Accelerated MRI With Un-Trained Neural Networks

Passive sensing applications are limited by their inability to determine who is using a device, a critical concern in child mobile device use research, where devices are often shared between siblings or between a child and their parent. Our previous work leveraged behavioral biometrics to identify a target child user; however, it is unknown what type of training data is necessary for optimal model performance. This study evaluated model performance across different characteristics of training data. Thirty-six children (11.3 ± 0.9 years, 56% female) self-selected a video or a game on iPads for 10 min while laying and for another 5 min while sitting. The SensorLog application captured iPad accelerometer and gyroscope data while the child interacted with the device. Machine learning algorithms including Neural Network (NN), Random Forest (RF), k-Nearest Neighbors (k-NN), and SwipeFormer were applied to determine the most important aspects of training data to optimize model performance. The aspects of training data evaluated included (1) varying the length (i.e., seconds of training data), (2) varying the user position (i.e., sitting, laying), and (3) varying the time proximity between training and testing data. F1 score was used to evaluate model performance. The SwipeFormer F1 scores were lowest when the training data was further from the test data (0 when training data was 11 min away from test data) and highest when training data was close to test data (0.91 when training data was the minute preceding test data). The SwipeFormer F1 scores were highest when predicting the user laying from laying (0.97) and sitting from sitting (0.94), and lowest when predicting the user sitting from laying (0) and laying from sitting (0). The length of training data had little impact on performance, with a SwipeFormer F1 score of 0.91 when training on one minute of data and a SwipeFormer F1 score of 0.94 when training on twelve minutes of data. Because researchers would likely be predicting users at different timepoints than their training data, research should focus on improving model performance for identifying users independent of time proximity for training and test data.

Evaluation on the generalization of a learned convolutional neural network for MRI reconstruction

Deep convolutional neural networks have achieved great success in recent years. They have been widely used in various applications such as optical and SAR image scene classification, object detection and recognition, semantic segmentation, and change detection. However, deep neural networks rely on large-scale high-quality training data, and can only guarantee good performance when the training and test data are independently sampled from the same distribution. Deep convolutional neural networks are found to be vulnerable to subtle adversarial perturbations. This adversarial vulnerability prevents the deployment of deep neural networks in security-sensitive applications such as medical, surveillance, autonomous driving and military scenarios. This paper first presents a holistic view of security issues for deep convolutional neural network-based image recognition systems. The entire information processing chain is analyzed regarding safety and security risks. In particular, poisoning attacks and evasion attacks on deep convolutional neural networks are analyzed in detail. The root causes of adversarial vulnerabilities of deep recognition models are also discussed. Then, we give a formal definition of adversarial robustness and present a comprehensive review of adversarial attacks, adversarial defense, and adversarial robustness evaluation. Rather than listing existing research, we focus on the threat models for the adversarial attack and defense arms race. We perform a detailed analysis of several representative adversarial attacks on SAR image recognition models and provide an example of adversarial robustness evaluation. Finally, several open questions are discussed regarding recent research progress from our workgroup. This paper can be further used as a reference to develop more robust deep neural network-based image recognition models in dynamic adversarial scenarios.

Text sentiment analysis is one of the most important tasks in the field of public opinion monitoring, service evaluation and satisfaction analysis under network environments. Compared with the traditional Natural Language Processing analysis tools, convolution neural networks can automatically learn useful features from sentences and improve the performance of the affective analysis model. However, the original convolution neural network model ignores sentence structure information which is very important for text sentiment analysis. In this paper, we add piece-wise pooling to the convolution neural network, which allows the model to obtain the sentence structure. And the main features of different sentences are extracted to analyze the emotional tendencies of the text. At the same time, the user’s feedback involves many different fields, and there is less labeled data. In order to alleviate the sparsity of the data, this paper also uses the generative adversarial network to make common feature extractions, so that the model can obtain the common features associated with emotions in different fields, and improves the model’s Generalization ability with less training data. Experiments on different datasets demonstrate the effectiveness of this method.

