Search results for: machine learning tools and techniques

Authors: Esra Ece Var

Abstract:

Beekeeping plays essential role both in terms of agricultural yields and agricultural economy; they produce honey, wax, royal jelly, apitoxin, pollen, and propolis. Nowadays, these natural products become more importantly suitable and preferable for nutrition, food supplement, medicine, and industry. However, to produce organic honey, majority of the apiaries are located in remote or distant rural areas where utilities such as electricity and Internet network are not available. Additionally, due to colony failures, world honey production decreases year by year despite the increase in the number of beehives. The objective of this paper is to develop a smart beehive monitoring system for apiaries including those that do not have access to Internet network. In this context, temperature and humidity inside the beehive, and ambient temperature were measured with RFID sensors. Control center, where all sensor data was sent and stored at, has a GSM module used to warn the beekeeper via SMS when an anomaly is detected. Simultaneously, using the collected data, an unsupervised machine learning algorithm is used for detecting anomalies and calibrating the warning system. The results show that the smart beehive monitoring system can detect fatal anomalies up to 4 weeks prior to colony loss.

Keywords: beekeeping, smart systems, machine learning, anomaly detection, apiculture

Procedia PDF Downloads 233

Authors: Jiwan Kumar, Pooja, Sandeep Negi, Anjum Rouf, Amit Kumar, Naveen Lakra

Abstract:

In modern times where, health issues are increasing day by day, breast cancer is also one of them, which is very crucial and really important to find in the early stages. Doctors can use this model in order to tell their patients whether a cancer is not harmful (benign) or harmful (malignant). We have used the knowledge of machine learning in order to produce the model. we have used algorithms like Logistic Regression, Random forest, support Vector Classifier, Bayesian Network and Radial Basis Function. We tried to use the data of crucial parts and show them the results in pictures in order to make it easier for doctors. By doing this, we're making ML better at finding breast cancer, which can lead to saving more lives and better health care.

Keywords: Bayesian network, radial basis function, ensemble learning, understandable, data making better, random forest, logistic regression, breast cancer

Procedia PDF Downloads 49

Authors: Felix Golla

Abstract:

In an era where technology increasingly intersects with education, the potential of chatbots and ChatGPT agents in enhancing student learning experiences in higher education is both significant and timely. This study explores the integration of these AI-driven tools in educational settings, emphasizing their design and functionality to meet the specific needs of students. Recognizing the gap in literature concerning student-centered AI applications in education, this research offers valuable insights into the role and efficacy of chatbots and ChatGPT agents as educational tools. Employing qualitative research methodologies, the study involved conducting semi-structured interviews with university students. These interviews were designed to gather in-depth insights into the students' experiences and expectations regarding the use of AI in learning environments. The High-Performance Cycle Model, renowned for its focus on goal setting and motivation, served as the theoretical framework guiding the analysis. This model helped in systematically categorizing and interpreting the data, revealing the nuanced perceptions and preferences of students regarding AI tools in education. The major findings of the study indicate a strong preference among students for chatbots and ChatGPT agents that offer personalized interaction, adaptive learning support, and regular, constructive feedback. These features were deemed essential for enhancing student engagement, motivation, and overall learning outcomes. Furthermore, the study revealed that students perceive these AI tools not just as passive sources of information but as active facilitators in the learning process, capable of adapting to individual learning styles and needs. In conclusion, this study underscores the transformative potential of chatbots and ChatGPT agents in higher education. It highlights the need for these AI tools to be designed with a student-centered approach, ensuring their alignment with educational objectives and student preferences. The findings contribute to the evolving discourse on AI in education, suggesting a paradigm shift towards more interactive, responsive, and personalized learning experiences. This research not only informs educators and technologists about the desirable features of educational chatbots but also opens avenues for future studies to explore the long-term impact of AI integration in academic curricula.

Keywords: chatbot design in education, high-performance cycle model application, qualitative research in AI, student-centered learning technologies

Procedia PDF Downloads 63

Authors: Shanshan Zhu, Mohammad Nasim

Abstract:

Financial fraud continues to be a major threat to financial institutions across the world, causing colossal money losses and undermining public trust. Fraud prevention techniques, based on hard rules, have become ineffective due to evolving patterns of fraud in recent times. Against such a background, the present study probes into distinct methodologies that exploit emergent AI-driven techniques to further strengthen fraud detection. We would like to compare the performance of generative adversarial networks and graph neural networks with other popular techniques, like gradient boosting, random forests, and neural networks. To this end, we would recommend integrating all these state-of-the-art models into one robust, flexible, and smart system for real-time anomaly and fraud detection. To overcome the challenge, we designed synthetic data and then conducted pattern recognition and unsupervised and supervised learning analyses on the transaction data to identify which activities were fishy. With the use of actual financial statistics, we compare the performance of our model in accuracy, speed, and adaptability versus conventional models. The results of this study illustrate a strong signal and need to integrate state-of-the-art, AI-driven fraud detection solutions into frameworks that are highly relevant to the financial domain. It alerts one to the great urgency that banks and related financial institutions must rapidly implement these most advanced technologies to continue to have a high level of security.

