Neural Computing & Applications最新文献

Anxiety affects approximately 5-10% of the adult population worldwide, placing a large burden on the health systems. Despite its omnipresence and impact on mental and physical health, most of the individuals affected by anxiety do not receive appropriate treatment. Current research in the field of psychiatry emphasizes the need to identify and validate biological markers relevant to this condition. Neurophysiological preclinical studies are a prominent approach to determine brain rhythms that can be reliable markers of key features of anxiety. However, while neuroimaging research consistently implicated prefrontal cortex and subcortical structures, such as amygdala and hippocampus, in anxiety, there is still a lack of consensus on the underlying neurophysiological processes contributing to this condition. Methods allowing non-invasive recording and assessment of cortical processing may provide an opportunity to help identify anxiety signatures that could be used as intervention targets. In this study, we apply Source-Power Comodulation (SPoC) to electroencephalography (EEG) recordings in a sample of participants with different levels of trait anxiety. SPoC was developed to find spatial filters and patterns whose power comodulates with an external variable in individual participants. The obtained patterns can be interpreted neurophysiologically. Here, we extend the use of SPoC to a multi-subject setting and test its validity using simulated data with a realistic head model. Next, we apply our SPoC framework to resting state EEG of 43 human participants for whom trait anxiety scores were available. SPoC inter-subject analysis of narrow frequency band data reveals neurophysiologically meaningful spatial patterns in the theta band (4-7 Hz) that are negatively correlated with anxiety. The outcome is specific to the theta band and not observed in the alpha (8-12 Hz) or beta (13-30 Hz) frequency range. The theta-band spatial pattern is primarily localised to the superior frontal gyrus. We discuss the relevance of our spatial pattern results for the search of biomarkers for anxiety and their application in neurofeedback studies.

In this work, we present a perspective on the role machine intelligence can play in supporting human abilities. In particular, we consider research in rehabilitation technologies such as prosthetic devices, as this domain requires tight coupling between human and machine. Taking an agent-based view of such devices, we propose that human-machine collaborations have a capacity to perform tasks which is a result of the combined agency of the human and the machine. We introduce communicative capital as a resource developed by a human and a machine working together in ongoing interactions. Development of this resource enables the partnership to eventually perform tasks at a capacity greater than either individual could achieve alone. We then examine the benefits and challenges of increasing the agency of prostheses by surveying literature which demonstrates that building communicative resources enables more complex, task-directed interactions. The viewpoint developed in this article extends current thinking on how best to support the functional use of increasingly complex prostheses, and establishes insight toward creating more fruitful interactions between humans and supportive, assistive, and augmentative technologies.

Demand forecasting is a scientific and methodical assessment of future demand for a critical product.The effective Demand Forecast Model (DFM) enables pharmaceutical companies to be successful in the global market. The purpose of this research paper is to validate various shallow and deep neural network methods for demand forecasting, with the aim of recommending sales and marketing strategies based on the trend/seasonal effects of eight different groups of pharmaceutical products with different characteristics. The root mean squared error (RMSE) is used as the predictive accuracy of DFMs. This study also found that the mean RMSE value of the shallow neural network-based DFMs was 6.27 for all drug categories, which was lower than deep neural network models. According to the findings, DFMs based on shallow neural networks can effectively estimate future demand for pharmaceutical products.

The detection and location of image splicing forgery are a challenging task in the field of image forensics. It is to study whether an image contains a suspicious tampered area pasted from another image. In this paper, we propose a new image tamper location method based on dual-channel U-Net, that is, DCU-Net. The detection framework based on DCU-Net is mainly divided into three parts: encoder, feature fusion, and decoder. Firstly, high-pass filters are used to extract the residual of the tampered image and generate the residual image, which contains the edge information of the tampered area. Secondly, a dual-channel encoding network model is constructed. The input of the model is the original tampered image and the tampered residual image. Then, the deep features extracted from the dual-channel encoding network are fused for the first time, and then the tampered features with different granularity are extracted by dilation convolution, and then, the secondary fusion is carried out. Finally, the fused feature map is input into the decoder, and the predicted image is decoded layer by layer. The experimental results on Casia2.0 and Columbia datasets show that DCU-Net performs better than the latest algorithm and can accurately locate tampered areas. In addition, the attack experiments show that DCU-Net model has good robustness and can resist noise and JPEG recompression attacks.

Drinking water safety is a safety issue that the whole society attaches great importance to currently. For sudden water pollution accidents, it is necessary to trace the water pollution source in real time to determine the pollution source's characteristic information and provide technical support to emergency management departments for decision making. The problems of water pollution's real-time traceability are as follows: non-uniqueness and dynamic real time of pollution sources. Aiming at these two difficulties, an intelligent traceability algorithm based on dynamic multi-mode optimization was designed and proposed in the work. As a multi-mode optimization problem, pollution traceability could have multiple similar optimal solutions. Firstly, the new algorithm divided the population reasonably through the optimal subpopulation division strategy, which made the nodes' distribution in a single subpopulation more similar and conducive to local optimization. Then, a similar peak penalty strategy was used to eliminate similar solutions and reduce the non-unique solutions' number, since real-time traceability required higher algorithm convergence than traditional offline traceability and dynamic problems with parameter changes, historical information preservation, and adaptive initialization strategies could make reasonable use of the algorithm's historical knowledge to improve the population space and increase the population convergence rate when the problem changed. The experimental results showed the proposed new algorithm's effectiveness in solving problems-accurately tracing the source of pollution, and obtain corresponding characteristic information in a short time.

