Inverse optimality in the class of Hopfield neural networks with input nonlinearity

This paper presents the chaos suppression problem in the class of Hopfield neural networks (HNNs) with input nonlinearity using inverse optimality approach. Using the inverse optimality technique and based on Lyapunov stability theory, a stabilizing control law, which is optimal with respect to meaningful cost functional, is determined to achieve global asymptotically stability in the closed-loop system. Numerical simulation is performed on a four-dimensional hyper-chaotic HNN to demonstrate the effectiveness of the proposed method.     

The interaction of plane frames with elastic foundation having normal and shear moduli of subgrade reactions

The interaction of plane frames with an elastic foundation, of the Winkler type, having normal and shear moduli of subgrade reactions was studied.

An exact stiffness matrix for a beam element on an elastic foundation having only a normal modulus of subgrade reaction was modified to include the shear modulus of subgrade reaction of the foundation as well as the axial force in the beam. A computer program was written and used in two case studies. In the first case study the convergence of the modified element was tested: in the second it was employed to study the effect of the foundation normal and shear moduli of subgrade reactions on the bending moments in a selected plane frame. The results indicated that bending moments might be considerably affected according to the type of frame and loading.     

Quality assessment of 3D synthesized images based on structural and textural distortion

Depth image based rendering (DIBR) is a popular technique for rendering virtual 3D views in stereoscopic and autostereoscopic displays. The quality of DIBR-synthesized images may decrease due to various factors, e.g., imprecise depth maps, poor rendering techniques, inaccurate camera parameters. The quality of synthesized images is important as it directly affects the overall user experience. Therefore, the need arises for designing algorithms to estimate the quality of the DIBR-synthesized images. The existing 2D image quality assessment metrics are found to be insufficient for 3D view quality estimation because the 3D views not only contain color information but also make use of disparity to achieve the real depth sensation. In this paper, we present a new algorithm for evaluating the quality of DIBR generated images in the absence of the original references. The human visual system is sensitive to structural information; any deg radation in structure or edges affects the visual quality of the image and is easily noticeable for humans. In the proposed metric, we estimate the quality of the synthesized view by capturing the structural and textural distortion in the warped view. The structural and textural information from the input and the synthesized images is estimated and used to calculate the image quality. The performance of the proposed quality metric is evaluated on the IRCCyN IVC DIBR images dataset. Experimental evaluations show that the proposed metric outperforms the existing 2D and 3D image quality metrics by achieving a high correlation with the subjective ratings.

     

Intelligent facial emotion recognition and semantic-based topic detection for a humanoid robot

Automatic perception of human affective behaviour from facial expressions and recognition of intentions and social goals from dialogue contexts would greatly enhance natural human robot interaction. This research concentrates on intelligent neural network based facial emotion recognition and Latent Semantic Analysis based topic detection for a humanoid robot. The work has first of all incorporated Facial Action Coding System describing physical cues and anatomical knowledge of facial behaviour for the detection of neutral and six basic emotions from real-time posed facial expressions. Feedforward neural networks (NN) are used to respectively implement both upper and lower facial Action Units (AU) analysers to recognise six upper and 11 lower facial actions including Inner and Outer Brow Raiser, Lid Tightener, Lip Corner Puller, Upper Lip Raiser, Nose Wrinkler, Mouth Stretch etc. An artificial neural network based facial emotion recogniser is subsequently used to accept the derived 17 Action Units as inputs to decode neutral and six basic emotions from facial expressions. Moreover, in order to advise the robot to make appropriate responses based on the detected affective facial behaviours, Latent Semantic Analysis is used to focus on underlying semantic structures of the data and go beyond linguistic restrictions to identify topics embedded in the users’ conversations. The overall development is integrated with a modern humanoid robot platform under its Linux C++ SDKs. The work presented here shows great potential in developing personalised intelligent agents/robots with emotion and social intelligence.     

Fisher’s decision tree

Univariate decision trees are classifiers currently used in many data mining applications. This classifier discovers partitions in the input space via hyperplanes that are orthogonal to the axes of attributes, producing a model that can be understood by human experts. One disadvantage of univariate decision trees is that they produce complex and inaccurate models when decision boundaries are not orthogonal to axes. In this paper we introduce the Fisher’s Tree, it is a classifier that takes advantage of dimensionality reduction of Fisher’s linear discriminant and uses the decomposition strategy of decision trees, to come up with an oblique decision tree. Our proposal generates an artificial attribute that is used to split the data in a recursive way.The Fisher’s decision tree induces oblique trees whose accuracy, size, number of leaves and training time are competitive with respect to other decision trees reported in the literature. We use more than ten public available data sets to demonstrate the effectiveness of our method.     

