Search results for: machine learning applications

Authors: Nihal Murali, Kunal Gupta, Surekha Bhanot

Abstract:

Training of artificial neural networks (ANNs) using reinforcement learning (RL) techniques is being widely discussed in the robot learning literature. The high model complexity of ANNs along with the model-free nature of RL algorithms provides a desirable combination for many robotics applications. There is a huge need for algorithms that generalize using raw sensory inputs, such as vision, without any hand-engineered features or domain heuristics. In this paper, the standard control problem of line following robot was used as a test-bed, and an ANN controller for the robot was trained on images from a live video feed using Q-learning. A virtual agent was first trained in simulation environment and then deployed onto a robot’s hardware. The robot successfully learns to traverse a wide range of curves and displays excellent generalization ability. Qualitative analysis of the evolution of policies, performance and weights of the network provide insights into the nature and convergence of the learning algorithm.

Keywords: artificial neural networks, q-learning, reinforcement learning, robot learning

Procedia PDF Downloads 371

Authors: Ahmed I. Alutabi, Naghmeh Dezhabad, Sudhakar Ganti

Abstract:

Data centers have been growing in size and dema nd continuously in the last two decades. Planning for the deployment of resources has been shallow and always resorted to over-provisioning. Data center operators try to maximize the availability of their services by allocating multiple of the needed resources. One resource that has been wasted, with little thought, has been energy. In recent years, programmable resource allocation has paved the way to allow for more efficient and robust data centers. In this work, we examine the predictability of resource usage in a data center environment. We use a number of models that cover a wide spectrum of machine learning categories. Then we establish a framework to guarantee the client service level agreement (SLA). Our results show that using prediction can cut energy loss by up to 55%.

Keywords: machine learning, artificial intelligence, prediction, data center, resource allocation, green computing

Procedia PDF Downloads 106

Authors: Todd Zhou, Mikhail Yurochkin

Abstract:

Out-of-distribution (OOD) detection is receiving increasing amounts of attention in the machine learning research community, boosted by recent technologies, such as autonomous driving and image processing. This newly-burgeoning field has called for the need for more effective and efficient methods for out-of-distribution generalization methods. Without accessing the label information, deploying machine learning models to out-of-distribution domains becomes extremely challenging since it is impossible to evaluate model performance on unseen domains. To tackle this out-of-distribution detection difficulty, we designed a model selection pipeline algorithm and developed a model selection framework with different impurity and randomness measurements to evaluate and choose the best-performing models for out-of-distribution data. By exploring different randomness scores based on predicted probabilities, we adopted the out-of-distribution entropy and developed a custom-designed score, ”CombinedScore,” as the evaluation criterion. This proposed score was created by adding labeled source information into the judging space of the uncertainty entropy score using harmonic mean. Furthermore, the prediction bias was explored through the equality of opportunity violation measurement. We also improved machine learning model performance through model calibration. The effectiveness of the framework with the proposed evaluation criteria was validated on the Folktables American Community Survey (ACS) datasets.

Keywords: model selection, domain generalization, model fairness, randomness measurements, bias index

Procedia PDF Downloads 123

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

Today as in the other domains, there are an enormous number of political transcripts available in the Web which is waiting to be mined and used for various purposes such as statistics and recommendations. Therefore, automatically determining the political orientation on these transcripts becomes crucial. The methodologies used by machine learning algorithms to do the automatic classification are based on different features such as Linguistic. Considering the ideology differences between Liberals and Conservatives, in this paper, the effect of Personality Traits on political orientation classification is studied. This is done by considering the correlation between LIWC features and the BIG Five Personality Traits. Several experiments are conducted on Convote U.S. Congressional-Speech dataset with seven benchmark classification algorithms. The different methodologies are applied on selecting different feature sets that constituted by 8 to 64 varying number of features. While Neuroticism is obtained to be the most differentiating personality trait on classification of political polarity, when its top 10 representative features are combined with several classification algorithms, it outperformed the results presented in previous research.

Keywords: politics, personality traits, LIWC, machine learning

Procedia PDF Downloads 493

Authors: Amin Naboureh, Ainong Li, Jinhu Bian, Guangbin Lei, Hamid Ebrahimy

Abstract:

Large-scale land cover mapping has become a new challenge in land change and remote sensing field because of involving a big volume of data. Moreover, selecting the right classification method, especially when there are different types of landscapes in the study area is quite difficult. This paper is an attempt to compare the performance of different machine learning (ML) algorithms for generating a land cover map of the China-Central Asia–West Asia Corridor that is considered as one of the main parts of the Belt and Road Initiative project (BRI). The cloud-based Google Earth Engine (GEE) platform was used for generating a land cover map for the study area from Landsat-8 images (2017) by applying three frequently used ML algorithms including random forest (RF), support vector machine (SVM), and artificial neural network (ANN). The selected ML algorithms (RF, SVM, and ANN) were trained and tested using reference data obtained from MODIS yearly land cover product and very high-resolution satellite images. The finding of the study illustrated that among three frequently used ML algorithms, RF with 91% overall accuracy had the best result in producing a land cover map for the China-Central Asia–West Asia Corridor whereas ANN showed the worst result with 85% overall accuracy. The great performance of the GEE in applying different ML algorithms and handling huge volume of remotely sensed data in the present study showed that it could also help the researchers to generate reliable long-term land cover change maps. The finding of this research has great importance for decision-makers and BRI’s authorities in strategic land use planning.

