Detecting and classifying vehicles as objects from images and videos is challenging in appearance-based representation, yet plays a significant role in the substantial real-time applications of Intelligent Transportation Systems (ITSs). The rapid development of Deep Learning (DL) has resulted in the computer-vision community demanding efficient, robust, and outstanding services to be built in various fields. This paper covers a wide range of vehicle detection and classification approaches and the application of these in estimating traffic density, real-time targets, toll management and other areas using DL architectures. Moreover, the paper also presents a detailed analysis of DL techniques, benchmark datasets, and preliminaries. A survey of some vital detection and classification applications, namely, vehicle detection and classification and performance, is conducted, with a detailed investigation of the challenges faced. The paper also addresses the promising technological advancements of the last few years.

In a conventional speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language do not exist, data from other languages can be used instead. We experiment with cross-lingual and multilingual SER, working with Amharic, English, German, and Urdu. For Amharic, we use our own publicly available Amharic Speech Emotion Dataset (ASED). For English, German and Urdu, we use the existing RAVDESS, EMO-DB, and URDU datasets. We followed previous research in mapping labels for all of the datasets to just two classes: positive and negative. Thus, we can compare performance on different languages directly and combine languages for training and testing. In Experiment 1, monolingual SER trials were carried out using three classifiers, AlexNet, VGGE (a proposed variant of VGG), and ResNet50. The results, averaged for the three models, were very similar for ASED and RAVDESS, suggesting that Amharic and English SER are equally difficult. Similarly, German SER is more difficult, and Urdu SER is easier. In Experiment 2, we trained on one language and tested on another, in both directions for each of the following pairs: Amharic↔German, Amharic↔English, and Amharic↔Urdu. The results with Amharic as the target suggested that using English or German as the source gives the best result. In Experiment 3, we trained on several non-Amharic languages and then tested on Amharic. The best accuracy obtained was several percentage points greater than the best accuracy in Experiment 2, suggesting that a better result can be obtained when using two or three non-Amharic languages for training than when using just one non-Amharic language. Overall, the results suggest that cross-lingual and multilingual training can be an effective strategy for training an SER classifier when resources for a language are scarce.

The advancements in Vehicular Ad Hoc Networks (VANETs) require more intelligent security protocols that ultimately provide unbreakable security to vehicles and other components of VANETs. VANETs face various types of security pitfalls due to the openness characteristics of the VANET communication infrastructure. Researchers have recently proposed different mutual authentication schemes that address security and privacy issues in vehicle‐to‐vehicle (V2V) communication. However, some V2V security schemes suffer from inadequate design and are hard to implement practically. In addition, some schemes face vehicle traceability and lack anonymity. Hence, this paper’s primary goal is to enhance privacy preservation through mutual authentication and to achieve better security and performance. Therefore, this article first describes the vulnerabilities of a very recent authentication scheme presented by Vasudev et al. Our analysis proves that the design of Vasudev et al.’s scheme is incorrect, and resultantly, the scheme does not provide mutual authentication between a vehicle and vehicle server when multiple vehicles are registered with the vehicle sever. Furthermore, this paper proposes a secure message transmission scheme for V2V in VANETs. The proposed scheme fulfills the security and performance requirements of VANETs. The security analysis of the proposed scheme using formal BAN and informal discussion on security features confirm that the proposed scheme fulfills the security requirements, and the performance comparisons show that the proposed scheme copes with the lightweightness requirements of VANETs.

A vehicular ad hoc network (VANET) is essential for the autonomous vehicle industry, and with the advancement in VANET technology, security threats are increasing rapidly. Mitigation of these threats needs an intelligent security protocol that provides unbreakable security. In recent times, various three-factor authentication solutions for VANET were introduced that adopt the centralized Trusted Authority , which is responsible for assigning authentication parameters during vehicle registration, and the authentication process depends on these parameters. This article first explains the vulnerabilities of the recent three-factor (3F) authentication scheme presented by Xu et al. Our analysis proves that if an is dishonest, it can easily bypass the and can create a session with . Furthermore, this paper puts forward a new scheme that provides the 3F authentication for VANETs (TFPPASV) to resist from bypassing the and to offer user privacy. The proposed scheme fulfills the security and performance requirements of the VANET. We use BAN-Logic analysis to perform a formal security analysis of the proposed scheme, in addition to the informal security feature discussion. Finally, we compare the security and performance of the proposed TFPPASV with some recent and related schemes.

Crack inspections of automotive engine components are usually conducted manually; this is often tedious, with a high degree of subjectivity and cost. Therefore, establishing a robust and efficient method will improve the accuracy and minimize the subjectivity of the inspection. This paper presents a robust approach towards crack classification, using transfer learning and fine-tuning to train a pre-trained ConvNet model. Two deep convolutional neural network (DCNN) approaches to training a crack classifier—namely, via (1) a Light ConvNet architecture from scratch, and (2) fined-tuned and transfer learning top layers of the ConvNet architectures of AlexNet, InceptionV3, and MobileNet—are investigated. Data augmentation was utilized to minimize over-fitting caused by an imbalanced and inadequate training sample. Data augmentation improved the accuracy index by 4%, 5%, 7%, and 4%, respectively, for the proposed four approaches. The transfer learning and fine-tuning approach achieved better recall and precision scores. The transfer learning approach using the fine-tuned features of MobileNet attained better classification accuracy and is thus proposed for the training of crack classifiers. Moreover, we employed an up-to-date YOLOv5s object detector with transfer learning to detect the crack region. We obtained a mean average precision (mAP) of 91.20% on the validation set, indicating that the model effectively distinguished diverse engine part cracks.