Computational Intelligence and Neuroscience

Journal Information
ISSN / EISSN : 1687-5265 / 1687-5273
Published by: Hindawi Limited (10.1155)
Total articles ≅ 2,663
Current Coverage
SCOPUS
INSPEC
LOCKSS
COMPENDEX
MEDICUS
MEDLINE
PUBMED
PMC
DOAJ
SCIE
Archived in
EBSCO
SHERPA/ROMEO
Filter:

Latest articles in this journal

Xuezhu Li
Computational Intelligence and Neuroscience, Volume 2022, pp 1-8; https://doi.org/10.1155/2022/6174708

Abstract:
Aiming at the problem that computing power and resources of Mobile Edge Computing (MEC) servers are difficult to process long-period intensive task data, this study proposes a 5G converged network resource allocation strategy based on reinforcement learning in edge cloud computing environment. n order to solve the problem of insufficient local computing power, the proposed strategy offloads some tasks to the edge of network. Firstly, we build a multi-MEC server and multi-user mobile edge system, and design optimization objectives to minimize the average response time of system tasks and total energy consumption. Then, task offloading and resource allocation process is modeled as Markov decision process. Furthermore, the deep Q-network is used to find the optimal resource allocation scheme. Finally, the proposed strategy is analyzed experimentally based on TensorFlow learning framework. Experimental results show that when the number of users is 110, final energy consumption is about 2500J, which effectively reduces task delay and improves the utilization of resources.
Yan Cao, Peng Shi, , Wenqin Li
Computational Intelligence and Neuroscience, Volume 2022, pp 1-15; https://doi.org/10.1155/2022/4316163

Abstract:
Aiming at the problems of small key space, low security, and low algorithm complexity in a low-dimensional chaotic system encryption algorithm, an image encryption algorithm based on the ML neuron model and DNA dynamic coding is proposed. The algorithm first performs block processing on the R, G, and B components of the plaintext image to obtain three matrices, and then constructs a random matrix with the same size as the image components through logistic mapping and performs DNA encoding, DNA operation, and DNA decoding on the two parts. Second, it performs determinant permutation on the matrix by two different chaotic sequences obtained by logistic mapping iteration. Finally, it merges the block and image components to complete the image encryption and obtain the ciphertext image. Wherein, DNA encoding, DNA operation, and DNA decoding methods are all randomly and dynamically determined by the chaotic sequence generated by the ML neuron chaotic system. According to simulation results and performance analysis, the algorithm has a larger key space, can effectively resist various statistical and differential attacks, and has better security and higher complexity.
Ling Ma, Wei Zhang, Manjin Lv, Jingning Li
Computational Intelligence and Neuroscience, Volume 2022, pp 1-8; https://doi.org/10.1155/2022/6234883

Abstract:
The current boom in Internet technology has paved the way for the research and evolution of various technologies related to it. One such technology is immersive virtual reality (IVR). Immersive technology is referred to as creating a reality-like experience by combining the physical world with digital reality. There are two main types of immersive technologies. Immersion in virtual reality is the perception of being physically present in an artificially created world. Perception is artificially created by images, videos, sounds, or other stimuli with the help of a virtual reality (VR) system that the user is connected to. VR uses rendered computer-generated simulations and results in a complete sense of immersion. Immersive virtual reality (immersive VR) refers to engaging users in an artificial environment that replaces their natural surroundings and fully engages them with the artificially created environment. In this research, we will research immersive physiology courses based on artificial intelligence combined with wireless network VR technology in the context of 5G. The teaching methodology has been kept up-to-date along with the technology. Teaching physiology courses also incorporate new technologies like immersive technologies. The use of technology in anatomy and physiology courses allows students to view structures and physiological concepts in a realistic environment. Virtual dissection in 3D is available with a life-like artificial environment. Students can attend the classes with VR headsets, laptops, or smartphones to experience immersive and interactive 3D classes. This advanced technology enhances and empowers the students to learn from real-life situations like those available in the classes. In this research, CNN with AI is proposed for effective learning of physiology courses. This algorithm is compared with the existing NNGA, KNN, and Random Forest, and it is observed that the proposed model has obtained an accuracy of 99%.
Jinquan Hu, , Guoliang Zhao, Ruizhi Zhou
Computational Intelligence and Neuroscience, Volume 2022, pp 1-8; https://doi.org/10.1155/2022/6215101

Abstract:
In this paper, aiming at the application of online rapid sorting of waste textiles, a large number of effective high-content blending data are generated by using generative adversity network to deeply mine the combination relationship of blending spectra, and A BEGAN-RBF-SVM classification model is constructed by compensating the imbalance of negative samples in the data set. Various experiments show that the model can effectively extract the spectrum of pure textile samples. The classification model has high robustness and high speed, reaches the performance of similar products in the world, and has a broad application market.
Xiaobo Jiang
Computational Intelligence and Neuroscience, Volume 2022, pp 1-9; https://doi.org/10.1155/2022/7559523

