policy decision-making. Many professionals encounter difficulties deciphering these classifications, hindering confident utilization of the system. This accessibility barrier obstructs a vast number of professionals, students, policymakers, and the public from leveraging the abundant data and information within the GFS. Leveraging R programming language, Data Science Analytics and Machine Learning, an efficient methodology enabling users to access, navigate, and conduct exploratory comparisons was developed. The machine learning Fiscal Analytics App (FLOWZZ) democratizes access to advanced analytics through its user-friendly interface, breaking down expertise barriers.

Keywords: data science, data wrangling, drilldown analytics, government finance statistics, hierarchical network classification, machine learning, web application.

Procedia PDF Downloads 45

Authors: Seongjun Kim, Jinwooung Kim, Sung-Ah Kim

Abstract:

The development of information and communication technology also affects human cognition and thinking, especially in the field of design, new techniques are being tried. In architecture, new design methodologies such as machine learning or data-driven design are being applied. In particular, these methodologies are used in analyzing the factors related to the value of real estate or analyzing the feasibility in the early planning stage of the apartment housing. However, since the value of apartment buildings is often determined by external factors such as location and traffic conditions, rather than the interior elements of buildings, data is rarely used in the design process. Therefore, although the technical conditions are provided, the internal elements of the apartment are difficult to apply the data-driven design in the design process of the apartment. As a result, the designers of apartment housing were forced to rely on designer experience or modular design alternatives rather than data-driven design at the design stage, resulting in a uniform arrangement of space in the apartment house. The purpose of this study is to propose a methodology to support the designers to design the apartment unit plan with high consumer preference by deriving the correlation and importance of the floor plan elements of the apartment preferred by the consumers through the machine learning and reflecting this information from the early design process. The data on the pre-sale competition rate and the elements of the floor plan are collected as data, and the correlation between pre-sale competition rate and independent variables is analyzed through machine learning. This analytical model can be used to review the apartment unit plan produced by the designer and to assist the designer. Therefore, it is possible to make a floor plan of apartment housing with high preference because it is possible to feedback apartment unit plan by using trained model when it is used in floor plan design of apartment housing.

Keywords: apartment unit plan, data-driven design, design methodology, machine learning

Procedia PDF Downloads 239

Authors: René A. Sørensen, Søren Skovsen, Peter Christiansen, Henrik Karstoft

Abstract:

Autonomous agricultural machines act in stochastic surroundings and therefore, must be able to perceive the surroundings in real time. This perception can be achieved using image sensors combined with advanced machine learning, in particular Deep Learning. Deep convolutional neural networks excel in labeling and perceiving color images and since the cost of high-quality RGB-cameras is low, the hardware cost of good perception depends heavily on memory and computation power. This paper investigates the possibility of designing lightweight convolutional neural networks for semantic segmentation (pixel wise classification) with reduced hardware requirements, to allow for embedded usage in autonomous agricultural machines. Using compression techniques, a lightweight convolutional neural network is designed to perform real-time semantic segmentation on an embedded platform. The network is trained on two large datasets, ImageNet and Pascal Context, to recognize up to 400 individual classes. The 400 classes are remapped into agricultural superclasses (e.g. human, animal, sky, road, field, shelterbelt and obstacle) and the ability to provide accurate real-time perception of agricultural surroundings is studied. The network is applied to the case of autonomous grass mowing using the NVIDIA Tegra X1 embedded platform. Feeding case-specific images to the network results in a fully segmented map of the superclasses in the image. As the network is still being designed and optimized, only a qualitative analysis of the method is complete at the abstract submission deadline. Proceeding this deadline, the finalized design is quantitatively evaluated on 20 annotated grass mowing images. Lightweight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show competitive performance with regards to accuracy and speed. It is feasible to provide cost-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: autonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 369

Authors: They Shao Peng

Abstract:

Machine vision system for inspection is an automated technology that is normally utilized to analyze items on the production line for quality control purposes, it also can be known as an automated visual inspection (AVI) system. By applying automated visual inspection, the existence of items, defects, contaminants, flaws, and other irregularities in manufactured products can be easily detected in a short time and accurately. However, AVI systems are still inflexible and expensive due to their uniqueness for a specific task and consuming a lot of set-up time and space. With the rapid development of mobile devices, smartphones can be an alternative device for the visual system to solve the existing problems of AVI. Since the smartphone-based AVI system is still at a nascent stage, this led to the motivation to investigate the smartphone-based AVI system. This study is aimed to provide a low-cost AVI system with high efficiency and flexibility. In this project, the object detection models, which are You Only Look Once (YOLO) model and Single Shot MultiBox Detector (SSD) model, are trained, evaluated, and integrated with the smartphone and webcam devices. The performance of the smartphone-based AVI is compared with the webcam-based AVI according to the precision and inference time in this study. Additionally, a mobile application is developed which allows users to implement real-time object detection and object detection from image storage.

