Showing papers by "Sabu M. Thampi published in 2020"

A Psychologically Inspired Fuzzy Cognitive Deep Learning Framework to Predict Crowd Behavior

Abstract: In an intelligent surveillance system, detecting and predicting diverse collective crowd behaviors has emerged as a challenging problem for efficient crowd management. In real-world scenarios, potential disasters and hazards can be averted by considering crowd psychology for predicting crowd behaviors. This paper proposes an approach that exploits the psychological and cognitive aspects of human behavior in determining nine diverse crowd behaviors. The proposed approach is a combination of two cognitive deep learning frameworks and a psychological fuzzy computational model that utilizes OCC theory of emotions, OCEAN five-factor model of personality and visual attention for detecting crowd behaviors. Experiments are performed on different datasets and the results prove that our approach is successful in detecting and predicting crowd behavior in confronting situations and also outperforms the state-of-the-art methods. In particular, considering psychological aspects and cognition in determining crowd behavior is beneficial for rectifying the semantic ambiguity in identifying crowd behaviors.

Anomaly Detection in UASN Localization Based on Time Series Analysis and Fuzzy Logic

Abstract: Underwater acoustic sensor network (UASN) offers a promising solution for exploring underwater resources remotely. For getting a better understanding of sensed data, accurate localization is essential. As the UASN acoustic channel is open and the environment is hostile, the risk of malicious activities is very high, particularly in time-critical military applications. Since the location estimation with false data ends up in wrong positioning, it is necessary to identify and ignore such data to ensure data integrity. Therefore, in this paper, we propose a novel anomaly detection system for UASN localization. To minimize computational power and storage, we designed separate anomaly detection schemes for sensor nodes and anchor nodes. We propose an auto-regressive prediction-based scheme for detecting anomalies at sensor nodes. For anchor nodes, a fuzzy inference system is designed to identify the presence of anomalous behavior. The detection schemes are implemented at every node for enabling identification of multiple and duplicate anomalies at its origin. We simulated the network, modeled anomalies and analyzed the performance of detection schemes at anchor nodes and sensor nodes. The results indicate that anomaly detection systems offer an acceptable accuracy with high true positive rate and F-Score.

A Systematic Review on the Influence of User Personality in Rumor and Misinformation Propagation Through Social Networks

Abstract: Even though social networks serve as a prominent medium for faster dissemination of information, the rate of rumors and false information spreading through social networks has increased to a great extent in recent times The fast spread of rumors through social networks greatly depends on the number of people who believe rumors and share it with other users in their social network circle In order to combat rumor propagation through social networks effectively, the personality of people involved in rumor propagation needs to be studied in detail This paper discusses the significance of user behavior analysis in rumor propagation analysis highlighting the concepts of personality study as user personality play a major role in rumor sharing This survey throws lights into some of the personality theories for user personality prediction in the context of social networks and explains how user personality is associated with rumor diffusion on social networks This paper presents an overview of the works done in the domain of rumor propagation through social networks utilizing user personality and it summarizes the different approaches put forward by the researchers to elicit personality of users from their social networking pattern This survey presents some of the available datasets for user personality prediction using social network data and it also outlines the open challenges and future directions in this research domain This review attempts to serve as a reference for upcoming researchers working towards rumor propagation analysis utilizing the concept of user behavior prediction

Application of Cognitive Computing for Smart Crowd Management

Abstract: A crowd can be defined as a large gathering of people at a particular place showing different types of attitudes and behaviors. Monitoring and tracking these wide varieties of people is tedious in a real environment. The crowded scenarios have a high tendency to change into an abnormal condition due to sudden external pressures such as gunshots/fire or internal stress such as overcrowding, where things get often uncontrollable and the consequences are disastrous. Moreover, the use of a large number of monitoring cameras and the limited capability of human operators to analyze the video contents result in an urge to developing smart crowd monitoring systems with humanlike capabilities. This article discusses the human cognition capability and its application for smart crowd management. Cognitive computing facilitates complex task automation, real-time decision-making, predictive analytics, and processing of voluminous structured and unstructured data.

Deep Learning Approaches for IoT Security in the Big Data Era

Abstract: The confluence of innovative technologies in wireless communications led to the evolution of the Internet of Things (IoT). According to recent studies, this cartel of things entrenched with electronic components, software, sensors, actuators coupled with the Internet, will increase to 50 billion by 2020. The giant stride in the number of IoT devices makes them the major genesis of data. IoT is triggering a massive influx of big data. To reap out the maximum efficacy of IoT, the massive amount of data is harnessed and converted to actionable insights utilizing the big data analytics. This makes the Internet of Things more intelligent than mere monitoring devices. Big data and IoT works well conjointly to offer analysis and insights. With the conjunction of the Internet of things, big data analytics shift the computing paradigm to the edges for real-time decision making.

Security in Computing and Communications : 7th International Symposium, SSCC 2019, Trivandrum, India, December 18–21, 2019, Revised Selected Papers

Abstract: This book constitutes the refereed proceedings of the 7th International Symposium on Security in Computing and Communications, SSCC 2019, held in Trivandrum, India, in December 2019. The 22 revised full papers and 7 revised short papers presented were carefully reviewed and selected from 61 submissions. The papers cover wide research fields including cryptography, database and storage security, human and societal aspects of security and privacy.

A psychology-inspired trust model for emergency message transmission on the Internet of Vehicles (IoV)

Abstract: The future transportation systems demand an intelligent traffic system that can be achieved by connecting the vehicles to the Internet of Things (IoT) which in turn forms an Internet of Vehicles (I...

Flying Ad Hoc Networks: Security, Authentication Protocols, and Future Directions

Abstract: This chapter also gives an insight into the latest trends in the field of authentication and the possibilities for developing lightweight and novel mechanisms for Flying Ad hoc NETwork (FANET) authentication. Authentication is the primary step towards securing any ad hoc network which ensures the identity of the entity involved in the communication and gives the privilege of accessing the secret and sensitive network data only to the authentic users. The node mobility and dynamic topology changes are very high in FANET and hence pose higher security challenges when compared with other ad hoc networks like Mobile Ad hoc NETwork and Vehicular Ad hoc Network. Message authentication is different from user authentication. Message authentication is the process of checking the integrity of the data and verifying its source. Authentication provides a mechanism to filter out unauthorized users from valid users and provide network privacy and security.

Secure Big Data Transmission with Trust Management for the Internet of Things (IoT)

Abstract: Big data and Internet of Things (IoT) are the highly sought-after frameworks these days because IoT connects abundant amount of data which cannot be labeled and stored in the typical database system. Generating intelligent decisions from enormously increasing data in a real-time system is of major concern. Although big data seems to change our lives, it tries to make a burden in the computing environment due to the proliferation of data. In such a context, the efficient collection, processing, analyzing and secure storage are identified to be some of the crucial steps. The continuous flow of incoming data to the big data is the first and major challenge and this concern may play a key role in designing a viable and secure big data. In addition, the security issues can be even worse when the stored data include highly sensitive and confidential information. Therefore, if strong security measures are not applied in big data storage, it will cause some vital consequences. Trust management can be considered as a critical factor which operates seamlessly behind the scenes in IoT big data era to provide a reliable communication between devices. This chapter aims to disclose the trust management techniques prevailing in IoT with a special focus on big data technologies, and will outline the new developments and approaches that are applicable in these areas.