An appraisal and design of a multi-agent system based cooperative wireless intrusion detection computational intelligence technique

The deployment of wireless sensor networks and mobile ad-hoc networks in applications such as emergency services, warfare and health monitoring poses the threat of various cyber hazards, intrusions and attacks as a consequence of these networks’ openness. Among the most significant research difficulties in such networks safety is intrusion detection, whose target is to distinguish between misuse and abnormal behavior so as to ensure secure, reliable network operations and services. Intrusion detection is best delivered by multi-agent system technologies and advanced computing techniques. To date, diverse soft computing and machine learning techniques in terms of computational intelligence have been utilized to create Intrusion Detection and Prevention Systems (IDPS), yet the literature does not report any state-of-the-art reviews investigating the performance and consequences of such techniques solving wireless environment intrusion recognition issues as they gain entry into cloud computing. The principal contribution of this paper is a review and categorization of existing IDPS schemes in terms of traditional artificial computational intelligence with a multi-agent support. The significance of the techniques and methodologies and their performance and limitations are additionally analyzed in this study, and the limitations are addressed as challenges to obtain a set of requirements for IDPS in establishing a collaborative-based wireless IDPS (Co-WIDPS) architectural design. It amalgamates a fuzzy reinforcement learning knowledge management by creating a far superior technological platform that is far more accurate in detecting attacks. In conclusion, we elaborate on several key future research topics with the potential to accelerate the progress and deployment of computational intelligence based Co-WIDPSs.     

Predicting the determinants of the NFC-enabled mobile credit card acceptance: A neural networks approach

The main aim of this study is to determine the factors influencing the adoption of Near Field Communication (NFC)-enabled mobile credit card, an innovation in contactless payment for the future generation. Constructs from psychological science, trust-based and behavioral control theories were incorporated into the parsimonious TAM. Using empirical data and Structural Equation Modeling-Artificial Neural Networks approach together with multi group analysis, the effects of social influence, personal innovativeness in information technology, trust, perceived financial cost, perceived usefulness and perceived ease of use were examined. The significance of indirect effects was examined using the bias-corrected percentile with two-tailed significance through bootstrapping. Gender, age, experience and usage were introduced as the moderator variables with industry being the control variable in the research model. The scarcity in studies regarding the moderating effects of these variables warranted the needs to further investigate their impacts. The mediating effect of perceived usefulness was examined using the Baron–Kenny’s technique. The findings of this study have provided invaluable theoretical, methodological and managerial implications and will contribute to the decision making process by CEOs, managers, manufacturers and policy makers from the mobile manufacturing industry, businesses and financial institutions, mobile commerce, mobile telecommunication providers, mobile marketers, private or government practitioners and etc.     

Investigating the Tribological Characteristics of Burnished Polyoxymethylene—ANFIS and FE Modeling

ABSTRACT

Polymers are utilized in numerous tribological applications because of their excellent characteristics; for example, accommodating shock loading and shaft misalignment. A high surface finish is required to ensure consistently good performance and extended service life of manufactured polymeric components. Burnishing is the best choice as a finishing process for this study due to its ability to increase hardness, fatigue strength, and wear resistance and also introduce compressive residual stress on the burnished workpiece. Due to the complexity and uncertainty of the machining processes, soft computing techniques are preferred for anticipating the performance of the machining processes. In this study, ANFIS as an adaptive neuro-fuzzy inference system was applied to anticipate the workpiece hardness and surface roughness after the roller burnishing process. Five burnishing variables, including burnishing depth, feed rate, speed, roller width, and lubrication mode, were analyzed. A Gauss membership function was used for the training process in this study. The predicted surface roughness and hardness data were compared with experimental results and indicated that the Gauss membership function in ANFIS has satisfying accuracy as high as 97% for surface roughness and 96% for hardness. Furthermore, the generated compressive residual stress on the burnished surface was studied by a 2D finite element model (FEM). The simulated results of residual stress were validated with the experimental results obtained from X-ray diffraction (XRD) tests.     

Investigation of the effect of machining parameters on the surface quality of machined brass (60/40) in CNC end milling—ANFIS modeling

Brass and brass alloys are widely employed industrial materials because of their excellent characteristics such as high corrosion resistance, non-magnetism, and good machinability. Surface quality plays a very important role in the performance of milled products, as good surface quality can significantly improve fatigue strength, corrosion resistance, or creep life. Surface roughness (Ra) is one of the most important factors for evaluating surface quality during the finishing process. The quality of surface affects the functional characteristics of the workpiece, including fatigue, corrosion, fracture resistance, and surface friction. Furthermore, surface roughness is among the most critical constraints in cutting parameter selection in manufacturing process planning. In this paper, the adaptive neuro-fuzzy inference system (ANFIS) was used to predict the surface roughness in computer numerical control (CNC) end milling. Spindle speed, feed rate, and depth of cut were the predictor variables. Experimental validation runs were conducted to validate the ANFIS model. The predicted surface roughness was compared with measured data, and the maximum prediction error for surface roughness was 6.25 %, while the average prediction error was 2.75 %.     

Electric field enhancements in In2O3-coated single-walled carbon nanotubes

In₂O₃ nanoparticles are coated on the surfaces of single-walled carbon nanotubes (SWCNTs) by a successive ionic layer adsorption and reaction process. The thickness of the In₂O₃ nanoparticle film is tuned by controlling the number of coating cycles. The electric field around the In₂O₃-coated SWCNTs is compared with that of pristine SWCNTs. Field enhancement of the In₂O₃-coated SWCNTs is confirmed by conductive atomic force microscopy at low electric field (contact mode: 1 V to −1 V) and also field emission (FE) analysis at high electric field (0–4.2 V/μm). The uniformity and emission stability are also measured via FE analysis. Near infrared and X-ray photoemission spectroscopy data are suggested to explain the charge transfer, bandgap change between the In₂O₃ nanoparticles and SWCNTs, and the electric field enhancements in the In₂O₃-coated SWCNTs at both low and high electric field.     

