Dipti Srinivasan

Dhivya Dharshini Kannan, Anupam Trivedi, Dipti Srinivasan

Data centers account for significant global energy consumption and a carbon footprint. The recent increasing demand for edge computing and AI advancements drives the growth of data center storage capacity. Energy efficiency is a cost-effective way to combat climate change, cut energy costs, improve business competitiveness, and promote IT and environmental sustainability. Thus, optimizing data center energy management is the most important factor in the sustainability of the world. Power Usage Effectiveness (PUE) is used to represent the operational efficiency of the data center. Predicting PUE using Neural Networks provides an understanding of the effect of each feature on energy consumption, thus enabling targeted modifications of those key features to improve energy efficiency. In this paper, we have developed Bidirectional Gated Recurrent Unit (BiGRU) based PUE prediction model and compared the model performance with GRU. The data set comprises 52,560 samples with 117 features using EnergyPlus, simulating a DC in Singapore. Sets of the most relevant features are selected using the Recursive Feature Elimination with Cross-Validation (RFECV) algorithm for different parameter settings. These feature sets are used to find the optimal hyperparameter configuration and train the BiGRU model. The performance of the optimized BiGRU-based PUE prediction model is then compared with that of GRU using mean squared error (MSE), mean absolute error (MAE), and R-squared metrics.

H M Dipu Kabir, Moloud Abdar, Seyed Mohammad Jafar Jalali et al.

Deep neural networks (DNNs) have achieved the state of the art performance in numerous fields. However, DNNs need high computation times, and people always expect better performance in a lower computation. Therefore, we study the human somatosensory system and design a neural network (SpinalNet) to achieve higher accuracy with fewer computations. Hidden layers in traditional NNs receive inputs in the previous layer, apply activation function, and then transfer the outcomes to the next layer. In the proposed SpinalNet, each layer is split into three splits: 1) input split, 2) intermediate split, and 3) output split. Input split of each layer receives a part of the inputs. The intermediate split of each layer receives outputs of the intermediate split of the previous layer and outputs of the input split of the current layer. The number of incoming weights becomes significantly lower than traditional DNNs. The SpinalNet can also be used as the fully connected or classification layer of DNN and supports both traditional learning and transfer learning. We observe significant error reductions with lower computational costs in most of the DNNs. Traditional learning on the VGG-5 network with SpinalNet classification layers provided the state-of-the-art (SOTA) performance on QMNIST, Kuzushiji-MNIST, EMNIST (Letters, Digits, and Balanced) datasets. Traditional learning with ImageNet pre-trained initial weights and SpinalNet classification layers provided the SOTA performance on STL-10, Fruits 360, Bird225, and Caltech-101 datasets. The scripts of the proposed SpinalNet are available at the following link: https://github.com/dipuk0506/SpinalNet

Noelle Y. L. Wong, Eng Yeow Cheu, Zhonglin Chiam et al.

Conflicting objectives present a considerable challenge in interleaving multi-task learning, necessitating the need for meticulous design and balance to ensure effective learning of a representative latent data space across all tasks without mutual negative impact. Drawing inspiration from the concept of marginal and conditional probability distributions in probability theory, we design a principled and well-founded approach to disentangle the original input into marginal and conditional probability distributions in the latent space of a variational autoencoder. Our proposed model, Deep Disentangled Interleaving Variational Encoding (DeepDIVE) learns disentangled features from the original input to form clusters in the embedding space and unifies these features via the cross-attention mechanism in the fusion stage. We theoretically prove that combining the objectives for reconstruction and forecasting fully captures the lower bound and mathematically derive a loss function for disentanglement using Naïve Bayes. Under the assumption that the prior is a mixture of log-concave distributions, we also establish that the Kullback-Leibler divergence between the prior and the posterior is upper bounded by a function minimized by the minimizer of the cross entropy loss, informing our adoption of radial basis functions (RBF) and cross entropy with interleaving training for DeepDIVE to provide a justified basis for convergence. Experiments on two public datasets show that DeepDIVE disentangles the original input and yields forecast accuracies better than the original VAE and comparable to existing state-of-the-art baselines.

Hamzeh Asgharnezhad, Afshar Shamsi, Roohallah Alizadehsani et al.

Deep neural networks (DNNs) have been widely applied for detecting COVID-19 in medical images. Existing studies mainly apply transfer learning and other data representation strategies to generate accurate point estimates. The generalization power of these networks is always questionable due to being developed using small datasets and failing to report their predictive confidence. Quantifying uncertainties associated with DNN predictions is a prerequisite for their trusted deployment in medical settings. Here we apply and evaluate three uncertainty quantification techniques for COVID-19 detection using chest X-Ray (CXR) images. The novel concept of uncertainty confusion matrix is proposed and new performance metrics for the objective evaluation of uncertainty estimates are introduced. Through comprehensive experiments, it is shown that networks pertained on CXR images outperform networks pretrained on natural image datasets such as ImageNet. Qualitatively and quantitatively evaluations also reveal that the predictive uncertainty estimates are statistically higher for erroneous predictions than correct predictions. Accordingly, uncertainty quantification methods are capable of flagging risky predictions with high uncertainty estimates. We also observe that ensemble methods more reliably capture uncertainties during the inference.