In recent years, Convolutional Neural Networks (CNNs) have been widely successful for numerous computer vision tasks using 2D color and 3D point data, such as object detection and classification, and 3D pose estimation. Despite these successes, it comes with a price --- CNNs require a vast amount of labeled training data to be successful. Many training datasets are now available, however, they are mostly limited to general objects in the public domain such as people, cars, buildings, fruit, and more. Thus, not all fields have sufficient training data. Even if an adequate number of data samples can be built into a dataset, manually collecting and labeling the training data remains a laborious task. Several approaches to reduce or eradicate the need for training data have been proposed by researchers. The two most popular approaches are training with synthetic data and training on generalized object features. Training with synthetic data refers to the use of computer graphics to generate training data. While this approach has demonstrated success, it comes with its own challenges. In contrast, training a CNN on generalized object features identifies specific local 3D features or control points on objects. Local 3D features and their descriptors have proven in the past to be universally applicable and effective for general object detection, and thus, this method allows for a generalized CNN. A generalized CNN refers to a network architecture that, after initial training, can be specialized for a new task with a minimum amount or no new training data. This dissertation investigates an encoder-decoder architecture and determines the capabilities of it to generalize the CNN architecture for object detection tasks in point cloud data. A CNN is trained to recognize 3D features and demonstrates, without retraining, its successful applicability for point cloud object detection using disparate data. Additionally, the geometric consistency of the descriptors is evaluated to obtain further insight. The results demonstrate that the proposed 3D feature descriptors, and their increased geometric consistency contribute to the increased encoder-decoder architecture performance. In summary, this dissertation contributes a state-of-the-art, generalized, feature descriptor-based CNN architecture that can be transferred to different objects without retraining. Furthermore, it provides insight explaining the increased performance of the CNN compared to the state-of-the-art.

Currency volatility is an important aspect of time series data analysis in economics and finance. This study aims to compare the performance of four methods: Generalized Autoregressive Conditional Heteroscedasticity (GARCH), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN), in predicting the volatility of the Rupiah against the US Dollar. The data used is daily exchange rates from January 2015 to March 2024. The evaluation is conducted by calculating the Root Mean Square Error (RMSE) and the percentage of actual values within a 95% confidence interval on training and testing data. The results indicate that LSTM achieves the lowest RMSE, with values of 5.30E-05 on training data and 2.50E-05 on testing data, demonstrating high accuracy in capturing non-linear patterns and long-term fluctuations. GRU records the highest percentage of actual values within the confidence interval, at 90.32% for training data and 91.72% for testing data, reflecting superior consistency compared to other methods. Meanwhile, GARCH shows competitive performance but lacks robustness on testing data. CNN exhibits the lowest performance, with high RMSE and a low percentage of data within the confidence interval. Overall, GRU emerges as the best method, offering an optimal balance between predictive accuracy and consistency, making it a reliable tool for modeling exchange rate volatility in high-volatility scenarios. Consequently, GRU is utilized for forecasting exchange rate volatility for the next 30 days. These findings contribute to the selection of appropriate methods for modeling exchange rate volatility, particularly amidst global market uncertainty.

Brain tumors, encompassing subtypes with distinct progression and risk profiles, are a serious public health concern. Magnetic resonance imaging (MRI) is the primary imaging modality for non-invasive assessment, providing the contrast and detail necessary for diagnosis, subtype classification, and individualized care planning. In this paper, we evaluate the capability of modern deep learning models to classify gliomas as high-grade (HGG) or low-grade (LGG) using reduced training data from MRI scans. Utilizing the BraTS 2019 best-slice dataset (2185 images in two classes, HGG and LGG) divided in two folders, training and testing, with different images obtained from different patients, we created subsets including 10%, 25%, 50%, 75%, and 100% of the dataset. Six deep learning architectures, DeiT3_base_patch16_224, Inception_v4, Xception41, ConvNextV2_tiny, swin_tiny_patch4_window7_224, and EfficientNet_B0, were evaluated utilizing three-fold cross-validation (k = 3) and increasingly large training datasets. Explainability was assessed using Grad-CAM. With 25% of the training data, DeiT3_base_patch16_224 achieved an accuracy of 99.401% and an F1-Score of 99.403%. Under the same conditions, Inception_v4 achieved an accuracy of 99.212% and a F1-Score of 99.222%. Considering how the models performed across both data subsets and their compute demands, Inception_v4 struck the best balance for MRI-based glioma classification. Both convolutional networks and vision transformers achieved superior discrimination between HGGs and LGGs, even under data-limited conditions. Architectural disparities became increasingly apparent as training data diminished, highlighting unique inductive biases and efficiency characteristics. Even with a relatively limited amount of training data, current deep learning (DL) methods can achieve reliable performance in classifying gliomas from MRI scans. Among the architectures evaluated, Inception_v4 offered the most consistent balance between accuracy, F1-Score, and computational cost, making it a strong candidate for integration into MRI-based clinical workflows.

