International Transactions in Operational Research最新文献

Parkinson's disease (PD) is a neurological condition that occurs in nearly 1% of the world's population. The disease is manifested by a sharp drop in dopamine production, resulting from the death of the related producing cells in an area of the midbrain called the substantia nigra. Early diagnosis and accurate staging of the disease are essential to apply the appropriate therapeutic approaches to slow cognitive and motor decline. At present, there is not a singular blood test or biomarker accessible for diagnosing PD or monitoring the progression of its symptoms. Clinical professionals identify the disease by assessing the symptoms, which, however, may vary from case to case, as well as their progression speed. Magnetic resonance imaging (MRIs) have been used for the past three decades to diagnose and distinguish between PD and other neurological conditions.

However, to the best of our knowledge, no neural network models have been designed to identify the disease stage. This paper aims to fill this gap. Using the “Parkinson's Progression Markers Initiative” dataset, which reports the patient's MRI and an indication of the disease stage, we developed a model to identify the level of progression. The images and the associated scores were used for training and assessing different deep learning models. Our analysis distinguished four distinct disease progression levels based on a standard scale (Hoehn and Yah scale). The final architecture consists of the cascading of a 3D-CNN network, adopted to reduce and extract the spatial characteristics of the MRI for efficient training of the successive LSTM layers, aiming at modeling the temporal dependencies among the data. Before training the model, the patient's MRI is preprocessed to correct acquisition errors by applying image registration techniques, to extract irrelevant content from the image, such as nonbrain tissue (e.g., skull, neck, fat). We also adopted template-based data augmentation techniques to obtain a balanced dataset about progression classes. Our results show that the proposed 3D-CNN + LSTM model achieves state-of-the-art results by classifying the elements with 91.90 as macro averaged OVR AUC on four classes.

In this work, new mixed integer nonlinear optimization models are proposed for two clustering problems: the unitary weighted Weber problem and the minimum sum of squares clustering. The proposed formulations are convex quadratic models with linear and second-order cone constraints that can be efficiently solved by interior point algorithms. Their continuous relaxation is convex and differentiable. The numerical experiments show the proposed models are more efficient than some classical models for these problems known in the literature.

QUBO (quadratic unconstrained binary optimization) has become the modeling language for quantum annealing and quantum-inspired annealing solvers. We present different approaches in QUBO for the magic square problem and the quadratic assignment problem (QAP), which can be modeled by linear equations and a permutation constraint over integer variables. Different ways of encoding integers by Booleans in QUBO amount to models, the implementation of which could have very different performance. Experiments performed on the Fixstars Amplify Annealer Engine, a quantum-inspired annealing solver, show that, compared to the classical one-hot encoding, using unary encoding for integers performs slightly better for the QAP and much better for magic square.

The $�p$-median problem has been widely studied in the literature. However, there are several variants that include new constraints to the classical problem that make it more realistic. In this work, we study the variant that considers interconnected facilities, that is, the distances between each pair of facilities are less than or equal to a certain threshold $�r$. This optimization problem, usually known as the median location problem with interconnected facilities, consists of locating a set of interconnected facilities to minimize the distance between those interconnected facilities and the demand points. The large variety of real-world applications that fit into this model makes it attractive to design an algorithm able to solve the problem efficiently. To this end, a procedure based on the variable neighborhood search methodology is designed and implemented by using problem-dependent neighborhoods. Experimental results show that our proposal is able to reach most of the optimal solutions when they are known. Additionally, it outperforms previous state-of-the-art methods in those instances where the optima are unknown. These results are further confirmed by conducting nonparametrical statistical tests.