Novel approach for KrF chemically amplified resist optimization assisted by deep learning

This paper introduces a new intelligent integration between an IoT platform and deep learning neural network (DNN) algorithm for the online monitoring of computer numerical control (CNC) machines. The proposed infrastructure is utilized for monitoring the cutting process while maintaining the cutting stability of CNC machines in order to ensure effective cutting processes that can help to increase the quality of products. For this purpose, a force sensor is installed in the milling CNC machine center to measure the vibration conditions. Accordingly, an IoT architecture is designed to connect the sensor node and the cloud server to capture the real-time machine’s status via message queue telemetry transport (MQTT) protocol. To classify the different cutting conditions (i.e., stable cutting and unstable cuttings), an improved model of DNN is designed in order to maintain the healthy state of the CNC machine. As a result, the developed deep learning can accurately investigate if the transmitted data of the smart sensor via the internet is real cutting data or fake data caused by cyber-attacks or the inefficient reading of the sensor due to the environment temperature, humidity, and noise signals. The outstanding results are obtained from the proposed approach indicating that deep learning can outperform other traditional machine learning methods for vibration control. The Contact elements for IoT are utilized to display the cutting information on a graphical dashboard and monitor the cutting process in real-time. Experimental verifications are performed to conduct different cutting conditions of slot milling while implementing the proposed deep machine learning and IoT-based monitoring system. Diverse scenarios are presented to verify the effectiveness of the developed system, where it can disconnect immediately to secure the system automatically when detecting the cyber-attack and switch to the backup broker to continue the runtime operation.

As semiconductor device structures become more complex and sophisticated, the formation of finer and deeper patterns is required. To achieve a higher yield for mass production as the number of process steps increases and process variables become more diverse, process optimization requires extensive engineering effort to meet the target process requirements, such as uniformity. In this study, we propose an efficient process design framework that can efficiently search for optimal process conditions by combining deep learning (DL) with plasma simulations. To establish the DL model, a dataset was created using a two-dimensional (2D) hybrid plasma equipment model code for an argon inductively coupled plasma system under a given process window. The DL model was implemented and trained using the dataset to learn the functional relationship between the process conditions and their consequential plasma states, which was characterized by 2D field data. The performance of the DL model was confirmed by comparison of the output with the ground truth, validating its high consistency. Moreover, the DL results provide a reasonable interpretation of the fundamental features of plasmas and show a good correlation with the experimental observations in terms of the measured etch rate characteristics. Using the designed DL, an extensive exploration of process variables was conducted to find the optimal processing condition using the multi-objective particle swarm optimization algorithm for the given objective functions of high etch rate and its uniform distribution. The obtained optimal candidates were evaluated and compared to other process conditions experimentally, demonstrating a fairly enhanced etch rate and uniformity at the same time. The proposed computational framework substantially reduced trial-and-error repetitions in tailoring process conditions from a practical perspective. Moreover, it will serve as an effective tool to narrow the processing window, particularly in the early stages of development for advanced equipment and processes.

Deep Learning (DL) is continuously adopted in many industrial applications at a rapidly increasing pace. This includes safety- and security-critical applications where errors in the DL system can lead to massive or even fatal losses. With the rise of DL adoption, trustworthy AI initiatives have been introduced that cover quality assurance principles such as robustness, fairness, and security of a DL system. Robustness aims to address the DL system's ability to predict new unseen inputs that are relevant to the DL application. Fairness aims to enable equal performance for all demographics, such as gender, age or ethnicity. Security aims to address new DL threats and defenses. Combining all three principles enables a more trustworthy DL system, which gives benefits to developers and end users. Developers gain confidence in deployment and end users gain trust in adopting a DL system. So far, the principles of robustness, fairness and security have been outlined in trustworthy initiatives from an expectations point of view under ISO or regulatory acts under the European Commission\cite{ai_act}. However, these initiatives give little attention to methods and quantitative assessment strategies on how those principles can be enabled and validated. Without assessment strategies, forming benchmarks to determine the quality of a DL system becomes a challenging task. This motivates research questions such as: ``\textit{At what point can a DL system be considered sufficient for deployment?}” and ``\textit{Is the data used for testing relevant and complete for the target application?}” In this thesis, we aim to address such questions and present foundational improvements by introducing out-of-distribution (OOD) awareness to robustness, fairness and security. Finally, the research methodologies are integrated into a national standard of Singapore which represents a high impact outcome of this work. First, we conduct a large-scale OOD empirical study to analyse which OOD technique is most suited for real-world DL system testing. Then, we propose an OOD testing criteria to enhance error discovery and propose distribution aware robustness enhancement by showing that filtering errors far from the trained distribution increases robustness by 21.5\%. We then enhance the field of OOD by introducing a fine-grained OOD technique assessing the ground truth of data augmentation and increasing accuracy by 31.9\% by guiding data augmentation selection with distribution awareness. We further apply the same augmentation technique to subsets of the training data to balance accuracy among demographics to enhance fairness. Finally, we introduce OOD defense approaches against two novel DL threats which fully evade traditional defenses. Ultimately, the thesis concludes with increasing quality assurance research impact by presenting the methodology that led to launching a national standard. The standard integrates our security research and evaluates it among four real-world use cases. This represents an important step in creating and validating trustworthy DL systems enabling increased trust in the intelligent solution and thereby further accelerating adoption in a safeguarded manner.