Roohallah Alizadehsani, Mohamad Roshanzamir, Sadiq Hussain et al.

Understanding data and reaching valid conclusions are of paramount importance in the present era of big data. Machine learning and probability theory methods have widespread application for this purpose in different fields. One critically important yet less explored aspect is how data and model uncertainties are captured and analyzed. Proper quantification of uncertainty provides valuable information for optimal decision making. This paper reviewed related studies conducted in the last 30 years (from 1991 to 2020) in handling uncertainties in medical data using probability theory and machine learning techniques. Medical data is more prone to uncertainty due to the presence of noise in the data. So, it is very important to have clean medical data without any noise to get accurate diagnosis. The sources of noise in the medical data need to be known to address this issue. Based on the medical data obtained by the physician, diagnosis of disease, and treatment plan are prescribed. Hence, the uncertainty is growing in healthcare and there is limited knowledge to address these problems. We have little knowledge about the optimal treatment methods as there are many sources of uncertainty in medical science. Our findings indicate that there are few challenges to be addressed in handling the uncertainty in medical raw data and new models. In this work, we have summarized various methods employed to overcome this problem. Nowadays, application of novel deep learning techniques to deal such uncertainties have significantly increased.

Afshar Shamsi Jokandan, Hamzeh Asgharnezhad, Shirin Shamsi Jokandan et al.

The early and reliable detection of COVID-19 infected patients is essential to prevent and limit its outbreak. The PCR tests for COVID-19 detection are not available in many countries and also there are genuine concerns about their reliability and performance. Motivated by these shortcomings, this paper proposes a deep uncertainty-aware transfer learning framework for COVID-19 detection using medical images. Four popular convolutional neural networks (CNNs) including VGG16, ResNet50, DenseNet121, and InceptionResNetV2 are first applied to extract deep features from chest X-ray and computed tomography (CT) images. Extracted features are then processed by different machine learning and statistical modelling techniques to identify COVID-19 cases. We also calculate and report the epistemic uncertainty of classification results to identify regions where the trained models are not confident about their decisions (out of distribution problem). Comprehensive simulation results for X-ray and CT image datasets indicate that linear support vector machine and neural network models achieve the best results as measured by accuracy, sensitivity, specificity, and AUC. Also it is found that predictive uncertainty estimates are much higher for CT images compared to X-ray images.

H M Dipu Kabir, Abbas Khosravi, Abdollah Kavousi-Fard et al.

The neural network (NN)-based direct uncertainty quantification (UQ) methods have achieved the state of the art performance since the first inauguration, known as the lower-upper-bound estimation (LUBE) method. However, currently-available cost functions for uncertainty guided NN training are not always converging and all converged NNs are not generating optimized prediction intervals (PIs). Moreover, several groups have proposed different quality criteria for PIs. These raise a question about their relative effectiveness. Most of the existing cost functions of uncertainty guided NN training are not customizable and the convergence of training is uncertain. Therefore, in this paper, we propose a highly customizable smooth cost function for developing NNs to construct optimal PIs. The optimized average width of PIs, PI-failure distances and the PI coverage probability (PICP) are computed for the test dataset. The performance of the proposed method is examined for the wind power generation and the electricity demand data. Results show that the proposed method reduces variation in the quality of PIs, accelerates the training, and improves convergence probability from 99.2% to 99.8%.

Anupam Trivedi, Kunal Pal, Chiranjib Saha et al.

The unit commitment (UC) problem is a nonlinear, high-dimensional, highly constrained, mixed-integer power system optimization problem and is generally solved in the literature considering minimizing the system operation cost as the only objective. However, due to increasing environmental concerns, the recent attention has shifted to incorporating emission in the problem formulation. In this paper, a multi-objective evolutionary algorithm based on decomposition (MOEA/D) is proposed to solve the UC problem as a multi-objective optimization problem considering minimizing cost and emission as the multiple objec- tives. Since, UC problem is a mixed-integer optimization problem consisting of binary UC variables and continuous power dispatch variables, a novel hybridization strategy is proposed within the framework of MOEA/D such that genetic algorithm (GA) evolves the binary variables while differential evolution (DE) evolves the continuous variables. Further, a novel non-uniform weight vector distribution strategy is proposed and a parallel island model based on combination of MOEA/D with uniform and non-uniform weight vector distribution strategy is implemented to enhance the performance of the presented algorithm. Extensive case studies are presented on different test systems and the effectiveness of the proposed hybridization strategy, the non-uniform weight vector distribution strategy and parallel island model is verified through stringent simulated results. Further, exhaustive benchmarking against the algorithms proposed in the literature is presented to demonstrate the superiority of the proposed algorithm in obtaining significantly better converged and uniformly distributed trade-off solutions.