Advances in computational intelligence最新文献

Due to their dependence on a task-specific reward function, reinforcement learning agents are ineffective at responding to a dynamic goal or environment. This paper seeks to overcome this limitation of traditional reinforcement learning through a task-agnostic, self-organising autonomous agent framework. The proposed algorithm is a hybrid of TMGWR for self-adaptive learning of sensorimotor maps and value iteration for goal-directed planning. TMGWR has been previously demonstrated to overcome the problems associated with competing sensorimotor techniques such SOM, GNG, and GWR; these problems include: difficulty in setting a suitable number of neurons for a task, inflexibility, the inability to cope with non-markovian environments, challenges with noise, and inappropriate representation of sensory observations and actions together. However, the binary sensorimotor-link implementation in the original TMGWR enables catastrophic forgetting when the agent experiences changes in the task and it is therefore not suitable for self-adaptive learning. A new sensorimotor-link update rule is presented in this paper to enable the adaptation of the sensorimotor map to new experiences. This paper has demonstrated that the TMGWR-based algorithm has better sample efficiency than model-free reinforcement learning and better self-adaptivity than both the model-free and the traditional model-based reinforcement learning algorithms. Moreover, the algorithm has been demonstrated to give the lowest overall computational cost when compared to traditional reinforcement learning algorithms.

Machine learning approaches can serve as powerful tools in the machining optimization process. Criteria, such as accuracy and stability, are important to consider when choosing among different models. For the industrial application, it also is essential to balance cost, applicabilities, and ease of implementations. Here, we develop Gaussian process regression models for predicting the main cutting force (R) and its components in three directions of the coordinate system ((F_{x}), (F_{y}), and (F_{z})) based on two predictors: the depth of cut ((a_{p})) and the feed rate (f) in milling processes of functionally graded materials. The model performance shows high accuracy and stability, and the models are thus promising for estimating the cutting force and its component in a fast, cost effective, and robust fashion.

It is an established fact that the genuineness of facial micro-expression is an effective means for estimating concealed emotions (Li et al. in Micro-expression recognition under low-resolution cases. SciTePress, Science and Technology Publications, Setúbal, 2019). Conventionally, analysis of these expressions has been performed using high resolution images which are ideal cases. However, in a real-world scenario, capturing expressions with high resolution images may not always be possible particularly using low-cost surveillance cameras. Faces captured using such cameras are often very tiny and of poor resolution. Due to the loss of discriminative features these images may not be of much use particularly for identifying certain minute facial details. To make these images useful, enhancing the textural information becomes essential and super-resolution algorithms can be ideal to achieve this. In this work, we utilize algorithms based on deep learning and generative adversarial network for transforming low-resolution micro-expression images into super-resolution images and examine their fitness particularly for micro-expression recognition. The proposed approach is tested on simulated dataset obtained from two popular spontaneous micro-expression datasets namely CASME II and SMIC-VIS; the experimental results demonstrate that the method achieved favourable results with the best recognition performance recorded as 61.63%. The significance of this work is: first, it thoroughly investigates reconstruction performance of several deep learning super-resolution algorithms on simulated low-quality micro-expression images; second, it provides a comprehensive analysis of the results obtained employing these reconstructed images to determine their contribution in addressing image quality issues specifically for micro-expression recognition.

Finding the definitions of acronyms in any given text has been an on going problem with multiple proposed solutions. In this paper, we use the bidirectional encoder representations from transformers question answer model provided by Google to find acronym definitions in a given text. Given an acronym and a passage containing the acronym, our model is expected to find the expansion of the acronym in the passage. Through our experiments, we show that this model can correctly predict 94% of acronym expansions assuming a Jaro–Winkler threshold distance of greater than 0.8. One of the main contributions of this paper is a systematic method to create datasets and use them to build a corpus for acronym expansion. Our approach for data generation can be used in many applications where there are no standard datasets.

Type 2 diabetes has recently acquired the status of an epidemic silent killer, though it is non-communicable. There are two main reasons behind this perception of the disease. First, a gradual but exponential growth in the disease prevalence has been witnessed irrespective of age groups, geography or gender. Second, the disease dynamics are very complex in terms of multifactorial risks involved, initial asymptomatic period, different short-term and long-term complications posing serious health threat and related co-morbidities. Majority of its risk factors are lifestyle habits like physical inactivity, lack of exercise, high body mass index (BMI), poor diet, smoking except some inevitable ones like family history of diabetes, ethnic predisposition, ageing etc. Nowadays, machine learning (ML) is increasingly being applied for alleviation of diabetes health burden and many research works have been proposed in the literature to offer clinical decision support in different application areas as well. In this paper, we present a review of such efforts for the prevention and management of type 2 diabetes. Firstly, we present the medical gaps in diabetes knowledge base, guidelines and medical practice identified from relevant articles and highlight those that can be addressed by ML. Further, we review the ML research works in three different application areas namely—(1) risk assessment (statistical risk scores and ML-based risk models), (2) diagnosis (using non-invasive and invasive features), (3) prognosis (from normoglycemia/prior morbidity to incident diabetes and prognosis of incident diabetes to related complications). We discuss and summarize the shortcomings or gaps in the existing ML methodologies for diabetes to be addressed in future. This review provides the breadth of ML predictive modeling applications for diabetes while highlighting the medical and technological gaps as well as various aspects involved in ML-based diabetes clinical decision support.