Developing computational algorithms to model the biological vision system has challenged researchers in the computer vision field for several decades. As a result, state-of-the-art algorithms such as the Convolutional Neural Network (CNN) have emerged for image classification and recognition tasks with promising results. CNNs however remain view-specific, producing good results when the variation between test and train data is small. Making CNNs learn invariant features to effectively recognise objects that undergo appearance changes as a result of transformations such as scaling remains a technical challenge. Recent physiological studies of the visual system are suggesting new paradigms. Firstly, our visual system uses both local features and global features in its recognition function. Secondly, cells tuned to global features respond quickly to visual stimuli for recognising objects. Thirdly, information from modalities that handle local features, global features and color are integrated in the brain for performing recognition tasks. While CNNs rely on aggregation of local features for recognition, these theories provide the potential for using global features to solve transformation invariance problems in CNNs. In this paper we realise these paradigms into a computational model, named as global features improved CNN (GCNN), and test it on classification of scaled images. We experiment combining Histogram of Gradients (HOG) global features, CNN local features and color information and test our technique on benchmark data sets. Our results show GCNN outperforms traditional CNN on classification of scaled images indicating potential effectiveness of our model towards improving scale-invariance in CNN based networks.

Image-based localization, or camera relocalization, is a fundamental problem in computer vision and robotics, and it refers to estimating camera pose from an image. Recent state-of-the-art approaches use learning based methods, such as Random Forests (RFs) and Convolutional Neural Networks (CNNs), to regress for each pixel in the image its corresponding position in the scene's world coordinate frame, and solve the final pose via a RANSAC-based optimization scheme using the predicted correspondences. In this paper, instead of in a patch-based manner, we propose to perform the scene coordinate regression in a full-frame manner to make the computation efficient at test time and, more importantly, to add more global context to the regression process to improve the robustness. To do so, we adopt a fully convolutional encoder-decoder neural network architecture which accepts a whole image as input and produces scene coordinate predictions for all pixels in the image. However, using more global context is prone to overfitting. To alleviate this issue, we propose to use data augmentation to generate more data for training. In addition to the data augmentation in 2D image space, we also augment the data in 3D space. We evaluate our approach on the publicly available 7-Scenes dataset, and experiments show that it has better scene coordinate predictions and achieves state-of-the-art results in localization with improved robustness on the hardest frames (e.g., frames with repeated structures).

The application of deep learning, specifically deep convolutional neural networks (DCNNs), to the classification of remotely-sensed imagery of natural landscapes has the potential to greatly assist in the analysis and interpretation of geomorphic processes. However, the general usefulness of deep learning applied to conventional photographic imagery at a landscape scale is, at yet, largely unproven. If DCNN-based image classification is to gain wider application and acceptance within the geoscience community, demonstrable successes need to be coupled with accessible tools to retrain deep neural networks to discriminate landforms and land uses in landscape imagery. Here, we present an efficient approach to train/apply DCNNs with/on sets of photographic images, using a powerful graphical method called a conditional random field (CRF), to generate DCNN training and testing data using minimal manual supervision. We apply the method to several sets of images of natural landscapes, acquired from satellites, aircraft, unmanned aerial vehicles, and fixed camera installations. We synthesize our findings to examine the general effectiveness of transfer learning to landscape-scale image classification. Finally, we show how DCNN predictions on small regions of images might be used in conjunction with a CRF for highly accurate pixel-level classification of images.

Artificial Intelligence and Deepfake Technologies have brought a new dimension to the generation of fake data, making it easier and faster than ever before—this fake data could include text, images, sounds, videos, etc. This has brought new challenges that require the faster development of tools and techniques to avoid fraudulent activities at pace and scale. Our focus in this research study is to empirically evaluate the use and effectiveness of deep learning models such as Convolutional Neural Networks (CNNs) and Patch-based Neural Networks in the context of successful identification of real and fake images. We chose the healthcare domain as a potential case study where the fake medical data generation approach could be used to make false insurance claims. For this purpose, we obtained publicly available skin cancer data and used recently introduced stable diffusion approaches—a more effective technique than prior approaches such as Generative Adversarial Network (GAN)—to generate fake skin cancer images. To the best of our knowledge, and based on the literature review, this is one of the few research studies that uses images generated using stable diffusion along with real image data. As part of the exploratory analysis, we analyzed histograms of fake and real images using individual color channels and averaged across training and testing datasets. The histogram analysis demonstrated a clear change by shifting the mean and overall distribution of both real and fake images (more prominent in blue and green) in the training data whereas, in the test data, both means were different from the training data, so it appears to be non-trivial to set a threshold which could give better predictive capability. We also conducted a user study to observe where the naked eye could identify any patterns for classifying real and fake images, and the accuracy of the test data was observed to be 68%. The adoption of deep learning predictive approaches (i.e., patch-based and CNN-based) has demonstrated similar accuracy (~100%) in training and validation subsets of the data, and the same was observed for the test subset with and without StratifiedKFold (k = 3). Our analysis has demonstrated that state-of-the-art exploratory and deep-learning approaches are effective enough to detect images generated from stable diffusion vs. real images.

