Classifying the status of NSCLC PD-L1 on chest CT is a cost-effective and non-invasive method. The existing multiple instance learning (MIL) methods are not effective for this task, due to the lack of an efficient feature encoder for 3D instances and ignoring the importance of representative instance selection. Thus, they cannot capture weak visual cues related to PD-L1 status on CT images. To address this, we propose a 2.5D top-K ranked multiple instance learning method. We design a 2.5D instance feature encoder, which takes advantage of knowledge from a 2D pre-trained model and has trainable parameters to learn information for 3D instances. In addition, we design a top-K ranked multiple instance learning strategy, which fully exploits the bag-level labels to select representative instances to eliminate the effect of atypical instances and guide the network to learn effective information. We demonstrate that our method can not only outperform state-of-the-art MIL methods on the PD-L1 status classification but also generalize well on a COVID-19 classification task.

Many privacy-preserving multidimensional data aggregation (PPMDA) schemes have been proposed to safeguard user privacy and provide aggregated real-time data for the control center (CC) to optimize power allocation in the smart grid. However, without Trusted Authority (TA), existing PPMDA schemes cannot simultaneously provide lightweight encryption, achieve fault tolerance, and resist collusion attacks between fog nodes and CC. To address these issues, we propose a fault-tolerant and privacy-enhanced multidimensional data aggregation scheme without TA (FPMDA) based on fog computing. Specifically, the Chinese Remainder Theorem is leveraged to enhance the efficiency of multidimensional data processing, and an innovative dual-masking approach is introduced to ensure the security of data aggregation. In addition, employing the homomorphic property of the (t, k)-threshold secret sharing algorithm, we design a data aggregation method that enhances security and fault tolerance, making it resilient against insider attacks. Finally, compared with existing schemes, FPMDA not only significantly enhances privacy preservation while maintaining required security properties but also achieves low computational and communication load, demonstrating practicality for resource-constrained smart meters.

Massive multidimensional health data collected from Internet of Things (IoT) devices are driving a new era of smart health, and with it come privacy concerns. Privacy-preserving data aggregation (PDA) is a proven solution providing statistics while hiding raw data. However, existing PDA schemes ignore the willingness of data owners to share, so data owners may refuse to share data. To increase their willingness to contribute data, we propose an OPtional dimEnsional pRivacy-preserving data Aggregation scheme(OPERA)to provide data contributors with options on sharing dimensions while keeping their choices and data private. OPERA uses selection vectors to represent the decisions of users and count participants dimensionally and achieves data privacy and utility based on a multisecret sharing method and symmetric homomorphic cryptography. Analyses show that in OPERA, the probability of adversaries breaching privacy is less than 4.68e-97. Performance evaluations demonstrate that OPERA is outstanding in computation and practical in communication.

In smart grids (SG), data aggregation is widely used to strike a balance between data usability and privacy protection. The fault tolerance is an important requirement to improve the robustness of data aggregation protocols, which enables normal execution of the protocols even with failures on some entities. However, to achieve fault tolerance, most schemes either sacrifice the aggregation accuracy due to the use of differential privacy or substitution strategy or need to rely on an online trusted entity to manage all user blinding factors. In this paper, a ( k,n ) threshold privacy-preserving data aggregation scheme named ( k,n )-PDA is proposed, which reconciles data usability and data privacy through the BGN cryptosystem and achieves fault tolerance with accurate aggregation using Shamir’s secret sharing without any online trusted entity. Besides, our scheme supports the efficient changing of users’ membership. Specifically, the dynamic secrete key is distributed to n smart meters (SMs) through the threshold secret sharing algorithm. When k or more meters participate in the aggregation, the data service center (DSC) can reconstruct the key to compute the aggregate results, and less than k SMs cannot recover the key. Thus, our solution still works functionally even if up to n−k SMs fail; also, it resists attacks from the collusion of less than k SMs. Moreover, system and performance analyses demonstrate that our scheme achieves privacy, fault tolerance, and membership dynamics with high efficiency.