Tactics to determine the emotions of authors of texts such as Twitter messages often rely on multiple annotators who label relatively small data sets of text passages. An alternative method gathers large text databases that contain the authors' self-reported emotions, to which artificial intelligence, machine learning, and natural language processing tools can be applied. Both approaches have strength and weaknesses. Emotions evaluated by a few human annotators are susceptible to idiosyncratic biases that reflect the characteristics of the annotators. But models based on large, self-reported emotion data sets may overlook subtle, social emotions that human annotators can recognize. In seeking to establish a means to train emotion detection models so that they can achieve good performance in different contexts, the current study proposes a novel transformer transfer learning approach that parallels human development stages: (1) detect emotions reported by the texts' authors and (2) synchronize the model with social emotions identified in annotator-rated emotion data sets. The analysis, based on a large, novel, self-reported emotion data set (n = 3,654,544) and applied to 10 previously published data sets, shows that the transfer learning emotion model achieves relatively strong performance.

Telemedicine is one of the safest methods to provide healthcare facilities to the remote patients with the help of digitization. In this paper, state-of-the-art session key has been proposed based on the priority oriented neural machines followed by its validation. State-of-the-art technique can be mentioned as newer scientific method. Soft computing has been extensively used and modified here under the ANN domain. Telemedicine facilitates secure data communication between the patients and the doctors regarding their treatments. The best fitted hidden neuron can contribute only in the formation of the neural output. Minimum correlation was taken into consideration under this study. Hebbian learning rule was applied on both the patient's neural machine and the doctor's neural machine. Lesser iterations were needed in the patient's machine and the doctor's machine for the synchronization. Thus, the key generation time has been shortened here which were 4.011 ms, 4.324 ms, 5.338 ms, 5.691 ms, and 6.105 ms for 56 bits, 128 bits, 256 bits, 512 bits, and 1024 bits of state-of-the-art session keys, respectively. Statistically, different key sizes of the state-of-the-art session keys were tested and accepted. Derived value-based function had yielded successful outcomes too. Partial validations with different mathematical hardness had been imposed here too. Thus, the proposed technique is suitable for the session key generation and authentication in the telemedicine in order to preserve the patients' data privacy. This proposed method has been highly protective against numerous data attacks inside the public networks. Partial transmission of the state-of-the-art session key disables the intruders to decode the same bit patterns of the proposed set of keys.

Researchers have adapted the conventional deep learning classification networks to generate Fully Conventional Networks (FCN) for carrying out accurate semantic segmentation. However, such models are expensive both in terms of storage and inference time and not readily employable on edge devices. In this paper, a compressed version of VGG16-based Fully Convolution Network (FCN) has been developed using Particle Swarm Optimization. It has been shown that the developed model can offer tremendous saving in storage space and also faster inference time, and can be implemented on edge devices. The efficacy of the proposed approach has been tested using potato late blight leaf images from publicly available PlantVillage dataset, street scene image dataset and lungs X-Ray dataset and it has been shown that it approaches the accuracies offered by standard FCN even after 851× compression.

In this study, we present a cohort study involving 106 COPD patients using portable environmental sensor nodes with attached air pollution sensors and activity-related sensors, as well as daily symptom records and peak flow measurements to monitor patients' activity and personal exposure to air pollution. This is the first study which attempts to predict COPD symptoms based on personal air pollution exposure. We developed a system that can detect COPD patients' symptoms one day in advance of symptoms appearing. We proposed using the Probabilistic Latent Component Analysis (PLCA) model based on 3-dimensional and 4-dimensional spectral dictionary tensors for personalised and population monitoring, respectively. The model is combined with Linear Dynamic Systems (LDS) to track the patients' symptoms. We compared the performance of PLCA and PLCA-LDS models against Random Forest models in the identification of COPD patients' symptoms, since tree-based classifiers were used for remote monitoring of COPD patients in the literature. We found that there was a significant difference between the classifiers, symptoms and the personalised versus population factors. Our results show that the proposed PLCA-LDS-3D model outperformed the PLCA and the RF models between 4 and 20% on average. When we used only air pollutants as input, the PLCA-LDS-3D forecasting results in personalised and population models were 48.67 and 36.33% accuracy for worsening of lung capacity and 38.67 and 19% accuracy for exacerbation of COPD patients' symptoms, respectively. We have shown that indicators of the quality of an individual's environment, specifically air pollutants, are as good predictors of the worsening of respiratory symptoms in COPD patients as a direct measurement.