Model-Based Approaches to Investigating Mismatch Responses in Schizophrenia.

The auditory mismatch negativity (MMN) has been proposed as a biomarker of NMDA receptor (NMDAR) dysfunction in schizophrenia. Such dysfunction may be caused by aberrant interactions of different neuromodulators with NMDARs, which could explain clinical heterogeneity among patients. In two studies (N = 81 each), we used a double-blind placebo-controlled between-subject design to systematically test whether auditory mismatch responses under varying levels of environmental stability are sensitive to diminishing and enhancing cholinergic vs. dopaminergic function. We found a significant drug × mismatch interaction: while the muscarinic acetylcholine receptor antagonist biperiden delayed and topographically shifted mismatch responses, particularly during high stability, this effect could not be detected for amisulpride, a dopamine D2/D3 receptor antagonist. Neither galantamine nor levodopa, which elevate acetylcholine and dopamine levels, respectively, exerted significant effects on MMN. This differential MMN sensitivity to muscarinic versus dopaminergic receptor function may prove useful for developing tests that predict individual treatment responses in schizophrenia.

Text sentiment analysis is used to discover the public’s appreciation and preferences for specific events. In order to effectively extract the deep semantic features of sentences and reduce the dependence of long distance information dependency, two models based on convolutional neural network and bidirectional long short-term memory model, CNN-BLSTM and BLSTM-CNN are proposed. Convolutional neural networks can get text features better. Bidirectional long-short time memory model can not only capture long-range information and solve gradient attenuation problem, but also represent future contextual information semantics of word sequence better. These two network architectures are explained in detail in this paper, and performed comparisons against some normal methods, such as methods based emotion lexicon, machine learning methods, LSTM and other neural network models. Experiments show that these two proposed models have achieved better results in text sentiment analysis. The best model CNN-BLSTM is better than the normal neural network models in accuracy.

Background Incidence rate of thyroid cancer is steadily increasing due to overdiagnosis and overtreatment. Thyroid ultrasound is commonly used to diagnose thyroid cancer. The aim of this study is to examine the accuracy of using deep convolutional neural network (DCNN) models to improve diagnosis of thyroid cancer by analyzing sonographic imaging data from clinical thyroid ultrasound. Methods A total of 131,731 sonographic images from 17,627 thyroid cancer patients and 180,668 sonographic images from 25,325 controls used as training set were obtained from Tianjin Cancer Hospital. Images from anatomical sites that did not have cancer according to location sign on the image were not included. All thyroid cancer patients and 13·2% of controls (51,255 images) were confirmed by pathological reports. DCNN is a specific type of neural network optimized for image recognition. We trained two DCNN models on the training set and subsequently evaluated the performance on one independent internal (Tianjin, 1,118 individuals) and two external (Jilin,154 individuals; Weihai, 1,420 individuals) validation sets. Individuals in the validation sets all have pathological examinations. We compared the specificity/sensitivity of DCNN models with the performance of six thyroid ultrasound radiologists on these three validation sets. Findings DCNN model achieved high performance in identifying thyroid cancer patients versus six experience radiologists: for Tianjin validation set, sensitivity was 92·2% versus 96·9% (95% CI 89·7% - 94·3% vs. 93·9% - 98·6%; p = 0·003), and specificity was 85·6% versus 59·4% (95% CI 82·4% - 88·4% vs. 53% - 65·6%; p < 0·0001); for Jilin validation set, sensitivity was 84·3% versus 92·9% (95% CI 73·6% - 91·9% vs. 84·1% - 97·6%; p = 0·05), and specificity was 86·9% versus 57·1% (95% CI 77·8% - 93·3% vs. 45·9% - 67·9%; p < 0·0001); for Weihai validation set, sensitivity was 84·5% versus 89% (95% CI 81·2% - 87·4% vs. 81·9% - 94%; p = 0·2), and specificity was 87·5% versus 68·6% (95% CI 85·1% - 89·6% vs. 60·7% - 75·8%; p < 0·0001). Interpretation DCNN models exhibited high accuracy, sensitivity, and specificity in identifying thyroid cancer patients at levels comparable to or higher than six experienced radiologists. Conferred by the high specificity of DCNN models, the rate of overdiagnosis and overtreatment of patients with thyroid cancer is expected to decrease. This supports future application of the deep learning models to clinical practice for thyroid cancer diagnosis. However, further validation of these DCNN models in prospective clinical trials is warranted. Funding The Program for Changjiang Scholars and Innovative Research Team in University in China (IRT_14R40), National Natural Science Foundation of China (31801117). Citation Format: Xiangchun Li, Sheng Zhang, Qiang Zhang, Xi Wei, Yi Pan, Jing Zhao, Xiaojie Xin, Xiaoqing Wang, Fan Yang, Jianxin Li, Meng Yang, Qinghua Wang, Xiangqian Zheng, Yanhui Zhao, Lun Zhang, Xudong Wang, Zhimin Zheng, Christopher T. Whitlow, Metin N. Gurcan, Boris Pasche, Ming Gao, Wei Zhang, Kexin Chen. Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images from clinical ultrasound exams [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 1394.

