multi-objective optimization
در نشریات گروه پزشکی-
Background
Mammography is the most fundamental and widely used method for detecting breast abnormalities. Distinguishing malignant from benign lesions requires extracting relevant information, which can be challenging and timeconsuming for radiologists. Computer-aided diagnosis (CAD) techniques can serve as complementary diagnostic tools, assisting radiologists in the early detection and analysis of abnormalities in mammograms.
ObjectivesThis study aimed to propose a CAD system for extracting significant features of abnormalities in breast mammograms using Curvelet transform and fractal analysis, and classifying breast tumors as malignant or benign based on the calculated features. Patients and
MethodsIn this study, an efficient feature extraction method was applied, utilizing Curvelet transform and fractal analysis, on a dataset comprising 113 abnormal images from the Mammographic Image Analysis Society (MIAS) database, which included 62 benign and 51 malignant cases. The method yielded 575 features, but due to potential irrelevance or redundancy, a multi-objective optimization (MOO) approach based on a genetic algorithm (GA) for an artificial neural network (ANN), named GA-MOO-ANN, was proposed to obtain and focus on an optimal and effective feature set. As a result of this approach, a set of 17 efficient features was extracted. The proposed algorithm was implemented in MATLAB 2014a, and the performance metrics were calculated using 6-fold cross-validation.
ResultsThe experimental results demonstrated exceptional performance, with an accuracy (Acc) of 98.2%, specificity (Sp) of 100%, sensitivity (Se) of 96.8%, positive predictive value (PPV) of 100%, negative predictive value (NPV) of 96.2%, and an impressive area under the curve (AUC) of 0.98, providing comparable results to other recent methods.
ConclusionThe current findings suggest that the proposed method could be a valuable tool for breast cancer diagnosis, potentially reducing the number of unnecessary breast biopsies. This method may lead to more efficient patient evaluation and earlier detection of breast tumors.
Keywords: Breast Cancer, Curvelet Transform, Multi-Objective Optimization, Artificial Neural Network -
مقدمه
با توجه به اهمیت خون به عنوان یک عنصر حیاتی در سیستم سلامت، در این پژوهش، زنجیره تامین خون در سه سطح اهداکنندگان، بانک ها (مراکز خون) و بیمارستان ها در قالب یک مدل چندهدفه به منظور حداقل سازی مجموع هزینه ها، حداقل سازی زمان کلی ارسال واحدهای خونی و حداقل سازی میزان تقاضای برآورد نشده بیمارستان ها در هر دوره، مدل سازی شده است.
روش پژوهشپژوهش حاضر از نظر هدف، کاربردی، از نظر روش توصیفی و از نوع کمی است. داده های مورد نیاز برای پیاده سازی مساله واقعی در سال 1400 با مراجعه به دفتر منطقه ای سازمان انتقال خون استان تهران و با همکاری سیستم نگاره گردآوری شده است. با توجه به ماهیت Np-hard مساله، مدل پیشنهادی با استفاده از سه الگوریتم ژنتیک، NSGAII و MOPSO در نرم افزار گمز حل شده است.
یافته هادر مدل پیشنهادی، تطابق گروه های خونی در تامبن تقاضا، سیستم صف، تخصیص گروه های خونی در آزمایشگاه ها و بانک های خون، هدر رفت خون در آزمایشگاه، انتقال محصولات بین مراکز تقاضا و نیز پارامترهای حساس و تعیین کننده ای مدل مانند؛ پارامتر تقاضا، اهدای خون و زمان حمل محصولات خونی بین اجزای شبکه، به صورت غیرقطعی در نظر گرفته شده است. یافته ها نشان می دهند که در اجرای مسایل 3، 7، 10 و 12 برای شاخص کیفیت الگوریتم MOPSO دارای عملکرد مناسب تری است، اما به طور کلی و بر اساس دفعات اجرا و همچنین میانگین آنها، الگوریتم NSGA-II عملکرد بهتری دارد.
نتیجه گیریبر اساس نتایج، مدل ارایه شده منجر به کاهش مجموع هزینه ها، زمان کلی ارسال واحدهای خونی و میزان تقاضای برآورد نشده بیمارستان ها می شود.
کلید واژگان: بهینه سازی چند هدفه، شبکه تامین فرآورده های خونی، رویکرد هیبریدی، الگوریتم فرا ابتکاریIntroductionDue to the importance of blood as a vital element in the health system, in this study, the blood supply chain is modeled at three levels of donors, banks (blood centers) and hospitals in the form of a multi-objective model to minimize total costs, total delivery time of blood units and non-estimated demand of hospitals in each period.