Robotic systems are ever more capable of automation and fulfilment of complex tasks, particularly with reliance on recent advances in intelligent systems, deep learning and artificial intelligence. However, as robots and humans come closer in their interactions, the matter of interpretability, or explainability of robot decision-making processes for the human grows in importance. A successful interaction and collaboration will only take place through mutual understanding of underlying representations of the environment and the task at hand. This is currently a challenge in deep learning systems. We present a hierarchical deep reinforcement learning system, consisting of a low-level agent handling the large actions/states space of a robotic system efficiently, by following the directives of a high-level agent which is learning the high-level dynamics of the environment and task. This high-level agent forms a representation of the world and task at hand that is interpretable for a human operator. The method, which we call Dot-to-Dot, is tested on a MuJoCo-based model of the Fetch Robotics Manipulator, as well as a Shadow Hand, to test its performance. Results show efficient learning of complex actions/states spaces by the low-level agent, and an interpretable representation of the task and decision-making process learned by the high-level agent.

Lattice degeneration and/or retinal breaks, defined as notable peripheral retinal lesions (NPRLs), are prone to evolving into rhegmatogenous retinal detachment which can cause severe visual loss. However, screening NPRLs is time-consuming and labor-intensive. Therefore, we aimed to develop and evaluate a deep learning (DL) system for automated identifying NPRLs based on ultra-widefield fundus (UWF) images. A total of 5,606 UWF images from 2,566 participants were used to train and verify a DL system. All images were classified by 3 experienced ophthalmologists. The reference standard was determined when an agreement was achieved among all 3 ophthalmologists, or adjudicated by another retinal specialist if disagreements existed. An independent test set of 750 images was applied to verify the performance of 12 DL models trained using 4 different DL algorithms (InceptionResNetV2, InceptionV3, ResNet50, and VGG16) with 3 preprocessing techniques (original, augmented, and histogram-equalized images). Heatmaps were generated to visualize the process of the best DL system in the identification of NPRLs. In the test set, the best DL system for identifying NPRLs achieved an area under the curve (AUC) of 0.999 with a sensitivity and specificity of 98.7% and 99.2%, respectively. The best preprocessing method in each algorithm was the application of original image augmentation (average AUC =0.996). The best algorithm in each preprocessing method was InceptionResNetV2 (average AUC =0.996). In the test set, 150 of 154 true-positive cases (97.4%) displayed heatmap visualization in the NPRL regions. A DL system has high accuracy in identifying NPRLs based on UWF images. This system may help to prevent the development of rhegmatogenous retinal detachment by early detection of NPRLs.

Deep learning (DL) defines a new data-driven programming paradigm that\nconstructs the internal system logic of a crafted neuron network through a set\nof training data. We have seen wide adoption of DL in many safety-critical\nscenarios. However, a plethora of studies have shown that the state-of-the-art\nDL systems suffer from various vulnerabilities which can lead to severe\nconsequences when applied to real-world applications. Currently, the testing\nadequacy of a DL system is usually measured by the accuracy of test data.\nConsidering the limitation of accessible high quality test data, good accuracy\nperformance on test data can hardly provide confidence to the testing adequacy\nand generality of DL systems. Unlike traditional software systems that have\nclear and controllable logic and functionality, the lack of interpretability in\na DL system makes system analysis and defect detection difficult, which could\npotentially hinder its real-world deployment. In this paper, we propose\nDeepGauge, a set of multi-granularity testing criteria for DL systems, which\naims at rendering a multi-faceted portrayal of the testbed. The in-depth\nevaluation of our proposed testing criteria is demonstrated on two well-known\ndatasets, five DL systems, and with four state-of-the-art adversarial attack\ntechniques against DL. The potential usefulness of DeepGauge sheds light on the\nconstruction of more generic and robust DL systems.\n