Keywords: AI-driven fraud detection, financial security, machine learning, anomaly detection, real-time fraud detection

Procedia PDF Downloads 27

Authors: Alisha Sinha, Laxmi Kant Sharma

Abstract:

Forest fires are a recurring issue in many parts of the world, including India. These fires can have various causes, including human activities (such as agricultural burning, campfires, or discarded cigarettes) and natural factors (such as lightning). This study presents a comprehensive and advanced methodology for assessing wildfire susceptibility by integrating diverse environmental variables and leveraging cutting-edge machine learning techniques across Rajasthan, India. The primary goal of the study is to utilize Google Earth Engine to compare locations in Sariska National Park, Rajasthan (India), before and after forest fires. High-resolution satellite data were used to assess the amount and types of changes caused by forest fires. The present study meticulously analyzes various environmental variables, i.e., slope orientation, elevation, normalized difference vegetation index (NDVI), drainage density, precipitation, and temperature, to understand landscape characteristics and assess wildfire susceptibility. In addition, a sophisticated random forest regression model is used to predict land surface temperature based on a set of environmental parameters.

Keywords: wildfire susceptibility mapping, LST, random forest, GEE, MODIS, climatic parameters

Procedia PDF Downloads 12

Authors: Ahmed Elzainy, Abir El Sadik, Waleed Al Abdulmonem, Ahmad Alamro, Homaidan Al-Homaidan

Abstract:

Problem-based learning (PBL) is an educational modality which stimulates critical and creative thinking. PBL has been practiced in the college of medicine, Qassim University, Saudi Arabia, since the 2002s with offline face to face activities. Therefore, crucial technological changes in paperless work were needed. The aim of the present study was to design and implement the digitalization of the PBL activities and to evaluate its impact on students' and tutors’ performance. This approach promoted the involvement of all stakeholders after their awareness of the techniques of using online tools. IT support, learning resources facilities, and required multimedia were prepared. Students’ and staff perception surveys reflected their satisfaction with these remarkable changes. The students were interested in the new digitalized materials and educational design, which facilitated the conduction of PBL sessions and provided sufficient time for discussion and peer sharing of knowledge. It enhanced the tutors for supervision and tracking students’ activities on the Learning Management System. It could be concluded that introducing of digitalization of the PBL activities promoted the students’ performance, engagement and enabled a better evaluation of PBL materials and getting prompt students as well as staff feedback. These positive findings encouraged the college to implement the digitalization approach in other educational activities, such as Team-Based Learning, as an additional opportunity for further development.

Keywords: multimedia in PBL, online PBL, problem-based learning, PBL digitalization

Procedia PDF Downloads 113

Authors: H. Zidoum, A. AlShareedah, S. Al Sawafi, A. Al-Ansari, B. Al Lawati

Abstract:

Systemic lupus erythematosus (SLE) is an autoimmune disease with genetic and environmental components. SLE is characterized by a wide variability of clinical manifestations and a course frequently subject to unpredictable flares. Despite recent progress in classification tools, the early diagnosis of SLE is still an unmet need for many patients. This study proposes an interpretable disease classification model that combines the high and efficient predictive performance of CatBoost and the model-agnostic interpretation tools of Shapley Additive exPlanations (SHAP). The CatBoost model was trained on a local cohort of 219 Omani patients with SLE as well as other control diseases. Furthermore, the SHAP library was used to generate individual explanations of the model's decisions as well as rank clinical features by contribution. Overall, we achieved an AUC score of 0.945, F1-score of 0.92 and identified four clinical features (alopecia, renal disorders, cutaneous lupus, and hemolytic anemia) along with the patient's age that was shown to have the greatest contribution on the prediction.

Keywords: feature selection, classification, systemic lupus erythematosus, model interpretation, SHAP, Catboost

Procedia PDF Downloads 77

Authors: Ashi Gautam, Isha Shukla, Akhil Seghal

Abstract:

Biosensors are analytical devices that use a biological sensing element to detect and measure a specific chemical substance or biomolecule in a sample. These devices are widely used in various fields, including medical diagnostics, environmental monitoring, and food analysis, due to their high specificity, sensitivity, and selectivity. In this research paper, a machine learning model is proposed for predicting the suitability of skin care products based on biosensor readings. The proposed model takes in features extracted from biosensor readings, such as biomarker concentration, skin hydration level, inflammation presence, sensitivity, and free radicals, and outputs the most appropriate skin care product for an individual. This model is trained on a dataset of biosensor readings and corresponding skin care product information. The model's performance is evaluated using several metrics, including accuracy, precision, recall, and F1 score. The aim of this research is to develop a personalised skin care product recommendation system using biosensor data. By leveraging the power of machine learning, the proposed model can accurately predict the most suitable skin care product for an individual based on their biosensor readings. This is particularly useful in the skin care industry, where personalised recommendations can lead to better outcomes for consumers. The developed model is based on supervised learning, which means that it is trained on a labeled dataset of biosensor readings and corresponding skin care product information. The model uses these labeled data to learn patterns and relationships between the biosensor readings and skin care products. Once trained, the model can predict the most suitable skin care product for an individual based on their biosensor readings. The results of this study show that the proposed machine learning model can accurately predict the most appropriate skin care product for an individual based on their biosensor readings. The evaluation metrics used in this study demonstrate the effectiveness of the model in predicting skin care products. This model has significant potential for practical use in the skin care industry for personalised skin care product recommendations. The proposed machine learning model for predicting the suitability of skin care products based on biosensor readings is a promising development in the skin care industry. The model's ability to accurately predict the most appropriate skin care product for an individual based on their biosensor readings can lead to better outcomes for consumers. Further research can be done to improve the model's accuracy and effectiveness.

