Search

In April 2022, I was invited to lecture at Villanova University, Villanova, PA, USA, and I met Dr. Pritpal Singh. Later, in June of that year during the IEEE TAB Series, I met the then President of the Humanitarian Activities Committee (HAC), Dr. Sampathkumar Veeraraghavan. Later, in July during the IEEE Latin American Electron Devices Conference (LAEDC) sponsored by the IEEE Electron Devices Society (EDS), I was invited to give a keynote talk and to be part of a panel. Mario Aleman conducted this panel session on Humanitarian Technology 2022, which also included both above-mentioned individuals. I also had the opportunity to meet the fourth panelist, Dr. Morgan Kiani (see). [ABSTRACT FROM AUTHOR]

Edge computing is an emerging computing paradigm representing decentralized and distributed information technology architecture. The demand for edge computing is primarily driven by the increased number of smart devices and the Internet of Things (IoT) that generate and transmit a substantial amount of data, that would otherwise be stored on cloud computing services. The edge architecture enables data and computation to be performed in close proximity to users and data sources and acts as the pathway toward upstream data centers. Rather than sending data to the cloud for processing, the analysis and work is done closer to where the source of the data is generated (). Edge services leverage local infrastructure resources allowing for reduced network latency, improved bandwidth utilization, and better energy efficiency compared to cloud computing. [ABSTRACT FROM AUTHOR]

Welcome to this March 2024 Special Issue on Advancing Sustainable Development Goals with AI This issue features research on how AI and data technologies can be used to advance the United Nations (UN) sustainable development goals (SDGs). [ABSTRACT FROM AUTHOR]

In this Article, we will introduce several interrelated problems present in municipal solid waste recycling efforts, both globally and locally. The introduction serves to demonstrate how the lack of adequate global waste tracking and community-level waste contamination are related issues. This article elaborates on how these issues could be addressed with the Internet of Things (IoT), artificial intelligence (AI), and open data technology deployment. We will investigate the existing and possible applicability of this solution in resource-constrained environments, as opposed to exclusive use in the typical “smart city” context. Finally, we will discuss the risks and limitations of this approach. [ABSTRACT FROM AUTHOR]

In 2015, the United Nations (UN) launched an ambitious set of 17 Sustainable Development Goals (SDGs) to end poverty, protect the planet, and ensure prosperity for all as part of the 2030 Agenda for Sustainable Development. Achieving these far-reaching goals requires effective tracking of progress across 169 targets and over 230 indicators. Furthermore, adopted in 2015, Africa Agenda 2063 is a strategic framework developed by the African Union (AU) to optimize the use of the continent’s resources for sustainable and inclusive growth. It aims to deliver on key aspirations shared by African nations including a high standard of living, well-educated citizens, good governance, strong cultural identity, and Africa’s strong voice in global affairs. Built around 20 goals and seven priority areas, Agenda 2063 provides a shared vision and roadmap for socioeconomic transformation in Africa over the next 50 years. However, numerous countries in Africa face considerable challenges in collecting, timely, granular, high-quality data to adequately monitor SDG metrics. Traditional data sources like surveys and administrative records often have gaps, especially at subnational levels. As a result, national statistics offices, particularly in Africa, lack the data needed to properly inform SDG-related policies and interventions. [ABSTRACT FROM AUTHOR]

The article announces the IEEE International Symposium on Technology and Society, scheduled from September 18-20 in Puebla, Mexico, focusing on the Social Implications of Artificial Intelligence (AI), inviting submissions from academia, industry, and government to explore AI's impacts.

As we enter a New Year, we can look back on another year of solid accomplishment at IEEE Transactions on Semiconductor Manufacturing. I am happy to report that our impact factor remains steady at 2.70, and our mean time to first decision remains competitive at 8.3 weeks. Our Editorial Board remains as strong as ever, with the addition of Dr. Jun-Haeng Lee in the area of machine learning and data science applications in 2023, and we are actively seeking new board members. Our submissions remain strong, as do the special sections from conferences (ASMC, ISSM and CS-MANTECH). The Special Issue on Production-Level Artificial Intelligence Applications in Semiconductor Manufacturing appeared in the November issue, and two additional special issues are in preparation. Prof. Duane Boning of MIT and Dr. Bill Nehrer of Technology Consultancy are co-editing a special issue on “Semiconductor Design for Manufacturing,” which will be a collaborative effort with the IEEE Transactions on Electron Devices. Drs. Oliver Patterson of Intel and Tomasz Brozek of PDF Solutions are also co-editing a special issue on sustainable semiconductor manufacturing. We are also happy to announce the Best paper Award for 2023, in the companion editorial appearing in this issue. Congratulations to all the honorees, and we hope we will continue to see their submissions in the future. Our thanks go to Drs. Jeanne Bickford, Dragan Djurdjanovic and Mahadeva Iyer Natarajan for their work on this committee. [ABSTRACT FROM AUTHOR]