Abstract:
With the rapid development of information technology, the amount of data in various digital archives has exploded. How to reasonably mine and analyze archive data and improve the effect of intelligent management of newly included archives has become an urgent problem to be solved. The existing archival data classification method is manual classification oriented to management needs. This manual classification method is inefficient and ignores the inherent content information of the archives. In addition, for the discovery and utilization of archive information, it is necessary to further explore and analyze the correlation between the contents of the archive data. Facing the needs of intelligent archive management, from the perspective of the text content of archive data, further analysis of manually classified archives is carried out. Therefore, this paper proposes an intelligent classification method for archive data based on multigranular semantics. First, it constructs a semantic-label multigranular attention model; that is, the output of the stacked expanded convolutional coding module and the label graph attention module are jointly connected to the multigranular attention Mechanism network, the weighted label output by the multigranularity attention mechanism network is used as the input of the fully connected layer, and the output value of the fully connected layer used to map the predicted label is input into a Sigmoid layer to obtain the predicted probability of each label; then, the model for training: use the multilabel data set to train the constructed semantic-label multigranularity attention model, adjust the parameters until the semantic-label multigranularity attention model converges, and obtain the trained semantic-label multigranularity attention model. Taking the multilabel data set to be classified as input, the semantic-label multigranularity attention model after training outputs the classification result.
Lei Han, Li Gan
Computational Intelligence and Neuroscience, Volume 2022, pp 1-7; https://doi.org/10.1155/2022/7562167

Abstract:
Virtual reality is a computer technology that produces a simulated environment. It is completely immersive and gives users the viewpoint that they are somewhere else. In recent times, it has become a highly interactive and visualization tool that has gained interest among educators and scholars. Art learning is a teaching-learning approach that is dependent on learning through the arts and with the arts; it can be a procedure in which art develops the medium of teaching-learning and an important model in some subjects of the curriculum. In this work, we develop a grey wolf optimization with the residual network form of virtual reality application for environmental art learning (GWORN-EAL) technique. It aims to provide metacognitive actions to improve environmental art learning for young children or adults. The GWORN-EAL technique is mainly based on the stimulation of particular features of the target painting over a default image. The color palette of the recognized image of the Fauve painter was mapped to the target image using the Fauve vision of the painter and represented by vivid colors. For optimal hyperparameter tuning of the ResNet model, the GWO algorithm is employed. The experimental results indicated that the GWORN-EAL technique has accomplished effectual outcomes in several aspects. A brief experimental study highlighted the improvement of the GWORN-EAL technique compared to existing models.
, Areej A. Malibari, Marwa Obayya, Jaber S. Alzahrani, Mohammad Alamgeer, Abdullah Mohamed, Abdelwahed Motwakel, Ishfaq Yaseen, Manar Ahmed Hamza, Abu Sarwar Zamani
Computational Intelligence and Neuroscience, Volume 2022, pp 1-12; https://doi.org/10.1155/2022/1698137

Abstract:
Recently, bioinformatics and computational biology-enabled applications such as gene expression analysis, cellular restoration, medical image processing, protein structure examination, and medical data classification utilize fuzzy systems in offering effective solutions and decisions. The latest developments of fuzzy systems with artificial intelligence techniques enable to design the effective microarray gene expression classification models. In this aspect, this study introduces a novel feature subset selection with optimal adaptive neuro-fuzzy inference system (FSS-OANFIS) for gene expression classification. The major aim of the FSS-OANFIS model is to detect and classify the gene expression data. To accomplish this, the FSS-OANFIS model designs an improved grey wolf optimizer-based feature selection (IGWO-FS) model to derive an optimal subset of features. Besides, the OANFIS model is employed for gene classification and the parameter tuning of the ANFIS model is adjusted by the use of coyote optimization algorithm (COA). The application of IGWO-FS and COA techniques helps in accomplishing enhanced microarray gene expression classification outcomes. The experimental validation of the FSS-OANFIS model has been performed using Leukemia, Prostate, DLBCL Stanford, and Colon Cancer datasets. The proposed FSS-OANFIS model has resulted in a maximum classification accuracy of 89.47%.
Yuhong Zhang, Xinyue Lu, Longying Wang, Min An, Xibin Sun
Computational Intelligence and Neuroscience, Volume 2022, pp 1-11; https://doi.org/10.1155/2022/2985557