Keywords: biosensors, data model, machine learning, skin care

Procedia PDF Downloads 92

Authors: Jingwen Ou

Abstract:

Writing for academic purposes in a second or foreign language poses a significant challenge for non-native speakers, particularly at the tertiary level, where English academic writing for L2 students is often hindered by difficulties in academic discourse, including vocabulary, academic register, and organization. The past two decades have witnessed a rising popularity in the application of the data-driven learning (DDL) approach in EAP writing instruction. In light of such a trend, this study aims to enhance the integration of DDL into English for academic purposes (EAP) writing classrooms by investigating the perception of Chinese college students regarding the use of corpus tools for improving EAP writing. Additionally, the research explores their corpus consultation behaviors during training to provide insights into corpus-assisted EAP instruction for DDL practitioners. Given the uprising popularity of DDL, this research aims to investigate Chinese university students’ use of corpus tools with three main foci: 1) the influence of corpus tools on learning behaviours, 2) the influence of corpus tools on students’ academic writing performance outcomes, and 3) students’ perceptions and potential perceptional changes towards the use of such tools. Three corpus tools, CQPWeb, Sketch Engine, and LancsBox X, are selected for investigation due to the scarcity of empirical research on patterns of learners’ engagement with a combination of multiple corpora. The research adopts a pre-test / post-test design for the evaluation of students’ academic writing performance before and after the intervention. Twenty participants will be divided into two groups: an intervention and a non-intervention group. Three corpus training workshops will be delivered at the beginning, middle, and end of a semester. An online survey and three separate focus group interviews are designed to investigate students’ perceptions of the use of corpus tools for improving academic writing skills, particularly the rhetorical functions in different essay sections. Insights from students’ consultation sessions indicated difficulties with DDL practice, including insufficiency of time to complete all tasks, struggle with technical set-up, unfamiliarity with the DDL approach and difficulty with some advanced corpus functions. Findings from the main study aim to provide pedagogical insights and training resources for EAP practitioners and learners.

Keywords: corpus linguistics, data-driven learning, English for academic purposes, tertiary education in China

Procedia PDF Downloads 54

Authors: Emmanuel Osaze Oshoiribhor, Adetokunbo MacGregor John-Otumu

Abstract:

There has been a need in recent years to predict student academic achievement prior to graduation. This is to assist them in improving their grades, especially for those who have struggled in the past. The purpose of this research is to use supervised learning techniques to create a model that predicts student academic progress. Many scholars have developed models that predict student academic achievement based on characteristics including smoking, demography, culture, social media, parent educational background, parent finances, and family background, to mention a few. This element, as well as the model used, could have misclassified the kids in terms of their academic achievement. As a prerequisite to predicting if the student will perform well in the future on related courses, this model is built using a logistic regression classifier with basic features such as the previous semester's course score, attendance to class, class participation, and the total number of course materials or resources the student is able to cover per semester. With a 96.7 percent accuracy, the model outperformed other classifiers such as Naive bayes, Support vector machine (SVM), Decision Tree, Random forest, and Adaboost. This model is offered as a desktop application with user-friendly interfaces for forecasting student academic progress for both teachers and students. As a result, both students and professors are encouraged to use this technique to predict outcomes better.

Keywords: artificial intelligence, ML, logistic regression, performance, prediction

Procedia PDF Downloads 103

Authors: Yu Zhang, Pedro Desouza

Abstract:

Since big data has become substantially more accessible and manageable due to the development of powerful tools for dealing with unstructured data, people are eager to mine information from social media resources that could not be handled in the past. Sentiment analysis, as a novel branch of text mining, has in the last decade become increasingly important in marketing analysis, customer risk prediction and other fields. Scientists and researchers have undertaken significant work in creating and improving their sentiment models. In this paper, we present a concept of selecting appropriate classifiers based on the features and qualities of data sources by comparing the performances of five classifiers with three popular social media data sources: Twitter, Amazon Customer Reviews, and Movie Reviews. We introduced a couple of innovative models that outperform traditional sentiment classifiers for these data sources, and provide insights on how to further improve the predictive power of sentiment analysis. The modelling and testing work was done in R and Greenplum in-database analytic tools.

