This paper investigates virtual reality (VR) technology which can increase the quality of experience (QoE) on the graphics quality within the gaming environment. The graphics quality affects the VR environment and user experience. To gather relevant data, we conduct a live user experience and compare games with high- and low-quality graphics. The qualitative feedback obtained through questionnaires prove the importance ofcontextualizing users’ experiences playing both games. Furthermore, our findings prove the crucial role of graphics quality in adopting user engagement and enjoyment during gaming sessions. Users consistently reported their feeling more connected when interacting with games and receiving high-quality graphics. If the graphics quality received is low, the user rating for a particular game is low. Further examination of VR technology reveals its potential to revolutionize graphics quality within game play.

The coupling of packet forwarding, Internet gateway (IGW) selection, and vehicle mobility in the Internet of Vehicles (IoV) presents challenges for multi-hop routing. Particularly, IGWs and vehicles near IGWs are most likely to be congested, since all the Internet traffic loads converge at IGWs in IoV. To this end, we propose a distance-weighted back-pressure dynamic routing (DBDR), which prioritizes the vehicles that are close to the destination and have a large backlog differential of buffer queues to provide dynamic hop-by-hop forwarding. DBDR is also jointly designed with multi-hop IGW discovery and vehicle mobility management to implement both uplink and downlink forwarding for Internet services. Our analysis using Lyapunov drift theory proves that DBDR achieves the network stability on the buffer queues and the network capacity. Simulations in a practical road scenario using NS-2 and VanetMobiSim show that DBDR outperforms the existing protocols in terms of packet delivery ratio, throughput, and success rate of HTTP requests/responses, as well as average packet delay when the network becomes congested.

Vehicular Ad hoc Networks (VANETs) can help reduce traffic-related accidents by broadcasting Emergency Messages (EMs) in advance between vehicles. Due to the high-speed mobility of VANETs and attenuation of the wireless signal, reliable and fast transmission of EMs is a challenging task. Such as the chosen next-hop vehicle may have driven away from the neighborhood of the sender before receiving the EM, and rerouting may increase the delay when the EMs encounter transmission failure. To this end, we propose a Speed and Position aware Dynamic Routing (SPDR) for EM dissemination in VANETs. First, we introduce a speed metric dynamic greedy routing to provide a dynamic hop-by-hop rebroadcast of the EM. SPDR dynamically shrinks the Routing Decision Area (RDA) range based on the velocity variance of candidate neighbors and prioritizes the farthest vehicle in the shrunk RDA as the optimal next-hop, enhancing the reliable transmission of EMs. Then, we present a collaborative forwarding strategy to enable candidate neighbors to collaborate in communication. In case of transmission failure, SPDR elects the candidate vehicle close to the destination as the forwarder to reduce rerouting. Simulations in a practical motorway scenario using NS-2 and VanetMobiSim show that SPDR outperforms the existing protocols in terms of message delivery ratio, network throughput, and average dissemination delay.

Few-shot (FS) sound event detection (SED) is the process of identifying and recognizing specific sounds or events within an audio recording, specifically in the field of bioacoustics. This task is especially challenging due to the substantial unpredictability, complexity of the sounds, and the limited amount of labeled training data available. We recommend a transudative learning technique with data augmentation in response to the recent success of transudative inference (TI) in the field of computer vision. It aims to make predictions about new, unseen data by maximizing the mutual information between features of the labeled training data and the features of the unlabeled test data. We use the detection and classification of acoustic scenes and events (DCASE)-2021 and DCASE-2022 official datasets from the DCASE to do FS bioacoustics event detection experiments. Research findings illustrate that the recommended approach using TI along with spectrogram augmentation improves the performance of the FS bioacoustics event detection system. The proposed method improves the F-score by 0.10 and 0.16 on DCASE-2021 and DCASE-2022, respectively, compared with the average baseline and state-of-the-art methods.

Cloud gaming has rapidly transformed the gaming industry, allowing users to play games on demand from anywhere without the need for powerful hardware. Cloud service providers are striving to enhance user Quality of Experience (QoE) using traditional assessment methods. However, these traditional methods often fail to capture the actual user QoE because some users are not serious about providing feedback regarding cloud services. Additionally, some players, even after receiving services as per the Service Level Agreement (SLA), claim that they are not receiving services as promised. This poses a significant challenge for cloud service providers in accurately identifying QoE and improving actual services. In this paper, we have compared our previous proposed novel technique that utilizes a deep learning (DL) model to assess QoE through players’ facial expressions during cloud gaming sessions in a virtual reality (VR) environment. The EmotionNET model technique is based on a convolutional neural network (CNN) architecture. Later, we have compared the EmotionNET technique with three other DL techniques, namely ConvoNEXT, EfficientNET, and Vision Transformer (ViT). We trained the EmotionNET, ConvoNEXT, EfficientNET, and ViT model techniques on our custom-developed dataset, achieving 98.9% training accuracy and 87.8% validation accuracy with the EmotionNET model technique. Based on the training and comparison results, it is evident that the EmotionNET model technique predicts and performs better than the other model techniques. At the end, we have compared the EmotionNET results on two network (WiFi and mobile data) datasets. Our findings indicate that facial expressions are strongly correlated with QoE.