To fit for the demand of extending the power, increasing maintainability and improving performance, a SVG with parallel independent DC capacitance converter modules is presented. In respect that the parameter difference among converters, reactive power of total output sharing has to be resolved. By analyzing the parallel converter mathematics model with DQ analytic transformation, a new control strategy is proposed, which is based on double close-loop decoupling control, reactive power balance current sharing. To reduce tracking error of current, source voltage in d-q coordinators feed forward method is adopted. Active and reactive current, and DC voltage controller is designed. Further, for the purpose of reducing switch frequency of single module, CPS-SPWM is employed to operate the equipment. A based on double FPGA-DSP controller is devised, and a 2Mvar platform is carried out. The simulation and practical performance of SVG are given. The validity and feasibility of the method is demonstrated by the results and the industrial application.

Service hosting platforms typically run a large number of third-party applications that are composed of multiple communicating components distributed on a dynamic set of hosting servers. Understanding the real-time behaviors of these applications and the intricate interactions/dependency relationships among these application components is very important to service management tasks such as load balancing, capacity planning, performance debugging and fault diagnosis. In this paper, we present the scalable real-time application monitoring and diagnosis (SRAMD) tool, for applications consisting of "black box" components: software without source code available, and usually without desired logging instrumentation. SRAMD runs at application layer and requires no modification to existing applications, middleware, or messages. For each application component collocated at its hosting server, a SRAMD monitor traces the component's packet-level traffic unobtrusively, summarizes its local resource utilization and performance (e.g. response time) online, performs interactive queries (e.g. per- request resource utilization) to locate possible bottlenecks on- demand, and discovers inter-component dependence relationships statistically. The SRAMD controller simply aggregates reports from distributed monitors to construct real-time application topologies with rich runtime information. We have developed mechanisms to decentralize the computation overhead and minimize the communication cost in the monitoring and diagnosis process, and two schemes to discover application component dependency relationships in different scenarios. The SRAMD tool offers an alternative to server logs and message-level traces for service monitoring and performance diagnosis.

To use heterogeneous and geographically distributed resources as a platform for parallel visualization is an intriguing topic of research. This is because of the immense potential impact of the work, and also because of its use of a full range of challenging technologies. In this work, we designed an execution environment for visualization of massive scientific datasets, using network functional units (NFU) for processing power, logistical networking for storage management and visualization cookbook library (vcblib) for visualization operations. This environment is based solely on computers distributed across the Internet that are owned and operated by independent institutions, while being openly shared for free. Those Internet computers are inherently of heterogeneous hardware configuration and running a variety of operating systems. Using 100 such processors, we have been able to obtain the same level of performance offered by a 64-node cluster of 2.2 GHz P4 processors, while processing a 75GBs subset of a cutting-edge simulation dataset. Due to its inherently shared nature, this execution environment for data-intensive visualization could provide a viable means of collaboration among geographically separated users.

We are interested in developing the infrastructural tools that allow a distributed data intensive computing environment to be shared by a group of collaborating but geographically separated researchers in an interactive manner, as opposed to a batch mode of operation. However, without advanced reservation, it is difficult to assure a certain level of performance on a large number of shared and heterogeneous servers. To achieve scalable parallel speedups in this scenario, we must closely integrate the management of computation and runtime data movement. In this paper, we first define the canonical scheduling problem for datasets distributed with k-way replication in the wide area. We then develop a dynamic co-scheduling algorithm that integrates the scheduling of computation and data movement. Using time-varying visualization as the driving application, we demonstrate that our co-scheduling approach improves not only application performance but also server utilization at a very reasonable cost.

To effectively share computation resources over the wide area network among a variety of data intensive applications, a scalable computation service needs to be provisioned. The end-to-end principles provide a scalable approach to the architecture of shared services on which these applications depend. We have shown the use of a best-effort network storage service, the Internet Backplane Protocol (IBP), for scalable data sharing by applying the end-to-end principles. This paper explores a way to scalable network computation by adhering to the end-to-end principles and discusses the costs to achieve scalability in our design