Keywords: automated visual inspection, deep learning, machine vision, mobile application

Procedia PDF Downloads 99

Authors: Pius Marthin, Nihal Ata Tutkun

Abstract:

Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional and machine learning models and our model demonstrates better performance across all datasets.

Keywords: cumulative incidence function (CIF), risk information weight (RIW), autoencoders (AE), survival analysis, recurrent events with competing risks, recurrent neural networks (RNN), long short-term memory (LSTM), self-attention, multilayers perceptrons (MLPs)

Procedia PDF Downloads 68

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: artificial neural networks, fuel consumption, friedman test, machine learning, statistical hypothesis testing

Procedia PDF Downloads 152

Authors: Xiaoyan Dai, Hsieh Yisan

Abstract:

Barcode processing of captured images is a huge challenge, as different shooting conditions can result in different barcode appearances. This paper proposes a deep learning-based barcode detection using synthetic-to-real data augmentation. We first augment barcodes themselves; we then augment images containing the barcodes to generate a large variety of data that is close to the actual shooting environments. Comparisons with previous works and evaluations with our original data show that this approach achieves state-of-the-art performance in various real images. In addition, the system uses hybrid resolution for barcode “scan” and is applicable to real-time applications.

Keywords: barcode detection, data augmentation, deep learning, image-based processing

Procedia PDF Downloads 136

Authors: Migena Mana, Ahmed Khalid Syed, Abdul Malik, Nikhil Cherian

Abstract:

In recent years, advancements in deep learning enabled researchers to tackle the problem of self-driving cars. Car companies use huge datasets to train their deep learning models to make autonomous cars a reality. However, this approach has certain drawbacks in that the state space of possible actions for a car is so huge that there cannot be a dataset for every possible road scenario. To overcome this problem, the concept of reinforcement learning (RL) is being investigated in this research. Since the problem of autonomous driving can be modeled in a simulation, it lends itself naturally to the domain of reinforcement learning. The advantage of this approach is that we can model different and complex road scenarios in a simulation without having to deploy in the real world. The autonomous agent can learn to drive by finding the optimal policy. This learned model can then be easily deployed in a real-world setting. In this project, we focus on three RL algorithms: Q-learning, Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO). To model the environment, we have used TORCS (The Open Racing Car Simulator), which provides us with a strong foundation to test our model. The inputs to the algorithms are the sensor data provided by the simulator such as velocity, distance from side pavement, etc. The outcome of this research project is a comparative analysis of these algorithms. Based on the comparison, the PPO algorithm gives the best results. When using PPO algorithm, the reward is greater, and the acceleration, steering angle and braking are more stable compared to the other algorithms, which means that the agent learns to drive in a better and more efficient way in this case. Additionally, we have come up with a dataset taken from the training of the agent with DDPG and PPO algorithms. It contains all the steps of the agent during one full training in the form: (all input values, acceleration, steering angle, break, loss, reward). This study can serve as a base for further complex road scenarios. Furthermore, it can be enlarged in the field of computer vision, using the images to find the best policy.

Keywords: autonomous driving, DDPG (deep deterministic policy gradient), PPO (proximal policy optimization), reinforcement learning

Procedia PDF Downloads 122

Authors: Hyeongbok Kim, Lingling Zhao, Xiaohong Su

Abstract:

Deep reinforcement learning has been applied to address various problems in robotics, such as autonomous driving and unmanned aerial vehicle. However, because of the sparse reward penalty for a collision with obstacles during the navigation mission, the agent fails to learn the optimal policy or requires a long time for convergence. Therefore, using obstacles and enemy agents, in this paper, we present a curriculum-based boost learning method to effectively train compound skills during multi-agent reinforcement learning. First, to enable the agents to solve challenging tasks, we gradually increased learning difficulties by adjusting reward shaping instead of constructing different learning environments. Then, in a benchmark environment with static obstacles and moving enemy agents, the experimental results showed that the proposed curriculum learning strategy enhanced cooperative navigation and compound collision avoidance skills in uncertain environments while improving learning efficiency.