Animal image classification with CNN (convolutional neural network) is commonly investigated in aera of image recogniation and classification, but major studies focus on species pictures classification with obvious distinctions. For example, CNN is usually employed to distinghish images between dogs and cats. This article puts the effort on similar animal images classification by applying simple 2D CNN via python. It focus on the binary classification for snub-nosed monkeys and normal monkeys. This distinguishment is hard to be done manually in a short time. For constructing complete convolutional neural network, some preparations are done in advance, such as the database construction and preprocess. The database is constructed by python crawler (downloading from google images), with 800 and 200 images for each class respectively as train data and test data. The pre-work includes image resizing, decoding and standardization. After that, the model is trained and then tested for verifying the model reliability. The training accuracy is 96.67% without any abnormality. On the basis of successful training, the test accuracy almost coincides with train accuracy in each 50 generations and plots in a graph. It indicates similar trends and results for them in the whole process. Because of this, CNN model in the study can help people identify rare animals in time and then people can effectively protect them. Therefore, CNN will be helpful in field of animal conservation, especially for rare species.

Online and continuous measurement of the mass flow rate of pneumatically conveyed solid particles is desirable in many industrial processes such as food processing, fertilizer handling, and power generation. In this paper, a multi-modal sensing system along with machine learning models is proposed to measure the mass flow rate of solid particles in pneumatic conveying pipelines. The multi-modal sensing system is comprised of an array of electrostatic sensors and temperature, humidity and differential-pressure transducers. A variable selection algorithm based on PMI (Partial Mutual Information) is applied to select useful features from the output signals of the sensing system. Machine learning models, including Artificial Neural Network (ANN), Support Vector Machine (SVM) and Convolutional Neural Network (CNN), are implemented to establish the relationship between the signal characteristics and the mass flow rate of particles based on the training data with selected features. Performance comparison between the three models is conducted with test data which is partially outside the range of the training data. Results suggest that the SVM model comparatively outperforms ANN and CNN in terms of generalization ability and offers the best trade-off between the input data length and measurement accuracy with relative error within ±10%.

This paper proposes a deep learning approach to recognize Tamil Letter from images which contains text. This is recognition process, the text in the images are divided to letter or characters. Each recognized letters are sending to recognition system and filter the text using deep learning algorithms. Our proposed algorithm is used to separate letter from the text using convolution neural network approach. The filtering system is used for identifying font based on that letters are found. The Tamil letters are test data and loaded in recognition systems. The trained data are input which contains filtered letter from image. For example, Tamil letters such as are available in test dataset. The trained data are applied into deep convolution neural network process. The two dataset are created which contains test data with Tamil letter and second one for recognized input data or trained data. 15 thousands of letters are taken and 512 X 512 X 3 size deep convolution network is created with font and letters. As the result, 85% Tamil letters are recognized and 82% are tested using font. TensorFlow is used for testing the accuracy and success rate.

paper, we focus on exploring the relationship between weave patterns and their mechanical properties in woven fiber composites through Machine Learning. Specifically, we explore the interactions between woven architectures and in-plane stiffness properties through Deep Convolutional Neural Network (DCNN) and Generative Adversarial Network (GAN). Our research is important for exploring how woven composite’s pattern is related to its mechanical properties and accelerating woven composite design as well as optimization. We focus on two tasks: (1) Stiffness prediction: Predicting in-plane stiffness properties for given weave patterns. Our DCNN extracts high-level features through several convolutional and fully connected layers to determine the final predictions. (2) Weave pattern prediction: Predicting weave patterns for target stiffness properties, which can be treated as the reverse task of the first one. Due to many-to-one mapping between weave patterns and the composite properties, we utilize a Decoder Neural Network as our baseline model and compare its performance with GAN and Genetic Algorithm. We represent the weave patterns as 2D checkerboard models and use finite element analysis (FEA) to determine in-plane stiffness properties, which serve as input data for our ML framework. We show that: (1) for stiffness prediction, DCNN can predict stiffness values for a given weave pattern with relatively high accuracy (above 93%); (2) for weave pattern prediction, the GAN model gives the best prediction accuracy (above 92%) while Decoder Neural Network has the best time efficiency. HAOTIAN FENG