Search

Rear end collisions are deadliest in nature and result in life losses and severe injuries. Many of the proposed rear-end collision avoidance schemes focus only on specific aspects without considering several non-direct factors, such as driver inattention or distraction, tailgating, panic stops, street surface circumstances, driver response time, person on foot stream and vehicle elements. Henceforth presenting greater challenges in proposing a precise numerical model of the vehicle control framework. Moreover, most collision avoidance schemes incorporate fuzzy logic for formulating human inspired collision avoidance controllers. But the problem with a fuzzy based controller is that their efficiency is greatly affected by the number of rules being deployed. Furthermore, no such agent-based modeling has been utilized, which can effectively model the human-inspired behavior. Literature is full of vehicle control frameworks that work in a connected and homogeneous environment, again critics have raised several questions for such frameworks working in a connected environment. This study aims not only to identify these key issues but also propose a human-inspired physics based Spiral Spring based Simple Reflex Agent for rear end collision avoidance. Our scheme will not only work in the non-connected and heterogeneous environment but will also consider the distraction causing road factors and effectively handle them. Extensive experimentations and presentation for the proof of concept have supported our claims and worthiness of proposed agent-based scheme.

Vehicular networks are continually gaining popularity, owing to the evolution of the Internet of things, by means of rapid communication in IP-based networks. Vehicles are being fitted with sensory devices to gain inputs from the external environment for information processing. Numerous applications of vehicular networks depend on the use of communication networks. The security and privacy of data communication are significant challenges, particularly in wireless applications, for example, the Internet of connected vehicles. When an official fleet of vehicles (government or military) begins its journey, the vehicles need to communicate with one another to share sensitive information. The security of such a fleet is maintained in various security layers, each of which coordinates and communicates with the others, but avoids disclosing sensitive information of higher security layers to lower security layers. No such access control model exists that can enforce the authority of security officials in layers. We propose a novel security and privacy based access control (SPBAC) model for the Internet of connected vehicles, which allows security officials to access information in combination with permissions and roles, instead of roles only, for officials traveling in vehicles belonging to the same fleet. Vehicle-to-vehicle communication is performed with the aid of onboard unit sensory devices. The vehicles can also communicate through wireless technology, namely WiFi and cellular communications (4G/5G). The SPBAC model provides communication among security layers in a secure, private, and efficient manner compared to other state-of-the-art algorithms. The SPBAC model is demonstrated here using mathematical modeling along with implementation examples.

This research paper presents a validated emotion enabled cognitive driver assistance model (EECDAM) as an accident prevention scheme while keeping in mind different types of driver distractions. It is observed that distracted drivers know that distraction can lead them to a crash but they are not aware of distractions when they take over and they continue to drive. With advancements in autonomous vehicles technologies, it is possible to have an onboard driver assistance systems. However, research is yet to be reported on this issue whether onboard driver assistance program will be effective or not. The Emotion Enabled Cognitive Driver Assistance Model is a system based on an encapsulated Emotion Enabled Cognitive Driver Assistant (EECDA), which computes the effects of external factors at the distraction level of the subject and generates algorithmically generated fear emotion. During experiments, the EECDA intervenes when the fear intensity of the driver crosses a threshold by sending two sound alerts to the driver to take appropriate action. To demonstrate the effectiveness of the proposed approach as a road safety system, a Cognitive Agent-Based Computing (CABC) framework has been utilized to validate the results of the EECDAM. Algorithms are utilized using fuzzy sets to compute distraction of the drivers. We also present an Agent-Based Model (ABM) to validate the implementation of the proposed scheme. Extensive experiments demonstrate the proficiency of the proposed model for robust collision avoidance.

This paper introduces the novel idea of using human social norms and human emotions to improve the collision avoidance of Autonomous Vehicles (AVs). Until now, the literature has been concerned with theoretical debates regarding ethical issues connected to AVs, while no practical steps have yet been undertaken. This paper introduces the concept of an artificial society of AVs with different personalities and with social norms coded into their autopilot so that they act like well-behaved drivers. For proof of concept, the standard agent modelling tool Netlogo is utilized to simulate the artificial society of AVs. Furthermore, comparisons are made with random walk-based non-social-based collision avoidance techniques. Extensive testing has been carried out using the behaviour space tool to determine the performance of the proposed approach regarding the number of collisions. A comparative study undertaken with a random walk method indicates that the proposed approach provides a better option for tailoring the autopilots of future AVs, while also promising to be more socially acceptable and trustworthy regarding safe road travel.

Social Internet of Things (SIoT) is an interdisciplinary emerging domain that enables autonomous interaction among social networking and Internet of Things. It provides an unprecedented opportunity to offer new applications and services. However, such an integration brings forth new issues and challenges. In this editorial, we briefly describe the notion of SIoT from the literature perspective. The motivation and challenges of the SIoT are also presented. Moreover, we categorize and classify the fifteen selected articles accepted in this Special Issue which are closely relevant to SIoT and a short summary of each of them is presented.

