Volume 24, Issue 4

This article describes and evaluates an approach to create and/or improve tactical agents through direct human interaction in real time through a force-feedback haptic device. This concept takes advantage of a force-feedback joystick to enhance motor skill and decision-making transfer from the human to the agent in real time. Haptic devices have been shown to have high bandwidth and sensitivity. Experiments are described for this new approach, named Instructional Learning. It is used both as a way to build agents from scratch as well as to improve and/or correct agents built through other means. The approach is evaluated through experiments that involve three applications of increasing complexity – chasing a fleer (Chaser), shepherding a flock of sheep into a pen (Sheep), and driving a virtual automobile (Car) through a simulated road network. The results indicate that in some instances, instructional learning can successfully create agents under some circumstances. However, instructional learning failed to build and/or improve agents in other instances. The Instructional Learning approach, the experiments, and their results are described and extensively discussed.

Images are an important source of data and information in the agricultural sciences. The use of image-processing techniques has outstanding implications for the analysis of agricultural operations. Fruit and vegetable classification is one of the major applications that can be utilized in supermarkets to automatically detect the kinds of fruits or vegetables purchased by customers and to determine the appropriate price for the produce. Training on-site is the underlying prerequisite for this type of arrangement, which is generally caused by the users having little or no expert knowledge. We explored various methods used in addressing fruit and vegetable classification and in recognizing fruit disease problems. We surveyed image-processing approaches used for fruit disease detection, segmentation and classification. We also compared the performance of state-of-the-art methods under two scenarios, i.e., fruit and vegetable classification and fruit disease classification. The methods surveyed in this paper are able to distinguish among different kinds of fruits and their diseases that are very alike in color and texture.

Human skin detection is an essential phase in face detection and face recognition when using color images. Skin detection is very challenging because of the differences in illumination, differences in photos taken using an assortment of cameras with their own characteristics, range of skin colors due to different ethnicities, and other variations. Numerous methods have been used for human skin color detection, including the Gaussian model, rule-based methods, and artificial neural networks. In this article, we introduce a novel technique of using the neural network to enhance the capabilities of skin detection. Several different entities were used as inputs of a neural network, and the pros and cons of different color spaces are discussed. Also, a vector was used as the input to the neural network that contains information from three different color spaces. The comparison of the proposed technique with existing methods in this domain illustrates the effectiveness and accuracy of the proposed approach. Tests were done on two databases, and the results show that the neural network has better precision and accuracy rate, as well as comparable recall and specificity, compared with other methods.

This work proposes a hybrid heuristic algorithm to solve the bus rapid transit (BRT) intelligent scheduling problem, which is a combination of the genetic algorithm, simulated annealing algorithm, and fitness scaling method. The simulated annealing algorithm can increase the local search ability of the genetic algorithm, so as to accelerate its convergence speed. Fitness scaling can reduce the differences between individuals in the early stage of the algorithm, to prevent the genetic algorithm from falling into a local optimum through increasing the diversity of the population. It can also increase the selection probability of outstanding individuals, and speed up the convergence at the late stage of the algorithm, by increasing the differences between individuals. Using real operational data of BRT Line 1 in a city of Zhejiang province, the new scheduling scheme can be obtained through algorithm simulation. The passengers’ total waiting time in a single way will be reduced by 40 h on average under the same operating cost compared with the original schedule scheme in a day.

Emotions play a significant role in human cognitive processes such as attention, motivation, learning, memory, and decision making. Many researchers have worked in the field of incorporating emotions in a cognitive agent. However, each model has its own merits and demerits. Moreover, most studies on emotion focus on steady-state emotions than emotion switching. Thus, in this article, a domain-independent computational model of emotions for intelligent agent is proposed that have modules for emotion elicitation, emotion regulation, and emotion transition. The model is built on some well-known psychological theories such as appraisal theories of emotions, emotion regulation theory, and multistore human memory model. The design of the model is using the concept of fuzzy logic to handle uncertain and subjective information. The main focus is on primary emotions as suggested by Ekman; however, simultaneous elicitation of multiple emotions (called secondary emotion) is also supported by the model.