Keywords: land cover, google earth engine, machine learning, remote sensing

Procedia PDF Downloads 112

Authors: Brian Tung, Yam Wing Siu, Tsun Se Cheong

Abstract:

Purpose: This research aims to explore how personal and environmental factors, especially the socio-economic changes and behavioral changes fostered by the COVID-19 outbreak pandemic, affect the financial vulnerability of a specific segment of people in financial distress. Innovative research methodology of machine learning will be applied to data collected from over 300 local individuals in Hong Kong seeking counseling or similar services in recent years. Results: First, machine learning has found that too much exposure to digital services and information on digitized services may lead to adverse effects on respondents’ financial vulnerability. Second, the improvement in financial literacy level provides benefits to the financially vulnerable group, especially those respondents who have started with a lower level. Third, serious addiction to digital technology can lead to worsened debt servicing ability. Machine learning also has found a strong correlation between debt servicing situations and income-seeking behavior as well as spending behavior. In addition, if the vulnerable groups are able to make appropriate investments, they can reduce the probability of incurring financial distress. Finally, being too active in borrowing and repayment can result in a higher likelihood of over-indebtedness. Conclusion: Findings can be employed in formulating a better counseling strategy for professionals. Debt counseling services can be more preventive in nature. For example, according to the findings, with a low level of financial literacy, the respondents are prone to overspending and unable to react properly to the e-marketing promotion messages pop-up from digital services or even falling into financial/investment scams. In addition, people with low levels of financial knowledge will benefit from financial education. Therefore, financial education programs could include tech-savvy matters as special features.

Keywords: personal finance, digitization of the economy, COVID-19 pandemic, addiction to digital technology, financial vulnerability

Procedia PDF Downloads 57

Authors: Mohammad Arabi

Abstract:

The development of advanced technologies in the field of signal processing and vibration analysis has enabled more accurate analysis and fault detection in electrical systems. This research investigates the application of temporal and frequency features in detecting faults in electric motor bearings, aiming to enhance fault detection accuracy and prevent unexpected failures. The use of methods such as deep learning algorithms and neural networks in this process can yield better results. The main objective of this research is to evaluate the efficiency and accuracy of methods based on temporal and frequency features in identifying faults in electric motor bearings to prevent sudden breakdowns and operational issues. Additionally, the feasibility of using techniques such as machine learning and optimization algorithms to improve the fault detection process is also considered. This research employed an experimental method and random sampling. Vibration signals were collected from electric motors under normal and faulty conditions. After standardizing the data, temporal and frequency features were extracted. These features were then analyzed using statistical methods such as analysis of variance (ANOVA) and t-tests, as well as machine learning algorithms like artificial neural networks and support vector machines (SVM). The results showed that using temporal and frequency features significantly improves the accuracy of fault detection in electric motor bearings. ANOVA indicated significant differences between normal and faulty signals. Additionally, t-tests confirmed statistically significant differences between the features extracted from normal and faulty signals. Machine learning algorithms such as neural networks and SVM also significantly increased detection accuracy, demonstrating high effectiveness in timely and accurate fault detection. This study demonstrates that using temporal and frequency features combined with machine learning algorithms can serve as an effective tool for detecting faults in electric motor bearings. This approach not only enhances fault detection accuracy but also simplifies and streamlines the detection process. However, challenges such as data standardization and the cost of implementing advanced monitoring systems must also be considered. Utilizing temporal and frequency features in fault detection of electric motor bearings, along with advanced machine learning methods, offers an effective solution for preventing failures and ensuring the operational health of electric motors. Given the promising results of this research, it is recommended that this technology be more widely adopted in industrial maintenance processes.

