This work aims to provide a novel multimodal sarcasm detection model that includes four stages: pre-processing, feature extraction, feature level fusion, and classification. The pre-processing uses multimodal data that includes text, video, and audio. Here, text is pre-processed using tokenization and stemming, video is pre-processed during the face detection phase, and audio is pre-processed using the filtering technique. During the feature extraction stage, such text features as TF-IDF, improved bag of visual words, n-gram, and emojis as well on the video features using improved SLBT, and constraint local model (CLM) are extraction. Similarly the audio features like MFCC, chroma, spectral features, and jitter are extracted. Then, the extracted features are transferred to the feature level fusion stage, wherein an improved multilevel canonical correlation analysis (CCA) fusion technique is performed. The classification is performer using a hybrid classifier (HC), e.g. bidirectional gated recurrent unit (Bi-GRU) and LSTM. The outcomes of Bi-GRU and LSTM are averaged to obtain an effective output. To make the detection results more accurate, the weight of LSTM will be optimally tuned by the proposed opposition learning-based aquila optimization (OLAO) model. The MUStARD dataset is a multimodal video corpus used for automated sarcasm Discovery studies. Finally, the effectiveness of the proposed approach is proved based on various metrics.

In recent years, connected vehicle technologies emerged to provide a safer and more connected environment for transportation systems, which has further evolved into cellular vehicle-to-everything (C-V2X) technology. The current study contributes in the direction of future research of smart India @2047 in connected vehicles. The study presents the diverse aspects of 5G V2X as a comprehensive overview of Vehicle-to-Everything (V2X) technology that covers the significant scope of V2X technology, including its development, components, functionality, use cases, and future potential. It is observed that few surveys are available that cover limited aspects of 5G V2X communication technologies, with one or two preferred architectures, and only few provides the definitions of 3GPP use cases. Emergency vehicles (EMV) are identified as an important part of an emergency service, and the main goal of EMV is to reduce the response time. The study discusses the research challenges in the field of V2X and presents future directions to reduce the probability of untoward incidents and enhance the EMV response time. The work leverages by synthesizing the latest research in 5G V2X technological advancements like Multiple Input Multiple Output, Beamforming, and Integrated Sensing and Communication, highlighting the roles of 5G architectures and providing a deeper understanding of the 5GAA V2X use cases from the perspective of societal benefit. The study provides a comprehensive future research directions to the researchers on 5G V2X technologies and current research trends for smart EMV applications.

Traffic safety applications using vehicle-to-vehicle (V2V) communication is an emerging and promising area within the ITS environment. Many of these applications require real-time communication with high reliability. To meet a real-time deadline, timely and predictable access to the channel is paramount. The medium access method used in 802.11p, CSMA with collision avoidance, does not guarantee channel access before a finite deadline. The well-known property of CSMA is undesirable for critical communications scenarios. The simulation results reveal that a specific vehicle is forced to drop over 80% of its packets because no channel access was possible before the next message was generated. To overcome this problem, we propose to use STDMA for real-time data traffic between vehicles. The real- time properties of STDMA are investigated by means of the highway road simulation scenario, with promising results.Comment: 28 pages, 18 figures, International Journal of Network Security & Its Applications, International Journal of Network Security & Its Applications (IJNSA), Vol.5, No.2, March 201

Vehicular mobility has some special characteristics of node mobility such as the high speed of cars, the strict constraints on nodes movement patterns, the periodicity of dense and sparse network areas, the clustering of users at intersections, or in traffic jams. These phenomena can only be captured with a limited level of realism in the simulated cars movement, and their impacts on the network performance cannot be ignored or assumed a priori, but need to be studied to guarantee the network simulation outcome to be reliable. We will study vehicular mobility models, which will describe an increasing level of detail in the vehicular movement. Also inter-vehicle communications metrics and the suitability of both existing and novel ad hoc protocols to car-to-car and car-to-road communication. One of the emerging applications that belongs to a ambient systems is to transparently and directly interconnect vehicles on roads, making an ad-hoc network that enables a variety of applications through distributed software's without the need of any fixed and dedicated infrastructure. The network as well as the embedded computers and sensors in the vehicle will be invisible to the driver, who will get the required services during his journey. Vehicular Ad-hoc Network (VANET), in which vehicles constitute the mobile nodes in the network. Most research work in VANET relies on simulations for evaluation purpose, so the key concept for VANET simulations is a real world vehicular mobility model which will ensures conclusions drawn from simulation experiments will carry through to real world deployments. In this paper we propose Random way-point model evaluate its effect in VANETs by ns-2 simulations.

In recent decades, abstractive text summarization using multimodal input has attracted many researchers due to the capability of gathering information from various sources to create a concise summary. However, the existing methodologies based on multimodal summarization provide only a summary for the short videos and poor results for the lengthy videos. To address the aforementioned issues, this research presented the Multimodal Abstractive Summarization using Bidirectional Encoder Representations from Transformers (MAS-BERT) with an attention mechanism. The purpose of the video summarization is to increase the speed of searching for a large collection of videos so that the users can quickly decide whether the video is relevant or not by reading the summary. Initially, the data is obtained from the publicly available How2 dataset and is encoded using the Bidirectional Gated Recurrent Unit (Bi-GRU) encoder and the Long Short Term Memory (LSTM) encoder. The textual data which is embedded in the embedding layer is encoded using a bidirectional GRU encoder and the features with audio and video data are encoded with LSTM encoder. After this, BERT based attention mechanism is used to combine the modalities and finally, the BI-GRU based decoder is used for summarizing the multimodalities. The results obtained through the experiments that show the proposed MAS-BERT has achieved a better result of 60.2 for Rouge-1 whereas, the existing Decoder-only Multimodal Transformer (D-MmT) and the Factorized Multimodal Transformer based Decoder Only Language model (FLORAL) has achieved 49.58 and 56.89 respectively. Our work facilitates users by providing better contextual information and user experience and would help video-sharing platforms for customer retention by allowing users to search for relevant videos by looking at its summary.