MethodsThe present study is applied in terms of purpose and descriptive and quantitative in terms of method. The data needed to implement the real problem in 2021 have been collected by through the regional office of the Tehran blood transfusion organization along with the Negareh system. Due to the Np-hard nature of the problem, the proposed model is solved using three algorithms of GA, NSGA-II and MOPSO in GAMS software.
ResultsIn the proposed model, matching the blood type in meeting demand; blood type delivery and allocation system in laboratories and blood banks, blood wasting in laboratory, transfer of products between demand centers, sensitive and determinative parameters of the model such as; demand, blood donation and delivery time of blood products between network components are considered indefinitely. The findings show that the MOPSO algorithm has a better performance in problems 3, 7, 10 and 12 for the QM index, but generally, based on running times and their average, the NSGA-II algorithm is better.
ConclusionBased on the results, the proposed model leads to a reduction in total costs, total delivery time of blood units and unapproved demand of hospitals.
Keywords: Multi-objective optimization, Blood product supply network, hybrid approach, Meta-Heuristic Algorithm -
Background and Objective
Blood as a vital element of the health system has an important role in this system, because any blood deficient results in death. Blood supply chain management aims to bridge the gap between blood donors and consumers. This results in no blood deficient, and minimization of, the corruption of blood products and lower costs. Humanitarian supply chain includes planning, managing activities related to materials, information, and finances when providing relief to affected people
MethodThe purpose of this study is to optimize the sustainable humanitarian supply chain of blood products in Tehran. In this study, a five-echelon blood supply chain network is presented that includes donors, mobile, fixed and regional blood collection centers, and hospitals. This study proposed a multi objective mixed integer linear programming optimization model considering economic, environment and social objectives. Due to the uncertain and random nature of blood supply and demand and cost parameters, the model develops into a robust optimization model. The ε-constraint method is used to transform the multi-objective problem into a single-objective mode. The model is coded in GAMS and solved by CPLEX solver.
ResultsThe model outputs include allocate blood donor to mobile and fixed blood collection centers, allocate fixed and mobile blood centers to regional blood centers, and allocate regional blood centers to hospitals. The application of the proposed model is investigated in a case problem in Tehran where real data is utilized to design a network for emergency supply of blood during potential disasters. The results indicate robust model is more efficient in controlling demand, supply and costs uncertainties. At ω = 100 the supply chain cost reaches to $51746 and unmet blood demand is zero under any earthquake scenario and, the supply chain is robust in all scenarios.
ConclusionThe proposed robust optimization model is useful for managers, as well as researchers, who have studied location–allocation of facilities in the blood supply chain network in post-disaster periods. To provide some managerial perspectives for the aforementioned problem, a sensitivity analysis has been performed. Important practical implications were drawn from the case study results. We showed how solution robustness (supply chain cost) can be balanced against model robustness (unmet demand). As the value of risk aversion weight, increases, the total cost indicating solution robustness increases, while the blood unmet demand indicating model robustness decreases. Finally results analysis, concluding remarks and directions for further research are presented.
Keywords: Sustainability, blood supply chain, humanitarian supply chain, robust optimization, Uncertainty, Multi objective Optimization -
مقدمه
گسترش روزافزون زندگی شهری یکی از چالش های بنیادی در مدیریت شهری چگونگی دفع پسماند است.موادزاید جامد شهری یکی از مشکلات عمده دولت ها و برنامه ریزان شهری در سراسر جهان به ویژه در شهرهای ساحلی است.هدف پژوهش طراحی الگوریتم برنامه ریزی خطی پیشرفته محل دفن پسماند شهرهای ساحلی با نگرش برریسک های بهداشت ایمنی و محیط زیست است.
روش بررسیپژوهش حاضر بصورت کیفی است. بهینه سازی چند هدفه با ارزیابی سه ریسک بهداشت، ایمنی و محیط زیست، یک مدل ریاضی را ارایه می کند. اطلاعات نخست با استفاده از مصاحبه و تحلیل کیفی، داده گردآوری و سپس در مرحله دوم تحلیل با استفاده از برنامه ریزی خطی مدل ارایه شده است.
