Cognitive Computation and Systems最新文献

The classifier efficiency of the brain-computer interface systems is significantly impacted by the non-stationarity of electroencephalogram (EEG) signals. We propose an adaptive variant of the linear discriminant analysis (LDA) classifier as a solution to this problem. This classifier constantly adjusts its parameters to account for the most recent EEG data. In this study, the authors will update the mean values as well as the covariance matrix of each class pair. Visually evoked cortical potential datasets are used to check how well the proposed classifier performs. The authors prove that the proposed adaptive LDA performs much better than both static multiclass LDA and adaptive PMean LDA.

Alzheimer's disease is a type of progressive neurological disorder which is irreversible and the patient suffers from severe memory loss. This disease is the seventh largest cause of death across the globe. As yet there is no cure for this disease, the only way to control it is its early diagnosis. Deep Learning techniques are mostly preferred in classification tasks because of their high accuracy over a large dataset. The main focus of this paper is on fine-tuning and evaluating the Deep Convolutional Networks for Alzheimer's disease classification. An empirical analysis of various deep learning-based neural network models has been done. The architectures evaluation includes InceptionV3, ResNet with 50 layers and 101 layers and DenseNet with 169 layers. The dataset has been taken from Kaggle which is publicly available and comprises of four classes which represents the various stages of Alzheimer's disease. In our experiment, the accuracy of DenseNet consistently improved with the increase in the number of epochs resulting in a 99.94% testing accuracy score better than the rest of the architectures. Although the results obtained are satisfactory, but for future research, we can apply transfer learning on other deep models like Inception V4, AlexNet etc., to increase accuracy and decrease computational time. Also, in future we can work on other datasets like ADNI or OASIS and use Positron emitted tomography, diffusion tensor imaging neuroimages and their combinations for better result.

If understanding sentiments is already a difficult task in human-human communication, this becomes extremely challenging when a human-computer interaction happens, as for instance in chatbot conversations. In this work, a machine learning neural network-based Speech Emotion Recognition system is presented to perform emotion detection in a chatbot virtual assistant whose task was to perform contact tracing during the COVID-19 pandemic. The system was tested on a novel dataset of audio samples, provided by the company Blu Pantheon, which developed virtual agents capable of autonomously performing contacts tracing for individuals positive to COVID-19. The dataset provided was unlabelled for the emotions associated to the conversations. Therefore, the work was structured using a sort of transfer learning strategy. First, the model is trained using the labelled and publicly available Italian-language dataset EMOVO Corpus. The accuracy achieved in testing phase reached 92%. To the best of their knowledge, thiswork represents the first example in the context of chatbot speech emotion recognition for contact tracing, shedding lights towards the importance of the use of such techniques in virtual assistants and chatbot conversational contexts for psychological human status assessment. The code of this work was publicly released at: https://github.com/fp1acm8/SER.

The authors wish to bring to the readers' attention the following error in the article by Zijin Li and Stephen McAdams, “Guest editorial: Music perception and cognition in music technology” [1].

The co-author Stephen McAdams' name should be removed from the article.

With the international development of the medical service informatisation, medical information sharing has become the key standard to measure the degree of medical informatisation. In this process, it is important to ensure the security of patients' medical information such as patients' records, examination reports, images and so on. In this article, an image encryption scheme based on Secure Hash Algorithm 3 (SHA-3), DNA coding and high dimensional chaos system is proposed to promote the security level of medical images in information sharing processes such as over the network. First, SHA-3 algorithm is used to calculate the hash value of the input image, and the result is taken as the initial value of the hyper-chaotic system. Second, the intensity value of the input image is converted into a serial binary digital stream. Third, the pseudo-random sequence generated by a 4-dimensional hyper-chaotic system is used to perturb the bit stream globally so as to achieve the purpose of hiding the effective information of the input image. During the operation of hyper-chaotic sequence and DNA sequence, algebraic and complementary operations are performed on DNA encoding values to enhance encryption performance. Finally, simulations have been applied on an open-source medical image database, and the results demonstrate obvious encryption effectiveness and high security level of the proposed encryption algorithm in the robustness of noise and clipping attacks.

The problem of optimal dispatching of a power system containing a high proportion of renewable energy is of great significance for the realisation of new energy consumption and the economic and reliable operation of the power system. For the solution of non-linear, non-convex, multi-objective problems for the optimal operation design of a power system with wind and photovoltaic access, traditional methods have difficulties in terms of computational real-time and iterative convergence. To address this issue, a deep reinforcement learning-based optimal scheduling method for the hybrid power system is proposed, which enables continuous action control to obtain an optimal scheduling strategy through the interaction between the agent and the hybrid power system. Firstly, a mathematical description of the optimal scheduling problem containing wind power and photovoltaic power system is presented, and the state space, action space, and reward function of the agent are designed. Secondly, the basic framework of the deep reinforcement learning optimal scheduling model is constructed, and the basic principles of the twin delayed deep deterministic policy gradient algorithm are introduced. Finally, the effectiveness of the deep reinforcement learning model for day-ahead optimal scheduling of the hybrid power system is verified by means of an arithmetic analysis of the modified New England 39-bus system.

Based on the characteristics of human cognition and the cloud model, the excursion of uncertain concepts by the similarity between uncertain concepts from the perspective of conceptual cognition is studied. Firstly, considering the different meanings of the numerical characters in cloud concept, the properties of cloud concepts similarity are given. Furthermore, in order to reflect the various similarities that may exist in uncertain concept, five similarities between cloud concepts are constructed, specifically include the similarity between concept expectations, the similarity between concept entropy, the similarity between concept hyper entropy, the shape similarity and the overall similarity. Secondly, the rationality of these proposed similarity measurements is illustrated by comparing with the existing methods through the specific data analysis. Finally, two cognitive experiments, including concept cognitive processes without prior knowledge and concept cognitive processes with prior knowledge (including positive prior knowledge and negative prior knowledge), are designed. These experiments are all used to study the excursion in the process of concept cognition by the similarity of cloud concepts. The experiment results show that the proposed similarities are reasonable by comparing the proposed method with the existing ones, and the effectiveness of the proposed method is also verified by the excursion of concept cognition.

Prostate brachytherapy is a validated treatment for prostate cancer. During the procedure, the accuracy of needle placement is critical to the treatment’s effectiveness. However, the inserted needle could deflect from the preset trajectory because of the needle deflection, tissue shifting caused by the interaction between the needle and soft tissue, as well as the effects of pre-inserted needles. There are significant challenges in needle placement areas, especially in prostate brachytherapy, because multiple needles are required for the effectiveness of radiation. To overcome these limitations, relevant research is carried out in mechanical, computer science, and material science areas. With the development of surgical robotics, researchers are also exploring the possibilities of raising the accuracy of needle placement with surgical-assisted robotics. This study provides a review over the last 3 decades in each of the component research areas that constitutes a surgical robotics system, including needle steering approaches, needle-tissue deformation models, path planning algorithms and different automatic level surgical robotics systems used for prostate cancer treatment, especially prostate brachytherapy. Further directions for researchers are also suggested.