Concurrency and Computation

Chen, Lei

doi: 10.1002/cpe.8079pmid: N/A

Computer assisted medical diagnosis technology is widely used in the field of medical assistance to assist doctors in making diagnostic decisions. But as the number of patients increases, the diagnostic pressure on doctors gradually increases, and more efficient computer‐aided medical diagnosis technology is needed to improve the accuracy of doctors' diagnosis. Today's computer‐based medically assisted diagnostic technologies suffer from the inability to fully simulate physical attributes and environmental factors, the large computational resources required for high‐precision models, the need for professional training for user operation, and the limited intuition for innovative design. For improving diagnostic efficiency, this study designs a medical Question answering intelligent interaction system in view of artificial intelligence algorithms. The system is constructed with an active interactive intelligent Q&A model consisting of a medical reasoning module and a medical examination recommendation module. Then, it uses local Bayesian network algorithm as the foundation to establish an intelligent strategy optimization network. And it puts forward the answer selection model of medical Question answering in view of hierarchical interaction for natural language processing tasks in the medical context. The performance test results show that when the diagnostic end threshold of the medical reasoning module is 0.8, the shortest diagnostic path is 3.33. When the diagnostic threshold is 0.85, the maximum length of the diagnostic path is 4.66, and the maximum difference between the diagnostic paths is 1.33, which is basically not affected by the diagnostic end threshold. The local Bayesian network algorithm can reduce the impact of noise features and extract more valuable information. The accuracy of the multilevel interactive answer selection model on the Stanford Natural Language Inference dataset without using external resources reached 89.2%. The ablation test results show that the overall accuracy of the model is 89.64%. The visualization results of the attention weight distribution test between interaction layers show that under different levels of interaction, the attention distribution will undergo significant changes.

Nie, Chenfei; Zhou, Zhipeng; Dong, Mianxiong; Ota, Kaoru; Li, Qiang

doi: 10.1002/cpe.8110pmid: N/A

Deep learning has shown its great potential in real‐world applications. However, users(clients) who want to use deep learning applications need to send their data to the deep learning service provider (server), which can make the client's data leak to the server, resulting in serious privacy concerns. To address this issue, we propose a protocol named EPIDL to perform efficient and secure inference tasks on neural networks. This protocol enables the client and server to complete inference tasks by performing secure multi‐party computation (MPC) and the client's private data is kept secret from the server. The work in EPIDL can be summarized as follows: First, we optimized the convolution operation and matrix multiplication, such that the total communication can be reduced; Second, we proposed a new method for truncation following secure multiplication based on oblivious transfer and garbled circuits, which will not fail and can be executed together with the ReLU activation function; Finally, we replace complex activation function with MPC‐friendly approximation function. We implement our work in C++ and accelerate the local matrix computation with CUDA support. We evaluate the efficiency of EPIDL in privacy‐preserving deep learning inference tasks, such as the time to execute a secure inference on the MNIST dataset in the LeNet model is about 0.14 s. Compared with the state‐ofthe‐art work, our work is 1.8×$$ \times $$–98×$$ \times $$ faster over LAN and WAN, respectively. The experimental results show that our EPIDL is efficient and privacy‐preserving.

Menguc, Kenan; Yilmaz, Alper

doi: 10.1002/cpe.8082pmid: N/A

The quality of the solution in resolving a complex network depends on either the speed or accuracy of the results. While some health studies prioritize high performance, fast algorithms are favored in scenarios requiring rapid decision‐making. A comprehensive understanding of the problem necessitates a detailed analysis of the network and its individual components. Betweenness Centrality (BC) and Closeness Centrality (CC) are commonly employed measures in network studies. This study introduces a new strategy to compute BC and CC that assesses their sensitivity in the scale space while measuring the shortest path. The scale space is generated by incorporating a scale parameter that is shown to achieve up to 60% performance improvements for various datasets. The study provides in‐depth insights into the importance of the scale space analysis. Finally, a flexible measurement tool is provided that is suitable for various types of problems. To demonstrate the flexibility and applicability, we experimented with two methods for 10 different graphs using the proposed approach.

Sun, Dawei; Wang, Yueru; Sui, Jialiang; Gao, Shang; Rong, Jia; Buyya, Rajkumar

doi: 10.1002/cpe.8085pmid: N/A

An effective scheduling strategy is critical for achieving better performance in real‐time stream processing systems. How to quickly and efficiently process real‐time data stream is always challenging, especially when clusters are collaborating in a Geo‐Distributed computing environment. To address these challenges, we propose an elastic scheduling strategy with Latency Constraints in Geo‐Distributed stream computing environments called Lc‐Stream. This article discusses our work from the following aspects: (1) An optimized data stream redirection method that is proposed based on queuing network algorithm, along with a computing resource model, a latency constrained scheduling model and a communication energy consumption model. (2) An updated node selection method based on the inter‐layer task correlation, to reduce the communication latency between groups at the executor granularity. (3) A network cluster distribution for Geo‐Distributed computing environment to ensure energy saving under low transmission latency. Experimental results show that compared to R‐Storm, Lc‐Stream reduces total latency by over 19% and increases throughput by over 37% in typical cross‐domain multi‐task topologies. Compared to Ts‐Stream, Lc‐Stream also reduces total latency by over 15% and increases throughput by over 21%. At the same time, it helps to balance the load among the systems and avoid overuse of compute nodes.