Keywords: curriculum learning, hard exploration, multi-agent reinforcement learning, robotic navigation, sparse reward

Procedia PDF Downloads 69

Authors: Beulah Rani Inbanathan

Abstract:

In the present era, it is vivid from the numerous outcomes that data privacy is being compromised in various ways. Machine learning is one technology that uses the centralized server, and then data is given as input which is being analyzed by the algorithms present on this mentioned server, and hence outputs are predicted. However, each time the data must be sent by the user as the algorithm will analyze the input data in order to predict the output, which is prone to threats. The solution to overcome this issue is federated learning, where the models alone get updated while the data resides on the local machine and does not get exchanged with the other local models. Nevertheless, even on these local models, there are chances of data poisoning, and it is crystal clear from various experiments done by many people. This paper delves into many ways where data poisoning occurs and the many methods through which it is prevalent that data poisoning still exists. It includes the poisoning attacks on IoT devices, Edge devices, Autoregressive model, and also, on Industrial IoT systems and also, few points on how these could be evadible in order to protect our data which is personal, or sensitive, or harmful when exposed.

Keywords: data poisoning, federated learning, Internet of Things, edge computing

Procedia PDF Downloads 68

Authors: Yunwei Zhang, Qiaochu Tang, Yao Zhang, Jiabin Wang, Ulrich Stimming, Alpha Lee

Abstract:

Forecasting the state of health and remaining useful life of Li-ion batteries is an unsolved challenge that limits technologies such as consumer electronics and electric vehicles. Here we build an accurate battery forecasting system by combining electrochemical impedance spectroscopy (EIS) -- a real-time, non-invasive and information-rich measurement that is hitherto underused in battery diagnosis -- with Gaussian process machine learning. We collect over 20,000 EIS spectra of commercial Li-ion batteries at different states of health, states of charge and temperatures -- the largest dataset to our knowledge of its kind. Our Gaussian process model takes the entire spectrum as input, without further feature engineering, and automatically determines which spectral features predict degradation. Our model accurately predicts the remaining useful life, even without complete knowledge of past operating conditions of the battery. Our results demonstrate the value of EIS signals in battery management systems.

Keywords: battery degradation, machine learning method, electrochemical impedance spectroscopy, battery diagnosis

Procedia PDF Downloads 122

Authors: Sunghae Jun

Abstract:

Technology management (TM) is important issue in a company improving the competitiveness. Among many activities of TM, technology analysis (TA) is important factor, because most decisions for management of technology are decided by the results of TA. TA is to analyze the developed results of target technology using statistics or Delphi. TA based on Delphi is depended on the experts’ domain knowledge, in comparison, TA by statistics and machine learning algorithms use objective data such as patent or paper instead of the experts’ knowledge. Many quantitative TA methods based on statistics and machine learning have been studied, and these have been used for technology forecasting, technological innovation, and management of technology. They applied diverse computing tools and many analytical methods case by case. It is not easy to select the suitable software and statistical method for given TA work. So, in this paper, we propose a methodology for quantitative TA using statistical computing software called R and data science to construct a general framework of TA. From the result of case study, we also show how our methodology is applied to real field. This research contributes to R&D planning and technology valuation in TM areas.

Keywords: technology management, R system, R data science, statistics, machine learning

Procedia PDF Downloads 438

Authors: Mouhammad Alkasassbeh, Mohammad Almseidin

Abstract:

Network security engineers work to keep services available all the time by handling intruder attacks. Intrusion Detection System (IDS) is one of the obtainable mechanisms that is used to sense and classify any abnormal actions. Therefore, the IDS must be always up to date with the latest intruder attacks signatures to preserve confidentiality, integrity, and availability of the services. The speed of the IDS is a very important issue as well learning the new attacks. This research work illustrates how the Knowledge Discovery and Data Mining (or Knowledge Discovery in Databases) KDD dataset is very handy for testing and evaluating different Machine Learning Techniques. It mainly focuses on the KDD preprocess part in order to prepare a decent and fair experimental data set. The J48, MLP, and Bayes Network classifiers have been chosen for this study. It has been proven that the J48 classifier has achieved the highest accuracy rate for detecting and classifying all KDD dataset attacks, which are of type DOS, R2L, U2R, and PROBE.