یافته هادر ارزیابی ریسک سایت دفن پسماند نتایج ارایه شده محاسباتی را می توان دریافت که مدل های پایدار نسبت به مدل های قطعی جواب های نامطلوب ارایه می نمایند. که این موضوع امری طبیعی می باشد چراکه در مدل های پایدار بدترین حالت جهت رسیدن به جواب بهینه در نظر گرفته شده و از این رو جواب های حاصل همواره نسبت به مدل های قطعی نامطلوب می باشند.
نتیجه گیریهمواره با تحلیل ارزیابی ریسک در سایت دفن پسماند علل حوادث و عوارض ناشی از کار در این مکان اعمال ناایمن یا شرایط ناایمن و غیر بهداشتی است،در حقیقت کوشش برای ایجاد و بهبود شرایط بهداشتی، ایمنی و زیست محیطی محل های دفن پسماند شهر بندرعباس و افزایش اعتماد پذیری، ثابت نمود که این دو عامل علل ثانویه حوادث می باشند ودلایل ریشه ای را می توان در نقص سیستم مدیریت سایت دفن پسماند دانست.
کلید واژگان: ارزیابی ریسک HSE، بهینه سازی چند هدفه، دفن پسماند، شهرهای ساحلیTolooe Behdasht, Volume:20 Issue: 3, 2021, PP 88 -100IntroductionThe increasing development of urban life is one of the fundamental challenges in urban management of waste disposal. Solid municipal waste is one of the major problems of governments and urban planners worldwide, especially in coastal cities. This study aimed to design of an advanced linear planning algorithm for coastal landfills with a focus on safety, health, and environmental risks.
MethodThis is a qualitative study. Multi-objective optimization presents a mathematical model by evaluating the three risks of health, safety, and environment. First, the data were collected using interviews and qualitative analysis, and then in the second stage, the analysis was presented using model linear planning.
ResultsIn the risk assessment of the landfill site, the presented computational results can be found that stable models provide unfavorable answers compared to definitive models. This is a natural issue; since in stable models, the worst case scenario is considered to achieve the optimal solution, and therefore the resulting answers are always unfavorable compared to the definitive models.
ConclusionBy analyzing the risk assessment at the landfill site, the causes of accidents and complications resulting from work in this place include unsafe practices or unsafe and unsanitary conditions. In fact, trying to create and improve health, safety, and environmental conditions of landfills in Bandar Abbas city and the increase in reliability confirmed that these two factors are the secondary causes of accidents. The root causes can be considered as a defect in the management system of the landfill site.
Keywords: HSE risk assessment, multi-objective optimization, landfill, coastal cities -
Background
The development of virtual human models has recently gained considerable attention in biomechanical studies intending to design for ergonomics. The computer-based simulations of virtual human models can reduce the time and cost of the design cycle. There is an increasing interest in finding the realistic posture of the human body with applications in prototype design and reduction of injuries in the workplace.
ObjectivesThis paper presents a generic method based on a multi-objective optimization (MOO) for posture prediction of a sagittal-plane lifting task.
MethodsImproved biomechanical models are used to formulate the predicted posture as a MOO problem. The lifting task has been defined by seven performance measures that are mathematically represented by the weighted sum of cost functions. Specific weights are assigned for each cost function to predict both stoop and squat type postures. Some inequality constraints have been used to ensure that the virtual human does not assume a completely unrealistic configuration.
ResultsThe method can predict the hand configuration effectively. Simulations reveal that predicting a squat posture requires the minimization of certain objective functions, while these measures are less significant for the prediction of a stooped posture.
ConclusionsIn this study, a MOO-based posture prediction model with a validation process is presented. We employed a three-dimensional model to evaluate the applicability of using a combination of seven performance measures to the posture prediction of symmetric lifting tasks. Results have been compared with the available empirical data to validate the simulated postures. Furthermore, the assigned weights are obtained for a range of percentiles from 50% male to 90% female according to the postures obtained by 3D SSPPTM software.
Keywords: Validation, Lifting, Posture Prediction, Multi-Objective Optimization
- نتایج بر اساس تاریخ انتشار مرتب شدهاند.
- کلیدواژه مورد نظر شما تنها در فیلد کلیدواژگان مقالات جستجو شدهاست. به منظور حذف نتایج غیر مرتبط، جستجو تنها در مقالات مجلاتی انجام شده که با مجله ماخذ هم موضوع هستند.
- در صورتی که میخواهید جستجو را در همه موضوعات و با شرایط دیگر تکرار کنید به صفحه جستجوی پیشرفته مجلات مراجعه کنید.