Convolutional neural networks are known to outperform all other neural network models when classifying a wide variety of 2D-shapes. This type of networks supports a massively parallel extraction of low-level features in the processed images. Especially this characteristic is assumed to impact the performance of convolutional networks in character recognition tasks - and in particular when considering scaled, rotated, translated or otherwise deformed patterns. Yet training of convolutional networks is rather time-consuming due to the relatively high complexity of the entire model. To speed-up the training process, we will propose a new variant of convolutional networks - the so-called hybrid convolutional neural network (HCNN). HCNN-networks combine the original idea of LeCun's convolutional networks with the benefits of RBF-like neurons in all the layers and with the winner-takes- all mechanism applied during recall. In the tests done so far in hand-written digit recognition, HCNN proved to be capable of considerably speeding-up the training process while maintaining roughly the same performance of the trained networks like original convolutional networks.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

In this paper, a software comparative analysis of two neural network models is presented, namely, Convolutional Neural Network (CNN), and Long Short Term Memory (LSTM) neural network. The evaluation is performed using the famous deep learning database the “MNIST” to check the accuracy, model size, speed and complexity of the two models for future digital realization on reconfigurable hardware. In addition to that, we optimize the size of the two models by quantizing the weights width to 8-bits instead of 32-bits. The results show an extensive reduction in the size of each model (by 10X) with a slight drop in the accuracy. The results also show that the CNN is more accurate and much faster than LSTMs making it the best model to be implemented on reconfigurable hardware.

Neural networks are a state-of-the-art approach that performs well for many tasks. The activation function (AF) is an important hyperparameter that creates an output against the coming inputs to the neural network model. AF significantly affects the training and performance of the neural network model. Therefore, selecting the most optimal AF for processing input data in neural networks is important. Determining the optimal AF is often a difficult task. To overcome this difficulty, studies on trainable AFs have been carried out in the literature in recent years. This study presents a different approach apart from fixed or trainable AF approaches. For this purpose, the activation function cyclically switchable convolutional neural network (AFCS-CNN) model structure is proposed. The AFCS-CNN model structure does not use a fixed AF value during training. It is designed in a self-regulating model structure by switching the AF during model training. The proposed model structure is based on the logic of starting training with the most optimal AF selection among many AFs and cyclically selecting the next most optimal AF depending on the performance decrease during neural network training. Any convolutional neural network (CNN) model can be easily used in the proposed model structure. In this way, a simple but effective perspective has been presented. In this study, first, ablation studies have been carried out using the Cifar-10 dataset to determine the CNN models to be used in the AFCS-CNN model structure and the specific hyperparameters of the proposed model structure. After the models and hyperparameters were determined, expansion experiments were carried out using different datasets with the proposed model structure. The results showed that the AFCS-CNN model structure achieved state-of-the-art success in many CNN models and different datasets.

To improve coastal adaptation and management, it is critical to better understand and predict the characteristics of sea levels. Here, we explore the capabilities of artificial intelligence, from four deep learning methods to predict the surge component of sea-level variability based on local atmospheric conditions. We use an Artificial Neural Networks, Convolutional Neural Network, Long Short-Term Memory layer (LSTM) and a combination of the latter two (ConvLSTM), to construct ensembles of Neural Network (NN) models at 736 tide stations globally. The NN models show similar patterns of performance, with much higher skill in the mid-latitudes. Using our global model settings, the LSTM generally outperforms the other NN models. Furthermore, for 15 stations we assess the influence of adding complexity more predictor variables. This generally improves model performance but leads to substantial increases in computation time. The improvement in performance remains insufficient to fully capture observed dynamics in some regions. For example, in the tropics only modelling surges is insufficient to capture intra-annual sea level variability. While we focus on minimising mean absolute error for the full time series, the NN models presented here could be adapted for use in forecasting extreme sea levels or emergency response.

