The diffusion tensor imaging (DTI) based Alzheimer's disease (AD) classification consists of the region of interest-based methods, voxel-based methods, and fiber tracer map-based methods. However, most of the studies utilize partial information of the DTI data. It is difficult to discover most discriminative biomarkers. To address this problem, this paper proposes a novel AD classification method based on 3D convolutional neural networks (3D-CNN) with multi-scale information fusion in order to uncover the differential features of AD. First, the significant voxels of anisotropy score and mean dispersion rate for each individual are extracted using Tract-Based Spatial Statistics (TBSS) method from the skeleton. Second, the texture and intensity features are extracted by utilizing radiomics method. Third, an improved 3D convolutional neural network is proposed to extract depth features from the fractional anisotropy (FA) and mean diffusivity (MD) images. Finally, the multi-scale features are linearly fused and select with LASSO algorithm. The support vector machine is utilized for five-fold cross-validation. The experimental results on the ADNI dataset with 185 DTI images containing AD and normal controls (NC) subjects show that the proposed method achieves better classification performance compared with existing methods for the AD assist diagnosis task.

Automatic methods that count the number of living bodies is extremely valuable for modern farms. Recently, there are an increasing number of studies conducted on imagery based automatic object counting. However, these studies suffer from extreme overlap of objects, scene perspective, the size of instances and etc. Moreover, real-time performance needs to be met in many application scenarios. In this study, we propose a video imagery based pipeline for real-time accurate object counting on smart farms. Firstly, we introduce the concept - overlap degree of a frame (ODF). Next, an end-to-end frame filtering algorithm based on ODF is established. Then, we propose an object detection and counting algorithm based on Faster region-based convolutional neural networks (Faster RCNN). Finally, the counting results are fused to accurately obtain the number of detected objects. The experimental results demonstrate that our proposed method can automatically and accurately count the living bodies on farms in real-time. In our experiments, the average speed of detection is 40 frames per second, and the total difference is 1.69%. Therefore, our method is considered to be a suitable tool to conduct automatic object counting on smart farms.

In this work, we propose a novel methodology that can be used to assess the relative popularity for any Internet application based on the data servers it uses. The basic idea is to infer popularity of data servers by periodically "poking" at local Domain Name servers (LDNSs) that service Domain Name System requests from a set of users running Internet applications and determining if LDNSs have cached resource records for the data servers. This approach allows us to measure the relative percentage of pokes that result in a cache hit as a coarse measure of the relative popularity of a particular data server among the users of a given LDNS. In addition, the time-to-live (TTL) of cached DNS resource records can be used to measure the gaps in time when a resource record for a data server is not cached. The cache gaps can be used to infer request interarrivals for more popular data servers.The methodology can be applied to any Internet application that uses distinguished server names and performs DNS lookups on these names as part of application use. The methodology can be used to collect usage information from any LDNS that accepts DNS queries. As example applications of the methodology, we evaluate the relative popularity of selected Web sites and the relative popularity of different Web servers serving content at a given Web site. We also apply the methodology to servers providing multimedia content, data servers for grid computing, and network game servers. We use data gathered from LDNSs of commercial and educational sites as well as Internet Service Providers serving both commercial and home customers.

Article Share on N for the price of 1: bundling web objects for more efficient content delivery Authors: Craig E. Wills Computer Science Dept., Worcester Polytechnic Institute, Worcester, MA Computer Science Dept., Worcester Polytechnic Institute, Worcester, MAView Profile , Mikhail Mikhailov Computer Science Dept., Worcester Polytechnic Institute, Worcester, MA Computer Science Dept., Worcester Polytechnic Institute, Worcester, MAView Profile , Hao Shang Computer Science Dept., Worcester Polytechnic Institute, Worcester, MA Computer Science Dept., Worcester Polytechnic Institute, Worcester, MAView Profile Authors Info & Claims WWW '01: Proceedings of the 10th international conference on World Wide WebMay 2001 Pages 257–265https://doi.org/10.1145/371920.372061Published:01 April 2001Publication History 19citation478DownloadsMetricsTotal Citations19Total Downloads478Last 12 Months3Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access