Recurrent neural network (RNN) and long short-term memory (LSTM) have achieved great success in processing sequential multimedia data yielded the state-of-the-art results speech recognition, digital signal processing, video text analysis. In this paper, we propose a novel action recognition method by using convolutional (CNN) deep bidirectional LSTM (DB-LSTM) network. First, features are extracted from every sixth frame of videos, which helps reduce redundancy complexity. Next, information...

Electric energy forecasting domain attracts researchers due to its key role in saving resources, where mainstream existing models are based on Gradient Boosting Regression (GBR), Artificial Neural Networks (ANNs), Extreme Learning Machine (ELM) and Support Vector (SVM). These encounter high-level of non-linearity between input data output predictions limited adoptability real-world scenarios. Meanwhile, demands more robustness, higher prediction accuracy generalization ability for...

Advances in information and signal processing technologies have a significant impact on autonomous driving (AD), improving safety while minimizing the efforts of human drivers with help advanced artificial intelligence (AI) techniques. Recently, deep learning (DL) approaches solved several real-world problems complex nature. However, their strengths terms control processes for AD not been deeply investigated highlighted yet. This survey highlights power DL architectures reliability efficient...

The worldwide utilization of surveillance cameras in smart cities has enabled researchers to analyze a gigantic volume data ensure automatic monitoring. An enhanced security system cities, schools, hospitals, and other domains is mandatory for the detection violent or abnormal activities avoid any casualties which could cause social, economic, ecological damages. Automatic violence quick actions very significant can efficiently assist concerned departments. In this paper, we propose...

Due to industrialization and the rising demand for energy, global energy consumption has been rapidly increasing. Recent studies show that biggest portion of is consumed in residential buildings, i.e., European Union countries up 40% total by households. Most buildings industrial zones are equipped with smart sensors such as metering electric sensors, inadequately utilized better management. In this paper, we develop a hybrid convolutional neural network (CNN) an long short-term memory...

Nowadays digital surveillance systems are universally installed for continuously collecting enormous amounts of data, thereby requiring human monitoring the identification different activities and events. Smarter is need this era through which normal abnormal can be automatically identified using artificial intelligence computer vision technology. In paper, we propose a framework activity recognition in videos captured over industrial systems. The continuous video stream first divided into...

Excessive Power Consumption (PC) and demand for power is increasing on a daily basis, due to advancements in technology, the rise electricity-dependent machinery, growth of human population. It has become necessary predict PC order improve management co-operation between energy used building grid. State-of-the-art Energy Prediction (ECP) methods are limited terms predicting effectively, various challenges such as weather conditions dynamic behaviour occupants. Thus, overcome drawbacks these...

Recognizing human activities has become a trend in smart surveillance that contains several challenges, such as performing effective analyses of huge video data streams, while maintaining low computational complexity, and this task real-time. Current activity recognition techniques are using convolutional neural network (CNN) models with computationally complex classifiers, creating hurdles obtaining quick responses for abnormal activities. To address these challenges real-time surveillance,...

Video anomaly recognition in smart cities is an important computer vision task that plays a vital role surveillance and public safety but challenging due to its diverse, complex, infrequent occurrence real-time environments. Various deep learning models use significant amounts of training data without generalization abilities with huge time complexity. To overcome these problems, the current work, we present efficient light-weight convolutional neural network (CNN)-based framework functional...

The massive amount of video data produced by surveillance networks in industries instigate various challenges exploring these videos for many applications, such as summarization (VS), analysis, indexing, and retrieval. task multiview (MVS) is very challenging due to the gigantic size data, redundancy, overlapping views, light variations, interview correlations. To address challenges, low-level features clustering-based soft computing techniques are proposed that cannot fully exploit MVS. In...

Smart grid technology based on renewable energy and storage systems are attracting considerable attention towards crises. Accurate reliable model for electricity prediction is considered a key factor suitable management policy. Currently, consumption rapidly increasing due to the rise in human population development. Therefore, this study, we established two-step methodology residential building load prediction, which comprises two stages: first stage, raw data of refined effective training;...

The prognostics and health management (PHM) plays the main role to handle risk of failure before its occurrence. Next, it has a broad spectrum applications including utility networks, energy storage systems (ESS), etc. However, an accurate capacity estimation batteries in ESS is mandatory for their safe operations decision making policy. comprises different mechanisms such as batteries, capacitors, Consequently, measurement charging profiles (CPs) strong relation battery capacity. These...

Smart cities stand as pivotal components in the ongoing pursuit of elevating urban living standards, facilitating rapid expansion areas while efficiently managing resources through sustainable and scalable innovations. In this regard, emerging technologies like Artificial Intelligence (AI), Internet Things (IoT), big data analytics, fog edge computing have become increasingly prevalent, smart city applications grapple with various challenges, including potential for unauthorized disclosure...

Mainstream Internet of Things (IoT) techniques for smart homes focus on appliances and surveillance in cities. Most the researchers utilize vision sensors IoT environment targeting only adult users various applications such as abnormal activity recognition. This paper introduces a new paradigm sensor technologies by analyzing behavior baby through an intelligent multimodal system. Traditional wearable heartbeat if attached to any body part make him uncomfortable also some babies are paranoid...

Multi-view action recognition (MVAR) is an optimal technique to acquire numerous clues from different views data for effective recognition, however, it not well explored yet. There exist several challenges MVAR domain such as divergence in viewpoints, invisible regions, and scales of appearance each view require better solutions real world applications. In this paper, we present a conflux long short-term memory (LSTMs) network recognize actions multi-view cameras. The proposed framework has...

The exponential growth in population and their overall reliance on the usage of electrical electronic devices have increased demand for energy production. It needs precise management systems that can forecast consumers future policymaking. Embedded smart sensors attached to electricity meters home appliances enable power suppliers effectively analyze generate distribute into residential areas based level consumption. Therefore, this paper proposes a clustering-based analysis consumption...