The vehicle routing problem with stochastic demand (VRPSD) is a well known NP-hard problem. The uncharacteristic behaviour associated with the problem enhances the computational efforts required to obtain a feasible and near-optimal solution. This paper proposes an algorithm portfolio methodology based on evolutionary algorithms, which takes into account the stochastic nature of customer demand to solve this computationally complex problem. These problems are well known to have computationally complex objective functions, which make their solutions hard to find, particularly when problem instances of large dimensions are considered. Of particular importance in such situations is the timeliness of the solution. For example, Apple was forced to delay their shipments of iPads internationally due to unprecedented demand and issues with their delivery systems in Samsung Electronics and Seiko Epson. Such examples illustrate the importance of stochastic customer demands and the timing of delivery. Moreover, most of the evolutionary algorithms, known for providing computationally efficient solutions, are unable to always provide optimal or near optimal solutions to all the VRPSD instances within allocated time interval. This is due to the characteristic variations in the computational time taken by evolutionary algorithms for same or varying size of the VRPSD instances. Therefore, this paper presents portfolios of different evolutionary algorithms to reduce the computational time taken to resolve the VRPSD. Moreover, an innovative concept of the mobility allowance (MA) in landmoves based on the levy's distribution function has been introduced to cope with real situations existing in vehicle routing problems. The proposed portfolio approach has been evaluated for the varying instances of the VRPSD. Experiments have been performed on varying dimensions of the VRPSD instances to validate the different properties of the algorithm portfolio. An illustrative example is presented to show that the set of metaheuristics allocated to certain number of processors (i.e., algorithm portfolio) performed better than their individual metaheuristics.

No abstract

A rare disease is any disease that affects a very small percentage (1 in 1,500) of population. It is estimated that there are nearly 7,000 rare disease affecting 30 million patients in the U. S. alone. Most of the patients suffering from rare diseases experience multiple misdiagnoses and may never be diagnosed correctly. This is largely driven by the low prevalence of the disease that results in a lack of awareness among healthcare providers. There have been efforts from machine learning researchers to develop predictive models to help diagnose patients using healthcare datasets such as electronic health records and administrative claims. Most recently, transformer models have been applied to predict diseases BEHRT, G-BERT and Med-BERT. However, these have been developed specifically for electronic health records (EHR) and have not been designed to address rare disease challenges such as class imbalance, partial longitudinal data capture, and noisy labels. As a result, they deliver poor performance in predicting rare diseases compared with baselines. Besides, EHR datasets are generally confined to the hospital systems using them and do not capture a wider sample of patients thus limiting the availability of sufficient rare dis-ease patients in the dataset. To address these challenges, we introduced an extension of the BERT model tailored for rare disease diagnosis called RareBERT which has been trained on administrative claims datasets. RareBERT extends Med-BERT by including context embedding and temporal reference embedding. Moreover, we introduced a novel adaptive loss function to handle the class imbal-ance. In this paper, we show our experiments on diagnosing X-Linked Hypophosphatemia (XLH), a genetic rare disease. While RareBERT performs significantly better than the baseline models (79.9% AUPRC versus 30% AUPRC for Med-BERT), owing to the transformer architecture, it also shows its robustness in partial longitudinal data capture caused by poor capture of claims with a drop in performance of only 1.35% AUPRC, compared with 12% for Med-BERT and 33.0% for LSTM and 67.4% for boosting trees based baseline.

No abstract