Identifying named entities is vital for many Natural Language Processing (NLP) applications. Much of the earlier work for identifying named entities focused on using handcrafted features and knowledge resources (feature engineering). This is a barrier for resource-scarce languages as many resources are not readily available. Recently, Deep Learning techniques have been proposed for various NLP tasks requiring little/no hand-crafted features and knowledge resources, instead the features are learned from the data. Many proposed deep learning solutions for Named Entity Recognition (NER) still rely on feature engineering as opposed to feature learning. However, it is not clear whether the deep learning system or the engineered features are responsible for the positive results reported. This is in contrast with the goal of deep learning systems i.e., to learn the features from the data itself. In this study, we show that a feature learned deep learning system is a viable solution to NER task. We test our deep learning systems on CoNLL English and Spanish NER datasets. Our system is able to give comparable results with the existing state-of-the-art feature engineered systems for English. We report the best performance of 89.27 F-Score for English when comparing with systems which do not use any handcrafted features or knowledge resources. Evaluation of our trained system on out-of-domain data indicate that the results are promising with the reported results. Our system when tested on Spanish NER achieves the best reported F-Score of 82.59 indicating its applicability to other languages.

Using Deep Learning Models to Characterize Major Retinal Features on Color Fundus Photographs

Gait is the human's natural walking style that is a complex biological process unique to each person. This paper aims to exploit millimeter wave (mmWave) to extract fine-grained microdoppler signatures of human movements, which are used as the mmWave gait biometric for user recognition. Towards this goal, a deep microdoppler learning system is proposed, which utilizes deep neural networks to automatically learn and extract the discriminative features in the mmWave gait biometic data to distinguish a large number of people from each other. In particular, our system consists of two subsystems including human target tracking and human target recognition. The tracking subsystem is responsible for detecting the appearance of a human subject, tracking his/her locations and estimating his/her walking velocity. The recognition subsystem utilizes the tracking data to generate the microdoppler signatures as the mmWave biometrics, which are fed into a custom-designed residual deep convolutional neural network (DCNN) for automatic feature extractions. Finally, a softmax classifier utilizes the extracted features for user identification. In a typical indoor environment, a top-1 identification accuracy of 97.45% is achieved for a dataset of 20 people.

The Internet of Things (IoT) has emerged as a crucial expansion of Internet services, linking numerous devices that produce and exchange substantial quantities of data. Strong defense against evolving cyberattacks that jeopardize the confidentiality, integrity, and availability (CIA Triad) of IoT systems is necessary due to this interconnectedness. Therefore, by controlling network activity to stop invasions and identify odd data patterns, intrusion detection systems can offer a robust layer of security for IoT systems. With a focus on identifying less frequent Advanced Persistent Threats (APT), this study aims to detect attacks directed at the CIA Triad. We examined two popular and unbalanced data sets, TON-IoT and BoT-IoT, for anomaly detection in IoT networks. By examining the usefulness of the ensemble learning and deep learning models in anomaly detection inside the IoT network data, we were able to study the security element of the network. The ensemble learning models considered are the following. Random Forest, XGBoost, and Stacking. The considered deep learning models are as follows: BiLSTM, GRU, Autoencoder, and Self-Taught Learning (STL: AE-SVM). The performance metrics studied are as follows: Accuracy, False Alert Rate, Recall, Precision, and F1-score. Regrettably, there were instances in which anomalies could not be detected using conventional techniques. This is because labeled data is scarce, particularly for APT attacks, and attack traffic is frequently sparse and noisy. We suggested a deep self-taught learning system (STL: AE-XGB) based on Transfer Learning to detect anomalies in IoT network data to tackle these difficult issues. To enhance classification performance and capture the changing landscape of attack methods in IoT networks. Our models automatically augment annotated data. The results show that our proposed model (STL: AE-XGB) outperforms the conventional models studied and provides interesting results in binary and multiclass classification.

Due to society’s practical demands, the legal profession’s growth within the context of the new liberal arts is necessary to improve teaching mechanisms and the comprehensive development of interdisciplinarity. In this paper, from the two major dilemmas of the specificity of legal instruments and the correlation between sentencing tasks, to examine the relationship between sentencing prediction, charge prediction, and law suggestion of legal instruments, respectively, the Bi-LSTM-attention model, end-to-end memory network model, and CNN-GRU network model are employed, to build an intelligent legal learning system. The outcomes demonstrate that, compared to the conventional machine learning algorithm, the intelligent legal learning system based on deep learning can increase prediction performance by 5.2% to 6%, global accuracy can reach 93.3%, and accuracy of legal documents processing by 7.9%. The deep learning-based intelligent legal learning system suggested in this study can assist law students in completing legal paperwork duties and increase their learning effectiveness.

