More Like this

1. A Data-driven Action Recommender System for Power System Operations using Deep Convolutional Neural Networks

   Bogodorova, Tetiana; Osipov, Denis; Vanfretti, Luigi (December 2025, ResearchGate, DOI: 10.13140/RG.2.2.33102.52802)

   The paper proposes an approach for data generation and action recommender system development when small-signal stability assessment is performed using deep learning algorithms. These algorithms are trained on labeled time-series data solving a classification task. In this paper we propose an approach that includes automatically generated labeled data for the action recommender and the deep learning methodology to implement the recommender framework. The deep learning methodology is based on convolutional neural networks (ResNet, Encoder, Time-LeNet) that are tuned for time-series input data and shown the best performance in comparison to other architectures. The proposed approach is validated on synthetic but realistic measurement data from the IEEE 9-bus system as a reference and further applied to a 769-bus system representing a region in the U. S. Eastern Interconnection. The performance of the method is evaluated using accuracy as a most common machine learning metric, as well as precision and recall. We show that the evaluation of the methodology on the generated imbalanced data has to be treated with additional metrics other than accuracy. The training time and the classification performance time is evaluated. 

   more » « less
2. Multi-Level Feature Abstraction from Convolutional Neural Networks for Multimodal Biometric Identification

   https://doi.org/10.1109/ICPR.2018.8545061  

   Soleymani, Sobhan; Dabouei, Ali; Kazemi, Hadi; Dawson, Jeremy; Nasrabadi, Nasser M. (August 2018, International Conference on Pattern Recognition (ICPR))

   In this paper, we propose a deep multimodal fusion network to fuse multiple modalities (face, iris, and fingerprint) for person identification. The proposed deep multimodal fusion algorithm consists of multiple streams of modality-specific Convolutional Neural Networks (CNNs), which are jointly optimized at multiple feature abstraction levels. Multiple features are extracted at several different convolutional layers from each modality-specific CNN for joint feature fusion, optimization, and classification. Features extracted at different convolutional layers of a modality-specific CNN represent the input at several different levels of abstract representations. We demonstrate that an efficient multimodal classification can be accomplished with a significant reduction in the number of network parameters by exploiting these multi-level abstract representations extracted from all the modality-specific CNNs. We demonstrate an increase in multimodal person identification performance by utilizing the proposed multi-level feature abstract representations in our multimodal fusion, rather than using only the features from the last layer of each modality-specific CNNs. We show that our deep multi-modal CNNs with multimodal fusion at several different feature level abstraction can significantly outperform the unimodal representation accuracy. We also demonstrate that the joint optimization of all the modality-specific CNNs excels the score and decision level fusions of independently optimized CNNs. 

   more » « less
3. Structural health monitoring using extremely compressed data through deep learning

   https://doi.org/10.1111/mice.12517  

   Azimi, Mohsen; Pekcan, Gokhan (November 2019, Computer-Aided Civil and Infrastructure Engineering)

   Abstract This study introduces a novel convolutional neural network (CNN)‐based approach for structural health monitoring (SHM) that exploits a form of measured compressed response data through transfer learning (TL)‐based techniques. The implementation of the proposed methodology allows damage identification and localization within a realistic large‐scale system. To validate the proposed method, first, a well‐known benchmark model is numerically simulated. Using acceleration response histories, as well as compressed response data in terms of discrete histograms, CNN models are trained, and the robustness of the CNN architectures is evaluated. Finally, pretrained CNNs are fine‐tuned to be adaptable for three‐parameter, extremely compressed response data, based on the response mean, standard deviation, and a scale factor. The performance of each CNN implementation is assessed using training accuracy histories as well as confusion matrices, along with other performance metrics. In addition to the numerical study, the performance of the proposed method is demonstrated using experimental vibration response data for verification and validation. The results indicate that deep TL can be implemented effectively for SHM of similar structural systems with different types of sensors. 

   more » « less
4. Fast Cascading Outage Screening based on Deep Convolutional Neural Network and Depth-First Search

   https://doi.org/10.1109/TPWRS.2020.2969956  

   Du, Yan; Li, Fangxing Fran; Zheng, Tongxin; Li, Jiang (July 2020, IEEE Transactions on Power Systems)

   In this paper, a data-driven method is proposed for fast cascading outage screening in power systems. The proposed method combines a deep convolutional neural network (deep CNN) and a depth-first search (DFS) algorithm. First, a deep CNN is constructed as a security assessment tool to evaluate system security status based on observable information.With its automatic feature extraction ability and the high generalization, a well-trained deep CNN can produce estimated AC optimal power flow (ACOPF) results for various uncertain operation scenarios, i.e., fluctuated load and system topology change, in a nearly computation-free manner. Second, a scenario tree is built to represent the potential operation scenarios and the associated cascading outages. The DFS algorithm is developed as a fast screening tool to calculate the expected security index value for each cascading outage path along the entire tree, which can be a reference for system operators to take predictive measures against system collapse. The simulation results of applying the proposed deep CNN and the DFS algorithm on standard test cases verify their accuracy, and the computational efficiency is thousands of times faster than the model-based traditional approach, which implies the great potential of the proposed algorithm for online applications. 

   more » « less
5. IMCE: Energy-efficient bit-wise in-memory convolution engine for deep neural network

   https://doi.org/10.1109/ASPDAC.2018.8297291  

   Angizi, Shaahin; He, Zhezhi; Parveen, Farhana; Fan, Deliang (January 2018, 2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC))

   In this paper, we pave a novel way towards the concept of bit-wise In-Memory Convolution Engine (IMCE) that could implement the dominant convolution computation of Deep Convolutional Neural Networks (CNN) within memory. IMCE employs parallel computational memory sub-array as a fundamental unit based on our proposed Spin Orbit Torque Magnetic Random Access Memory (SOT-MRAM) design. Then, we propose an accelerator system architecture based on IMCE to efficiently process low bit-width CNNs. This architecture can be leveraged to greatly reduce energy consumption dealing with convolutional layers and also accelerate CNN inference. The device to architecture co-simulation results show that the proposed system architecture can process low bit-width AlexNet on ImageNet data-set favorably with 785.25μJ/img, which consumes ~3× less energy than that of recent RRAM based counterpart. Besides, the chip area is ~4× smaller. 

   more » « less