The financial market has been developing rapidly in recent years, and the issue of credit risk concerning listed companies has become increasingly prominent. Therefore, predicting the credit risk of listed companies is an urgent concern for banks, regulators and investors. The commonly used models are the Z-score, Logit (logistic regression model), the kernel-based virtual machine (KVM) and neural network models. However, the results achieved could be more satisfactory. This paper proposes a credit-risk-prediction model for listed companies based on a CNN-LSTM and an attention mechanism, Our approach is based on the benefits of the long short-term memory network (LSTM) model for long-term time-series prediction combined with a convolutional neural network (CNN) model. Furthermore, the advantages of being integrated into a CNN-LSTM model include reducing the complexity of the data, improving the calculation speed and training speed of the model and solving the possible lack of historical data in the long-term sequence prediction of the LSTM model, resulting in prediction accuracy. To reduce problems, we introduced an attention mechanism to assign weights independently and optimize the model. The results show that our model has distinct advantages compared with other CNNs, LSTMs, CNN-LSTMs and other models. The research on the credit-risk prediction of the listing formula has significant meaning.

This study explores the potential of the VGG-16 architecture, a Convolutional Neural Network (CNN) model, for accurate brain tumor detection through deep learning. Utilizing a dataset consisting of 1655 brain MRI images with tumors and 1598 images with- out tumors, the VGG-16 model was fine-tuned and trained on this data. Initial training achieved an accuracy of 91%, which was improved to 94% after hyperparameter optimization. The model’s sensitivity, specificity, precision, recall, and F1 scores were strong, indicating its potential in accurately detecting brain tumors. The performance of the VGG-16 model was compared to several other techniques for brain tumor detection, including EasyDL, GoogLeNet, GrayNet, ImageNet, CNN, and a Multivariable Regression and Neural Network model. Although it did not achieve the highest accuracy, it outperformed GoogLeNet and ImageNet and demon- strated comparable accuracy to GrayNet and the Multivariable Regression and Neural Network. Its sensitivity and specificity suggest its potential in identifying tumors that other methods might miss, reinforcing its potential usefulness in medical applications. Never- theless, there is room for improvement. Future studies could collect and annotate larger datasets to improve model generalizability. Exploring other deep learning architectures and enhancing model interpretability could further boost its clinical relevance. Despite these challenges, this study demonstrates the untapped potential of the VGG-16 architecture in brain tumor detection and contributes to the growing body of research on applying deep learning in the medical field.

Convolutional Neural Networks (CNNs) have recently been utilized in a wide range of applications, including image and pattern identification, voice recognition, biometric embedded vision, food recognition, and video analysis for surveillance, industrial robots, and autonomous vehicles. Convolutional neural networks (CNNs) are gaining popularity for a variety of reasons. Feature extractors are created by hand in classic image recognition models. The weights of the convolutional layer utilized for feature extraction, as well as the fully connected layer, are used for classification in CNNs, and these weights are set throughout the training phase. The goal of this study is to evaluate a few convolutional neural network (CNN) learning machine approaches for image recognition. Furthermore, machine learning algorithms are used extensively in contemporary approaches to picture recognition. This article focuses on the development trend of convolution neural network (CNNs) model owing to various learning methods in image recognition during the 2000s, which is largely introduced from the angles of capturing, verification, and clustering, based on twenty five journals that have been reviewed. As a result, deep convolutional neural networks (DCNNs) have been very effective in a variety of machine learning and computer vision problems because they provide a large quality gain at a low computational cost. This training approach also enables models with many processing layers to learn different degrees of abstraction for data representation.

Self-mixing interferometry (SMI) is superior to other laser interferometry methods due to its simplicity and compactness. However, SMI signals are often complex and difficult to process due to interference in the form of variations in the effective reflectivity of the target, noisy signals, complex signal shapes, and other dependencies. Deep neural networks have been a very popular area of research in computer artificial intelligence in recent years, allowing more implicit features to be uncovered than traditional shallow machine learning. It has been shown that convolutional and back-propagation neural networks can be used for SMI signal processing. There are also studies that have used machine learning genetic algorithms for absolute distance measurement. Based on the above, this study used convolutional neural networks to form a deep neural network for absolute distance measurement based on SMI technology. We first trained the deep convolutional neural network at different feedback strengths. The results of the Convolutional Neural Network (CNN) model showed a coefficient of determination of 0.9987. which is consistent with the required model. The trained network was then used to estimate absolute distances with and without the addition of noise. The comparison proves that the proposed method is noise-proof and has high adaptability for measurements under different conditions.