Abstract:
A case-control study was conducted to explore the multifactor analysis and intervention of menstrual disorders in female athletes under the background of the Winter Olympic Games, which is based on a large sample. For this purpose, from January 2020 to September 2021, 381 female athletes in long-term ice and snow sports were investigated by random sampling. All of them promoted gynecological examination and counted the incidence of menstrual disorders. The subjects were assigned into two groups according to their menstrual status: abnormal (n = 163) and normal menstrual state groups (n = 218). The basic and clinical data of the two groups were compared, and univariate analysis and multivariate logistic regression analysis were employed to explore the risk factors of menstrual disorders in female athletes. According to the random number table method, the menstrual disorder group was again assigned into the intervention group and the control group. The intervention group received health education and glucose supplement intervention to correct EAMDs, while the control group only received health education. The improvement of patients’ ability balance and the changes of reproductive hormones were compared after intervention. The results of univariate analysis indicated that there exhibited no significant differences in age, menarche age, smoking history, drinking history, grade, sexual life history, abortion history, BMI, and location of household registration, but there were significant differences in family history, sleep quality, diet regularity, and mental health status ( P<0.05 ). The results of univariate analysis indicated that there exhibited no significant differences in age, menarche, smoking, drinking, grade, sexual life history, abortion history, family history, sleep quality, diet regularity, and mental health status. Logistic regression analysis indicated that family history of menstrual disorders, poor sleep quality, irregular diet, and mental health status all affected women’s menstrual disorders (OR: 1.411, 95% CI: 1.378∼1.444; OR: 1.501, 95% CI: 1.030∼2.187; OR: 1.554, 95% CI: 1.086∼2.225; OR: 1.383, 95% CI: 1.018∼1.877, respectively) independent risk factors. According to the comparison of menstrual cycle, in the intervention group, 12 patients had menstrual cycle 21–28 days, 12 patients had menstrual cycle 28–38 days, and 58 patients were irregular and had no amenorrhea, while in the control group, 36 patients had menstrual cycle 21–28 days, 24 patients had 28–38 days, 12 patients had amenorrhea, and 11 patients had irregular menstruation, and there exhibited no significant difference ( P>0.05 ). There exhibited no significant difference in energy balance before and after intervention ( P>0.05 ); after intervention, the ability balance of the two groups was significantly promoted, and the degree of improvement in the study group was better ( P<0.05 ). The indexes of reproductive hormones in the follicular phase were compared before and after glucose supplement intervention, and there exhibited no significant difference before intervention ( P>0.05 ); after intervention, the serum LH and GnRH of the two groups decreased, while FSH and P increased. The improvement degree of the intervention group was better than that of the control group, but there exhibited no significant difference ( P>0.05 ). Before intervention, there exhibited no significant difference in the serum E2 level in the follicular phase ( P>0.05 ); after the intervention, the serum E2 of the two groups increased significantly, and the improvement of the intervention group was better ( P<0.05 ). Before intervention, there exhibited no significant difference in the serum E2 level in the follicular phase ( P>0.05 ); after the intervention, the serum E2 of the two groups increased significantly, and the improvement of the intervention group was better ( P<0.05 ). Before intervention, there exhibited no significant difference in serum E2 and P levels in the luteal phase (
Ning Luo
Computational Intelligence and Neuroscience, Volume 2022, pp 1-9; https://doi.org/10.1155/2022/4818767

Abstract:
This paper analyzes the application of MEC multiserver heuristic joint task in resource allocation of the educational resource database. After constructing the scenario of educational resource database, a mathematical model is constructed from the dimensions of local execution strategy, unloading execution, and given educational resource allocation, in order to optimize the optimal allocation of educational resources through MEC. The results show that the DOOA scheme has good performance in terms of calculation cost and timeout rate. Compared with other benchmark schemes, the DQN-based unloading scheme has better performance, can effectively balance the load, and is better than the random unloading scheme and the SNR-based unloading scheme in terms of delay and calculation cost. The results show that the total hits of all category 1 users' content requests account for the proportion of the total content requests. The images have a small downward trend at the 15000 and 30000 time slots and then continue to rise. This shows that the proposed scheme can automatically adjust the caching strategy to adapt to the changes of content popularity, which proves that the agent can correctly perceive the changing trend of content popularity when the popularity of network content is unknown and improve the caching strategy accordingly to improve the cache hit rate. Therefore, the allocation of educational resources based on the MEC multiserver heuristic joint task is more reasonable and can achieve the optimal solution.
Li Xin, Hao Xiaoyan
Computational Intelligence and Neuroscience, Volume 2022, pp 1-8; https://doi.org/10.1155/2022/3139898

Abstract:
The Internet is rich in information related to the financial field. The financial entity information text containing new internet vocabulary has a certain impact on the results of existing recognition algorithms. How to solve the problems of new vocabulary and polysemy is a problem to be solved in the current field. This paper proposes an ERNIE-Doc-BiLSTM-CRF named entity recognition model based on the pretrained language model. Compared with the traditional model, the ERNIE-Doc pretrained language model constructs a unique word vector from the word vector and combines the location coding, which solves polysemy problem well. The intensive skimming mechanism realizes the long text processing well and captures the context information effectively. The experimental results show that the accuracy of this model is 86.72%, the recall rate is 83.39%, and the F1 value is 85.02%, which is 13.36% higher than other models; the recall rate is increased by 13.05%, and the F1 value is increased by 13.21%.
Back to Top Top