As integrated circuit manufacturing processes develop into the nanometer scale, precise control and prediction of the deposition process have become crucial. Nanoscale manufacturing imposes unprecedentedly high demands on film quality, uniformity, and consistency, presenting significant challenges to traditional control and prediction methodologies. This study proposes a novel approach that, for the first time, formulates the thin-film deposition process as a video prediction task, enabling the use of deep learning for morphological forecasting under varying process conditions, and introduces a novel hyperparameter-fusion neural network, referred to as DepositionNet (DepoNet). Unlike conventional video prediction models, DepoNet specifically accounts for the influence of deposition parameters on the entire simulation process. We have incorporated a novel Hyper Projector that allows the model to flexibly adapt to varying deposition conditions and material characteristics. Through comprehensive comparative experimental analyses, we demonstrate that DepoNet significantly outperforms existing deep-learning models and achieves a mean squared error of 17.34, representing a 3.67% improvement over the second best model and a 1,435 × speedup over physics-based methods, thereby validating its exceptional generalization capability. Extensive experiments reveal that the model maintains high performance even under conditions of limited training data, for instance, achieving a peak signal-to-noise ratio (PSNR) of 41.516 decibels (dB) when trained with only 20% of the available data.

Active learning (AL) can significantly reduce the overall amount of training data required to achieve near-optimal performance. Despite the notable advancements in active learning for image recognition, there remains a lack of a lightweight active learning method specifically designed for object detection. In this paper, we embark on an investigation into the uncertainty of predicted instances’ boxes within the object detection process, addressing three distinct types of uncertainty related to position, size, and category in object detection. We define proposals after regression as instances and feature instances belong to one object as instances bags. We estimate image uncertainty by calculating the position, size, and category variances of these instance bags. In object detection tasks, experiments validate that the proposed method significantly reduces computational complexity and outperforms state-of-the-art methods by a substantial margin.

Cohort study is one of the most commonly used study methods in medical and public health researches, which result in longitudinal data. Conventional statistical models and machine learning methods are not capable of modeling the evolution trend of the variables in longitudinal data. In this article, we propose a Trend Analysis Neural Networks (TANN), which models the evolution trend of the variables by adaptive feature learning. TANN was tested on dataset of Kaiuan research. The task was to predict occurrence of cardiovascular events within 2 and 5 years, with three repeated medical examinations during 2008 and 2013. For 2-year prediction, The AUC of the TANN is 0.7378, which is a significant improvement than that of conventional methods, while that of TRNS, RNN, DNN, GBDT, RF, and LR are 0.7222, 0.7034, 0.7054, 0.7136, 0.7160, and 0.7024, respectively. For 5-year prediction, TANN also shows improvement. The experimental results show that the proposed TANN achieves better prediction performance on cardiovascular events prediction than conventional models. Furthermore, by analyzing the weights of TANN, we could find out important trends of the indicators, which are ignored by conventional machine learning models. The trend discovery mechanism interprets the model well. TANN is an appropriate balance between high performance and interpretability.

Abstract With the development of the IC industry, electronic design automation (EDA) tools are also developing. Currently, EDA tools have been migrating to high‐performance computing clusters (HPC) or the cloud to meet increasing computing and storage requirements. EDA tasks are scientific workflows, whose scheduling is a well‐known NP‐hard problem. In this paper, we propose a novel workflow scheduling algorithm HEWS, which achieves better performance through a novel hierarchical sorting method. We conducted a series of simulation experiments in different environments, and the experimental results show that our HEWS scheduling algorithm achieves better scheduling performance compared to several conventional scheduling methods, the waiting time and makespan of workflow are significantly reduced.

The unsupervised anomaly detection in KPI (Key Performance Indicator) series has been an active research area due to its enormous potential for application in industry. KPI series representation, reconstruction, and forecasting have made extraordinary progress in existing work. However, long-term temporal patterns prohibit the model from learning reliable dependencies. To this end, we propose a novel approach based on VAE-TCN hybrid model. Our model uses VAE (variational automatic coder) to learn robust local features in a short window, and uses TCN (temporal convolution network) to estimate the long-term correlation in the sequence based on the features inferred by VAE module. Extensive experiments on various public benchmarks demonstrate that our method has achieved the state-of-the-art performance.

Unsupervised anomaly detection for time series has been an active research area due to its enormous potential for wireless network management. Existing works have made extraordinary progress in time series representation, reconstruction and forecasting. However, long-term temporal patterns prohibit the model from learning reliable dependencies. To this end, we propose a novel approach based on Transformer with dilated convolution for time anomaly detection. Specifically, we provide a dilated convolution module to extract long-term dependence features. Extensive experiments on various public benchmarks demonstrate that our method has achieved the state-of-the-art performance.

Accurate prediction for node CPU load is crucial for resource allocation in cluster. In this paper, we proposed a novel deep learning model named R-TPA-LSTM for the cluster node CPU load prediction. The proposed model is composed of two components, non-linear and linear component. The non-linear component contains residual LSTM-Conv module and attention module. Residual LSTM-Conv module includes two LSTM layers with residual connection and convolutional neural network for the sake of choosing the most informative timestep in the historical window while attention module captures the relationship among different features. The goal of the linear component, which is an AR module, is to catch the drastic changes in the data. The experimental results on a real-world dataset, show that the proposed model achieves better prediction performance for CPU load than conventional models.

