Ye Wang

Ye Wang

Auto-generated profile, based on publicly available information

Ye Wang

Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2019 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
OOOzan Ozdenizci
Ozan Ozdenizci
YWYe Wang
Ye Wang
TKToshiaki Koike-Akino
Toshiaki Koike-Akino
DEDeniz Erdogmus
Deniz Erdogmus
Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or recording session specific variability within EEG. Furthermore, recent methods have mostly trained and evaluated based on single session EEG data. We address this problem from an invariant representation-learning perspective. We propose an adversarial inference approach to extend such deep learning models to learn session-invariant person-discriminative representations that can provide robustness in terms of longitudinal usability. Using adversarial learning within a deep convolutional network, we empirically assess and show improvements with our approach based on longitudinally collected EEG data for person identification from half-second EEG epochs.

4 February 2020 in IEEE Access
Verified
Journal Article
Open access
OOOzan Ozdenizci
Ozan Ozdenizci
YWYe Wang
Ye Wang
TKToshiaki Koike-Akino
Toshiaki Koike-Akino
DEDeniz Erdogmus
Deniz Erdogmus
Discovering and exploiting shared, invariant neural activity in electroencephalogram (EEG) based classification tasks is of significant interest for generalizability of decoding models across subjects or EEG recording sessions. While deep neural networks are recently emerging as generic EEG feature extractors, this transfer learning aspect usually relies on the prior assumption that deep networks naturally behave as subject- (or session-) invariant EEG feature extractors. We propose a further step towards invariance of EEG deep learning frameworks in a systemic way during model training. We introduce an adversarial inference approach to learn representations that are invariant to inter-subject variabilities within a discriminative setting. We perform experimental studies using a publicly available motor imagery EEG dataset, and state-of-the-art convolutional neural network based EEG decoding models within the proposed adversarial learning framework. We present our results in cross-subject model transfer scenarios, demonstrate neurophysiological interpretations of the learned networks, and discuss potential insights offered by adversarial inference to the growing field of deep learning for EEG.

1 February 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
IGIván Sanz Gorrachategui
Iván Sanz Gorrachategui
PPPablo Pastor-Flores
Pablo Pastor-Flores
MMilutin Pajovic
Milutin Pajovic
YWYe Wang
Ye Wang
POPhil Orlik
Phil Orlik
JAJesús Sergio Artal-Sevil
Jesús Sergio Artal-Sevil
The increasing deployment of battery storage applications in both grid storage and electric vehicle fields is generating a vast used battery market. These batteries are typically recycled but could be reused in second-life applications. One of the challenges is to obtain an accurate remaining useful life (RUL) estimation algorithm, which determines whether a battery is suitable for reuse and estimates the number of second-life cycles the battery will last. In this article, the RUL estimation problem is considered. We propose several health indicators (HIs), some of which have not been explored before, along with simple yet effective estimation and classification algorithms. These algorithms include classification techniques such as regularized logistic regression (RLR), and regression techniques such as multivariable linear regression (MLR) and multilayer perceptron (MLP). As a more advanced solution, a multiple expert system combining said techniques is proposed. The performance of the algorithms and features is evaluated on a recent lithium iron phosphate (LFP) data set from Toyota Research Institute. We obtain satisfactory results in the estimation of RUL cycles with errors down to 49 root mean square error (RMSE) cycles for cells that live up to 1200 cycles, and 0.24% mean relative error (MRE) for the prediction of the evolution of capacity.

8 January 2021 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
KKKeisuke Kojima
Keisuke Kojima
MTMohammad H Tahersima
Mohammad H Tahersima
TKToshiaki Koike-Akino
Toshiaki Koike-Akino
DJDevesh K. Jha
Devesh K. Jha
YTYingheng Tang
Yingheng Tang
KPKieran Parsons
Kieran Parsons
Deep learning is now playing a major role in designing photonic devices, including nanostructured photonics. In this paper, we investigate three models for designing nanophonic power splitters with multiple splitting ratios. The first model is a forward regression model, wherein the trained deep neural network (DNN) is used within the optimization loop. The second is an inverse regression model, in which the trained DNN constructs a structure with the desired target performance given as input. The third model is a generative network, which can randomly produce a series of optimized designs for a target performance. Focusing on the nanophotonic power splitters, we show how the devices can be designed by these three types of DNN models.

27 February 2020 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
TKToshiaki Koike-Akino
Toshiaki Koike-Akino
YWYe Wang
Ye Wang
DMDavid Millar
David Millar
KKKeisuke Kojima
Keisuke Kojima
KPKieran Parsons
Kieran Parsons
Recently, data-driven approaches motivated by modern deep learning have been applied to optical communications in place of traditional model-based counterparts. The application of deep neural networks (DNN) allows flexible statistical analysis of complicated fiber-optic systems without relying on any specific physical models. Due to the inherent nonlinearity in DNN, various equalizers based on DNN have shown significant potentials to mitigate fiber nonlinearity. In this paper, we propose a turbo equalization (TEQ) based on DNN as a new alternative framework to deal with nonlinear fiber impairments. The proposed DNN-TEQ is constructed with nested deep residual networks (ResNet) to train extrinsic likelihood given soft-information feedback from channel decoding. Through extrinsic information transfer (EXIT) analysis, we verify that our DNN-TEQ can accelerate decoding convergence to achieve a significant gain in achievable throughput by 0.61b/s/Hz. We also demonstrate that optimizing irregular low-density parity-check (LDPC) codes to match EXIT chart of the DNN-TEQ can improve achievable rates by up to 0.12 b/s/Hz.

11 July 2022 in Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Verified
Conference Paper
Closed access
ADAndac Demir
Andac Demir
TKToshiaki Koike-Akino
Toshiaki Koike-Akino
YWYe Wang
Ye Wang
DEDeniz Erdogmus
Deniz Erdogmus
Graph neural networks (GNN) are an emerging framework in the deep learning community. In most GNN applications, the graph topology of data samples is provided in the dataset. Specifically, the graph shift operator (GSO), which could be adjacency, graph Laplacian, or their normalizations, is known a priori. However we often have no knowledge of the grand-truth graph topology underlying real-world datasets. One example of this is to extract subject-invariant features from physiological electroencephalogram (EEG) to predict a cognitive task. Previous methods use electrode sites to represent a node in the graph and connect them in various ways to hand-engineer a GSO e.g., i) each pair of electrode sites is connected to form a complete graph, ii) a specific number of electrode sites are connected to form a k-nearest neighbor graph, iii) each pair of electrode site is connected only if the Euclidean distance is within a heuristic threshold. In this paper, we overcome this limitation by parameterizing the GSO using a multi-head attention mechanism to explore the functional neural connectivity subject to a cognitive task between different electrode sites, and simultaneously learn the unsupervised graph topology in conjunction with the parameters of graph convolutional kernels.