Early diagnosis of Alzheimers disease and its prodromal stage, also known as mild cognitive impairment (MCI), is critical since some patients with progressive MCI will develop the disease. We propose a multi-stream deep convolutional neural network fed with patch-based imaging data to classify stable MCI and progressive MCI. First, we compare MRI images of Alzheimers disease with cognitively normal subjects to identify distinct anatomical landmarks using a multivariate statistical test. These landmarks are then used to extract patches that are fed into the proposed multi-stream convolutional neural network to classify MRI images. Next, we train the architecture in a separate scenario using samples from Alzheimers disease images, which are anatomically similar to the progressive MCI ones and cognitively normal images to compensate for the lack of progressive MCI training data. Finally, we transfer the trained model weights to the proposed architecture in order to fine-tune the model using progressive MCI and stable MCI data. Experimental results on the ADNI-1 dataset indicate that our method outperforms existing methods for MCI classification, with an F1-score of 85.96%.

Resource leveling problem is an attractive field of research in project management. Traditionally, a basic assumption of this problem is that network activities could not be split. However, in real-world projects, some activities can be interrupted and resumed in different time intervals but activity splitting involves some cost. The main contribution of this paper lies in developing a practical algorithm for resource leveling in large-scale projects. A novel hybrid genetic algorithm is proposed to tackle multiple resource-leveling problems allowing activity splitting. The proposed genetic algorithm is equipped with a novel local search heuristic and a repair mechanism. To evaluate the performance of the algorithm, we have generated and solved a new set of network instances containing up to 5,000 activities with multiple resources. For small instances, we have extended and solved an existing mixed integer programming model to provide a basis for comparison. Computational results demonstrate that, for larg...