Blogs

Short Term and Medium Term Forecasting of Household Power Consumption

- Gagandeep Kaur

Problem Statement:

Electric energy is a precious and indispensable resource. The mismanagement of its utilization can lead to a fall in the supply of electricity. It is therefore imperative that everybody should be concerned about the efficient use of energy in order to reduce consumption [1]. Management of power allocation and distribution as well as analyzing the consumption of electric power will become more significant as we move towards planning of Smart Cities. The purpose of this project was to find a model to forecast the electricity consumption in a household and to find the more suitable forecasting period whether it should be in daily, weekly, fortnightly, or monthly. A number of forecasting models were analyzed for this time series data including Random Forests with Auto Regression, AutoReg, ARIMA, and SARIMAX Model. Finally, the performance of a two step prediction where two forecasting models were used in sequence was also checked.

Read complete blog here

.

Beyond Random Sampling: Achieving Stable AI Explanations with the EAGLE Framework:

-Sumedha Chugh

Building trust in AI requires making "black-box" models transparent, but today's most popular post-hoc explanation methods share a critical flaw: they rely on random sampling that leads to unstable, fluctuating explanations. To solve this, we developed Expected Active Gain for Local Explanations (EAGLE). EAGLE reimagines how we unveil the model's reasoning by leveraging active learning. Rather than randomly probing the model, EAGLE intelligently queries the exact data points that maximize information gain, directly shrinking the surrogate model's epistemic uncertainty, without losing focus on the specific prediction at hand. Backed by rigorous mathematical guarantees for sample complexity, our framework drastically outperforms state-of-the-art baselines by delivering highly stable explanations, faster convergence, and tighter confidence intervals across both image and tabular datasets. Ultimately, EAGLE offers a robust, principled path forward for truly trustworthy Explainable AI.

Read complete paper here

.