Article
Computer Science, Hardware & Architecture
Fernando D. S. Lima, Francisco Lucas F. Pereira, Iago C. Chaves, Javam C. Machado, Joao Paulo P. Gomes
Summary: Predicting failures in Hard Disk Drives (HDD) is a major challenge faced by industry and academia. Health degree prediction is a popular strategy, but practical details have been neglected in previous works. A framework based on Deep Recurrent Neural Networks (DRNN) was proposed, taking into account the ordinal nature of the problem and different costs associated with mis-classifications.
IEEE TRANSACTIONS ON COMPUTERS
(2021)
Article
Chemistry, Analytical
Tek Raj Chhetri, Anelia Kurteva, Jubril Gbolahan Adigun, Anna Fensel
Summary: Hard drive failure can lead to system crashes and data loss. Current studies on hard drive failure prediction mostly rely on machine learning, lacking context-awareness. Semantic technology provides context-awareness through knowledge graphs, but lacks the learning patterns and prediction capabilities of machine learning. This paper presents a method that combines the advantages of both machine learning and semantic technology, achieving higher accuracy in hard drive failure prediction.
Article
Computer Science, Hardware & Architecture
Qibo Yang, Xiaodong Jia, Xiang Li, Jianshe Feng, Wenzhe Li, Jay Lee
Summary: This article proposes an evaluation methodology to compare feature selection methods and anomaly detection algorithms for hard drive failure prediction. It can quickly select the optimal algorithms for a specific model of drives and achieve better performance than existing approaches in the literature.
IEEE TRANSACTIONS ON RELIABILITY
(2021)
Article
Computer Science, Information Systems
Jing Shen, Yongjian Ren, Jian Wan, Yunlong Lan
Summary: With the advancement of technology in daily life applications such as real-time video surveillance systems, mobile edge computing, and Internet of things (IoT), the reliability of these systems can be greatly affected due to hard disk drive (HDD) failures. This paper proposes an LSTM recurrent neural network-based HDD failure prediction model and a new health degree evaluation method, which demonstrates good prediction accuracy with low overhead in comprehensive experiments on two real-world hard drive datasets.
MOBILE INFORMATION SYSTEMS
(2021)
Article
Engineering, Civil
Kan Guo, Yongli Hu, Zhen Qian, Hao Liu, Ke Zhang, Yanfeng Sun, Junbin Gao, Baocai Yin
Summary: This paper introduces an optimized graph convolution recurrent neural network for traffic prediction, which can better explore the spatial and temporal information of traffic data and learns an optimized graph through a data-driven approach to reveal the latent relationship among road segments.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Arpit Kapoor, Anshul Negi, Lucy Marshall, Rohitash Chandra
Summary: Cyclone track forecasting is a critical climate science problem, and machine learning methods, especially recurrent neural networks (RNNs), have shown promise in this field. However, these methods often lack uncertainty quantification. This paper proposes variational RNNs, which approximate the posterior distribution of parameters by minimizing the KL-divergence loss, for cyclone track and intensity prediction. The results demonstrate that variational RNNs provide a good approximation with uncertainty quantification while maintaining prediction accuracy.
ENVIRONMENTAL MODELLING & SOFTWARE
(2023)
Article
Computer Science, Artificial Intelligence
Cheng Yang, Hao Wang, Jian Tang, Chuan Shi, Maosong Sun, Ganqu Cui, Zhiyuan Liu
Summary: This article proposes a novel full-scale diffusion prediction model based on reinforcement learning, which integrates macroscopic diffusion size information into the RNN-based microscopic diffusion model to address the non-differentiable problem. Experimental results demonstrate that our proposed model outperforms state-of-the-art baseline models in both microscopic and macroscopic diffusion predictions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Sana Arastehfar, Mohammadjavad Matinkia, Mohammad Reza Jabbarpour
Summary: This study introduces a novel neural network architecture combining Graph Convolutional Networks and Long Short-Term Memory networks for Short-Term Load Forecasting problem. The model captures spatial information from users without prior knowledge of their geographic location and does not rely on additional environmental variables, showing significant improvement compared to baseline models.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Yan Ding, Yunan Zhai, Yujuan Zhai, Jia Zhao
Summary: The text discusses the importance of predicting impending failure of hard disk drives to avoid data loss and service downtime, and introduces a novel prediction model called Dab based on deep Auto-coder and Big data learning for better HDD failure prediction. Dab aims to improve accuracy, performance, prediction earnings, and proactive fault tolerance, while reducing false alarm rate and maintenance cost, and enhancing failure detection rate, reliability, and robustness of large-scale storage systems.
CONNECTION SCIENCE
(2022)
Article
Engineering, Petroleum
Xuechen Li, Xinfang Ma, Fengchao Xiao, Cong Xiao, Fei Wang, Shicheng Zhang
Summary: Machine learning is effective for predicting fractured well production compared to conventional methods, but predicting multistep production remains challenging. To address this, we propose a framework based on bidirectional gated recurrent units and multitask learning, which improves prediction performance by sharing task-dependent representations among multiphase production prediction tasks.
Article
Engineering, Mechanical
Unnati Thakkar, Hicham Chaoui
Summary: This research utilizes machine learning to provide a prediction framework for the remaining useful life of an aircraft's turbofan engine. The proposed Deep Layer Recurrent Neural Network (DL-RNN) model demonstrates higher predictive accuracy compared to other machine learning algorithms.
Article
Engineering, Aerospace
Jill Platts, Michael Reale, John Marsh, Christopher Urban
Summary: As the star closest to Earth, the Sun's violent magnetism causing solar activities such as solar flares can be successfully predicted using recurrent neural networks (RNNs) and multivariate time series data.
JOURNAL OF THE ASTRONAUTICAL SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Hongsong Wang, Jian Dong, Bin Cheng, Jiashi Feng
Summary: This paper introduces a novel human motion prediction method PVRED, utilizing pose velocities and temporal positional information, outperforming current methods. It employs quaternion parameterization of poses, and a trainable QT layer, effectively predicting short-term and long-term human poses.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Engineering, Industrial
Koosha Marashi, Sahra Sedigh Sarvestani, Ali R. Hurson
Summary: Interdependence is a key feature in cyber-physical systems, where a trivial impairment in one part of the system can lead to a sequence of failures that collapse the entire system. This study uses correlation metrics and neural networks to identify interdependencies among components and predict imminent failures, aiming to help system operators take timely preventive actions.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Computer Science, Information Systems
Xie Jun, Zhao Xudong, Xu Xinying, Han Xiaoxia, Ren Jinchang, Li Xingbing
Summary: This study proposes two models, Recurrent Interaction Network (RIN) and Deep Recurrent Interaction Network (DRIN), for click-through rate prediction. Compared to existing methods, these models have significant advantages in modeling feature interactions and learning explicit interactions.
INFORMATION SCIENCES
(2022)