Treatment of Bone Marrow Cancer Based on Model Predictive Control

Salajegheh, Ehsan; Mojalal, Sepide; Ghahfarokhi, Ali Mojarrad

doi:10.31763/ijrcs.v1i4.481

Cited by 2 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proportional Integral Derivative (PID) controller has been known for its wide use in many control systems; hence, it also has been applied to control altitude in quadrotor [9] [10]. The other controller is Sliding Mode Control (SMC) [11], Linear Quadratic Regulator (LQR) [12][13], Predictive Control [14], Fuzzy Control [15] [16], Neural Network [17] [18], Fractional Order PID [19], Feedback Linearization [20], and other control techniques [21]. This research presented an application of the Integral State Feedback (ISF) controller for altitude control in quadrotor as a practical solution that enables a precise and robust control system performance.…”

Section: Introductionmentioning

confidence: 99%

Altitude Control of UAV Quadrotor Using PID and Integral State Feedback

Ma’arif,

Suwarno,

Nur’aini

et al. 2023

BIO Web Conf.

View full text Add to dashboard Cite

Applications of control techniques for stabilizing altitude in a UAV Quadrotor, along with a comprehensive performance comparison, are presented in this paper. The two compared control techniques are: a Proportional Integral Derivative (PID) and Integral State Feedback (ISF) controller. While PID control consists of a Proportional, an Integral and a Derivative Controller, the Integral State Feedback consists of an Integral and a State Feedback Controller. Each part of the control technique provides advantages and drawbacks in the controlled system performance. Numerical simulations in the research were performed on Simulink MATLAB to provide quantitative results in control performance comparison; thus, a quadrotor model was designed prior to the application of control techniques. Based on the numerical results, ISF control resulted in a better settling time with zero overshoot than PID. Meanwhile, the PID control had a better rise time with a big overshoot than ISF in its system response. Therefore, it can be concluded that the ISF Controller was better than PID regarding the settling time and the overshoot response.

show abstract

Section: Introductionmentioning

confidence: 99%

Altitude Control of UAV Quadrotor Using PID and Integral State Feedback

Ma’arif,

Suwarno,

Nur’aini

et al. 2023

BIO Web Conf.

View full text Add to dashboard Cite

show abstract

Leveraging Machine Learning Algorithms for Predictive Analysis of Early Bone Marrow Cancer Detection

Shah,

Singh,

Tiwari

2023

Social Development and Governance Innovations in Education, Technology and Management

View full text Add to dashboard Cite

For better patient outcomes and higher likelihood of a successful course of therapy, early identification of bone marrow cancer is essential. Machine learning algorithms have emerged as a promising tool for predictive analysis in various medical fields, and they hold great potential for enhancing the early detection of bone marrow cancer. This abstract discusses the significance of early detection, the challenges in diagnosing bone marrow cancer, and the role of machine learning algorithms in improving predictive analysis for this purpose. Bone marrow cancer, including leukemia and lymphoma, remains a significant global health concern. These malignancies originate in the bone marrow and can lead to the proliferation of abnormal blood cells. Early diagnosis is essential, as it allows for timely intervention and tailored treatment plans. However, diagnosing bone marrow cancer is a complex task, as the symptoms can be subtle and mimic other, less severe conditions. Traditional diagnostic methods often rely on bone marrow biopsies and peripheral blood smears, which can be invasive, time consuming, and occasionally inconclusive.Machine learning algorithms offer a transformative approach to early bone marrow cancer detection. These algorithms, a subset of artificial intelligence, are capable of processing and analyzing vast amounts of medical data, ranging from clinical records to genetic information. They can identify patterns and correlations that may not be evident to human clinicians, ultimately leading to more accurate and timely diagnoses. Traditionally, cancer detection has relied on pretrained convolutional neural networks and conventional machine learning methods that analyze features extracted from medical images. However, a novel approach for bone marrow cancer detection has emerged, utilizing raw DNA sequences combined with state-of-the-art sentence transformers like SBERT and SimCSE. The results have shown promise, with one machine learning model achieving the highest accuracy. This innovative methodology, while in its early stages, presents a unique and potentially valuable avenue for early bone marrow cancer detection, highlighting the evolving role of machine learning in transforming cancer diagnostics beyond traditional imaging methods.In conclusion, early detection of bone marrow cancer is a critical factor in improving patient outcomes and increasing the chances of successful treatment. Machine learning algorithms offer a promising avenue for enhancing predictive analysis in this domain. By harnessing the power of these algorithms to analyze complex medical data, healthcare providers can improve the accuracy and timeliness of bone marrow cancer diagnosis, leading to more effective treatment strategies. Nevertheless, overcoming challenges related to data quality, ethics, and transparency is crucial for the successful integration of machine learning in the early detection of bone marrow cancer.The potential benefits, however, make it a compelling field of research and development in the ongoing battle against this devastating disease.

show abstract

Treatment of Bone Marrow Cancer Based on Model Predictive Control

Cited by 2 publications

References 23 publications

Altitude Control of UAV Quadrotor Using PID and Integral State Feedback

Altitude Control of UAV Quadrotor Using PID and Integral State Feedback

Leveraging Machine Learning Algorithms for Predictive Analysis of Early Bone Marrow Cancer Detection

Contact Info

Product

Resources

About