Keywords: sentiment analysis, social media, Twitter, Amazon, data mining, machine learning, text mining

Procedia PDF Downloads 346

Authors: Thohidul Islam, Md. Hamidul Haque, Robin Kumar Biswas

Abstract:

Floods are one of the deadliest natural disasters which are very complex to model; however, machine learning is opening the door for more reliable and accurate flood prediction. In this research, a multilayer perceptron neural network (MLP) is developed to model the rainfall-water level relation, in a subtropical monsoon climatic region of the Bangladesh-India border. Our experiments show promising empirical results to forecast the water level for 1 day lead time. Our best performing MLP model achieves 98.7% coefficient of determination with lower model complexity which surpasses previously reported results on similar forecasting problems.

Keywords: flood forecasting, machine learning, multilayer perceptron network, regression

Procedia PDF Downloads 167

Authors: Mohammed Al Sulaimani, Hamad Al Manhi

Abstract:

With the development of Remote Sensing technology, the resolution of optical Remote Sensing images has greatly improved, and images have become largely available. Numerous detectors have been developed for detecting different types of objects. In the past few years, Remote Sensing has benefited a lot from deep learning, particularly Deep Convolution Neural Networks (CNNs). Deep learning holds great promise to fulfill the challenging needs of Remote Sensing and solving various problems within different fields and applications. The use of Unmanned Aerial Systems in acquiring Aerial Photos has become highly used and preferred by most organizations to support their activities because of their high resolution and accuracy, which make the identification and detection of very small features much easier than Satellite Images. And this has opened an extreme era of Deep Learning in different applications not only in feature extraction and prediction but also in analysis. This work addresses the capacity of Machine Learning and Deep Learning in detecting and extracting Oil Leaks from Flowlines (Onshore) using High-Resolution Aerial Photos which have been acquired by UAS fixed with RGB Sensor to support early detection of these leaks and prevent the company from the leak’s losses and the most important thing environmental damage. Here, there are two different approaches and different methods of DL have been demonstrated. The first approach focuses on detecting the Oil Leaks from the RAW Aerial Photos (not processed) using a Deep Learning called Single Shoot Detector (SSD). The model draws bounding boxes around the leaks, and the results were extremely good. The second approach focuses on detecting the Oil Leaks from the Ortho-mosaiced Images (Georeferenced Images) by developing three Deep Learning Models using (MaskRCNN, U-Net and PSP-Net Classifier). Then, post-processing is performed to combine the results of these three Deep Learning Models to achieve a better detection result and improved accuracy. Although there is a relatively small amount of datasets available for training purposes, the Trained DL Models have shown good results in extracting the extent of the Oil Leaks and obtaining excellent and accurate detection.

Keywords: GIS, remote sensing, oil leak detection, machine learning, aerial photos, unmanned aerial systems

Procedia PDF Downloads 27

Authors: Sima Najafzadehkhoei, George Vega Yon

Abstract:

This paper presents an approach for calibrating Agent-Based Models (ABMs) efficiently, utilizing Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. These machine learning techniques are applied to Susceptible-Infected-Recovered (SIR) models, which are a core framework in the study of epidemiology. Our method replicates parameter values from observed trajectory curves, enhancing the accuracy of predictions when compared to traditional calibration techniques. Through the use of simulated data, we train the models to predict epidemiological parameters more accurately. Two primary approaches were explored: one where the number of susceptible, infected, and recovered individuals is fully known, and another using only the number of infected individuals. Our method shows promise for application in other ABMs where calibration is computationally intensive and expensive.

Keywords: ABM, calibration, CNN, LSTM, epidemiology

Procedia PDF Downloads 9

Authors: Meng-Tzu Cheng, Louisa Rosenheck, Chen-Yen Lin, Eric Klopfer

Abstract:

The purpose of the research is to explore some of the ways in which gameplay data can be analyzed to yield results that feedback into the learning ecosystem. Back-end data for all users as they played an MMOG, The Radix Endeavor, was collected, and this study reports the analyses on a specific genetics quest by using the data mining techniques, including the decision tree method. In the study, different reasons for quest failure between participants who eventually succeeded and who never succeeded were revealed. Regarding the in-game tools use, trait examiner was a key tool in the quest completion process. Subsequently, the results of decision tree showed that a lack of trait examiner usage can be made up with additional Punnett square uses, displaying multiple pathways to success in this quest. The methods of analysis used in this study and the resulting usage patterns indicate some useful ways that gameplay data can provide insights in two main areas. The first is for game designers to know how players are interacting with and learning from their game. The second is for players themselves as well as their teachers to get information on how they are progressing through the game, and to provide help they may need based on strategies and misconceptions identified in the data.