Keywords: electric motor, fault detection, frequency features, temporal features

Procedia PDF Downloads 45

Authors: Rui Wu

Abstract:

In the volatile modern manufacturing environment, new orders randomly occur at any time, while the pre-emptive methods are infeasible. This leads to a real-time scheduling method that can produce a reasonably good schedule quickly. The dynamic Flexible Job Shop problem is an NP-hard scheduling problem that hybrid the dynamic Job Shop problem with the Parallel Machine problem. A Flexible Job Shop contains different work centres. Each work centre contains parallel machines that can process certain operations. Many algorithms, such as genetic algorithms or simulated annealing, have been proposed to solve the static Flexible Job Shop problems. However, the time efficiency of these methods is low, and these methods are not feasible in a dynamic scheduling problem. Therefore, a dynamic rule selection scheduling system based on the reinforcement learning method is proposed in this research, in which the dynamic Flexible Job Shop problem is divided into several parallel machine problems to decrease the complexity of the dynamic Flexible Job Shop problem. Firstly, the features of jobs, machines, work centres, and flexible job shops are selected to describe the status of the dynamic Flexible Job Shop problem at each decision point in each work centre. Secondly, a framework of reinforcement learning algorithm using a double-layer deep Q-learning network is applied to select proper composite dispatching rules based on the status of each work centre. Then, based on the selected composite dispatching rule, an available operation is selected from the waiting buffer and assigned to an available machine in each work centre. Finally, the proposed algorithm will be compared with well-known dispatching rules on objectives of mean tardiness, mean flow time, mean waiting time, or mean percentage of waiting time in the real-time Flexible Job Shop problem. The result of the simulations proved that the proposed framework has reasonable performance and time efficiency.

Keywords: dynamic scheduling problem, flexible job shop, dispatching rules, deep reinforcement learning

Procedia PDF Downloads 106

Authors: Lei Zhang, Tingting Xu, Jun He, Zhenyu Yan

Abstract:

Email marketing is one of the most important segments of online marketing. It has been proved to be the most effective way to acquire and retain customers. The email content is vital to customers. Different customers may have different familiarity with a product, so a successful marketing strategy must personalize email content based on individual customers’ product affinity. In this study, we build our personalized email marketing strategy with three types of emails: nurture, promotion, and conversion. Each type of email has a different influence on customers. We investigate this difference by analyzing customers’ open rates, click rates and opt-out rates. Feature importance from response models is also analyzed. The goal of the marketing strategy is to improve the click rate on conversion-type emails. To build the personalized strategy, we formulate the problem as a reinforcement learning problem and adopt a Q-learning algorithm with variations. The simulation results show that our model-based strategy outperforms the current marketer’s strategy.

Keywords: email marketing, email content, reinforcement learning, machine learning, Q-learning

Procedia PDF Downloads 192

Authors: Filip Rusak, Yulia Arzhaeva, Dadong Wang

Abstract:

Machine learning based Computer-Aided Diagnosis (CAD) is gaining much popularity in medical imaging and diagnostic radiology. However, it requires a large amount of high quality and labeled training image datasets. The training images may come from different sources and be acquired from different radiography machines produced by different manufacturers, digital or digitized copies of film radiographs, with various sizes as well as different pixel intensity distributions. In this paper, a content-aware image augmentation method is presented to deal with these variations. The results of the proposed method have been validated graphically by plotting the removed and added seams of pixels on original images. Two different chest X-ray (CXR) datasets are used in the experiments. The CXRs in the datasets defer in size, some are digital CXRs while the others are digitized from analog CXR films. With the proposed content-aware augmentation method, the Seam Carving algorithm is employed to resize CXRs and the corresponding labels in the form of image masks, followed by histogram matching used to normalize the pixel intensities of digital radiography, based on the pixel intensity values of digitized radiographs. We implemented the algorithms, resized the well-known Montgomery dataset, to the size of the most frequently used Japanese Society of Radiological Technology (JSRT) dataset and normalized our digital CXRs for testing. This work resulted in the unified off-the-shelf CXR dataset composed of radiographs included in both, Montgomery and JSRT datasets. The experimental results show that even though the amount of augmentation is large, our algorithm can preserve the important information in lung fields, local structures, and global visual effect adequately. The proposed method can be used to augment training and testing image data sets so that the trained machine learning model can be used to process CXRs from various sources, and it can be potentially used broadly in any medical imaging applications.

Keywords: computer-aided diagnosis, image augmentation, lung segmentation, medical imaging, seam carving

Procedia PDF Downloads 220

Authors: Adekunle Taiwo Adenike, I. K. Ogundoyin

Abstract:

Lassa fever is a neglected tropical virus that has become a significant public health issue in Nigeria, with the country having the greatest burden in Africa. This paper presents a Geo-Computational Model for Analysis and Prediction of Lassa Fever Dynamics and Outbreaks in Nigeria. The model investigates the dynamics of the virus with respect to environmental factors and human populations. It confirms the role of the rodent host in virus transmission and identifies how climate and human population are affected. The proposed methodology is carried out on a Linux operating system using the OSGeoLive virtual machine for geographical computing, which serves as a base for spatial ecology computing. The model design uses Unified Modeling Language (UML), and the performance evaluation uses machine learning algorithms such as random forest, fuzzy logic, and neural networks. The study aims to contribute to the control of Lassa fever, which is achievable through the combined efforts of public health professionals and geocomputational and machine learning tools. The research findings will potentially be more readily accepted and utilized by decision-makers for the attainment of Lassa fever elimination.