Keywords: IDS, DDoS, MLP, KDD

Procedia PDF Downloads 212

Authors: Jian Qu, Akira Shimazu

Abstract:

OOV (Out Of Vocabulary) terms are terms that cannot be found in many dictionaries. Although it is possible to translate such OOV terms, the translations do not provide any real information for a user. We present an OOV term definition extraction method by using information available from the Internet. We use features such as occurrence of the synonyms and location distances. We apply machine learning method to find the correct definitions for OOV terms. We tested our method on both biomedical type and name type OOV terms, our work outperforms existing work with an accuracy of 86.5%.

Keywords: information retrieval, definition retrieval, OOV (out of vocabulary), biomedical information retrieval

Procedia PDF Downloads 471

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 78

Authors: Lavanya Annadi, Fahimeh Jafari

Abstract:

Transportation brings immense benefits to society, but it also has its costs. Costs include such as the cost of infrastructure, personnel and equipment, but also the loss of life and property in traffic accidents on the road, delays in travel due to traffic congestion and various indirect costs in terms of air transport. More research has been done to identify the various factors that affect road accidents, such as road infrastructure, traffic, sociodemographic characteristics, land use, and the environment. The aim of this research is to predict the probabilistic crash prediction of vehicles using machine learning due to natural and structural reasons by excluding spontaneous reasons like overspeeding etc., in the United States. These factors range from weather factors, like weather conditions, precipitation, visibility, wind speed, wind direction, temperature, pressure, and humidity to human made structures like road structure factors like bump, roundabout, no exit, turning loop, give away, etc. Probabilities are dissected into ten different classes. All the predictions are based on multiclass classification techniques, which are supervised learning. This study considers all crashes that happened in all states collected by the US government. To calculate the probability, multinomial expected value was used and assigned a classification label as the crash probability. We applied three different classification models, including multiclass Logistic Regression, Random Forest and XGBoost. The numerical results show that XGBoost achieved a 75.2% accuracy rate which indicates the part that is being played by natural and structural reasons for the crash. The paper has provided in-deep insights through exploratory data analysis.

Keywords: road safety, crash prediction, exploratory analysis, machine learning

Procedia PDF Downloads 89

Authors: Lagnajeet Mohanty, Mohnish Mishra, Pratham Tapdiya, Himanshu Sekhar Nayak, Swetapadma Singh

Abstract:

In the era of global interconnectedness, effective risk assessment and management are critical for organizational resilience. This review explores the integration of machine learning (ML) into risk processes, examining its transformative potential and the challenges it presents. The literature reveals ML's success in sectors like consumer credit, demonstrating enhanced predictive accuracy, adaptability, and potential cost savings. However, ethical considerations, interpretability issues, and the demand for skilled practitioners pose limitations. Looking forward, the study identifies future research scopes, including refining ethical frameworks, advancing interpretability techniques, and fostering interdisciplinary collaborations. The synthesis of limitations and future directions highlights the dynamic landscape of ML in risk management, urging stakeholders to navigate challenges innovatively. This abstract encapsulates the evolving discourse on ML's role in shaping proactive and effective risk management strategies in our interconnected and unpredictable global landscape.

Keywords: machine learning, risk assessment, ethical considerations, financial inclusion

Procedia PDF Downloads 42

Authors: M. Duran Toksari, Berrin Ucarkus

Abstract:

In this paper, we propose two algorithms to optimally solve makespan and total completion time scheduling problems with learning effect and job dependent delivery times in a single machine environment. The delivery time is the extra time to eliminate adverse effect between the main processing and delivery to the customer. In this paper, we introduce the job dependent delivery times for some single machine scheduling problems with position dependent learning effect, which are makespan are total completion. The results with respect to two algorithms proposed for solving of the each problem are compared with LINGO solutions for 50-jobs, 100-jobs and 150-jobs problems. The proposed algorithms can find the same results in shorter time.