Free and Open Source Software versus Internet content filtering and censorship: A case study

This study critically investigates the main characteristics and features of anti-filtering packages provided by Free and Open Source Software (FOSS). For over a decade, the digital communities around the globe have used FOSS packages not only as an inexpensive way to access to information available on Internet, but also to disseminate thoughts, opinions and concerns about various socio-political and economic matters. Proxy servers and FOSS played a vital role in helping citizens in repressed countries to bypass the state imposed Internet content filtering and censorship practices. On the one hand, proxy servers act as redirectors to websites, and on the other hand, many of these servers are the main source for downloading FOSS anti-filtering software packages. These packages can provide secure web surfing via anonymous web access, data encryption, IP address masking, location concealment, browser history and cookie clean-ups but they also provide proxy software updates as well as domain name updates.The main objectives of this study are to investigate the role of FOSS packages in combating Internet content filtering and censorship and empowering citizens to effectively participate in communication discourse. By evaluating some of the well known FOSS anti-filtering packages used by Iran's digital community, this study found that despite the success of FOSS in combating filtering and state censorship, the majority of these software packages were not designed to meet the needs of Internet users. In particular, they are poorly adapted to the slow Internet connections in many developing countries such as Iran. In addition, these software packages do not meet the level of sophistication used by authorities to filter the content of the Net. Therefore, this study offers a new model that takes into account not only the existing level of the Internet infrastructure but also the growing number of Internet users demanding more effective FOSS packages for faster access to uncensored information while maintaining anonymity.     

A novel image encryption/decryption scheme based on chaotic neural networks

This paper presents a novel image encryption/decryption algorithm based on chaotic neural network (CNN). The employed CNN is comprised of two 3-neuron layers called chaotic neuron layer (CNL) and permutation neuron layer (PNL). The values of three RGB (Red, Green and Blue) color components of image constitute inputs of the CNN and three encoded streams are the network outputs. CNL is a chaotic layer where, three well-known chaotic systems i.e. Chua, Lorenz and Lü systems participate in generating weights and biases matrices of this layer corresponding to each pixel RGB features. Besides, a chaotic tent map is employed as the activation function of this layer, and makes the relationship between the plain image and cipher image nonlinear. The output of CNL, i.e. the diffused information, is the input of PNL, where three-dimensional permutation is applied to the diffused information. The overall process is repeated several times to make the encryption process more robust and complex. A 160-bit-long authentication code has been used to generate the initial conditions and the parameters of the CNL and PNL. Some security analysis are given to demonstrate that the key space of the new algorithm is large enough to make brute-force attacks infeasible and simulations have been carried out with detailed numerical analysis, demonstrating the high security of the new image encryption scheme.     

Intelligent detection of unstable power swing for correct distance relay operation using S-transform and neural networks

The conventional power swing schemes used in distance relay operation are not fast enough to detect and distinguish a fault, stable swing and unstable swing and this may lead to unintended tripping of protection devices. Therefore, there is a need for fast detection of unstable swings so as to improve the reliability of distance relay operation. This paper presents an intelligent approach for detecting unstable swings during distance relay operation using the S-transform signal processing technique and artificial neural networks. To illustrate the effectiveness of the proposed approach, simulations were carried out on the IEEE 39 bus test system using the PSS/E software. Test results showed that the proposed approach using S-transform, multi layer perceptron network and probabilistic neural network can accurately detect and classify fault, stable swing, unstable swing, fault clearance and post fault events for correct distance relay operation.     

Can crisis management teams mitigate COVID-19's effects? A comparative case study between China and the United States

The COVID-19 pandemic has been the world's greatest challenge since World War II. As an unprecedented global public health crisis, crisis management teams (CMTs) in the infected countries need to rethink to cope with the similar uncertainty and urgency of the ongoing COVID-19 pandemic. The shared context of COVID-19 allows us to explore a cross-nation study of different constructs and CMT to communicate information about crises with the public effectively. Since the pandemic affected all countries, the comparison is warranted. Can CMTs mitigate the effects of COVID-19? Based on the analysis of China and the US cases, our study explores how shared and common knowledge cognition among crisis responders plays a pivotal role in effective CMTs' communication while technological failures and inadequate information disrupt the system, worsening pandemics like COVID-19. Furthermore, organizational dysfunction, such as institutional fragmentation, regulatory hurdles and bureaucratic arrogance, impede effective communication between CMTs. However, effective coordination and decisive leadership could improve coordination effectiveness and reduce crisis costs.