A low-cap power budget is challenging for exascale computing. Dynamic Voltage and Frequency Scaling (DVFS) and Uncore Frequency Scaling (UFS) are the two widely used techniques for limiting HPC application's energy footprint. ...

Widely adapted locally interpretable methods such as LIME [20] and SHAP [12] fail to capture the underlying causal relationships between the variables. They merely capture the linear and non-linear associations. These ...

With the increase in demand for enterprise wi- , there is a growing need to understand the functioning of these networks. Large scale Wi-Fi deployment is a challenging task. There is a need to diagnose network related ...

In an era where the volume of data sets for a particular topic keeps increasing, it is necessary to have quality checks on the data to keep it relevant to modern learning algorithms. Quality parameters provide an objective ...

In buildings, air conditioning consumes a significant proportion of the aggregate electricity bill. Specifically, in residential and small-scale commercial buildings, people prefer to use room-level ACs (AC stands for Air ...

The cryo-electron microscopy (cryo-EM) technique captures 2D projections of biological structures, revealing their inherent Heterogeneity arising from structural flexibility, conformational changes, and distinct functional ...

Current wireless applications such as autonomous driving, UAVs, IOT devices, etc. generate massive amounts of data that can be utilized to train machine learning models for decision making. Privacy, security and bandwidth ...

Lipid homeostasis refers to the balance of the levels of various lipids, such as fats and cholesterol, within cells and organisms. This balance is crucial for many physiological functions. Disruptions to lipid homeostasis, ...

The traditional way of clustering is first extracting the feature vectors according to domain-specific knowledge and then employing a clustering algorithm on the extracted features. Deep learning approaches attempt to ...

Currently there are three basic frameworks in deep learning - stacked autoencoders (SAE), deep belief network (DBN) and convolutional neural network (CNN); SAE and DBN can be applied to arbitrary inputs but CNN can only ...