Recent development toward innovative applications and technologies like self-driving, augmented reality, smart cities, and various other applications leads to excessive growth in the number of devices. These devices have finite computation resources and cannot handle the applications that require extensive computation with minimal delay. To overcome this, the mobile edge cloud (MEC) emerges as a practical solution that allows devices to offload their extensive computation to MEC located in their vicinity; this will lead to succeeding the arduous delay of the millisecond scale: requirement of $5^{th}$ generation communication system. This work examines the convex optimization problem. The objective is to minimize the task duration by optimal allocation of the resources like local and edge computational capabilities, transmission power, and optimal task segmentation. For optimal allocation of resources, an algorithm name E stimation of O ptimal R esource A llocator (EORA) is designed to optimize the function by keeping track of statistics of each candidate of the population. Using EORA, a comparative analysis of the hybrid approach (partial offloading) and edge computation only is performed. Results reveal the fundamental trade-off between both of these models. Simultaneously, the impact of devices’ computational capability, data volume, and computational cycles requirement on task segmentation is analyzed. Simulation results demonstrate that the hybrid approach: partial offloading scheme reduces the task's computation time and outperforms edge computing only.

Machine learning and deep learning algorithms are widely used in computer science domains. These algorithms are mostly used for classification and regression problems in almost every field of life. Semantic segmentation is an instantly growing research topic in the last few decades that refers to the association of each pixel in the image to the class it belongs. This paper illustrates the systematic survey of advanced research in the field of semantic segmentation till date. This study provides the brief knowledge about the latest proposed methods in the domain of semantic segmentation. The proposed study comprehends the concepts, techniques, tool, and results of different research frameworks proposed in the context of semantic segmentation. This study discusses the latest research papers in which machine learning and deep learning techniques are exploited for semantic segmentation and published between 2016 and 2021. The systematic literature review collected from seven different article libraries including ACM digital Library, Google Scholar, IEEE Xplore, Science Direct, Google Books, Refseek and Worldwide Science. For assuring the quality of the paper those papers are selected which have several citations on standardized platforms. Most of the studies used COCO, PASCAL, Cityscapes and CamVid dataset for training and validation of the machine learning and deep learning models. The results of the selected research articles are collected in the form of accuracy, mIoU value, F1 score, precision, and recall. In this study, we also conclude that most of the semantic segmentation studies use ResNet as the backbone of the architecture and none of the researchers used ensemble learning methods for semantic segmentation that is the loophole of the selected studies.

Sign language recognition (SLR) enables the deaf and speech-impaired community to integrate and communicate effectively with the rest of society. Word level or isolated SLR is a fundamental yet complex task with the main objective of using models to correctly recognize signed words. Sign language consists of very fast and complex hand, body, face movements, and mouthing cues that make the task very challenging. Several input modalities; RGB, optical Flow, RGB-D, and pose/skeleton have been proposed for SLR. However, the complexity of these modalities and the state-of-the-art (SOTA) methodologies tend to be exceedingly sophisticated and over-parametrized. In this paper, our focus is to use the hands and body poses as an input modality. One major problem in pose-based SLR is extracting the most valuable and distinctive features for all skeleton joints. In this regard, we propose an accurate, efficient, and lightweight pose-based pipeline leveraging a graph convolution network (GCN) along with residual connections and a bottleneck structure. The proposed architecture not only facilitates efficient learning during model training providing significantly improved accuracy scores but also alleviates computational complexity. With the proposed architecture in place, we are able to achieve improved accuracies on three different subsets of the WLASL dataset and the LSA-64 dataset. Our proposed model outperforms previous SOTA pose-based methods by providing a relative improvement of 8.91%, 27.62%, and 26.97% for WLASL-100, WLASL-300, and WLASL-1000 subsets. Moreover, our proposed model also outperforms previous SOTA appearance-based methods by providing a relative improvement of 2.65% and 5.15% for WLASL-300 and WLASL-1000 subsets. For the LSA-64 dataset, our model is able to achieve 100% test recognition accuracy. We are able to achieve this improved performance with far less computational cost as compared to existing appearance-based methods.

Facial expression is one of the most significant elements which can tell us about the mental state of any person. A human can convey approximately 55% of information nonverbally and the remaining almost 45% through verbal communication. Automatic facial expression recognition is presently one of the most difficult tasks in the computer science field. Applications of facial expression recognition (FER) are not just limited to understanding human behavior and monitoring person’s mood and the mental state of humans. It is also penetrating into other fields such as criminology, holographic, smart healthcare systems, security systems, education, robotics, entertainment, and stress detection. Currently, facial expressions are playing an important role in medical sciences, particularly helping the patients with bipolar disease, whose mood changes very frequently. In this study, an algorithm, automated framework for facial detection using a convolutional neural network (FD-CNN) is proposed with four convolution layers and two hidden layers to improve accuracy. An extended Cohn-Kanade (CK+) dataset is used that includes facial images of different males and females with expressions such as anger, fear, disgust, contempt, neutral, happy, sad, and surprise. In this study, FD-CNN is performed in three major steps that include preprocessing, feature extraction, and classification. By using this proposed method, an accuracy of 94% is obtained in FER. In order to validate the proposed algorithm, K-fold cross-validation is performed. After validation, sensitivity and specificity are calculated which are 94.02% and 99.14%, respectively. Furthermore, the f1 score, recall, and precision are calculated to validate the quality of the model which is 84.07%, 78.22%, and 94.09%, respectively.

In machine learning, sentiment analysis is a technique to find and analyze the sentiments hidden in the text. For sentiment analysis, annotated data is a basic requirement. Generally, this data is manually annotated. Manual annotation is time consuming, costly and laborious process. To overcome these resource constraints this research has proposed a fully automated annotation technique for aspect level sentiment analysis. Dataset is created from the reviews of ten most popular songs on YouTube. Reviews of five aspects—voice, video, music, lyrics and song, are extracted. An N-Gram based technique is proposed. Complete dataset consists of 369436 reviews that took 173.53 s to annotate using the proposed technique while this dataset might have taken approximately 2.07 million seconds (575 h) if it was annotated manually. For the validation of the proposed technique, a sub-dataset—Voice, is annotated manually as well as with the proposed technique. Cohen's Kappa statistics is used to evaluate the degree of agreement between the two annotations. The high Kappa value (i.e., 0.9571%) shows the high level of agreement between the two. This validates that the quality of annotation of the proposed technique is as good as manual annotation even with far less computational cost. This research also contributes in consolidating the guidelines for the manual annotation process.

Artificial intelligence- (AI-) empowered machines are devised to mimic human actions. In the automotive industry, AI plays a significant role in the development of vehicular technology. AI joins hands with the field of mechatronics to assist in the accurate execution of the vehicle functionalities. Autonomous vehicles get the scene information by using onboard sensors such as laser, radar, lidar, Global Positioning System (GPS), and vehicular communication networks. The data obtained is then used for various path planning and control techniques to make the vehicles capable of autonomously driving in complex environments. Autonomous vehicles use very up-to-date AI algorithms to localize themselves in known and unknown environments. AI algorithms are also exploited for perception, path planning, and motion control. A concise review of the state-of-the-art techniques to improve the performance of autonomous vehicles is presented.