Keywords: MMOG, decision tree, genetics, gaming-learning interaction

Procedia PDF Downloads 353

Authors: Dante J. Dorantes-González, Aldrin Balsa-Yepes

Abstract:

Existing learning techniques such as problem-based learning, project-based learning, or case study learning are learning techniques that focus mainly on technical details, but give no specific guidelines on learner’s experience and emotional learning aspects such as arousal salience and valence, being emotional states important factors affecting engagement and retention. Some approaches involving emotion in educational settings, such as social and emotional learning, lack neuroscientific rigorousness and use of specific neurobiological mechanisms. On the other hand, neurobiology approaches lack educational applicability. And educational approaches mainly focus on cognitive aspects and disregard conditioning learning. First, authors start explaining the reasons why it is hard to learn thoughtfully, then they use the method of neurobiological mapping to track the main limbic system functions, such as the reward circuit, and its relations with perception, memories, motivations, sympathetic and parasympathetic reactions, and sensations, as well as the brain cortex. The authors conclude explaining the major finding: The mechanisms of nonconscious learning and the triggers that guarantee long-term memory potentiation. Afterward, the educational framework for practical application and the instructors’ guidelines are established. An implementation example in engineering education is given, namely, the study of tuned-mass dampers for earthquake oscillations attenuation in skyscrapers. This work represents an original learning technique based on nonconscious learning mechanisms to enhance long-term memories that complement existing cognitive learning methods.

Keywords: emotion, emotion-enhanced memory, learning technique, STEM

Procedia PDF Downloads 85

Authors: Stephen Kyakulumbye, Vivian Kobusingye

Abstract:

Generally, World over, COVID-19 has had adverse effects on all sectors but with more debilitating effects on the education sector. After reactive lockdowns, education institutions that could continue teaching and learning had to go a distance mediated by digital technological tools. In Uganda, the Ministry of Education thereby issued COVID-19 Online Distance E-learning (ODeL) emergent guidelines. Despite such guidelines, academic institutions in Uganda and similar developing contexts with academically constrained resource environments were caught off-guard and ill-prepared to transform from face-to-face learning to online distance learning mode. Most academic institutions that migrated spontaneously did so with no deliberate tools, systems, strategies, or software to cause active, meaningful, and engaging learning for students. By experience, most of these academic institutions shifted to Zoom and WhatsApp and instead conducted online teaching in real-time than blended synchronous and asynchronous tools. This paper provides students’ experiences while blending synchronous and asynchronous content-creating and learning tools within a technological resource-constrained environment to navigate in such a challenging Uganda context. These conceptual case-based findings, using experience from Uganda Christian University (UCU), point at the design of learning activities with two certain characteristics, the enhancement of synchronous learning technologies with asynchronous ones to mitigate the challenge of system breakdown, passive learning to active learning, and enhances the types of presence (social, cognitive and facilitatory). The paper, both empirical and experiential in nature, uses online experiences from third-year students in Bachelor of Business Administration student lectured using asynchronous text, audio, and video created with Open Broadcaster Studio software and compressed with Handbrake, all open-source software to mitigate disk space and bandwidth usage challenges. The synchronous online engagements with students were a blend of zoom or BigBlueButton, to ensure that students had an alternative just in case one failed due to excessive real-time traffic. Generally, students report that compared to their previous face-to-face lectures, the pre-recorded lectures via Youtube provided them an opportunity to reflect on content in a self-paced manner, which later on enabled them to engage actively during the live zoom and/or BigBlueButton real-time discussions and presentations. The major recommendation is that lecturers and teachers in a resource-constrained environment with limited digital resources like the internet and digital devices should harness this approach to offer students access to learning content in a self-paced manner and thereby enabling reflective active learning through reflective and high-order thinking.

Keywords: synchronous learning, asynchronous learning, active learning, reflective learning, resource-constrained environment

Procedia PDF Downloads 132

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 107

Authors: Johan Loeckx, Joeri Bultheel

Abstract:

Recently, the application of deep learning to music has gained popularity. Its true potential, however, has been largely unexplored. In this paper, a new idea for representing the dynamic behavior of music is proposed. A ”forward” conditional RBM takes into account not only preceding but also future samples during training. Though this may sound controversial at first sight, it will be shown that it makes sense from a musical and neuro-cognitive perspective. The model is applied to reconstruct music based upon the first notes and to improvise in the musical style of a composer. Different to expectations, reconstruction accuracy with respect to a regular CRBM with the same order, was not significantly improved. More research is needed to test the performance on unseen data.

Keywords: deep learning, restricted boltzmann machine, music generation, conditional restricted boltzmann machine (CRBM)

Procedia PDF Downloads 519

Authors: Jian Zheng, Yoshiyasu Takahashi, Yuichi Kobayashi, Tatsuhiro Sato

Abstract:

In the study, we present a conceptual framework for developing a scheduling system that can generate self-explanatory and easy-understanding schedules. To this end, a user interface is conceived to help planners record factors that are considered crucial in scheduling, as well as internal and external sources relating to such factors. A hybrid approach combining machine learning and constraint programming is developed to generate schedules and the corresponding factors, and accordingly display them on the user interface. Effects of the proposed system on scheduling are discussed, and it is expected that scheduling efficiency and system understandability will be improved, compared with previous scheduling systems.