Cohort study is one of the most commonly used study methods in medical and public health researches, which result in longitudinal data. Conventional statistical models and machine learning methods are not capable of modeling the evolution trend of the variables in longitudinal data. In this paper, we propose a Trend Analysis Neural Networks (TANN), which models the evolution trend of the variables by adaptive feature learning. TANN was tested on dataset of Kaiuan research. The task was to predict occurrence of death within 5 years, with 3 repeated medical examinations from 2008 to 2013. The AUC of the TANN is 0.7888, which is a slightly improvement than that of conventional methods, while that of GBDT is 0.7824, that of random forests is 0.7822, and that of logistic regression is 0.7789. The experimental results show that the proposed TANN achieves better prediction performance on death events prediction than conventional models. Furthermore, by analyzing the weights of TANN, we could find out important trends of the indicators. The trend discovery mechanism interprets the model well. TANN is an appropriate trade-off between high performance and interpretability.

Accurate and timely prediction of the Internet traffic flow is important for network performance improvement. Few prediction methods incorporate the topology information of networks. In this paper, we present a novel Internet traffic forecasting algorithm named TTGCN, which applies the graph neural networks for traffic flow prediction on each link of a backbone network. The topology of the network was represented by a novel adjacency matrix, which models the relationship between links. The design makes TTGCN capable of capturing both the temporal and topological information of the traffic flow. TTGCN is validated on UKERNA, a dataset captured from a real backbone network. The experimental results show that the average error of the proposed TTGCN over 90 minutes is 28.249 (Mbit/s), which is a significant improvement of conventional models, while that of ARIMA and GRU and STGCN are 44.955, 40.935, and 36.152, respectively. The proposed TTGCN, by encoding both temporal and topological information in a neural representation, can achieve better prediction performance on network traffic.

The Electrocardiogram (ECG) is commonly used to detect arrhythmias. Traditionally, a single ECG observation is used for diagnosis, making it difficult to detect irregular arrhythmias. Recent technology developments, however, have made it cost-effective to collect large amounts of raw ECG data over time. This promises to improve diagnosis accuracy, but the large data volume presents new challenges for cardiologists. This paper introduces ECGLens, an interactive system for arrhythmia detection and analysis using large-scale ECG data. Our system integrates an automatic heartbeat classification algorithm based on convolutional neural network, an outlier detection algorithm, and a set of rich interaction techniques. We also introduce A-glyph, a novel glyph designed to improve the readability and comparison of ECG signals. We report results from a comprehensive user study showing that A-glyph improves the efficiency in arrhythmia detection, and demonstrate the effectiveness of ECGLens in arrhythmia detection through two expert interviews.

Atrial Fibrillation (AF) is the most common chronic arrhythmia. Effective detection of the AF would avoid serious consequences like stroke. Conventional AF detection methods need heuristic or hand-craft feature extraction. In this paper, A deep neural network named multi-scale convolutional neural networks (MCNN) based AF detector is proposed. Instant heart rate sequence is extracted from ECG signal, then an end-to-end MCNN detects AF with the instant heart rate sequence as input and detection result as output. The algorithm was tested on both public and private datasets. On the public dataset, with the sensitivity achieved being 0.9822, the corresponding specificity is 0.9811, and the overall accuracy is 0.9818. The area under an ROC curve is as high as 0.9962, compared to the AUC of the best conventional method is 0.9947. Comparison shows that the MCNN based AF detector give superior accuracy than conventional methods. Test on private dataset also shows significant improvement.

Fundus image is important for the medical screening and diagnosis of variety ophthalmopathy. The effectiveness of such a process, however, depends very much on the quality of the fundus image captured. This paper aims to asses in real-time the quality of a fundus image by first extracting a multitude of generic features, including statistical characteristics, entropy, texture, symmetry, frequency components and blur metric, which is then followed by a support vector machine (SVM) trained to filter out the poor quality image for clinic usage. The method was tested on a dataset of 3224 images collected from an eye hospital's practical screening project in rural areas in Northeastern Region of China. With the detection rate achieved being 0.9308, the corresponding false alarm rate is 0.1127, and the overall accuracy is 0.9138. The area under an ROC curve is as high as 0.9619. It is shown that the fundus images of poor quality can be automatically detected on the spot to ensure a clinically meaningful ophthalmopathy screening and diagnosis by a human expert or even an artificial intelligence software.

Frame and fusion frame high-resolution image fusion formulations are presented. These techniques use the physical point spread function (PSF) of cameras as the building block of the mathematical frames in the fusion process. Cameras producing the low-resolution images are allowed to be different, and thereby possess different PSFs. Fused image reconstructions are carried out by a dimension invariance principle and by a set of iterative reconstruction algorithms. These frame fundamental approaches are also seen to be robust to realistic fusion problems from inhomogeneous image measurements (taken at different space or time or by different cameras), which is one of the main focuses of this paper. The effectiveness of this approach is demonstrated through both simulated and realistic examples. The results are quite encouraging.