The diagnosis and prognosis of misaligned rotor systems have gained importance in recent times. Misalignment has become one of the main reasons for system vibration, which reduces the life and stability of machine parts, making it vitally important for machines to perform effectively without any catastrophic failure. Limited research has been reported on understanding its effect on rotor systems. Even if zero misalignment is achieved at the beginning, it cannot be retained over longer durations due to various reasons. Many techniques like DWT, CWT, and HHT are also used to understand the misalignment problem. Some advanced techniques such as MCSA, thermal imaging, and the acoustic emission technique have come into existence and become important tools to classify faults, leading to more reliable misalignment diagnosis. In the present study, a detailed literature review is conducted to diagnose and classify misalignments. All recent techniques and their limitations are discussed, and a hybrid approach is presented for the lucid understanding of this fault and its classification.

In many dynamic complex systems, the insufficiency of data makes components state probability estimation more difficult in most cases. This paper presents a new approach for evaluating complex system availability under epistemic uncertainties, based on a combination of the Dempster-Shafer Theory (DST) and a dynamic Bayesian network (DBN). This combination is called a dynamic evidential network (DEN). DST is well known for its utility and purpose to express uncertain experts' judgments about components state beliefs for treating epistemic uncertainty. In addition, the dynamic evidential network makes it possible to propagate this uncertainty while taking into consideration dynamic evolution and the dependency between components using conditional mass tables. Finally, a case study is presented as a validation of this approach.

Computers and mobile phones have become an essential part of modern life. Improper ergonomic posture while looking at screens and reduced physical activities in regular life can lead to musculoskeletal disorders. Irrespective of age, many adults these days are being affected due to their working cultures and lifestyles. The therapies used for musculoskeletal disorders at the early stages of the disease yield good results. A cervical traction device is one such therapeutic device used for treating several such disorders like cervical spondylosis, cervical disc bulges, and cervical compression syndrome. Although several therapeutic machines exist, they are bulky, expensive, uncomfortable, and lack self-assistance. Moreover, the existing device can only provide uniaxial traction irrespective of the patient's problem. These devices create unnecessary traction on the other side of the cervical spine for patients with a one-sided disc bulge. Thus, there is a strong need for a new therapeutic device that can provide traction on a single desired side for these patients. A novel therapeutic machine is developed with the feasibility of traction coupled with single-sided twist in the neck. The new traction device uses a pneumatic piston-cylinder arrangement. The individual can have the pressure in the traction device set to his/her liking and can even lower or raise it as needed. For patients who suffer from single-sided cervical problems, the mechanism proposed in the current device can additionally generate a twist along with traction. A study has been conducted on a group of people of different ages, and the new traction device has been proven to be more effective than previous devices.

Online courses will produce different learning effects due to the differences in the structure of knowledge points and the design of the teaching process. Therefore, a knowledge point recommendation algorithm based on enhanced correction factor and weighted sequence pattern mining (ECF-WSPM) is proposed, which divides learners into different groups according to their cognitive levels. To further improve the accuracy of the similarity calculation between learners, we innovatively propose the enhanced correction factor and reconstruct the similarity calculation model between learners based on the enhanced correction factor. In addition, the conceptual interaction of knowledge points and the sequential learning patterns of learners are combined for the first time to effectively mine the differences in the learning behavior characteristics of learners, so as to generate the final recommendation list of knowledge points based on the differences and improve the learning effects of learners. Comparison experiments on the real dataset demonstrate that our proposed algorithm improves the overall performance of the recommended algorithm.

To solve the problem of insulation fault in battery packs in the application of pure electric vehicles, a method of measuring the insulation resistance and the location of the fault is studied. Based on the traditional insulation algorithm, this method makes some improvements. First, this paper builds a system model of insulation resistance. Secondly, the system model is verified by simulation software. Finally, an experimental prototype with designed parameters is built to verify the theoretical derivation and simulation results. The experimental results show that the system can monitor the insulation resistance value at the internal fault location of the battery pack and the corresponding ground short-circuit fault location in a short period of time while ensuring more efficient insulation detection function.

Service evaluation algorithm based on QoS can help users quickly select the best one from mass services to meet their needs. However, the existing service evaluation algorithm rarely considers real-time problems such as users' real-time scenario and QoS volatility. To solve this problem, a grey weighted QoS evaluation algorithm based on real-time scene is proposed. The algorithm is divided into three stages: In the first stage, the environment matching algorithm is used to quickly reject the services that cannot be successfully called due to the current user environment; in the second stage, the real-time dynamic attribute QoS value of candidate services is corrected; in the third stage, the comprehensive weight combined by AHP and entropy weighting method is used to weight the correlation coefficient generated by the grey comprehensive evaluation algorithm, and the service with maximum correlation degree is the optimal selection. The algorithm is tested on QWS dataset, and its feasibility and validity are verified by analysis.

This paper focuses on data information preprocessing methods in the fault classification of rotating machinery. In order to avoid the information loss caused by the weighted fusion method, a merging fusion method is provided to obtain the final feature information. Furthermore, a direct fusion method that synchronizes the extraction and fusion of multi-sensor feature information is also proposed. The artificial neural network is used to test the three proposed information preprocessing methods and obtain rotary machinery fault classification methods. A final comparative experiment is given to compare the three methods proposed above in the fault classification of rotating machinery.