Keywords: geo-computational model, lassa fever dynamics, lassa fever, outbreak prediction, nigeria

Procedia PDF Downloads 92

Authors: Mohammed Arif, Abdessalam Kifouche

Abstract:

Speech is a very convenient way of communication between people and machines. It conveys information about the identity of the talker. Since speaker recognition technology is increasingly securing our everyday lives, the objective of this paper is to develop two automatic text-independent speaker verification systems (TI SV) using low-level spectral features and machine learning methods. (i) The first system is based on a support vector machine (SVM), which was widely used in voice signal processing with the aim of speaker recognition involving verifying the identity of the speaker based on its voice characteristics, and (ii) the second is based on Gaussian Mixture Model (GMM) and Universal Background Model (UBM) to combine different functions from different resources to implement the SVM based.

Keywords: speaker verification, text-independent, support vector machine, Gaussian mixture model, cepstral analysis

Procedia PDF Downloads 56

Authors: Luanna B. Prevost, Kelli Carter, Margaurete Romero, Kirsti Martinez

Abstract:

Writing is an essential scientific practice, yet, in several countries, the increasing university science class-size limits the use of written assessments. Written assessments allow students to demonstrate their learning in their own words and permit the faculty to evaluate students’ understanding. However, the time and resources required to grade written assessments prohibit their use in large-enrollment science courses. This study examined the use of machine learning algorithms to automatically analyze student writing and provide timely feedback to the faculty about students' writing in biology. Written responses to questions about matter and energy transformation were collected from large-enrollment undergraduate introductory biology classrooms. Responses were analyzed using the LightSide text mining and classification software. Cohen’s Kappa was used to measure agreement between the LightSide models and human raters. Predictive models achieved agreement with human coding of 0.7 Cohen’s Kappa or greater. Models captured that when writing about matter-energy transformation at the ecosystem level, students focused on primarily on the concepts of heat loss, recycling of matter, and conservation of matter and energy. Models were also produced to capture writing about processes such as decomposition and biochemical cycling. The models created in this study can be used to provide automatic feedback about students understanding of these concepts to biology faculty who desire to use formative written assessments in larger enrollment biology classes, but do not have the time or personnel for manual grading.

Keywords: machine learning, written assessment, biology education, text mining

Procedia PDF Downloads 279

Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh

Abstract:

This study researches the combination of Random. Forest classifiers with large language models (LLMs) and natural language processing (NLP) to improve diagnostic accuracy in chest X-ray analysis using the Indiana University dataset. Utilizing advanced NLP techniques, the research preprocesses textual data from radiological reports to extract key features, which are then merged with image-derived data. This improved dataset is analyzed with Random Forest classifiers to predict specific clinical results, focusing on the identification of health issues and the estimation of case urgency. The findings reveal that the combination of NLP, LLMs, and machine learning not only increases diagnostic precision but also reliability, especially in quickly identifying critical conditions. Achieving an accuracy of 99.35%, the model shows significant advancements over conventional diagnostic techniques. The results emphasize the large potential of machine learning in medical imaging, suggesting that these technologies could greatly enhance clinician judgment and patient outcomes by offering quicker and more precise diagnostic approximations.

Keywords: natural language processing (NLP), large language models (LLMs), random forest classifier, chest x-ray analysis, medical imaging, diagnostic accuracy, indiana university dataset, machine learning in healthcare, predictive modeling, clinical decision support systems

Procedia PDF Downloads 42

Authors: Jazim Sohail, Filipe Teixeira-Dias

Abstract:

