The climate of Houston, classified as a humid subtropical climate with tropical influences, makes the heating, ventilation, and air conditioning (HVAC) systems the largest electricity consumers in buildings. HVAC systems in commercial buildings are usually operated by a centralized control system and/or an energy management system based on a fixed schedule and scheduled control of a zone setpoint, which is not appropriate for many buildings with changing occupancy rates. Lately, as part of energy efficiency analysis, attention has focused on collecting and analyzing smart meters and building-related data, as well as applying supervised learning techniques, to propose new strategies to operate HVAC systems and reduce energy consumption. On the other hand, unsupervised learning techniques have been used to study the consumption information and profile characterization of different buildings after cluster analysis is performed. This paper adopts a different approach by revealing the power of unsupervised learning to cluster data and unveiling hidden patterns. In this study, we also identify energy inefficiencies after exploring the cluster results of a single building’s HVAC consumption data and building usage data as part of the energy efficiency analysis. Time series analysis and the K-means clustering algorithm are successfully applied to identify new energy-saving opportunities in a highly efficient office building located in the Houston area (TX, USA). The paper uses 1-year data from a highly efficient Leadership in Energy and Environment Design (LEED)-, Energy Star-, and Net Zero-certified building, showing a potential energy savings of 6% using the K-means algorithm. The results show that clustering is instrumental in helping building managers identify potential additional energy savings.

The two steps in human intelligence development, namely, mimicking and tentative application of expertise, are reflected by imitation learning (IL) and reinforcement learning (RL) in artificial intelligence (AI). However, the RL process does not always improve the skills learned from expert demonstrations and enhance the algorithm performance. To solve the problem, this paper puts forward a novel algorithm called optimal combination of imitation and reinforcement learning (OCIRL). First, the concept of deep q-learning from demonstrations (DQfD) was introduced to the actor-critic (A2C) model, creating the A2CfD model. Then, a threshold was estimated from a trained IL model with the same inputs and reward function with the DOfD, and applied to the A2CfD model. The threshold represents the minimum reward that conserves the learned expertise. The resulting A2CfDoC model was trained and tested on self-driving cars in both discrete and continuous environments. The results show that the model outperformed several existing algorithms in terms of speed and accuracy.

Nowadays, Customer's product reviews can be widely found on the Web, be it in personal blogs, forums, or ecommerce websites. They contain important products' in-forma�on and therefore became a new data source for compe��ve intelligence. �n that account, these reviews need to be analyzed and summarized in order to help the leader of an en�ty (company, brand, etc.) to make appropriate decisions in an e�ec�ve way. �owever, most previous review summariza�on studies focus on summarizing sen�ment distribu�on toward di�erent product features without taking into account that the real advantages and disadvantages of a product clarify over �me. For this reason, in this work we aim to propose a new system for product opinion summariza�on which depends on the �me when reviews are e�pressed and that covers the sen�ments change about product features. The proposed system firstly, generates a summary based on product features in order to give more accurate and efficient informa�on about di�erent features. �econdly, classify the product based on its features in its appropriate class (good, medium or bad product) using a fuzzy logic system. The e�perimental results demonstrate the e�ec�veness of the proposed system to generate the real image of a product and its features in reviews.

No abstract

The authors wish to make the following correction to their paper [...]