Machine-learning techniques are being used in the health-care industry to improve care delivery at a lower cost and in less time. Artificial Neural Network (ANN) is well-known machine-learning techniques for its diagnostic applications, but it is also increasingly being utilized to guide health-care management decisions. At the same time, in the healthcare industry, ANN has made significant progress in solving a variety of real-world classification problems that range from linear to non-linear and also from simple to complex. In this research work, an Adaptive Hybrid Classification Model named as Genetic-based Linear Adaptive Skipping Training (GLAST) Algorithm has been proposed for the health-care dataset. It has been designed as two-stage process. In first stage, Genetic Algorithm (GA) is adapted to optimize the Learning rate. After optimizing the Learning rate, the optimal Learning rate has been set to the ANN model is ŋ = 1e−4. In the second stage, The training process is carried out using the Linear Adaptive Skipping Training (LAST) algorithm, which reduces the total training time and thus increases the training speed. As a result, the highlighted characteristics of LAST have been integrated with GA to accomplish rapid classification and enhance computational efficiency. On 8 different health-care datasets extracted from the UCI Repository, the proposed GLAST algorithm outperforms both the BPN and LAST algorithms in terms of accuracy and training time, according to simulation results. The result analyses have proved that the efficiency of this proposed GLAST Algorithm outperforms over the existing techniques such as BPN and LAST in terms of accuracy and training time. On various datasets, experimental results show that GLAST improves accuracy from 4 to 17% over BPN training algorithm and reduces overall training time from 10 to 57% over BPN training algorithm.

The increasing data volumes impose unprecedented challenges to traditional data mining in data preprocessing, learning, and analyzing, it has attracted much attention in designing efficient compressing, indexing and searching methods recently. Inspired by locally sensitive hashing (LSH), divide-and-conquer strategy, and double-voting mechanism, we proposed an iterative instance selection algorithm, which needs to run p rounds iteratively to reduce or eliminate the unwanted bias of the optimal solution by double-voting. In each iteration, the proposed algorithm partitions the big dataset into several subsets and distributes them to different computing nodes. In each node, the instances in local data subset are transformed into Hamming space by l hash function in parallel, and each instance is assigned to one of the l hash tables by the corresponding hash code, the instances with the same hash code are put into the same bucket. And then, a proportion of instances are randomly selected from each hash bucket in each hash table, and a subset is obtained. Thus, totally l subsets are obtained, which are used for voting to select the locally optimal instance subset. The process is repeated p times to obtain p subsets. Finally, the globally optimal instance subset is obtained by voting with the p subsets. The proposed algorithm is implemented with two open source big data platforms, Hadoop and Spark, and experimentally compared with three state-of-the-art methods on testing accuracy, compression ratio, and running time. The experimental results demonstrate that the proposed algorithm provides excellent performance and outperforms three baseline methods.

Aiming at the problems of single input mode and lack of naturalness in the assembly process of existing AR systems, a tracking registration method of mobile AR assembly system is proposed based on multi-quantity and multi-degree of freedom natural fingertip interaction. Firstly, the real-time and stable tracking of hand area in complex environment is realized based on the hand region tracking; secondly, the fingertip detection and recognition based on K-COS and parallel vector is used to improve the precision and stability of fingertip recognition; thirdly, the special movement track of fingertip is recognized based on improved DTW algorithm, which has strong compatibility and feature gradient transformation for complex fingertip trajectory recognition; finally, through the real-time transformation of projection relationship between fingertip and virtual object, the interaction between fingertip and virtual object is made more natural and realistic. The experimental results show that in the complex environment of background, illumination, scale and rotation, the precision of fingertip detection and recognition is about 93%, and the precision of fingertip motion template matching is about 91%. The translation error of the registration method based on visual feature recognition is reduced by about 100pix compared with fingertip tracking registration method, and the efficiency of mobile AR-guided assembly method is improved by about 24.77% compared with the traditional manual assisted assembly method. These data verifies the strong interaction and practicability of the fingertips based on the user's multi-quantity and multi-degree of freedom features in the process of mobile AR guided assembly.

The expansion of Internet-of-Things and Information and Communication Technology allows the application of intelligent concepts to university campus spaces. Several Smart Campus models were implemented recently. However, solutions that foster flexibility in the incorporation of new hardware and software solutions on the existing infrastructure are still a gap, motivating this research. Sapientia smart campus model promotes flexibility by facilitating the incorporation of new solutions on existing infrastructure. The model’s architecture is composed of layers that facilitate technology management and update. A university campus received a model implementation, allowing the execution of experiments to evaluate the incorporation of new hardware and applications. These included a mobile application to support user orientation and internal applications to collect and process campus information, such as temperature. The experiments show how the model incorporates a new hardware component and two new applications on the existing infrastructure. Also, it evidenced the use of the installed devices in more than one application with distinct configurations and purposes.

This systematic review focuses on control strategies and machine learning techniques used in prosthetic knees for restoring mobility of individuals with trans-femoral amputations. Review and classification of control strategies that determine how these prosthetic knees interact with the user and gait strategy inspired algorithms for phase identification, locomotion mode, and motion intention recognition were studied. Relevant studies were identified using electronic databases such as PubMed, EMBASE, SCOPUS, and the Cochrane Controlled Trials Register (Rehabilitation and Related Therapies) up to April 2021. Abstracts were screened and inclusion and exclusion criteria were applied. Out of 278 potentially relevant studies, 65 articles were included. The specific variables on control approach, control modes, gait control, hardware level, machine learning algorithm, and measured signals mechanism were extracted and added to summary table. The results indicate that advanced methods for adapting position or torque depiction and automatic detection of terrains or gait modes are more commonly utilized, but they are largely limited to laboratory environments. It is concluded that a correct combination of control strategies and machine learning techniques will enable the improvement of prosthetic performance and enhance the standard of amputee’s lives.