Mild traumatic brain injury (mTBI) within non-helmeted contact sports is a growing concern due to the serious risk of potential injury. Extensive research is being conducted looking into head kinematics in non-helmeted contact sports utilizing instrumented mouthguards that allow researchers to record accelerations and velocities of the head during and after an impact. This does not, however, allow the location of the impact on the head, and its magnitude and orientation, to be determined. This research proposes and validates two methods to quantify impact locations from instrumented mouthguard kinematic data, one using rigid body dynamics, the other utilizing machine learning. The rigid body dynamics technique focuses on establishing and matching moments from Euler’s and torque equations in order to find the impact location on the head. The methodology is validated with impact data collected from a lab test with the dummy head fitted with an instrumented mouthguard. Additionally, a Hybrid III Dummy head finite element model was utilized to create synthetic kinematic data sets for impacts from varying locations to validate the impact location algorithm. The algorithm calculates accurate impact locations; however, it will require preprocessing of live data, which is currently being done by cross-referencing data timestamps to video footage. The machine learning technique focuses on eliminating the preprocessing aspect by establishing trends within time-series signals from instrumented mouthguards to determine the impact location on the head. An unsupervised learning technique is used to cluster together impacts within similar regions from an entire time-series signal. The kinematic signals established from mouthguards are converted to the frequency domain before using a clustering algorithm to cluster together similar signals within a time series that may span the length of a game. Impacts are clustered within predetermined location bins. The same Hybrid III Dummy finite element model is used to create impacts that closely replicate on-field impacts in order to create synthetic time-series datasets consisting of impacts in varying locations. These time-series data sets are used to validate the machine learning technique. The rigid body dynamics technique provides a good method to establish accurate impact location of impact signals that have already been labeled as true impacts and filtered out of the entire time series. However, the machine learning technique provides a method that can be implemented with long time series signal data but will provide impact location within predetermined regions on the head. Additionally, the machine learning technique can be used to eliminate false impacts captured by sensors saving additional time for data scientists using instrumented mouthguard kinematic data as validating true impacts with video footage would not be required.

Keywords: head impacts, impact location, instrumented mouthguard, machine learning, mTBI

Procedia PDF Downloads 216

Authors: Samar Swaid

Abstract:

Today, corporates are moving toward the adoption of Design-Thinking techniques to develop products and services, putting their consumer as the heart of the development process. One of the leading companies in Design-Thinking, IDEO (Innovation, Design, Engineering Organization), defines Design-Thinking as an approach to problem-solving that relies on a set of multi-layered skills, processes, and mindsets that help people generate novel solutions to problems. Design thinking may result in new ideas, narratives, objects or systems. It is about redesigning systems, organizations, infrastructures, processes, and solutions in an innovative fashion based on the users' feedback. Tim Brown, president and CEO of IDEO, sees design thinking as a human-centered approach that draws from the designer's toolkit to integrate people's needs, innovative technologies, and business requirements. The application of design thinking has been witnessed to be the road to developing innovative applications, interactive systems, scientific software, healthcare application, and even to utilizing Design-Thinking to re-think business operations, as in the case of Airbnb. Recently, there has been a movement to apply design thinking to machine learning and artificial intelligence to ensure creating the "wow" effect on consumers. The Association of Computing Machinery task force on Data Science program states that" Data scientists should be able to implement and understand algorithms for data collection and analysis. They should understand the time and space considerations of algorithms. They should follow good design principles developing software, understanding the importance of those principles for testability and maintainability" However, this definition hides the user behind the machine who works on data preparation, algorithm selection and model interpretation. Thus, the Data Science program includes design thinking to ensure meeting the user demands, generating more usable machine learning tools, and developing ways of framing computational thinking. Here, describe the fundamentals of Design-Thinking and teaching modules for data science programs.

Keywords: data science, design thinking, AI, currculum, transformation

Procedia PDF Downloads 79

Authors: Titanilla Komenda

Abstract:

Human-machine-collaboration defines a direct interaction between humans and machines to fulfil specific tasks. Those so-called collaborative machines are used without fencing and interact with humans in predefined workspaces. Even though, human-machine-collaboration enables a flexible adaption to variable degrees of freedom, industrial applications are rarely found. The reasons for this are not technical progress but rather limitations in planning processes ensuring safety for operators. Until now, humans and machines were mainly considered separately in the planning process, focusing on ergonomics and system performance respectively. Within human-machine-collaboration, those aspects must not be seen in isolation from each other but rather need to be analysed in interaction. Furthermore, a simulation model is needed that can validate the system performance and ensure the safety for the operator at any given time. Following on from this, a holistic simulation model is presented, enabling a simulative representation of collaborative tasks – including both, humans and machines. The presented model does not only include a geometry and a motion model of interacting humans and machines but also a numerical behaviour model of humans as well as a Boole’s probabilistic sensor model. With this, error scenarios can be simulated by validating system behaviour in unplanned situations. As these models can be defined on the basis of Failure Mode and Effects Analysis as well as probabilities of errors, the implementation in a collaborative model is discussed and evaluated regarding limitations and simulation times. The functionality of the model is shown on industrial applications by comparing simulation results with video data. The analysis shows the impact of considering human factors in the planning process in contrast to only meeting system performance. In this sense, an optimisation function is presented that meets the trade-off between human and machine factors and aids in a successful and safe realisation of collaborative scenarios.

Keywords: human-machine-system, human-robot-collaboration, safety, simulation

Procedia PDF Downloads 360

Authors: Lihong Wu, Raymond Young

Abstract:

The ability to learn is one of the most critical skills in the information age. However, many students do not have a clear understanding of what learning is, what they are learning, and why they are learning. Many students study simply to pass rather than to learn something useful for their career and their life. They have a misconception about learning and a wrong attitude towards learning. This research explores student attitudes to study in management education and explores how to intercede to lead students from shallow to deeper modes of learning.