Ns2 is an open-source communications network simulator primarily used in research and teaching. Ns2 provides substantial support for simulation of TCP, routing, and multicast protocols over wired and wireless networks. Although Ns2 is a widely used powerful simulator, it lacks a way to measure networks that are used to assess reliability and performance metrics (e.g., the number of packets transferred from source to destination, delay in packets, packet loss, etc.) and it does not analyse the trace files it produces. The data obtained from the simulations are not straightforward to analyse. Ns2 is still unable to provide any data analysis statistics or graphics as requested. Moreover, the analysis of the Ns2 trace file using any software scripts requires further steps by a developer to do data processing and then produce graphical outputs. Lack of standardisation of tools means that results from different users may not be strictly comparable. There are alternative tools; however, most of them are not standalone applications, requiring some additional libraries. Also, they lack a user-friendly interface. This article presents the architecture and development considerations for the NsGTFA (Ns2 GUI Trace File Analyser) tool, which intends to simplify the management and enable the statistical analysis of trace files generated during network simulations. NsGTFA runs under Windows and has a friendly graphical user interface. This tool is a very fast standalone application implemented in VC++, taking as input an Ns2 trace file. It can output two-dimensional (2D) and 3D graphs (points, lines, and bar charts) or data sets, whatever the trace file format (Tagged, Old, or New). It is also possible to specify the output of standard network performance metrics. NsGTFA satisfies most user needs. There is no complex installation process, and no external libraries are needed.

In a communication network with a source node, a multicast tree is defined as a tree rooted at the source node and all its leaves being recipients of the multicast originating at the source. The tree or bandwidth cost is normally measured by its utilization of tree links along with the quality of service (QoS) measures such as delay constraint and end-to-end delay. However, if nodes are allowed to join or leave the multicast group at any time during the lifetime of the multicast connection, then the problem is known as dynamic multicast routing problem. In this article, we combine a greedy approach with static multicast routing using Tabu Search to find a low-cost dynamic multicast tree with desirable QoS parameters. The proposed algorithm is then compared with several static multicast routing algorithms. The simulation results show that, on a large number of events, i.e., where nodes are leaving or joining, the proposed algorithm is able to find multicast trees of lower cost and more desirable QoS properties.

Online social networks are highly dynamic and sparse. One of the main problems in analyzing these networks is the problem of predicting the existence of links between users on these networks: the link prediction problem. Many studies have been conducted to predict links using a variety of techniques like the decision tree and the logistic regression approaches. In this work, we will illustrate the use of the rough set theory in predicting links over the Facebook social network based on homophilic features. Other supervised learning algorithms are also employed in our experiments and compared with the rough set classifier, such as naive Bayes, J48 decision tree, support vector machine, logistic regression, and multilayer perceptron neural network. Moreover, we studied the influence of the “common groups” and “common page likes” homophilic features on predicting friendship between users of Facebook, and also studied the effect of using the Jaccard coefficient in measuring the similarity between users’ homophilic attributes compared with using the overlap coefficient. We conducted our experiments on two different datasets obtained from the Facebook online social network, where users in each dataset live within the same geographical region. The results showed that the rough set classifier significantly outperformed the other classifiers in all experiments. The results also demonstrated that the common groups and the common page likes features have a significant influence on predicting the friendship between users of Facebook. Finally, the results revealed that using the overlap coefficient homophilic features provided better results than that of the Jaccard coefficient features.

We address the problems of localization, mapping, and guidance for robots with limited computational resources by combining vision with the metrical information given by the robot odometry. We propose in this article a novel light and robust topometric simultaneous localization and mapping framework using appearance-based visual loop-closure detection enhanced with the odometry. The main advantage of this combination is that the odometry makes the loop-closure detection more accurate and reactive, while the loop-closure detection enables the long-term use of odometry for guidance by correcting the drift. The guidance approach is based on qualitative localization using vision and odometry, and is robust to visual sensor occlusions or changes in the scene. The resulting framework is incremental, real-time, and based on cheap sensors provided on many robots (a camera and odometry encoders). This approach is, moreover, particularly well suited for low-power robots as it is not dependent on the image processing frequency and latency, and thus it can be applied using remote processing. The algorithm has been validated on a Pioneer P3DX mobile robot in indoor environments, and its robustness is demonstrated experimentally for a large range of odometry noise levels.

A new method of multiattribute decision making is proposed based on the max-min and min-max gray association degree. The gray association coefficients between the alternative, positive ideal solution and negative ideal solution are defined. Here, we construct a bi-objective programming model that maximizes the minimum gray association degree and minimizes the maximum gray association degree simultaneously. By using the linear weighted summation method, the bi-objective programming model is transformed into a linear programming model. Thus, we can obtain the weight vector of attributes by solving the linear programming model. The ranking order of alternatives is generated according to the relative closeness. A numerical example is examined to demonstrate the applicability and implementation process of the decision method proposed in this paper.

The purpose of this study is to propose and develop an intelligent e-learning system based on advanced document management techniques at Al-Quds Open University (QOU). In this article, we focus on a case using e-mail contents as supplement educational materials at QOU. We describe how the interactive classification system based on concept hierarchy can simplify this task. This system provides the functions to index, classify, and retrieve a collection of e-mail messages based on user profiles. By automatically indexing e-mail messages using our E-mail Classification System for e-Learning, instructors and/or students can easily find their messages and find the topics. The test results of our system evaluation showed that a good classification quality has been achieved, with a precision of 77.4%, recall of 90%, and F -measure of 82.8.