Maintaining a fair use of energy consumption in smart homes with many household appliances requires sophisticated algorithms working together in real time. Similarly, choosing a proper schedule for appliances operation can be used to reduce inappropriate energy consumption. However, scheduling appliances always depend on the behavior of a smart home user. Thus, modeling human interaction with appliances is needed to design an efficient scheduling algorithm with real-time support. In this regard, we propose a scheduling algorithm based on human appliances interaction in smart homes using reinforcement learning (RL). The proposed scheduling algorithm divides the entire day into various states. In each state, the agents attached to household appliances perform various actions to obtain the highest reward. To adjust the discomfort which arises due to performing inappropriate action, the household appliances are categorized into three groups i.e., (1) adoptable, (2) un-adoptable, (3) manageable. Finally, the proposed system is tested for the energy consumption and discomfort level of the home user against our previous scheduling algorithm based on least slack time phenomenon. The proposed scheme outperforms the Least Slack Time (LST) based scheduling in context of energy consumption and discomfort level of the home user.

A smart home provides a facilitated environment for the detection of human activity with appropriate Deep Learning algorithms to manipulate data collected from numerous sensors attached to various smart things in a smart home environment. Human activities comprise expected and unexpected behavior events; therefore, detecting these events consisting of mutual dependent activities poses a key challenge in the activities detection paradigm. Besides, the battery-powered sensor ubiquitously and extensively monitors activities, disputes, and sensor energy depletion. Therefore, to address these challenges, we propose an Energy and Event Aware-Sensor Duty Cycling scheme. The proposed model predicts the future expected event using the Bi-Directional Long-Short Term Memory model and allocates Predictive Sensors to the predicted event. To detect the unexpected events, the proposed model localizes a Monitor Sensor within a cluster of Hibernate Sensors using the Jaccard Similarity Index. Finally, we optimize the performance of our proposed scheme by employing the Q-Learning algorithm to track the missed or undetected events. The simulation is executed against the conventional Machine Learning algorithms for the sensor duty cycle, scheduling to reduce the sensor energy consumption and improve the activity detection accuracy. The experimental evaluation of our proposed scheme shows significant improvement in activity detection accuracy from 94.12% to 96.12%. Besides, the effective rotation of the Monitor Sensor significantly improves the energy consumption of each sensor with the entire network lifetime.

Vehicles are highly mobile nodes; therefore, they frequently change their topology. To maintain a stable connection with the server in high-speed vehicular networks, the handover process is restarted again to satisfy the content requests. To satisfy the requested content, a vehicular-content-centric network (VCCN) is proposed. The proposed scheme adopts in-network caching instead of destination-based routing to satisfy the requests. In this regard, various routing protocols have been proposed to increase the communication efficiency of VCCN. Despite disruptive communication links due to head vehicle mobility, the vehicles create a broadcasting storm that increases communication delay and packet drop fraction. To address the issues mentioned above in the VCCN, we proposed a multihead nomination clustering scheme. It extends the hello packet header to get the vehicle information from the cluster vehicles. The novel cluster information table (CIT) has been proposed to maintain several nominated head vehicles of a cluster on roadside units (RSUs). In disruptive communication links due to the head vehicle’s mobility, the RSU nominates the new head vehicle using CIT entries, resulting in the elimination of the broadcasting storm effect on disruptive communication links. Finally, the proposed scheme increases the successful communication rate, decreases the communication delay, and ensures a high cache success ratio on an increasing number of vehicles.

Vehicular ad hoc network (VANET) is a special form of mobile ad hoc network (MANET), which plays a key role in the intelligent transportation system (ITS). Though many outstanding geographic routing protocols are designed for VANETs, a majority of them use parameters that only affect routing performance. In this article, we propose an intersection routing based on fuzzy multi-factor decision (IRFMFD), which utilizes several features. The scheme is divided into two parts, namely vehicular decision management and intersection decision management. In the vehicular component, candidate vehicles between two static nodes (SNs) located at two intersections derive potential routing paths considering distance, neighbor quantity, and relative velocity. In the intersection component, the candidate SN was chosen from the current intersection’s 2-hop neighbors which were connected with the current intersection by a route that was decided on in part one. To get the best scheme, we also introduced other factors to estimate the number of hops in each link and link lifetime. The simulation shows that the IRFMFD outperforms on delivery ratio and end-to-end delay compared with AODV (Ad hoc on-demand distance vector), GPSR (Greedy perimeter stateless routing) and GeOpps (Geographical opportunistic routing).

Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are generally trained to minimise the distance between clean and enhanced speech features. These often result in improved speech quality however they suffer from a lack of generalisation and may not deliver the required speech intelligibility in everyday noisy situations. In an attempt to address these challenges, researchers have explored intelligibility-oriented (I-O) loss functions to train DL approaches for robust speech enhancement (SE). In this paper, we formulate a novel canonical correlation-based I-O loss function to more effectively train DL algorithms. Specifically, we present a fully convolutional SE model that uses a modified canonical-correlation based short-time objective intelligibility (CC-STOI) metric as a training cost function. To the best of our knowledge, this is the first work that exploits the integration of canonical correlation in an I-O based loss function for SE. Comparative experimental results demonstrate that our proposed CC-STOI based SE framework outperforms DL models trained with conventional STOI and distance-based loss functions, in terms of both standard objective and subjective evaluation measures when dealing with unseen speakers and noises.