Keywords: knowledge, surface learning, deep learning, education

Procedia PDF Downloads 497

Authors: Gizem Eser Erdek

Abstract:

This study is research on predicting the remaining life of industrial cutting tools used in the industrial production process with deep learning methods. When the life of cutting tools decreases, they cause destruction to the raw material they are processing. This study it is aimed to predict the remaining life of the cutting tool based on the damage caused by the cutting tools to the raw material. For this, hole photos were collected from the hole-drilling machine for 8 months. Photos were labeled in 5 classes according to hole quality. In this way, the problem was transformed into a classification problem. Using the prepared data set, a model was created with convolutional neural networks, which is a deep learning method. In addition, VGGNet and ResNet architectures, which have been successful in the literature, have been tested on the data set. A hybrid model using convolutional neural networks and support vector machines is also used for comparison. When all models are compared, it has been determined that the model in which convolutional neural networks are used gives successful results of a %74 accuracy rate. In the preliminary studies, the data set was arranged to include only the best and worst classes, and the study gave ~93% accuracy when the binary classification model was applied. The results of this study showed that the remaining life of the cutting tools could be predicted by deep learning methods based on the damage to the raw material. Experiments have proven that deep learning methods can be used as an alternative for cutting tool life estimation.

Keywords: classification, convolutional neural network, deep learning, remaining life of industrial cutting tools, ResNet, support vector machine, VggNet

Procedia PDF Downloads 75

Authors: Yan Cheng, Yijun Shao, James Rudolph, Charlene R. Weir, Beth Sahlmann, Qing Zeng-Treitler

Abstract:

Supervised predictive models require labeled data for training purposes. Complete and accurate labeled data, i.e., a ‘gold standard’, is not always available, and imperfectly labeled data may need to serve as an alternative. An important question is if the accuracy of the labeled data creates a performance ceiling for the trained model. In this study, we trained several models to recognize the presence of delirium in clinical documents using data with annotations that are not completely accurate (i.e., weakly-supervised learning). In the external evaluation, the support vector machine model with a linear kernel performed best, achieving an area under the curve of 89.3% and accuracy of 88%, surpassing the 80% accuracy of the training sample. We then generated a set of simulated data and carried out a series of experiments which demonstrated that models trained on imperfect data can (but do not always) outperform the accuracy of the training data, e.g., the area under the curve for some models is higher than 80% when trained on the data with an error rate of 40%. Our experiments also showed that the error resistance of linear modeling is associated with larger sample size, error type, and linearity of the data (all p-values < 0.001). In conclusion, this study sheds light on the usefulness of imperfect data in clinical research via weakly-supervised learning.

Keywords: weakly-supervised learning, support vector machine, prediction, delirium, simulation

Procedia PDF Downloads 197

Authors: Roshani S. Golhar, Neerajkumar S. Sathawane, Snehal Dongre

Abstract:

Background and objectives: As the, cardiovascular illnesses increasing and becoming cause of mortality worldwide, killing around lot of people each year. Arrhythmia is a type of cardiac illness characterized by a change in the linearity of the heartbeat. The goal of this study is to develop novel deep learning algorithms for successfully interpreting arrhythmia using a single second segment. Because the ECG signal indicates unique electrical heart activity across time, considerable changes between time intervals are detected. Such variances, as well as the limited number of learning data available for each arrhythmia, make standard learning methods difficult, and so impede its exaggeration. Conclusions: The proposed method was able to outperform several state-of-the-art methods. Also proposed technique is an effective and convenient approach to deep learning for heartbeat interpretation, that could be probably used in real-time healthcare monitoring systems

Keywords: electrocardiogram, ECG classification, neural networks, convolutional neural networks, portable document format

Procedia PDF Downloads 69

Authors: Han-Jeong Hwang, Jae-Hyun Jo, Fatemeh Alimardani

Abstract:

An accurate diagnosis of psychiatric diseases is a challenging issue, in particular when distinct symptoms for different diseases are overlapped, such as delusions appeared in bipolar mood disorder (BMD) and schizophrenia (SCH). In the present study, we propose a useful way to discriminate BMD and SCH using electroencephalography (EEG). A total of thirty BMD and SCH patients (15 vs. 15) took part in our experiment. EEG signals were measured with nineteen electrodes attached on the scalp using the international 10-20 system, while they were exposed to a visual stimulus flickering at 16 Hz for 95 s. The flickering visual stimulus induces a certain brain signal, known as steady-state visual evoked potential (SSVEP), which is differently observed in patients with BMD and SCH, respectively, in terms of SSVEP amplitude because they process the same visual information in own unique way. For classifying BDM and SCH patients, machine learning technique was employed in which leave-one-out-cross validation was performed. The SSVEPs induced at the fundamental (16 Hz) and second harmonic (32 Hz) stimulation frequencies were extracted using fast Fourier transformation (FFT), and they were used as features. The most discriminative feature was selected using the Fisher score, and support vector machine (SVM) was used as a classifier. From the analysis, we could obtain a classification accuracy of 83.33 %, showing the feasibility of discriminating patients with BMD and SCH using EEG. We expect that our approach can be utilized for psychiatrists to more accurately diagnose the psychiatric disorders, BMD and SCH.