Early detection of human actions—A hybrid approach

Early detection of human actions is essential in a wide spectrum of applications ranging from video surveillance to health-care. While human action recognition has been extensively studied, little attention is paid to the problem of detecting ongoing human action early, i.e. detecting an action as soon as it begins, but before it finishes. This study aims at training a detector to be capable of recognizing a human action when only partial action sample is seen. To do so, a hybrid technique is proposed in this work which combines the benefits of computer vision as well as fuzzy set theory based on the fuzzy Bandler and Kohout's sub-triangle product (BK subproduct). The novelty lies in the construction of a frame-by-frame membership function for each kind of possible movement. Detection is triggered when a pre-defined threshold is reached in a suitable way. Experimental results on a publicly available dataset demonstrate the benefits and effectiveness of the proposed method.     

In vitro behaviour of sol-gel interconnected porous scaffolds of doped wollastonite

Using the sol-gel method, two different three-dimensional (3D) porous interconnected scaffolds were prepared, whose compositions were MgO-K₂O-CaO-SiO₂ (MgO-K₂O-wollastonite) and Na₂O-K₂O-CaO-SiO₂ (Na₂O-K₂O-wollastonite). Scaffold sintering was performed at 950 °C for 8 h. The scaffolds were obtained and soaked in simulated body fluid for different times (6 h, 3 d, 7 d and 14 d) to study their in vitro behaviour. Scanning electron microscopy and energy-dispersive X-ray spectroscopy revealed the presence of both a hydroxyapatite-like microstructure and a nanostructure on the surface of 3D scaffolds. The presence of Na and K in the scaffolds resulted in the precipitation of a hierarchical hydroxyapatite-like layer composed of nanorods, approximately 200–400 nm in size. The presence of Mg and K ions in the composition caused the precipitation of particles with a nanorod morphology, approximately 50–100 nm in size. The addition of Na, K and Mg, K to the wollastonite resulted in scaffolds with mechanical strengths of 0.03 and 0.02 MPa, respectively.     

Cooperative learning for radial basis function networks using particle swarm optimization

This paper presents a new evolutionary cooperative learning scheme, able to solve function approximation and classification problems with improved accuracy and generalization capabilities. The proposed method optimizes the construction of radial basis function (RBF) networks, based on a cooperative particle swarm optimization (CPSO) framework. It allows for using variable-width basis functions, which increase the flexibility of the produced models, while performing full network optimization by concurrently determining the rest of the RBF parameters, namely center locations, synaptic weights and network size. To avoid the excessive number of design variables, which hinders the optimization task, a compact representation scheme is introduced, using two distinct swarms. The first swarm applies the non-symmetric fuzzy means algorithm to calculate the network structure and RBF kernel center coordinates, while the second encodes the basis function widths by introducing a modified neighbor coverage heuristic. The two swarms work together in a cooperative way, by exchanging information towards discovering improved RBF network configurations, whereas a suitably tailored reset operation is incorporated to help avoid stagnation. The superiority of the proposed scheme is illustrated through implementation in a wide range of benchmark problems, and comparison with alternative approaches.     

Highly efficient photo-degradation of methyl blue and band gap shift of SnS nanoparticles under different sonication frequencies

Stannous sulfide (SnS) nanoparticles (NPs) were synthesized via a sonochemical route with 20 and 50 kHz sonication frequencies. Structure study revealed an orthorhombic phase of SnS. The SnS NPs that were synthesized by 20 kHz sonication had smaller diameter in comparison to the NPs that were synthesized by 50 kHz sonication. An optical investigation confirmed that the SnS particles had strong emission bands located at the UV and visible regions and suggested that they have the potential to be used as optical devices. This inference was further strengthened by the absorption coefficient values. In addition, their photocatalytic properties were tested by degrading methyl blue in distilled water under visible light. The results showed that SnS nanoparticles synthesized under the lower sonication frequency had better photocatalytic activity. Given these results, the sonication frequency appears to be an important synthesis parameter in the formation of SnS nanoparticles and their optical and photocatalytic properties.     

Numerical study of nanofluid forced convection flow in channels using different shaped transverse ribs

A numerical investigation is performed to study the effects of different rib shapes and turbulent nanofluid flow on the thermal and flow fields through transversely roughened rectangular channels with Reynolds number ranging from 5000 to 20000 and uniform heat flux of 10 kW/m². Considering single-phase approach, the two-dimensional continuity, Navier–Stokes, and energy equations were solved by using the finite volume method (FVM). The optimization was carried out by using various rib shapes (rectangular shape, triangular shape, wedge pointing upstream, and wedge pointing downstream) in two arrangements (in-line and staggered) and three different aspect ratios (w/e = 0.5, 2, and 4) to reach the optimal geometry with maximum performance evaluation criterion (PEC). The main aim of this study is to analyze the effects of nanoparticle types (Al₂O₃, CuO, SiO₂, and ZnO), concentration (1–4%), and nanoparticle diameter (30–80 nm), on the heat transfer and fluid flow characteristics. Simulation results show that the ribbed channels' performance was greatly influenced by rib shapes and their geometrical parameters. The highest PEC was obtained for the in-line triangular ribs with w/e = 4 at Re = 5000. It is found that the water–SiO₂ shows the highest heat transfer enhancement compared with other tested nanofluids. The Nusselt number through the ribbed channels was enhanced with the increase of the particle volume fraction and Reynolds number, and with the decrease of nanoparticle diameter.