Human-centric Computing and Information Sciences

As network traffic grows and attacks become more prevalent and complex, we must find creative new ways to enhance intrusion detection systems (IDSes). Recently, researchers have begun to harness both machine learning and cloud computing technology to better identify threats and speed up computation times. This paper explores current research at the intersection of these two fields by examining cloud-based network intrusion detection approaches that utilize machine learning algorithms (MLAs). Specifically, we consider clustering and classification MLAs, their applicability to modern intrusion detection, and feature selection algorithms, in order to underline prominent implementations from recent research. We offer a current overview of this growing body of research, highlighting successes, challenges, and future directions for MLA-usage in cloud-based network intrusion detection approaches.

3D face recognition has become a trending research direction in both industry and academia. It inherits advantages from traditional 2D face recognition, such as the natural recognition process and a wide range of applications. Moreover, 3D face recognition systems could accurately recognize human faces even under dim lights and with variant facial positions and expressions, in such conditions 2D face recognition systems would have immense difficulty to operate. This paper summarizes the history and the most recent progresses in 3D face recognition research domain. The frontier research results are introduced in three categories: pose-invariant recognition, expression-invariant recognition, and occlusion-invariant recognition. To promote future research, this paper collects information about publicly available 3D face databases. This paper also lists important open problems.

In the present scenario, the term wireless body area network (WBAN) is becoming an integral part of human day to day life due its wide variety of applications, especially in the field of healthcare systems. To design such a reliable body area network system, there are a number of factors to be considered both in hardware and software levels. One of such factors still developing is the design and the analysis of routing protocols in the network layer. Routing protocols are a set of protocols which can identify and maintain the routes in the network so that the data can be exchanged between the nodes efficiently. Hence, routing protocol plays a vital role in the wireless sensor networks for reliable communication between the sensor nodes. In this paper, different routing protocols for body area networks are surveyed and observed that they are affected by factors like energy, network topology, various quality of services (QoS) in the nodes, node temperature, transmission range of nodes, human posture, etc. An evocative taxonomy of protocols is presented such as cluster-based, cross-layered, postural movement based, QoS aware and temperature-aware routing protocols. From the survey, it is found that the selection of a routing protocol is application dependent. For example, the energy efficient protocols like reinforcement learning based routing with QoS support or wireless autonomous spanning tree protocol can be used for daily health monitoring systems due to its high packet delivery ratio. If the system is for in vivo networks, routing algorithm for network of homogeneous and Id-less biomedical sensor nodes or mobility-supporting adaptive threshold-based Thermal-aware energy-efficient multi-hop protocols are the suitable ones. For critical and emergency cases, where accuracy with little delay is the major concern, the protocols like critical data routing, reliability aware routing, data-centric multi objective QoS-aware routing protocol, etc. can be rightly chosen. This entire survey paper can be used by the researchers as a reference for studying various WBAN routing protocols, especially in the field of medical health care systems.

Email is of critical importance as a communication channel for both business and personal matters. Unfortunately, it is also often exploited for phishing attacks. To defend against such threats, many organizations have begun to provide anti-phishing training programs to their employees. A central question in the development of such programs is how they can be designed sustainably and effectively to minimize the vulnerability of employees to phishing attacks. In this paper, we survey and categorize works that consider different elements of such programs via a clearly laid-out methodology, and identify key findings in the technical literature. Overall, we find that researchers agree on the answers to many relevant questions regarding the utility and effectiveness of anti-phishing training. However, we identified influencing factors, such as the impact of age on the success of anti-phishing training programs, for which mixed findings are available. Finally, based on our comprehensive analysis, we describe how a well-founded anti-phishing training program should be designed and parameterized with a set of proposed research directions.

Training Programs to enhance Math Solving Skills, Memory, Visualization, etc in children are gaining popularity worldwide. Any skill is better acquired, when attention, the basic cognitive ability of the trainee is improved. This study makes an attempt to devise a technique in the form of a Brain Computer Interface (BCI) Game, to assist the trainers in monitoring and evaluating the attention levels of the trainees, at regular intervals during the training period.