With the rapid growth of software products, software-intensive system-of-systems (SiSoS) is gradually taking shape in many domains, whilst the existing software systems are considered as constituent systems in the SoS. In this research, smart tourism is considered as a SiSoS, which can provide tourists with a better service by gathering abilities of different software systems. However, in system-of-systems engineering, architecture design always consumes a large chunk of time and human resources, with the main reason being knowledge barriers between various fields, which means that knowledge cannot be easily transferred across domains. Consequently, the architecture design is a work that relies on subject-matter experts' communication. Therefore, architecture design is a vital challenge in the development of smart tourism SoS. This paper represents a knowledge-driven architecture design method, which contains two parts. On one hand, ontology is applied as the knowledge representation method so that the constituents' information can be visualised in graph format; on the other hand, description logic based inference rules are designed to be combined with creativity to reason potential connections between the tourism constituent systems. The former helps stakeholders and domain experts understand knowledge of different domains, and the latter assists in revealing potential relationships that can be built between the independent constituent systems. Both of them aim to support decision making for architecture design of the smart tourism SoS. Therefore, the proposed novel ontological approach provides a more automatic method for architecture design in the software-intensive smart tourism SoS. The approach is applied and evaluated in a prototype of Jiangsu Tourism SoS as an application scenario.

Suppose there are two oligopolistic creative enterprises with bounded rationality in the market. In order to maximise profits, they may adopt the strategy of production competition. In this paper, mathematical modeling and numerical simulation are carried out. Specifically, a multi-period duopoly Stackelberg game model with bounded rationality is formulated. Its dynamical evolution and economic equilibrium are investigated. The local stability analysis of four equilibrium points is also carried out. The study shows that the equilibrium will become unstable or chaotic as the output adjustment speed parameter value increases. The greater the adjustment speed is, the higher the degree of complexity of the economic system becomes. Finally, numerical simulations are used to demonstrate the stability region, bifurcation diagrams, and chaos.

Software quality plays an important part in software engineering. Active learning is introduced to conduct supervised learning classifier because labeling cost is very high. However, in the real software quality assurance process, there are fewer labeled instances in the initial stage of software development, and there may be a historical data set developed by the same team. Therefore, learning from the historical data set can be used for an active learning query strategy. In our empirical study, we design and conduct experiments on promise datasets, which are gathered from real open-source projects. We find that the meta active learning query strategy can perform better than the commonly used query strategy when a little data is labeled.

To solve the problems of time consuming and high energy consumption of task scheduling in mobile cloud computing environment, a task scheduling strategy based on fruit fly optimization algorithm was proposed. First, establish a mobile cloud computing task scheduling model; second, in the fruit fly optimization algorithm, orthogonal arrays and quantization techniques are used to initialize the population. The exploration step is used to dynamically adjust to avoid individuals falling into a local optimum. Finally, in each iteration of the fruit fly optimization algorithm, a global search update is performed by introducing an artificial bee colony algorithm. In the simulation experiments, compared with the basic fruit fly optimization algorithm, the improved particle swarm algorithm, and the improved artificial bee colony algorithm, the algorithm in this paper has certain advantages in the comparison of the four indicators: completion time, cost, bandwidth and energy consumption. Besides, this algorithm can effectively improve the task scheduling efficiency under mobile cloud computing.

ZigBee automatic irrigation is a new technology based on Internet of things. Its purpose is to replace the current manual operation mode, reduce costs, and improve efficiency. It uses the mainstream Internet of things technology ZigBee and solar energy water-saving irrigation system. A wireless sensor acquisition network based on ZigBee RF chip CC2530 is constructed. The network coordinator communicates with the host computer through the RS-232 serial port. It realizes the data collection and monitoring of the whole network, thus achieving the automatic monitoring and control of irrigation. The system also uses solar energy as the main power to provide clean energy for the operation of the system, so as to achieve the goal of water saving, energy saving, intelligence, and efficiency.

In this article, a new method for constructing multiple memristors chaotic systems is proposed. The system can generate three-dimensional four-wing smooth continuous chaotic attractors. The dynamic characteristics of the system are analyzed in detail through the results of phase plane diagrams, Poincaré maps, and Lyapunov exponents. Theoretical and numerical simulation results confirm the multi-wing chaotic characteristics of the system. Furthermore, this system is implemented through circuit experiments, and the results show that it can be applied to related chaotic systems.

The inspection of electrical transmission lines is necessary for preventing accidents and power interruptions. In order to save cost and reduce risks, a transmission line detection algorithm based on pixel search is proposed in this paper for camera monitoring. The algorithm can overcome the disadvantages of the Hough transform algorithm, such as large amount of computation and large memory space consumption. Specifically, first, some preprocessing is performed on the obtained image, such as gray processing, Gaussian blur denoising, image arithmetic operations, and grayscale linear transformation. Then, the edges are detected by Canny operator, and an ROI is set to reduce the background interference. Finally, a pixel search method is designed, which searches all the edge pixels of each line in turn, fits the transmission line equations, outputs the quantity of lines, and plots the transmission lines in the image. Experiments show that the proposed algorithm can effectively detect transmission lines, which lays a foundation for judging broken lines, icing, and other issues.

The network security situation assessment of wireless optical waveguide communication networks is non-stationary. In order to improve the evaluation accuracy and ensure the security of these networks, a network security situation assessment algorithm of wireless optical waveguide communication networks based on information quality control is proposed. The intrusion information transmission channel model is constructed, and the fuzzy correlation characteristics of simulating the security situation attribute are extracted. The distributed transmission channel equalization method is used to design the transmission channel equilibrium, and the security situation is evaluated in the equalization channel model. The network security situation assessment parameters of the detected wireless optical waveguide communication network virus attack information are estimated jointly, and the security situation assessment is realized according to the parameter estimation results. The simulation results show that the method has good accuracy and anti-interference ability, and it improves the ability of network security situation assessment.