Keywords: bipolar mood disorder, electroencephalography, schizophrenia, machine learning

Procedia PDF Downloads 418

Authors: Aditi Viswanathan, Shree Ranjani, Aruna Govada

Abstract:

With data sizes constantly expanding, and with classical machine learning algorithms that analyze such data requiring larger and larger amounts of computation time and storage space, the need to distribute computation and memory requirements among several computers has become apparent. Although substantial work has been done in developing distributed binary SVM algorithms and multi-class SVM algorithms individually, the field of multi-class distributed SVMs remains largely unexplored. This research seeks to develop an algorithm that implements the Support Vector Machine over a multi-class data set and is efficient in a distributed environment. For this, we recursively choose the best binary split of a set of classes using a greedy technique. Much like the divide and conquer approach. Our algorithm has shown better computation time during the testing phase than the traditional sequential SVM methods (One vs. One, One vs. Rest) and out-performs them as the size of the data set grows. This approach also classifies the data with higher accuracy than the traditional multi-class algorithms.

Keywords: distributed algorithm, MapReduce, multi-class, support vector machine

Procedia PDF Downloads 399

Authors: Fatima S. Rodriguez, Victorino T. Taylan, Manolito C. Bulaong, Helen F. Gavino, Vitaliana U. Malamug

Abstract:

In sundrying, the quality of the grains are greatly reduced when paddy grains were caught by the rain unsacked and unstored resulting to reduced profit. The objectives of this study were to design and fabricate a quick covering machine for grain drying pavement to test and evaluate the operating characteristics of the machine according to its deployment speed, recovery speed, deployment time, recovery time, power consumption, aesthetics of laminated sack, conducting partial budget, and cost curve analysis. The machine was able to cover the grains in a 12.8 m x 22.5 m grain drying pavement at an average time of 17.13 s. It consumed 0 .53 W-hr for the deployment and recovery of the cover. The machine entailed an investment cost of $1,344.40 and an annual cost charge of $647.32. Moreover, the savings per year using the quick covering machine was $101.83.

Keywords: quick, covering machine, grain, drying pavement

Procedia PDF Downloads 372

Authors: Doseong Eom, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

Large exhibition halls require a lot of energy to maintain comfortable atmosphere for the visitors viewing inside. One way of reducing the energy cost is to have thermal energy storage systems installed so that the thermal energy can be stored in the middle of night when the energy price is low and then used later when the price is high. To minimize the overall energy cost, however, we should be able to decide how much energy to save during which time period exactly. If we can foresee future energy load and the corresponding cost, we will be able to make such decisions reasonably. In this paper, we use machine learning technique to obtain models for predicting weather conditions and the number of visitors on hourly basis for the next day. Based on the energy load thus predicted, we build a cost-optimal daily operation plan for the thermal energy storage systems and cooling and heating facilities through simulation-based optimization.

Keywords: building energy management, machine learning, operation planning, simulation-based optimization

Procedia PDF Downloads 321

Authors: Pinel Sebastien, Bourrin François, De Madron Du Rieu Xavier, Ludwig Wolfgang, Arnau Pedro

Abstract:

Heavy precipitation constitutes a major meteorological threat in the western Mediterranean. Research has investigated the relationship between the states of the Mediterranean Sea and the atmosphere with the precipitation for short temporal windows. However, at a larger temporal scale, the precursor signals of heavy rainfall in the sea and atmosphere have drawn little attention. Moreover, despite ongoing improvements in numerical weather prediction, the medium-term forecasting of rainfall events remains a difficult task. Here, we aim to investigate the influence of early-spring environmental parameters on the following autumnal heavy precipitations. Hence, we develop a machine learning model to predict extreme autumnal rainfall with a 6-month lead time over the Spanish Catalan coastal area, based on i) the sea pattern (main current-LPC and Sea Surface Temperature-SST) at the mesoscale scale, ii) 4 European weather teleconnection patterns (NAO, WeMo, SCAND, MO) at synoptic scale, and iii) the hydrological regime of the main local river (Rhône River). The accuracy of the developed model classifier is evaluated via statistical analysis based on classification accuracy, logarithmic and confusion matrix by comparing with rainfall estimates from rain gauges and satellite observations (CHIRPS-2.0). Sensitivity tests are carried out by changing the model configuration, such as sea SST, sea LPC, river regime, and synoptic atmosphere configuration. The sensitivity analysis suggests a negligible influence from the hydrological regime, unlike SST, LPC, and specific teleconnection weather patterns. At last, this study illustrates how public datasets can be integrated into a machine learning model for heavy rainfall prediction and can interest local policies for management purposes.