Keywords: constraint programming, factors considered in scheduling, machine learning, scheduling system

Procedia PDF Downloads 317

Authors: Miguel Contreras, David Long, Will Bachman

Abstract:

Background: Microscopy plays a central role in cell and developmental biology. In particular, fluorescence microscopy can be used to visualize specific cellular components and subsequently quantify their morphology through development of virtual-cell models for study of effects of mechanical forces on cells. However, there are challenges with these imaging experiments, which can make it difficult to quantify cell morphology: inconsistent results, time-consuming and potentially costly protocols, and limitation on number of labels due to spectral overlap. To address these challenges, the objective of this project is to develop an automatic computational machine learning pipeline to predict cellular components morphology for virtual-cell generation based on fluorescence cell membrane confocal z-stacks. Methods: Registered confocal z-stacks of nuclei and cell membrane of endothelial cells, consisting of 20 images each, were obtained from fluorescence confocal microscopy and normalized through software pipeline for each image to have a mean pixel intensity value of 0.5. An open source machine learning algorithm, originally developed to predict fluorescence labels on unlabeled transmitted light microscopy cell images, was trained using this set of normalized z-stacks on a single CPU machine. Through transfer learning, the algorithm used knowledge acquired from its previous training sessions to learn the new task. Once trained, the algorithm was used to predict morphology of nuclei using normalized cell membrane fluorescence images as input. Predictions were compared to the ground truth fluorescence nuclei images. Results: After one week of training, using one cell membrane z-stack (20 images) and corresponding nuclei label, results showed qualitatively good predictions on training set. The algorithm was able to accurately predict nuclei locations as well as shape when fed only fluorescence membrane images. Similar training sessions with improved membrane image quality, including clear lining and shape of the membrane, clearly showing the boundaries of each cell, proportionally improved nuclei predictions, reducing errors relative to ground truth. Discussion: These results show the potential of pre-trained machine learning algorithms to predict cell morphology using relatively small amounts of data and training time, eliminating the need of using multiple labels in immunofluorescence experiments. With further training, the algorithm is expected to predict different labels (e.g., focal-adhesion sites, cytoskeleton), which can be added to the automatic machine learning pipeline for direct input into Principal Component Analysis (PCA) for generation of virtual-cell mechanical models.

Keywords: cell morphology prediction, computational machine learning, fluorescence microscopy, virtual-cell models

Procedia PDF Downloads 200

Authors: Basel Halak, Christian Hall, Syed Abdul Father, Nelson Chow Wai Kit, Ruwaydah Widaad Raymode

Abstract:

The attack surface on computing devices is becoming very sophisticated, driven by the sheer increase of interconnected devices, reaching 50B in 2025, which makes it easier for adversaries to have direct access and perform well-known physical attacks. The impact of increased security vulnerability of electronic systems is exacerbated for devices that are part of the critical infrastructure or those used in military applications, where the likelihood of being targeted is very high. This continuously evolving landscape of security threats calls for a new generation of defense methods that are equally effective and adaptive. This paper proposes an intelligent defense mechanism to protect from physical tampering, it consists of a tamper detection system enhanced with machine learning capabilities, which allows it to recognize normal operating conditions, classify known physical attacks and identify new types of malicious behaviors. A prototype of the proposed system has been implemented, and its functionality has been successfully verified for two types of normal operating conditions and further four forms of physical attacks. In addition, a systematic threat modeling analysis and security validation was carried out, which indicated the proposed solution provides better protection against including information leakage, loss of data, and disruption of operation.

Keywords: anti-tamper, hardware, machine learning, physical security, embedded devices, ioT

Procedia PDF Downloads 148

Authors: Komon Paisal

Abstract:

The aim of this research was to create collaborative learning activities in the course of Principles of Mathematics for graduate level by investigating the students’ ability in proving the mathematics principles as well as their attitudes towards the activities. The samples composed of 2 main group; lecturers and students. The lecturers consisted of 3 teachers who taught the course of Principles of Mathematics at Rajabhat Suan Sunandha Unicersity in the academic year 2012. The students consisted of 32 students joining the cooperative learning activities in the subject of Principles of Mathematics in the academic year 2012. The research tools included activity plan for cooperative learning, testing on mathematics with the reliability of 0.8067 and the attitude questionnaires reported by the students. The results showed that: 1) the efficiency of the developed cooperative learning activities was 69.76/ 68.57 which was lower than the set criteria at 70/70. 2) The students joining the cooperative learning activities were able to prove the principles of mathematics at the average of 70%. 3) The students joining the cooperative learning activities reported moderate attitude towards the activities.

Keywords: instructional design, pedagogical, teaching strategies, learning strategies

Procedia PDF Downloads 265

Authors: Sokkhey Phauk, Takeo Okazaki

Abstract:

The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.