Precise and fast shape matching and retrieval from very large datasets is a challenging task because of the existence of many distortions such as noise, occlusion and affine distortions. In this paper, we aim to propose a time-saving and effective shape matching and retrieval framework, that employs pruning which will enable online shape retrieval from extremely large datasets. First, using a hierarchical tree-based structure supporting parallel processing and efficient feature descriptors, irrelevant shapes are pruned and a subset of shapes relevant to the query is selected, then using more sophisticated feature descriptors, accurate retrieval is performed. Contour representation of an object is considered as most significant visual shape similarity measure by the humans. Using boundary information, we generate two simplified and efficient feature descriptors for fast pruning, and a sophisticated feature descriptor for effective and accurate retrieval. Tests performed on standard datasets unveil that the proposed technique is computationally more efficient than the state-of-the-art techniques while maintaining comparable matching and retrieval performance. Its performance is scalable for huge datasets and is robust against affine transformations, articulations and occlusion.

Interoperability remains a major burden to the developers of Internet of Things systems. It is due to IoT devices are extremely heterogeneous regarding basic communication protocols, data formats, and technologies. Furthermore, due to the absence of worldwide satisfactory standards, Interoperability tools remains imperfect. In this paper, we have proposed Semantic Interoperability Model for Big-data in IoT (SIMB-IoT) to deliver semantic interoperability among heterogeneous IoT devices in health care domain. This model is used to recommend medicine with side effects for different symptoms collected from heterogeneous IoT sensors. Two datasets are taken for the analysis of big-data. One dataset contains diseases with drug details and the second dataset contains medicines with side effects. Information between physician and patient are semantically annotated and transferred in a meaningful way. A Lightweight Model for Semantic annotation of Big-data using heterogeneous devices in IoT is proposed to provide annotations for big data. Resource Description Framework (RDF) is a semantic web framework that is recycled to communicate things using Triples to make it semantically significant. RDF annotated patients’ data and made it semantically interoperable. SPARQL query is used to extract records from RDF graph. Tableau, Gruff-6.2.0, and Mysql tools are used in simulation in this article.

Constructing a smart home is not a task without intricate challenges due to involvement of various tools and technologies. Therefore, this research work presents a concept of context-aware low power intelligent SmartHome (CLPiSmartHome). For CLPiSmartHome, we propose a communication model, which provides a common medium for communication, i.e., same communication language. Moreover, an architecture is also proposed that welcomes all the electronic devices to communicate with each other using a single platform service. The proposed architecture describes the application, analysis and visualization aspects of the CLPiSmartHome. Furthermore, the feasibility and efficiency of the proposed system are implemented on Hadoop single node setup on UBUNTU 14.04 LTS coreTMi5 machine with 3.2GHz processor and 4 GB memory. Sample medical sensory data sets and fire detection datasets are tested on the proposed system. Finally, the results show that the proposed system architecture efficiently processes, analyzes, and integrates different datasets and triggers actions to provide safety measurements for elderly age people, patients, and others.

Source Code Authorship Attribution (SCAA) is a direct challenge to the privacy and anonymity of developers. However, it is important to recognize the malicious authors and the origin of the attack. In this paper, we proposed Source Code Authorship Attribution using Abstract Syntax Tree (SCAA-AST) for efficient classification of programmers. First, the AST hierarchal features are generated from different programming codes. Second, preprocessing techniques are used to obtain useful features without sound data. Third, the Term Frequency Inverse Document Frequency (TFIDF) weighting technique is used to zoom in on the significance of each feature. Fourth, the Adaptive Synthetic (ADASYN) oversampling method is used to solve the imbalanced class problem. Finally, a deep learning algorithm is designed with the TensorFlow framework, and the Keras API is used to classify programming authors. A deep learning algorithm is further configured with a dropout layer, learning error rate, loss and activation function, and dense layers to enhance the classification results. The results are appreciable in outperforming the existing techniques from the perspective of classification accuracy.

Now the Industrial Internet of Things (IIoT) devices can be deployed to monitor the flow of data, the source of collection and supervision on a large scale of complex networks. It implements large networks for sending and receiving data connected by smart devices. Malware threats, which are primarily targeted at conventional computers linked to the Internet, can also be targeted at IoT machines. Therefore, a smart protection approach is needed to protect millions of IIoT users against malicious attacks. On the other hand, existing state-of - the-art malware identification methods are not better in terms of computational complexity. In this paper, we design architecture to detect malware attacks on the Industrial Internet of Things (MD-IIOT). For an in-depth analysis of malware, a methodology is proposed based on color image visualization and deep convolution neural network. The findings of the proposed method are compared to former approaches to malware detection. The experimental results indicate that the proposed method's predictive time and detection accuracy are higher than that of previous machine learning and deep learning methods.