Keywords: delivery Times, learning effect, makespan, scheduling, total completion time

Procedia PDF Downloads 453

Authors: Jiangbo Shi, Zeyu Gao, Chen Li

Abstract:

Nuclei segmentation is a fundamental task in digital pathology analysis and can be automated by deep learning-based methods. However, the development of such an automated method requires a large amount of data with precisely annotated masks which is hard to obtain. Training with weakly labeled data is a popular solution for reducing the workload of annotation. In this paper, we propose a novel meta-learning-based nuclei segmentation method which follows the label correction paradigm to leverage data with noisy masks. Specifically, we design a fully conventional meta-model that can correct noisy masks by using a small amount of clean meta-data. Then the corrected masks are used to supervise the training of the segmentation model. Meanwhile, a bi-level optimization method is adopted to alternately update the parameters of the main segmentation model and the meta-model. Extensive experimental results on two nuclear segmentation datasets show that our method achieves the state-of-the-art result. In particular, in some noise scenarios, it even exceeds the performance of training on supervised data.

Keywords: deep learning, histopathological image, meta-learning, nuclei segmentation, weak annotations

Procedia PDF Downloads 122

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 322

Authors: Alica Höpken, Hergen Pargmann

Abstract:

The resource-efficient planning of the complex production planning processes in the meat industry and the reduction of food waste is a permanent challenge. The complexity of the production planning process occurs in every part of the supply chain, from agriculture to the end consumer. It arises from long and uncertain planning phases. Uncertainties such as stochastic yields, fluctuations in demand, and resource variability are part of this process. In the meat industry, waste mainly relates to incorrect storage, technical causes in production, or overproduction. The high amount of food waste along the complex supply chain in the meat industry could not be reduced by simple solutions until now. Therefore, resource-efficient production planning by conventional methods is currently only partially feasible. The realization of intelligent, automated production planning is basically possible through the application of machine learning algorithms, such as those of reinforcement learning. By applying the adapted design thinking method, machine learning methods (especially reinforcement learning algorithms) are used for the complex production planning process in the meat industry. This method represents a concretization to the application area. A resource-efficient production planning process is made available by adapting the design thinking method. In addition, the complex processes can be planned efficiently by using this method, since this standardized approach offers new possibilities in order to challenge the complexity and the high time consumption. It represents a tool to support the efficient production planning in the meat industry. This paper shows an elegant adaption of the design thinking method to apply the reinforcement learning method for a resource-efficient production planning process in the meat industry. Following, the steps that are necessary to introduce machine learning algorithms into the production planning of the food industry are determined. This is achieved based on a case study which is part of the research project ”REIF - Resource Efficient, Economic and Intelligent Food Chain” supported by the German Federal Ministry for Economic Affairs and Climate Action of Germany and the German Aerospace Center. Through this structured approach, significantly better planning results are achieved, which would be too complex or very time consuming using conventional methods.

Keywords: change management, design thinking method, machine learning, meat industry, reinforcement learning, resource-efficient production planning

Procedia PDF Downloads 108

Authors: Joseph Salim

Abstract:

This paper proposes the development of a supervised machine learning system to predict the consequences of untreated bruxism (teeth grinding) on gingival (gum) recession and jaw pain (most often bilateral jaw pain with possible headaches and limited ability to open the mouth). As a general dentist in a multi-specialty practice, the author has encountered many patients suffering from these issues due to uncontrolled bruxism (teeth grinding) at night. The most effective treatment for managing this problem involves wearing a nightguard during sleep and receiving therapeutic Botox injections to relax the muscles (the masseter muscle) responsible for grinding. However, some patients choose to postpone these treatments, leading to potentially irreversible and costlier consequences in the future. The proposed machine learning model aims to track patients who forgo the recommended treatments and assess the percentage of individuals who will experience worsening jaw pain, gingival (gum) recession, or both within a 3-to-5-year timeframe. By accurately predicting these outcomes, the model seeks to motivate patients to address the root cause proactively, ultimately saving time and pain while improving quality of life and avoiding much costlier treatments such as full-mouth rehabilitation to help recover the loss of vertical dimension of occlusion due to shortened clinical crowns because of bruxism, gingival grafts, etc.

Keywords: artificial intelligence, machine learning, predictive insights, bruxism, teeth grinding, therapeutic botox, nightguard, gingival recession, gum recession, jaw pain

Procedia PDF Downloads 62