BackgroundMissed fractures are the most common diagnostic errors in musculoskeletal imaging and can result in treatment delays and preventable morbidity. Deep learning, a subfield of artificial intelligence, can be used to accurately detect fractures by training algorithms to emulate the judgments of expert clinicians. Deep learning systems that detect fractures are often limited to specific anatomic regions and require regulatory approval to be used in practice. Once these hurdles are overcome, deep learning systems have the potential to improve clinician diagnostic accuracy and patient care.Questions/purposesThis study aimed to evaluate whether a Food and Drug Administration–cleared deep learning system that identifies fractures in adult musculoskeletal radiographs would improve diagnostic accuracy for fracture detection across different types of clinicians. Specifically, this study asked: (1) What are the trends in musculoskeletal radiograph interpretation by different clinician types in the publicly available Medicare claims data? (2) Does the deep learning system improve clinician accuracy in diagnosing fractures on radiographs and, if so, is there a greater benefit for clinicians with limited training in musculoskeletal imaging?MethodsWe used the publicly available Medicare Part B Physician/Supplier Procedure Summary data provided by the Centers for Medicare & Medicaid Services to determine the trends in musculoskeletal radiograph interpretation by clinician type. In addition, we conducted a multiple-reader, multiple-case study to assess whether clinician accuracy in diagnosing fractures on radiographs was superior when aided by the deep learning system compared with when unaided. Twenty-four clinicians (radiologists, orthopaedic surgeons, physician assistants, primary care physicians, and emergency medicine physicians) with a median (range) of 16 years (2 to 37) of experience postresidency each assessed 175 unique musculoskeletal radiographic cases under aided and unaided conditions (4200 total case-physician pairs per condition). These cases were comprised of radiographs from 12 different anatomic regions (ankle, clavicle, elbow, femur, forearm, hip, humerus, knee, pelvis, shoulder, tibia and fibula, and wrist) and were randomly selected from 12 hospitals and healthcare centers. The gold standard for fracture diagnosis was the majority opinion of three US board-certified orthopaedic surgeons or radiologists who independently interpreted the case. The clinicians’ diagnostic accuracy was determined by the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, sensitivity, and specificity. Secondary analyses evaluated the fracture miss rate (1-sensitivity) by clinicians with and without extensive training in musculoskeletal imaging.ResultsMedicare claims data revealed that physician assistants showed the greatest increase in interpretation of musculoskeletal radiographs within the analyzed time period (2012 to 2018), although clinicians with extensive training in imaging (radiologists and orthopaedic surgeons) still interpreted the majority of the musculoskeletal radiographs. Clinicians aided by the deep learning system had higher accuracy diagnosing fractures in radiographs compared with when unaided (unaided AUC: 0.90 [95% CI 0.89 to 0.92]; aided AUC: 0.94 [95% CI 0.93 to 0.95]; difference in least square mean per the Dorfman, Berbaum, Metz model AUC: 0.04 [95% CI 0.01 to 0.07]; p < 0.01). Clinician sensitivity increased when aided compared with when unaided (aided: 90% [95% CI 88% to 92%]; unaided: 82% [95% CI 79% to 84%]), and specificity increased when aided compared with when unaided (aided: 92% [95% CI 91% to 93%]; unaided: 89% [95% CI 88% to 90%]). Clinicians with limited training in musculoskeletal imaging missed a higher percentage of fractures when unaided compared with radiologists (miss rate for clinicians with limited imaging training: 20% [95% CI 17% to 24%]; miss rate for radiologists: 14% [95% CI 9% to 19%]). However, when assisted by the deep learning system, clinicians with limited training in musculoskeletal imaging reduced their fracture miss rate, resulting in a similar miss rate to radiologists (miss rate for clinicians with limited imaging training: 9% [95% CI 7% to 12%]; miss rate for radiologists: 10% [95% CI 6% to 15%]).ConclusionClinicians were more accurate at diagnosing fractures when aided by the deep learning system, particularly those clinicians with limited training in musculoskeletal image interpretation. Reducing the number of missed fractures may allow for improved patient care and increased patient mobility.Level of EvidenceLevel III, diagnostic study.

