Search results

The purpose of this paper is to present a solution space searching method to study the initial design of interplanetary low thrust gravity assist trajectory.

For reducing the complexity and nonlinearity of the initial design problem, a sixth degree inverse polynomial shape based approach is brought. Then some improvements are provided for solving the parameters in the shape function and a quasi‐lambert solver is brought through the shape based method, the thrust profile can be generated under the given time of flight, boundary states including positions and velocities for low thrust phase. Combining gravity assist model, the problem is summarized and an improved pruning technique is used for searching the feasible solution space for low thrust gravity assist trajectory.

Using the solution space searching method, the feasible solution region would be generated under the given mission condition. The treatment about gravity assist demonstrates more accurate than previous method. Also another advantage is that the searching method can be used to design different types of mission trajectory, including flyby and rendezvous trajectories.

The method can be used as an efficient approach to search the feasible region for the complex low thrust gravity assist trajectory, and it can provide appropriate initial guesses for the low thrust gravity assist trajectory in mission design phase.

Feasible solution space would be obtained through the searching method. The quasi‐Lambert solver in the paper is found under the shape‐based method and relative improvement, and it shows its availability during the searching process. Through mission trajectory design, the effectiveness of the method is shown.

The purpose of this paper is three-fold: to review the categories explaining mainly optimization algorithms (techniques) in that needed to improve the generalization performance and learning speed of the Feedforward Neural Network (FNN); to discover the change in research trends by analyzing all six categories (i.e. gradient learning algorithms for network training, gradient free learning algorithms, optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) collectively; and recommend new research directions for researchers and facilitate users to understand algorithms real-world applications in solving complex management, engineering and health sciences problems.

The FNN has gained much attention from researchers to make a more informed decision in the last few decades. The literature survey is focused on the learning algorithms and the optimization techniques proposed in the last three decades. This paper (Part II) is an extension of Part I. For the sake of simplicity, the paper entitled “Machine learning facilitated business intelligence (Part I): Neural networks learning algorithms and applications” is referred to as Part I. To make the study consistent with Part I, the approach and survey methodology in this paper are kept similar to those in Part I.

Combining the work performed in Part I, the authors studied a total of 80 articles through popular keywords searching. The FNN learning algorithms and optimization techniques identified in the selected literature are classified into six categories based on their problem identification, mathematical model, technical reasoning and proposed solution. Previously, in Part I, the two categories focusing on the learning algorithms (i.e. gradient learning algorithms for network training, gradient free learning algorithms) are reviewed with their real-world applications in management, engineering, and health sciences. Therefore, in the current paper, Part II, the remaining four categories, exploring optimization techniques (i.e. optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) are studied in detail. The algorithm explanation is made enriched by discussing their technical merits, limitations, and applications in their respective categories. Finally, the authors recommend future new research directions which can contribute to strengthening the literature.

The FNN contributions are rapidly increasing because of its ability to make reliably informed decisions. Like learning algorithms, reviewed in Part I, the focus is to enrich the comprehensive study by reviewing remaining categories focusing on the optimization techniques. However, future efforts may be needed to incorporate other algorithms into identified six categories or suggest new category to continuously monitor the shift in the research trends.

The authors studied the shift in research trend for three decades by collectively analyzing the learning algorithms and optimization techniques with their applications. This may help researchers to identify future research gaps to improve the generalization performance and learning speed, and user to understand the applications areas of the FNN. For instance, research contribution in FNN in the last three decades has changed from complex gradient-based algorithms to gradient free algorithms, trial and error hidden units fixed topology approach to cascade topology, hyperparameters initial guess to analytically calculation and converging algorithms at a global minimum rather than the local minimum.

The existing literature surveys include comparative study of the algorithms, identifying algorithms application areas and focusing on specific techniques in that it may not be able to identify algorithms categories, a shift in research trends over time, application area frequently analyzed, common research gaps and collective future directions. Part I and II attempts to overcome the existing literature surveys limitations by classifying articles into six categories covering a wide range of algorithm proposed to improve the FNN generalization performance and convergence rate. The classification of algorithms into six categories helps to analyze the shift in research trend which makes the classification scheme significant and innovative.

The trend of “Deep Learning for Internet of Things (IoT)” has gained fresh momentum with enormous upcoming applications employing these models as their processing engine and Cloud as their resource giant. But this picture leads to underutilization of ever-increasing device pool of IoT that has already passed 15 billion mark in 2015. Thus, it is high time to explore a different approach to tackle this issue, keeping in view the characteristics and needs of the two fields. Processing at the Edge can boost applications with real-time deadlines while complementing security.

This review paper contributes towards three cardinal directions of research in the field of DL for IoT. The first section covers the categories of IoT devices and how Fog can aid in overcoming the underutilization of millions of devices, forming the realm of the things for IoT. The second direction handles the issue of immense computational requirements of DL models by uncovering specific compression techniques. An appropriate combination of these techniques, including regularization, quantization, and pruning, can aid in building an effective compression pipeline for establishing DL models for IoT use-cases. The third direction incorporates both these views and introduces a novel approach of parallelization for setting up a distributed systems view of DL for IoT.

DL models are growing deeper with every passing year. Well-coordinated distributed execution of such models using Fog displays a promising future for the IoT application realm. It is realized that a vertically partitioned compressed deep model can handle the trade-off between size, accuracy, communication overhead, bandwidth utilization, and latency but at the expense of an additionally considerable memory footprint. To reduce the memory budget, we propose to exploit Hashed Nets as potentially favorable candidates for distributed frameworks. However, the critical point between accuracy and size for such models needs further investigation.

