Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
259,185
result(s) for
"machine learning algorithms"
Sort by:
Assessing the Influence of Land Use/Land Cover Alteration on Climate Variability: An Analysis in the Aurangabad District of Maharashtra State, India
Examining the influence of land use/land cover transformation on meteorological variables has become imperative for maintaining long-term climate sustainability. Rapid growth and haphazard expansion have caused the conversion of prime agricultural land into a built-up area. This study used multitemporal Landsat data to analyze land use/land cover (LULC) changes, and Terra Climate monthly data to examine the impact of land transformation on precipitation, minimum and maximum temperature, wind speed, and soil moisture in the Aurangabad district of Maharashtra state in India during 1999–2019. Multiple linear regression and correlation analysis were performed to determine the association among LULC classes and climatic variables. This study revealed rapid urbanization in the study area over the years. The built-up area, water bodies, and barren lands have recorded a steep rise, while the agricultural area has decreased in the district. Drastic changes were observed in the climatic variables over the years. The precipitation and wind speed have shown decreasing trends during the study period. A positive relationship between soil moisture and agricultural land was found through a correlation analysis. Conspicuous findings about the positive relationship between the agricultural land and maximum temperature need further investigation. A multiple linear regression analysis demonstrated a negative relationship between the built-up area and precipitation. The intensity of the precipitation has reduced as a consequence of the developmental activities in the study area. Moreover, a positive relationship was observed between the built-up area and maximum temperature. Thus, this study calls for policy implications to formulate a futuristic land-use plan considering climate change projection in the district.
Journal Article
Scalable and distributed machine learning and deep learning patterns
\"By the end of this book, you will have the knowledge and abilities necessary to construct and implement a distributed data processing pipeline for machine learning model inference and training. Reduced time costs in machine learning result in shorter model training and model updating cycle wait times. Distributed machine learning enables ML professionals to reduce model training and inference time drastically. With the aid of this helpful manual, you'll be able to use your Python development experience and quickly get started with the creation of distributed ML, including multi-node ML systems\"-- Provided by publisher.
BOOK
Evaluating human–machine collaboration through a comparative analysis of experts, machine learning, and hybrid approaches in real estate valuation
Accurate prediction of real estate prices remains a major challenge due to dynamic market conditions and the limitations of traditional valuation methods. Empirical studies that directly compare human experts, machine learning (ML) models, and hybrid approaches are rare. This study examines the predictive accuracy and efficiency of an XGBoost-based ML model, real estate experts, and a hybrid human–machine approach. A model was trained using 21,736 real estate transactions from Vienna (2018–2022). We then conducted an experimental procedure with 13 experts who evaluated newly built apartments sold in 2023 under three conditions: limited information, state-of-the-art expert methods, and collaboration between experts and ML model. The results show that the ML model achieves accuracy comparable to that of experts while significantly reducing the time required for the task. Within the hybrid approach, experts were able to achieve the highest accuracy in comparison to other methods. These results underscore the potential of human-ML collaboration.
Journal Article
Identification of key factors for early detection of rheumatoid arthritis in primary care using machine learning
Rheumatoid arthritis (RA) is a chronic disease that causes irreversible joint damage. Early detection, especially in primary care settings, is crucial for effective disease management. This study aimed to identify the factors that help screen individuals at risk of RA to reduce delays in referral to rheumatologists. This analytical and applied research used a questionnaire to gather data from 377 patients at a rheumatology diagnostic center in Ahvaz, Iran, between August and November 2024. Study variables included patients’ articular and extra-articular symptoms at disease onset, demographic data, and initial laboratory markers. After performing statistical correlation analysis, the dataset was split into training (80%) and testing (20%) subsets. Five machine learning models were developed, and the SHAP method was applied to the best-performing model to identify influential features. The results were obtained via 5-fold nested cross-validation, which identified the CatBoost model as the top performer, with AUC-ROC = 0.966, Accuracy = 0.947, and F1-Score = 0.951. SHAP (with a threshold of 0.01) highlighted the following significant features: Anti-CCP, tender joint count, swollen joint count, gastrointestinal issues, fatigue, age, RF (Rheumatoid Factor), and hearing problems. Due to the importance of early RA diagnosis and the challenges encountered in primary care, three main screening factors stand out: Anti-CCP, tender joint count, and swollen joint count. These, along with fatigue, age, and positive RF, markedly increase the likelihood of RA and justify referring a patient to a specialist.
Journal Article
Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data
The validity of results in race walking is often questioned due to subjective decisions in the detection of faults. This study aims to compare machine-learning algorithms fed with data gathered from inertial sensors placed on lower-limb segments to define the best-performing classifiers for the automatic detection of illegal steps. Eight race walkers were enrolled and linear accelerations and angular velocities related to pelvis, thighs, shanks, and feet were acquired by seven inertial sensors. The experimental protocol consisted of two repetitions of three laps of 250 m, one performed with regular race walking, one with loss-of-contact faults, and one with knee-bent faults. The performance of 108 classifiers was evaluated in terms of accuracy, recall, precision, F1-score, and goodness index. Generally, linear accelerations revealed themselves as more characteristic with respect to the angular velocities. Among classifiers, those based on the support vector machine (SVM) were the most accurate. In particular, the quadratic SVM fed with shank linear accelerations was the best-performing classifier, with an F1-score and a goodness index equal to 0.89 and 0.11, respectively. The results open the possibility of using a wearable device for automatic detection of faults in race walking competition.
Journal Article
When Ultrasonic Sensors and Computer Vision Join Forces for Efficient Obstacle Detection and Recognition
In the most recent report published by the World Health Organization concerning people with visual disabilities it is highlighted that by the year 2020, worldwide, the number of completely blind people will reach 75 million, while the number of visually impaired (VI) people will rise to 250 million. Within this context, the development of dedicated electronic travel aid (ETA) systems, able to increase the safe displacement of VI people in indoor/outdoor spaces, while providing additional cognition of the environment becomes of outmost importance. This paper introduces a novel wearable assistive device designed to facilitate the autonomous navigation of blind and VI people in highly dynamic urban scenes. The system exploits two independent sources of information: ultrasonic sensors and the video camera embedded in a regular smartphone. The underlying methodology exploits computer vision and machine learning techniques and makes it possible to identify accurately both static and highly dynamic objects existent in a scene, regardless on their location, size or shape. In addition, the proposed system is able to acquire information about the environment, semantically interpret it and alert users about possible dangerous situations through acoustic feedback. To determine the performance of the proposed methodology we have performed an extensive objective and subjective experimental evaluation with the help of 21 VI subjects from two blind associations. The users pointed out that our prototype is highly helpful in increasing the mobility, while being friendly and easy to learn.
Journal Article