Simple SummaryActional mutations and PD-L1 expression are of paramount importance for the precision treatment of lung cancer. Radiogenomics is a promising field that integrated radiologic images and genomic data through artificial intelligence technology. This approach enables non-invasive assessment of genes, but the vast majority of studies are limited to single gene mutation prediction. Our study aimed to propose a multi-label multi-task deep learning (MMDL) system to predict molecular status based on routinely acquired computed tomography (CT) images using deep learning and radiomics. A dataset of CT images from 1096 non-small cell lung cancer (NSCLC) patients with molecular tests was curated to train, validate and test. The MMDL model achieved superior performance on the classification task of simultaneous identification of eight genes or even ten molecules. This system has the potential to be an auxiliary support tool to advance precision oncology.Purpose: Personalized treatments such as targeted therapy and immunotherapy have revolutionized the predominantly therapeutic paradigm for non-small cell lung cancer (NSCLC). However, these treatment decisions require the determination of targetable genomic and molecular alterations through invasive genetic or immunohistochemistry (IHC) tests. Numerous previous studies have demonstrated that artificial intelligence can accurately predict the single-gene status of tumors based on radiologic imaging, but few studies have achieved the simultaneous evaluation of multiple genes to reflect more realistic clinical scenarios. Methods: We proposed a multi-label multi-task deep learning (MMDL) system for non-invasively predicting actionable NSCLC mutations and PD-L1 expression utilizing routinely acquired computed tomography (CT) images. This radiogenomic system integrated transformer-based deep learning features and radiomic features of CT volumes from 1096 NSCLC patients based on next-generation sequencing (NGS) and IHC tests. Results: For each task cohort, we randomly split the corresponding dataset into training (80%), validation (10%), and testing (10%) subsets. The area under the receiver operating characteristic curves (AUCs) of the MMDL system achieved 0.862 (95% confidence interval (CI), 0.758–0.969) for discrimination of a panel of 8 mutated genes, including EGFR, ALK, ERBB2, BRAF, MET, ROS1, RET and KRAS, 0.856 (95% CI, 0.663–0.948) for identification of a 10-molecular status panel (previous 8 genes plus TP53 and PD-L1); and 0.868 (95% CI, 0.641–0.972) for classifying EGFR / PD-L1 subtype, respectively. Conclusions: To the best of our knowledge, this study is the first deep learning system to simultaneously analyze 10 molecular expressions, which might be utilized as an assistive tool in conjunction with or in lieu of ancillary testing to support precision treatment options.

Deep learning has evolved as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. The advancement of deep learning has been so radical that today it can surpass human‐level performance. As a consequence, deep learning is being extensively used in most of the recent day‐to‐day applications. However, efficient deep learning systems can be jeopardised by using crafted adversarial samples, which may be imperceptible to the human eye, but can lead the model to misclassify the output. In recent times, different types of adversaries based on their threat model leverage these vulnerabilities to compromise a deep learning system where adversaries have high incentives. Hence, it is extremely important to provide robustness to deep learning algorithms against these adversaries. However, there are only a few strong countermeasures which can be used in all types of attack scenarios to design a robust deep learning system. Herein, the authors attempt to provide a detailed discussion on different types of adversarial attacks with various threat models and also elaborate on the efficiency and challenges of recent countermeasures against them.

Ultra-precision CNC machine tools play a significant role in the machining of precision dies and molds, optics, consumer electronics, etc., Due to the nature of ultra-precision machining, a subtle change in process condition, machine anomalies, etc. may significantly influence the machining outcome. Hence, continuous monitoring of the equipment’s operation is required to better understand the variations associated with the process and the machine. The conventional monitoring platform requires comprehensive data analysis using multiple sensors, and controller data to detect, diagnose, and prognose machine and process conditions. This increases the cost and complexity of installing a monitoring platform. The energy consumption data contains valuable information that could be potentially used to identify machine and process variations. The information can also be used to develop potential energy-saving strategies in an effort towards Green Manufacturing. This paper proposes an intelligent energy monitoring method using a 1-dimensional convolutional neural network (1D-CNN) to effortlessly and accurately obtain the working status information of the machine with minimal retrofitting. The 1D-CNN uses the energy consumption data to determine the equipment’s operation status by identifying the working components and the feed rate of the moving axis. The hyper-parameters of the developed model were optimized to improve the prediction accuracy. The paper also compares different Deep Learning and Machine Learning algorithms to gauge their effective performance in this application. Finally, the model with the highest accuracy was validated on a 5-axis ultra-precision CNC machine tool. Results show that 1D-CNN performs better than multi-layer neural networks and machine learning algorithms in processing time-series datasets. The classification accuracy of 1D-CNN on the detection of operation status and feed rate of each axis can reach 95.7 and 91.4%, respectively. Further studies are currently in progress to improve prediction accuracy of the model, and to detect subtle changes in energy consumption which would enable identification of the machine and process anomalies.