To the best of our knowledge, no study has explored the inherent parallelism in deep neural network architectures for their efficient distribution over the Edge-Fog continuum. Besides covering techniques and frameworks that have tried to bring inference to the Edge, the review uncovers significant issues and possible future directions for endorsing deep models as processing engines for real-time IoT. The study is directed to both researchers and industrialists to take on various applications to the Edge for better user experience.

Ensemble methods have been widely used in the field of pattern recognition due to the difficulty of finding a single classifier that performs well on a wide variety of problems. Despite the effectiveness of these techniques, studies have shown that ensemble methods generate a large number of hypotheses and that contain redundant classifiers in most cases. Several works proposed in the state of the art attempt to reduce all hypotheses without affecting performance.

In this work, the authors are proposing a pruning method that takes into consideration the correlation between classifiers/classes and each classifier with the rest of the set. The authors have used the random forest algorithm as trees-based ensemble classifiers and the pruning was made by a technique inspired by the CFS (correlation feature selection) algorithm.

The proposed method CES (correlation-based Ensemble Selection) was evaluated on ten datasets from the UCI machine learning repository, and the performances were compared to six ensemble pruning techniques. The results showed that our proposed pruning method selects a small ensemble in a smaller amount of time while improving classification rates compared to the state-of-the-art methods.

CES is a new ordering-based method that uses the CFS algorithm. CES selects, in a short time, a small sub-ensemble that outperforms results obtained from the whole forest and the other state-of-the-art techniques used in this study.

The purpose of this paper is to present extended least squares support vector machines (LS‐SVM) where data selection methods are used to get sparse LS‐SVM solution, and to overview and compare the most important data selection approaches.

The selection methods are compared based on their theoretical background and using extensive simulations.

The paper shows that partial reduction is an efficient way of getting a reduced complexity sparse LS‐SVM solution, while partial reduction exploits full knowledge contained in the whole training data set. It also shows that the reduction technique based on reduced row echelon form (RREF) of the kernel matrix is superior when compared to other data selection approaches.

Data selection for getting a sparse LS‐SVM solution can be done in the different representations of the training data: in the input space, in the intermediate feature space, and in the kernel space. Selection in the kernel space can be obtained by finding an approximate basis of the kernel matrix.

The RREF‐based method is a data selection approach with a favorable property: there is a trade‐off tolerance parameter that can be used for balancing complexity and accuracy.

The paper gives contributions to the construction of high‐performance and moderate complexity LS‐SVMs.

The goal of this research is to develop a dynamic step path planning algorithm based on the rapidly exploring random tree (RRT) algorithm that combines Q-learning with the Gaussian distribution of obstacles. A route for autonomous vehicles may be swiftly created using this algorithm.

The path planning issue is divided into three key steps by the authors. First, the tree expansion is sped up by the dynamic step size using a combination of Q-learning and the Gaussian distribution of obstacles. The invalid nodes are then removed from the initially created pathways using bidirectional pruning. B-splines are then employed to smooth the predicted pathways.

The algorithm is validated using simulations on straight and curved highways, respectively. The results show that the approach can provide a smooth, safe route that complies with vehicle motion laws.

An improved RRT algorithm based on Q-learning and obstacle Gaussian distribution (QGD-RRT) is proposed for the path planning of self-driving vehicles. Unlike previous methods, the authors use Q-learning to steer the tree's development direction. After that, the step size is dynamically altered following the density of the obstacle distribution to produce the initial path rapidly and cut down on planning time even further. In the aim to provide a smooth and secure path that complies with the vehicle kinematic and dynamical restrictions, the path is lastly optimized using an enhanced bidirectional pruning technique.

Machine learning (ML) analytical tools are increasingly being considered as an alternative quantitative methodology in management research. This paper proposes a new approach for uncovering the antecedents behind product and product–service innovation (PSI).

The ML approach is novel in the field of innovation antecedents at the country level. A sample of the Equatorian National Survey on Technology and Innovation, consisting of more than 6,000 firms, is used to rank the antecedents of innovation.

The analysis reveals that the antecedents of product and PSI are distinct, yet rooted in the principles of open innovation and competitive priorities.

The analysis is based on a sample of Equatorian firms with the objective of showing how ML techniques are suitable for testing the antecedents of innovation in any other context.

The novel ML approach, in contrast to traditional quantitative analysis of the topic, can consider the full set of antecedent interactions to each of the innovations analyzed.

To have all the required components of batches of product orders ready for timely assembly and delivery, the real time wood strip cutting patterns in a major solid wood furniture manufacturing plant has to be dynamically generated based on both the order priority and the minimum wood waste.

An adaptive fuzzy ranking method and a recursive function for pattern generation were integrated into an optimization procedure to solve the real time one‐dimensional multiple‐grade cutting stock problem when orders are prioritized.

The simulation results illustrate that the optimization algorithm produce considerably less waste than the current approach. If implemented in the industry, the saving in raw material could be in the range of 5‐10 percent.

The optimization algorithm is for the cut‐to‐size decisions only with the consideration of the order priorities. The overall scheduling of the production shop floor is not addressed.

The algorithm can be used on the cutting machines as an online patterns generator and cutting optimizer.

There is no literature available for the real time one‐dimensional multiple‐grade cutting stock problem when orders are prioritized. The few commercial optimizers have unknown algorithms with unpredictable waste.

Presents an inductive machine learning algorithm called CLIP3 (Cover learning using integer programming). CLIP3 is an extension of the CLILP2 algorithm. CLIP3 generates multiple rules for a given concept from two sets of discrete attribute data. It combines the best concepts of tree‐based and rule‐based algorithms to produce a highly reliable machine‐learning algorithm. The algorithm is run on the benchmark “MONK′s data sets”. Compares the results of standard machine learning algorithms such as the ID and AQ families of algorithms. The algorithm is also run on the breast cancer data set and the results are compared with C4.5 algorithm results.