Accurately identifying epileptogenic zone (EZ) using high-frequency oscillations (HFOs) is a challenge that must be mastered to transfer HFOs into clinical use. We analyzed the ability of a convolutional neural network (CNN) model to distinguish EZ and non-EZ HFOs. Nineteen medically intractable epilepsy patients with good surgical outcomes 2 years after surgery were studied. Five-minute interictal intracranial electroencephalogram epochs of slow-wave sleep were selected randomly. Then 5 s segments of ripples (80–200 Hz) and fast ripples (FRs, 200–500 Hz) were detected automatically. The EZs and non-EZs were identified using the surgery resection range. We innovatively converted all epochs into four types of images using two scales: original waveforms, filtered waveforms, wavelet spectrum images, and smoothed pseudo Wigner–Ville distribution (SPWVD) spectrum images. Two scales were fixed and fitted scales. We then used a CNN model to classify the HFOs into EZ and non-EZ categories. As a result, 7,000 epochs of ripples and 2,000 epochs of FRs were randomly selected from the EZ and non-EZ data for analysis. Our CNN model can distinguish EZ and non-EZ HFOs successfully. Except for original ripple waveforms, the results from CNN models that are trained using fixed-scale images are significantly better than those from models trained using fitted-scale images (p < 0.05). Of the four fixed-scale transformations, the CNN based on the adjusted SPWVD (ASPWVD) produced the best accuracies (80.89 ± 1.43% and 77.85 ± 1.61% for ripples and FRs, respectively, p < 0.05). The CNN using ASPWVD transformation images is an effective deep learning method that can be used to classify EZ and non-EZ HFOs.

With the development of computer technology, practitioners of computer-related industries pay more attention to the neural network. The excellent predictive ability makes neural network models stand out and almost fill every corner of the network. The convolutional neural network is one of the neural network models. Compared with other models, the convolutional neural network has more advantages in image recognition and segmentation technology due to its unique layer types. Research on convolutional neural networks started in the 1980s and 1990s. In the 21st century, convolutional neural networks have developed rapidly. The theory of deep learning and the improvement of numerical computing equipment make great progress in computer vision, natural language processing and other fields.

As Artificial Intelligence (AI) increasingly penetrates all aspects of society, many obstacles emerge. This thesis identifies and discusses the issues facing Computer Vision and significant deficiencies in the Software Development Life-cycle that need to be resolved to facilitate the evolution toward true artificial intelligence. We explicitly review the concepts behind Convolutional Neural Network (CNN) models, the benchmark for computer vision. Chapter 2 highlights the mechanisms that have popularized CNNs while also specifying significant gaps that could garner the model inadequate for future use in safety-critical systems. We put forward two main limitations. Namely, CNNs do not use lack of information as information, something that humans intuitively do. Further, the process of training puts CNNs at a disadvantage over the human brain and experience. While CNNs are trained by directly introducing entire concepts, people acquire knowledge incrementally. Because we learn the basics before the details, we are able to analyze imagery more expeditiously and successfully. Another obstacle limiting the progression of Artificial Intelligence is the factors that decrease the efficiency of programmers and their code. Chapters 3 and 4 explore some of these aspects. The analysis of computer code as a field of study has recently been getting more attention. However, most of this research focuses on the code as the artifact. This dissertation takes a different position by centering on the effects of computer programmers' behaviors on their code. We explore the practicality of current in-code documentation practices by assessing whether erroneous computer comments can mislead programmers. Our experimental model relies on asking participants to describe the functionality of code fragments which, unbeknownst to them, have misleading comments. We find that expert programmers are more prone to rely on these erroneous explanations and further visualize the phenomenon by using an eye-tracker. Finally, we present heatmaps that show experts concentrated more time and attention on the documentation than the code. In the next chapter, we conduct a large-scale analysis of the circumstances determining how long a bug will be present in a project. This study looks at 63,923 simple, one-statement fixes of bugs in open-source Java projects. We conclude that bugs fixed by the same programmer that introduced them are resolved 1.71 times faster. We also challenge Linus' law which states, " given enough eyeballs, all bugs are shallow." Our analysis finds that projects with more contributors have significantly longer-lived bugs, indicating that the mere number of people working on a