To address the multi-objective flexible job shop scheduling problem in rolling production mode (FJSP-RPM), this study proposes a Multi Objective Improved of Salp Swarm Algorithm (MISSA) that simultaneously optimizes equipment utilization and total tardiness. The MISSA generates initial population through various heuristic strategies to improve quality. exploitation capability algorithm is enhanced global crossover strategy variety local search strategies. In terms improvement strategies,...

Sampling subnet is an important topic of complex network research. methods influence the structure and characteristics subnet. Random multiple snowball with Cohen (RMSC) process sampling which combines advantages random proposed in this paper. It has ability to explore global information discover local at same time. The experiments indicate that novel method could keep similarity between original on degree distribution, connectivity rate average shortest path. This applicable situation where...

The Histogram of Oriented Gradient (HOG) feature for pedestrian detection has achieved good results, but it is time-consuming. For resolving this problem, a modified method HOG proposed to reduce the dimension features. On base analyzing process HOG, nine independent channels (HOG-C) are extracted according gradient orientation interval. Through evaluating effectiveness HOG-C individually, combination (CHOG-C) presented based on statistical regularities. Comprehensive experiments INRIA...

Interval Predictor Models (IPMs) offer a non-probabilistic, interval-valued, characterization of the uncertainty affecting random data generating processes. IPMs are constructed directly from data, with no assumptions on distributions uncertain factors driving process, and therefore exempt subjectivity induced by such practice. The reliability an IPM defines probability correct predictions for future samples and, in practice, its true value is always unknown due to finite sizes limited...

The appropriate iteration process model is the basis for managing and optimizing product development process. In this article, we attempt to introduce concept of effectiveness value. relationship between rework probability discussed. evolution function proposed drive overlapped multi-coupled activities. with input information update studied, a simulation presented obtain accurate development. It useful analyze risks during development, has good flexibility versatility. calculation method...

It is an important QFD decision problem to determine the engineering characteristics and their corresponding actual fulfillment levels. With increasing complexity of problems, matrixes become much huger, time spent on analyzing these making decisions will be unacceptable. In this paper, a solution for efficiently solving proposed. The reformulated as mixed integer nonlinear programming (MINLP) model, which aims maximize overall customer satisfaction with consideration enterprises’...

Monitoring multisensor MRI devices using anomaly detection for multivariate time series consists a challenging task. In this use case, we investigate and provide explanations abnormalities detected in sensors during failed scans propose framework sensor condition monitoring XAI feature selection. Sensor properties are preprocessed (normalized, aggregated resampled) used to generate statistical features that fed machine learning models Anomaly Detection (AD), namely Isolation Forest. A...

When designing a product service system scheme, the most critical issue is how to quickly and accurately translate customer value requirements into scheme technical characteristics. It difficult solve this problem by only experience knowledge of engineers. Effective configuration rules are necessary assist engineers in design. Therefore, paper proposes novel rule extraction method based on new imperialist competitive algorithm. Compared traditional algorithms, progressive Latin Hypercube...

Autonomous-Driving technology has begun to bring great convenience daily trip, transportation, and surveying harsh environment. Considering that deep reinforcement learning requirements for the convergence performance of training results, actual results sometimes cannot converge steadily or fail reach goals, in this paper, trained model reuse method was proposed, which can use generates Q(St, At) be used as a part Deep Reinforcement Learning model, built based on value function could predict...

Improving the architecture of product development process (PDP) is an effective approach to improve PDP performance.However, performance difficult model because criterion such as cost, time and quality are usually contradictory.The objective this paper use value evaluation indicator performance.The PDP, well ratio function discussed its quantitative method proposed.The defined effectiveness which considers importance each activity methods based on rework theory deployment (QFD) given.The...

In this paper, we consider a criminal investigation on the collective guilt of part members in working group.Assuming that statistics used are reliable, present Page Rank Model based mutual information.First, use average info rmation between non-suspicious topics and suspicious to score by degree suspicion.Second, build correl ation matrix suspicion acquire corresponding Markov state transition matrix.Then, set original v alue for all group suspicion.At last, calculate suspected each me mber...

In order to research the way increase efficiency of 6-DOF articulated manipulator, a technique optimal trajectory planning is presented. The robot's key positions were presented by series postures in robot linkable model, which can be transformed into joint space as composed value points joints, each adjacent connected period B-spline curves. According mechanical structure features and joints' drive modes, strategy that divides six joints waist, shoulder, elbow another three axis two...

Service supplier selection is the most important problem in process of service outsourcing. Aiming at fuzziness evaluation index and subjectivity decision-making process, a decision method for based on Choquet integral generalized evidence theory proposed. First, uncertainty information are solved by using interval rough number. The importance degree acquisition attribute corrected, relative weight absolute obtained. Second, considering interaction between indexes, n-additive model used to...

Whether the sampling subnets can accurately represent topology and dynamics of original networks is an important research topic. To improve quality network sampling, this paper attempts to convert complex process optimization problem, proposes a novel algorithm which based on Particle Swarm Optimization (PSO). Exponent power-law degree distribution clustering coefficient were set as objectives. Subnets sampled from scale-free by random method, objectives optimized multi-objective optimizer....

An age classification algorithm based on multi-feature weighted decision fusion is proposed. On the basis of calibration for facial positive posture, texture features are extracted by three methods. Firstly, uniform local binary pattern (ULBP) histogram through Gabor wavelet transform which has multi-scale and multi-directional characteristics. Secondly, an ASM-based approach used to complete partition, ULBP from labeled focus region. Thirdly, rate between wrinkles skin areas extracted. A...