Keywords: academic performance prediction system, educational data mining, dominant factors, feature selection method, prediction model, student performance

Procedia PDF Downloads 104

Authors: Behzad Behnia, Noah LaRussa-Trott

Abstract:

In recent years, fibers have been successfully used as an additive to reinforce asphalt concrete materials and to enhance the sustainability and resiliency of transportation infrastructure. Roads covered with fiber-reinforced asphalt concrete (FRAC) require less frequent maintenance and tend to have a longer lifespan. The present work investigates the application of sasobit-coated aramid fibers in asphalt pavements and employs machine learning to develop prediction models to evaluate the cracking performance of FRAC materials. For the experimental part of the study, the effects of several important parameters such as fiber content, fiber length, and testing temperature on fracture characteristics of FRAC mixtures were thoroughly investigated. Two mechanical performance tests, i.e., the disk-shaped compact tension [DC(T)] and indirect tensile [ID(T)] strength tests, as well as the non-destructive acoustic emission test, were utilized to experimentally measure the cracking behavior of the FRAC material in both macro and micro level, respectively. The experimental results were used to train the supervised machine learning approach in order to establish prediction models for fracture performance of the FRAC mixtures in the field. Experimental results demonstrated that adding fibers improved the overall fracture performance of asphalt concrete materials by increasing their fracture energy, tensile strength and lowering their 'embrittlement temperature'. FRAC mixtures containing long-size fibers exhibited better cracking performance than regular-size fiber mixtures. The developed prediction models of this study could be easily employed by pavement engineers in the assessment of the FRAC pavements.

Keywords: fiber reinforced asphalt concrete, machine learning, cracking performance tests, prediction model

Procedia PDF Downloads 133

Authors: Ruzanna Muradyan

Abstract:

Medical data mining is a crucial field in contemporary healthcare that offers cutting-edge tactics with enormous potential to transform patient care. This abstract examines how sophisticated data mining techniques could transform the healthcare industry, with a special focus on how they might improve patient outcomes. Healthcare data repositories have dynamically evolved, producing a rich tapestry of different, multi-dimensional information that includes genetic profiles, lifestyle markers, electronic health records, and more. By utilizing data mining techniques inside this vast library, a variety of prospects for precision medicine, predictive analytics, and insight production become visible. Predictive modeling for illness prediction, risk stratification, and therapy efficacy evaluations are important points of focus. Healthcare providers may use this abundance of data to tailor treatment plans, identify high-risk patient populations, and forecast disease trajectories by applying machine learning algorithms and predictive analytics. Better patient outcomes, more efficient use of resources, and early treatments are made possible by this proactive strategy. Furthermore, data mining techniques act as catalysts to reveal complex relationships between apparently unrelated data pieces, providing enhanced insights into the cause of disease, genetic susceptibilities, and environmental factors. Healthcare practitioners can get practical insights that guide disease prevention, customized patient counseling, and focused therapies by analyzing these associations. The abstract explores the problems and ethical issues that come with using data mining techniques in the healthcare industry. In order to properly use these approaches, it is essential to find a balance between data privacy, security issues, and the interpretability of complex models. Finally, this abstract demonstrates the revolutionary power of modern data mining methodologies in transforming the healthcare sector. Healthcare practitioners and researchers can uncover unique insights, enhance clinical decision-making, and ultimately elevate patient care to unprecedented levels of precision and efficacy by employing cutting-edge methodologies.

Keywords: data mining, healthcare, patient care, predictive analytics, precision medicine, electronic health records, machine learning, predictive modeling, disease prognosis, risk stratification, treatment efficacy, genetic profiles, precision health

Procedia PDF Downloads 55

Authors: Forouzan Salehi Fergeni

Abstract:

Converting the movement intents of a person into commands for action employing brain signals like electroencephalogram signals is a brain-computer interface (BCI) system. When left or right-hand motions are imagined, different patterns of brain activity appear, which can be employed as BCI signals for control. To make better the brain-computer interface (BCI) structures, effective and accurate techniques for increasing the classifying precision of motor imagery (MI) based on electroencephalography (EEG) are greatly needed. Subject dependency and non-stationary are two features of EEG signals. So, EEG signals must be effectively processed before being used in BCI applications. In the present study, after applying an 8 to 30 band-pass filter, a car spatial filter is rendered for the purpose of denoising, and then, a method of analysis of variance is used to select more appropriate and informative channels from a category of a large number of different channels. After ordering channels based on their efficiencies, a sequential forward channel selection is employed to choose just a few reliable ones. Features from two domains of time and wavelet are extracted and shortlisted with the help of a statistical technique, namely the t-test. Finally, the selected features are classified with different machine learning and neural network classifiers being k-nearest neighbor, Probabilistic neural network, support-vector-machine, Extreme learning machine, decision tree, Multi-layer perceptron, and linear discriminant analysis with the purpose of comparing their performance in this application. Utilizing a ten-fold cross-validation approach, tests are performed on a motor imagery dataset found in the BCI competition III. Outcomes demonstrated that the SVM classifier got the greatest classification precision of 97% when compared to the other available approaches. The entire investigative findings confirm that the suggested framework is reliable and computationally effective for the construction of BCI systems and surpasses the existing methods.