Keywords: extreme hazards, sensitivity analysis, heavy rainfall, machine learning, sea-atmosphere modeling, precipitation forecasting

Procedia PDF Downloads 133

Authors: M. Devaki, K. B. Jayanthi

Abstract:

The identification of water bodies from satellite images has recently received a great deal of attention. Different methods have been developed to distinguish water bodies from various satellite images that vary in terms of time and space. Urban water identification issues body manifests in numerous applications with a great deal of certainty. There has been a sharp rise in the usage of satellite images to map natural resources, including urban water bodies and forests, during the past several years. This is because water and forest resources depend on each other so heavily that ongoing monitoring of both is essential to their sustainable management. The relevant elements from satellite pictures have been chosen using a variety of techniques, including machine learning. Then, a convolution neural network (CNN) architecture is created that can identify a superpixel as either one of two classes, one that includes water or doesn't from input data in a complex metropolitan scene. The deep learning technique, CNN, has advanced tremendously in a variety of visual-related tasks. CNN can improve classification performance by reducing the spectral-spatial regularities of the input data and extracting deep features hierarchically from raw pictures. Calculate the water body using the satellite image's resolution. Experimental results demonstrate that the suggested method outperformed conventional approaches in terms of water extraction accuracy from remote-sensing images, with an average overall accuracy of 97%.

Keywords: water body, Deep learning, satellite images, convolution neural network

Procedia PDF Downloads 87

Authors: Gaurav Kumar Sinha

Abstract:

The volatility of the oil market, influenced by geopolitical, economic, and environmental factors, presents significant challenges for stakeholders in predicting trends and demand. This article explores the application of artificial intelligence (AI) in developing robust forecasting models to anticipate changes in the oil market more accurately. We delve into various AI techniques, including machine learning, deep learning, and time series analysis, that have been adapted to analyze historical data and current market conditions to forecast future trends. The study evaluates the effectiveness of these models in capturing complex patterns and dependencies in market data, which traditional forecasting methods often miss. Additionally, the paper discusses the integration of external variables such as political events, economic policies, and technological advancements that influence oil prices and demand. By leveraging AI, stakeholders can achieve a more nuanced understanding of market dynamics, enabling better strategic planning and risk management. The article concludes with a discussion on the potential of AI-driven models in enhancing the predictive accuracy of oil market forecasts and their implications for global economic planning and strategic resource allocation.

Keywords: AI forecasting, oil market trends, machine learning, deep learning, time series analysis, predictive analytics, economic factors, geopolitical influence, technological advancements, strategic planning

Procedia PDF Downloads 33

Authors: Atish Bagchi, Siva Chandrasekaran

Abstract:

Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.

Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning

Procedia PDF Downloads 149

Authors: Adamu Abdullahi, On Francisca, Saidu Isah Rambo, G. N. Obunadike, D. T. Chinyio

Abstract:

The paper discusses the potential threat of Denial of Service (DoS) attacks in the Internet of Things (IoT) networks on constrained application protocols (CoAP). As billions of IoT devices are expected to be connected to the internet in the coming years, the security of these devices is vulnerable to attacks, disrupting their functioning. This research aims to tackle this issue by applying mixed methods of qualitative and quantitative for feature selection, extraction, and cluster algorithms to detect DoS attacks in the Constrained Application Protocol (CoAP) using the Machine Learning Algorithm (MLA). The main objective of the research is to enhance the security scheme for CoAP in the IoT environment by analyzing the nature of DoS attacks and identifying a new set of features for detecting them in the IoT network environment. The aim is to demonstrate the effectiveness of the MLA in detecting DoS attacks and compare it with conventional intrusion detection systems for securing the CoAP in the IoT environment. Findings: The research identifies the appropriate node to detect DoS attacks in the IoT network environment and demonstrates how to detect the attacks through the MLA. The accuracy detection in both classification and network simulation environments shows that the k-means algorithm scored the highest percentage in the training and testing of the evaluation. The network simulation platform also achieved the highest percentage of 99.93% in overall accuracy. This work reviews conventional intrusion detection systems for securing the CoAP in the IoT environment. The DoS security issues associated with the CoAP are discussed.

Keywords: algorithm, CoAP, DoS, IoT, machine learning

Procedia PDF Downloads 79