A retrospective study using machine learning to develop predictive model to identify urinary infection stones in vivo.

Preoperative diagnosis of urinary infection stones is difficult, and accurate detection of stone composition can only be performed ex vivo. To provide guidance for better perioperative management and postoperative prevention of infection stones, we developed a machine learning model for preoperative identification of infection stones in vivo. The clinical data of patients with urolithiasis who underwent surgery in our hospital from January 2011 to December 2015 and January 2017 to December 2021 were retrospectively analyzed. A total of 2565 patients were included in the study, and 1168 eligible patients with urinary calculi were randomly divided into training set (70%) and test set (30%). Five machine learning algorithms (Support Vector Machine (SVM), Multilayer Perceptron (MLP), Decision Tree (DT), Random Forest Classifier (RFC), and Adaptive Boost (AdaBoost)) and 14 preoperative variables were used to construct the prediction model. The performance measure was the area under the receiver operating characteristic curve (AUC) of the validation set. The importance of 14 features in each prediction model for predicting infection stones was analyzed. A total of 89 patients (5.34%) with infection stones were included in the validation set. All the five prediction models showed strong discrimination in the validation set (AUC: 0.689-0.772). AdaBoost model was selected as the final model (AUC: 0.772(95% confidence interval, 0.657-0.887); Sensitivity: 0.522; Specificity: 0.902), UC positivity, and urine pH value were two important predictors of infection stones. We developed a predictive model through machine learning that can quickly identify infection stones in vivo with good predictive performance. It can be used for risk assessment and decision support of infection stones, optimize the disease management of urinary calculi and improve the prognosis of patients.

Design and Implementation of a Central-Controllable and Secure Multicast System Based on Universal Identifier Network.

With the rapid increase of network users and services, the breadth and depth of Internet have greatly changed. The mismatch between current network requirements and original network architecture design has spurred the evolution or revolution of Internet to remedy this gap. Lots of research projects on future network architecture have been launched, in which Universal Identifier Network (UIN) architecture that is based on the identifier/location separation, access/core separation and control/forwarding separation can provide better mobility, security and reliability. On the other hand, the demand of group communication has increased due to the fine-grained network services and successive booming of new applications such as IoT (Internet of Things). Most of current multicast schemes are based on the open group model with open group membership (multicast only care the multicast group state, not the group member) and open access to send/receive multicast data, which are beneficial to multicast routing for its simplification. However, the open group membership makes the group member management difficult to be realized, and open access may result in lots of security vulnerabilities such as Denial of service (DoS), eavesdropping and masquerading, which make deployment more difficult. Therefore, in this paper we propose a Central-Controllable and Secure Multicast (CCSM) system based on the UIN architecture, and redesign the multicast service procedures including registration, join/leave, multicast routing construction and update with objective to achieve better mobility support, security, scalability and controllable. More specifically, we design a new group management scheme to perform the multicast members join/leave with authentication and a central-controllable multicast routing scheme to provide a secure way to set up multicast entries on routers. The CCSM inherits the characteristics of UIN in terms of mobility and security, and it can provide the centralized multicast routing computation and distributes the multicast routing into forwarders. We compare CCSM with Protocol Independent Multicast-Sparse Mode (PIM-SM), and the results show that CCSM reduces the multicast join delay, and performs better than PIM-SM in term of reconstruction cost under low multicast density.

Peering strategic game models for interdependent ISPs in content centric Internet.

Emergent content-oriented networks prompt Internet service providers (ISPs) to evolve and take major responsibility for content delivery. Numerous content items and varying content popularities motivate interdependence between peering ISPs to elaborate their content caching and sharing strategies. In this paper, we propose the concept of peering for content exchange between interdependent ISPs in content centric Internet to minimize content delivery cost by a proper peering strategy. We model four peering strategic games to formulate four types of peering relationships between ISPs who are characterized by varying degrees of cooperative willingness from egoism to altruism and interconnected as profit-individuals or profit-coalition. Simulation results show the price of anarchy (PoA) and communication cost in the four games to validate that ISPs should decide their peering strategies by balancing intradomain content demand and interdomain peering relations for an optimal cost of content delivery.