Keywords: brain-computer interface, channel selection, motor imagery, support-vector-machine

Procedia PDF Downloads 43

Authors: Ian Omung'a

Abstract:

Breast cancer remains to be one of the deadliest cancers for women worldwide, with the risk of developing tumors being as high as 50 percent in Sub-Saharan African countries like Kenya. With as many as 42 percent of these cases set to be diagnosed late when cancer has metastasized and or the prognosis has become terminal, Full Field Digital [FFD] Mammography remains an effective screening technique that leads to early detection where in most cases, successful interventions can be made to control or eliminate the tumors altogether. FFD Mammograms have been proven to multiply more effective when used together with Computer-Aided Detection and Diagnosis [CADe] systems, relying on algorithmic implementations of Deep Learning techniques in Computer Vision to carry out deep pattern recognition that is comparable to the level of a human radiologist and decipher whether specific areas of interest in the mammogram scan image portray abnormalities if any and whether these abnormalities are indicative of a benign or malignant tumor. Within this paper, we review emergent Deep Learning techniques that will prove relevant to the development of State-of-The-Art FFD Mammogram CADe systems. These techniques will span self-supervised learning for context-encoded occlusion, self-supervised learning for pre-processing and labeling automation, as well as the creation of a standardized large-scale mammography dataset as a benchmark for CADe systems' evaluation. Finally, comparisons are drawn between existing practices that pre-date these techniques and how the development of CADe systems that incorporate them will be different.

Keywords: breast cancer diagnosis, computer aided detection and diagnosis, deep learning, whole mammogram classfication, ultrasound classification, computer vision

Procedia PDF Downloads 90

Authors: Supria Sarkar, Vasit Sagan, Sourav Bhadra, Meghnath Pokharel, Felix B.Fritschi

Abstract:

Soybean and their derivatives are very important agricultural commodities around the world because of their wide applicability in human food, animal feed, biofuel, and industries. However, the significance of soybean production depends on the quality of the soybean seeds rather than the yield alone. Seed composition is widely dependent on plant physiological properties, aerobic and anaerobic environmental conditions, nutrient content, and plant phenological characteristics, which can be captured by high temporal resolution remote sensing datasets. Planet scope (PS) satellite images have high potential in sequential information of crop growth due to their frequent revisit throughout the world. In this study, we estimate soybean seed composition while the plants are in the field by utilizing PlanetScope (PS) satellite images and different machine learning algorithms. Several experimental fields were established with varying genotypes and different seed compositions were measured from the samples as ground truth data. The PS images were processed to extract 462 hand-crafted vegetative and textural features. Four machine learning algorithms, i.e., partial least squares (PLSR), random forest (RFR), gradient boosting machine (GBM), support vector machine (SVM), and two recurrent neural network architectures, i.e., long short-term memory (LSTM) and gated recurrent unit (GRU) were used in this study to predict oil, protein, sucrose, ash, starch, and fiber of soybean seed samples. The GRU and LSTM architectures had two separate branches, one for vegetative features and the other for textures features, which were later concatenated together to predict seed composition. The results show that sucrose, ash, protein, and oil yielded comparable prediction results. Machine learning algorithms that best predicted the six seed composition traits differed. GRU worked well for oil (R-Squared: of 0.53) and protein (R-Squared: 0.36), whereas SVR and PLSR showed the best result for sucrose (R-Squared: 0.74) and ash (R-Squared: 0.60), respectively. Although, the RFR and GBM provided comparable performance, the models tended to extremely overfit. Among the features, vegetative features were found as the most important variables compared to texture features. It is suggested to utilize many vegetation indices for machine learning training and select the best ones by using feature selection methods. Overall, the study reveals the feasibility and efficiency of PS images and machine learning for plot-level seed composition estimation. However, special care should be given while designing the plot size in the experiments to avoid mixed pixel issues.

Keywords: agriculture, computer vision, data science, geospatial technology

Procedia PDF Downloads 131

Authors: Arun Sanjel, Greg Speegle

Abstract:

Every second, massive amounts of data are generated, and Data Intensive Scalable Computing (DISC) frameworks have evolved into effective tools for analyzing such massive amounts of data. Since the underlying architecture of these distributed computing platforms is often new to users, building a DISC application can often be time-consuming and prone to errors. The automated conversion of a sequential program to a DISC program will consequently significantly improve productivity. However, synthesizing a user’s intended program from an input specification is complex, with several important applications, such as distributed program synthesizing and code refactoring. Existing works such as Tyro and Casper rely entirely on deductive synthesis techniques or similar program synthesis approaches. Our approach is to develop a data-driven synthesis technique to identify sequential components and translate them to equivalent distributed operations. We emphasize using reinforcement learning and unit testing as feedback mechanisms to achieve our objectives.

Keywords: program synthesis, distributed computing, reinforcement learning, unit testing, DISC

Procedia PDF Downloads 97