The gaming environment is designed using Open Source Graphics Library (OpenGL) package and the game control is through the player’s brain waves using the BCI technology. The players control the movement of an object from a source to a destination location on the screen by focussing their thought processes. The time taken to complete one game can be recorded. More the time taken, lesser would be the attention sustaining capacity of the player.

Thirteen subjects under different levels of the ABACUS Math Solving training program controlled the ball movement while solving math problems mentally, the time taken reduced for most of the subjects as they reached higher levels of their training course, indicating the benefit of such training programmes. The game was also played by eight non-abacus literates. The evaluation procedure was found to be very easy and fast.

Drawing on a 1-year application design, implementation and evaluation experience, this paper examines how engaging users in the early design phases of a software application is tightly bound to the success of that application in use. Through the comparison between two different approaches to collaborative application design (namely, user-centered vs participatory), we reveal how sensitivity to the role that users may play during that collaborative practice rebounds to a good level of user satisfaction during the evaluation process. Our paper also contributes to conversations and reflections on the differences between those two design approaches, while providing evidences that the participatory approach may better sensitize designers to issues of users’ satisfaction. We finally offer our study as a resource and a methodology for recognizing and understanding the role of active users during a process of development of a software application.

Model checking is an influential method to verify complex interactions, concurrent and distributed systems. Model checking constructs a behavioral model of the system using formal concepts such as operations, states, events and actions. The model checkers suffer some weaknesses such as state space explosion problem that has high memory consumption and time complexity. Also, automating temporal logic is the main challenge to define critical specification rules in the model checking. To improve the model checking weaknesses, this paper presents Graphical Symbolic Modeling Toolkit (GSMT) to design and verify the behavioral models of distributed systems. A behavioral modeling framework is presented to design the system behavior in the forms of Kripke structure (KS) and Labeled Transition System (LTS). The behavioral models are created and edited using a graphical user interface platform in four layers that include a design layer, a modeling layer, a logic layer and a symbolic code layer. The GSMT generates a graphical modeling diagram visually for creating behavioral models of the system. Also, the temporal logic formulas are constructed according to some functional properties automatically. The executable code is generated according to the symbolic model verifier that user can choose the original model or reduced model with respect to a recursive reduced model. Finally, the generated code is executed using the NuSMV model checker for evaluating the constructed temporal logic formulas. The code generation time for transforming the behavioral model is compared to other model checking platforms. The proposed GSMT platform has outperformed evaluation than other platforms.

Location-based mobile marketing recommendation has become one of the hot spots in e-commerce. The current mobile marketing recommendation system only treats location information as a recommended attribute, which weakens the role of users and shopping location information in the recommendation. This paper focuses on location feedback data of user and proposes a location-based mobile marketing recommendation model by convolutional neural network (LBCNN). First, the users’ location-based behaviors are divided into different time windows. For each window, the extractor achieves users’ timing preference characteristics from different dimensions. Next, we use the convolutional model in the convolutional neural network model to train a classifier. The experimental results show that the model proposed in this paper is better than the traditional recommendation models in the terms of accuracy rate and recall rate, both of which increase nearly 10%.

Unlike retail stores, in which the user is forced to be physically present and active during restricted opening hours, online shops may be more convenient, functional and efficient. However, traditional online shops often have a narrow bandwidth for product visualizations and interactive techniques and lack a compelling shopping context. In this paper, we report a study on eliciting user-defined gestures for shopping tasks in an immersive VR (virtual reality) environment. We made a methodological contribution by providing a varied practice for producing more usable freehand gestures than traditional elicitation studies. Using our method, we developed a gesture taxonomy and generated a user-defined gesture set. To validate the usability of the derived gesture set, we conducted a comparative study and answered questions related to the performance, error count, user preference and effort required from end-users to use freehand gestures compared with traditional immersive VR interaction techniques, such as the virtual handle controller and ray-casting techniques. Experimental results show that the freehand-gesture-based interaction technique was rated to be the best in terms of task load, user experience, and presence without the loss of performance (i.e., speed and error count). Based on our findings, we also developed several design guidelines for gestural interaction.