Toor, Rashmeet; Chana, Inderveer

doi: 10.1002/cpe.8065pmid: N/A

Food is one of the most underrated entities with respect to diseases. Food or Diet plays a vital role in healing or recovery of a patient which brings forth the need of analyzing disease and diets associations. The study of such associations is crucial for recommending appropriate diets to patients but is an arduous task due to the complex interdependencies as is evident in literature. Thus, it becomes necessary to automate the analysis and make it available as a service. The main aim of this work is to efficiently collate and analyze disease‐diet associations and provide it as an accessible and adaptable service using a combination of advanced techniques. Complex disease‐diet interdependencies are curated from the literature and transformed into a network offering various parameters for further analysis. The analysis is done using machine learning algorithms to predict accurate and robust recommendations. Cloud computing aids this analysis by providing sufficient resources and making it more accessible. Thus, the recommendations are constructed using amalgamation of techniques including network analysis, machine learning, and cloud computing. The deduced associations from the analysis of medical data using these technologies would aid doctors and healthcare institutions in decision making thereby improving the prognosis of a disease.

Shekhawat, Hema; Gupta, Daya Sagar

doi: 10.1002/cpe.8080pmid: N/A

The present scenario witnesses “the second quantum revolution,” which has enabled the development of revolutionary novel quantum tools. Quantum computing endeavors to establish higher computing standards that can potentially solve complex structures. Post‐quantum cryptography (PQC) has emerged as one of the new domains of cryptography, which is resilient to quantum attacks owing to the revolution in quantum computing. To ensure quantum security, the lattice‐based cryptosystem (LB‐cryptosystem) is one of the promising tools of PQC to address quantum‐based threats. The traditional security algorithms, such as RSA and Diffie–Hellman (DH), are strong enough to resist present security threats. However, it has been predicted that quantum technologies have the capability to break the security of most traditional algorithms whose security is based on prime factorization and DH‐type hard problems. Therefore, research is currently focused on addressing the security and privacy threats by using LB‐cryptosystems to secure various applications, organizations' data, and information infrastructure in the quantum era. The purpose of this article is to investigate recent advances in LB‐cryptosystems that may allow the design of secure models for smart‐grid networks (SGNs) against existing and future quantum attacks. SGNs have been explored as the bi‐directional assimilation of communication in terms of electricity generation, transmission, allocation, and utilization. This survey provides a comprehensive overview of LB‐cryptosystems, as well as their potential applications in securing SGNs. Lastly, the article summarizes the various PQC primitives, NIST selected algorithms, open‐source tools along with their packages, and various PQC industrial initiatives, and also compares traditional cryptographic schemes with other PQC.

Jiang, Hao; Yu, Qizhou; Han, Dan; Chen, Yaqing; Li, Zejun

doi: 10.1002/cpe.8095pmid: N/A

In the rapidly developing field of unmanned aerial vehicle (UVA) technology, solving local optimal problems and achieving efficient smooth planning are crucial for improving the operational efficiency and safety of UVA systems. To address these needs, our study introduces a novel optimization algorithm, called IWPA‐APF, which aims to improve path planning efficiency. This algorithm is a fusion of the artificial potential field (APF) method and the improved wolf‐pack algorithm (IWPA) to solve common problems such as local optima and inefficient planning in the path planning process. The IWPA‐APF algorithm improves search efficiency and accuracy by incorporating an adaptive step size that significantly refines the key behaviors of the traditional IWPA, which is based on the wolf pack algorithm (WPA). In addition, the algorithm incorporates specific planning constraints, such as turn angles and tolerance limits, to minimize getting stuck in local optima. The process involves generating initial plans through multiple iterations of the IWPA, followed by further refinement using the method of integrating APF's repulsive force field. Simulation results show that the IWPA‐APF algorithm outperforms traditional methods, offering shorter flight distances and improved safety, thereby establishing itself as a robust solution for UAV path planning in obstacle‐rich environments.

Sonti, Nagaraju; Mulpuri Santhi Sri, Rukmini; Pamulapati, Venkatappa Reddy

doi: 10.1002/cpe.8090pmid: N/A

In recent years, social network analysis has received a lot of interest. A critical area of research in this field is link prediction. Link prediction is researched for other forms of social networks. Still, because social link networks (SLNs) change over time and depend on the discussed topics, this network has unique difficulties. Recent studies have focused on three main issues: extending link prediction to a dynamic environment, forecasting formation, and destroying network linkages that change over time. Although it is a challenging issue, deep learning (DL) techniques have been demonstrated to increase prediction accuracy significantly. This research proposes a novel approach to link correlation for social networks based on DL architectures in feature vector prediction and classification. Here the input data has been processed for smoothening and normalization with noise removal. Then, the feature vector was predicted using a dynamically structured convolutional radial basis neural network for this data. The expected feature vector has been classified using a stochastic gradient‐based graph neural network. The experimental analysis is carried out for various social network data in terms of accuracy of 98%, precision of 85%, recall of 86%, F‐1 score of 75%, AUC of 72%, and RMSE of 76%.

Keller Tesser, Rafael; Marques, Alvaro; Borin, Edson

doi: 10.1002/cpe.8104pmid: N/A

Cloud computing has become popular for training deep‐learning (DL) models, avoiding the costs of acquiring and maintaining on‐premise systems. SageMaker is a cloud service that automates the execution of DL workloads. Its features include automatic hyperparameter optimization and use of spot instances. Nonetheless, it does not assist in selecting the right instance type for a workload. In public clouds, rent price depends on the configuration of the chosen instance type. Advanced and faster instances are typically more expensive, but not always the best choice. To select the optimal instance type, users must compare the workload's relative performance (and hence cost) on several candidates. Building on the execution profiles of multiple DL applications, we model the performance and cost of training DL applications on SageMaker and propose a lightweight technique to estimate these at low temporal and monetary cost. This method is a performance proxy that can be used to replace more expensive performance measurement procedures. So, it could speed up any technique that relies on such measurements. We show how it can help cloud customers seeking suitable instance types to train DL models, and that it can accurately predict the performance of different instance types when training these models on SageMaker.

doi: 10.1002/cpe.7791pmid: N/A