A scheduling problem for parallel batch processing machines (BPMs) with jobs having unequal ready times in semiconductor wafer fabrication facilities (wafer fabs) is studied in this paper. A blended objective function combining the total weighted tardiness (TWT) and the total electricity cost (TEC) under a time-of-use (TOU) tariff is considered. A genetic programming (GP) procedure is designed to automatically discover priority indices for a heuristic scheduling framework. Results of computational experiments are reported that demonstrate that the learned priority indices lead to high-quality schedules in a short amount of computing time. [ABSTRACT FROM AUTHOR]

This work introduces a practical reinforcement learning (RL) techniques to address the complex scheduling challenges in producing Active Matrix Organic Light Emitting Diode displays. Specifically, we focus on autonomous optimization of the photolithography process, a critical bottleneck in the fabrication. This provides an outperforming scheduling method compared with the existing rule-based approach which requires diverse rules and engineer experience on adapting dynamic environments. Our purposing RL network was designed to make effective schedules aligning with layered structures of the planning and scheduling modules for mass production. In the training phase, historical production data is utilized to create a representative discrete event simulation environment. The RL agent, based on the Deep Q-Network, undergoes episodic training to learn optimal scheduling policies. To ensure safe and reliable scheduling decisions, we further introduce action filters and parallel competing schedulers. The performance of RL-based Scheduler (RLS) is compared to the Rule-Based Scheduler (RBS) over actual fabrication in a year-long period. Based on key performance indicators, we validate the RLS outperforms the RBS, with a remarkable improvement in step target matching, reduced setup times, and enhanced lot assignments. This work also paves a way for the gradual integration of AI-based algorithms into smart manufacturing practices. [ABSTRACT FROM AUTHOR]

This paper studies simultaneous scheduling of production and material transfer that arises in the semiconductor photolithography area. In particular, the right reticle and right job both need to be present to process the job. Jobs are transferred by a material handling system that employees a fleet of vehicles. Reticles serving as an auxiliary resource are also transferred from one place to another by a different set of vehicles. This intricate scheduling challenge, encompassing jobs, reticles, machines, and two distinct sets of vehicles, is explored here for the first time. The paper introduces a multi-stage methodology that involves relaxation, a constructive heuristic, constraint programming, and a warm-start approach to address this complex problem. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing demands a fast delivery of multiple gases to the tool. Hence this document provides formulas for the fluid-mechanical timescales of this delivery. This is done with a simple but realistic model of a gas-supply system, together with theory and computational-fluid-dynamic (CFD) simulations, and for representative but not comprehensive conditions relevant to etch. This timescale analysis shows that the rate-limiting process is (i) convection in the MFC-manifold tubing or (ii) convection in the tube between the flow splitter and the process chamber. This depends on (a) the lowest MFC sccm in the gas-supply system and (b) the total gas-supply-system sccm. Therefore, speeding up the gas delivery requires enhancing (i) and (ii). Moreover, (i) would become more important in view of a current trend towards smaller MFC sccms in etch. Examples on how to speed up the gas delivery and enhance the mixing are provided. The present analysis can be adapted to other conditions and manufacturing processes. [ABSTRACT FROM AUTHOR]

Doing high throughput high accuracy metrology in small geometries is challenging. One approach is to build easily measurable proxy targets onto dies and make a predictive model based on those signals. We use optical Pattern Shift Response (PSR) proxy targets to build predictive models of the electrical characteristics of devices in the Back End Of Line (BEOL). Given the wide choice of PSR targets, we explore how to select combinations of them to maximise the utility of the features for building an accurate Machine Learning (ML) model; we call this approach Multiplexed Optical Metrology. We also explore the trade-off between chip area dedicated to targets and achievable accuracy. We run ML experiments using different selections of targets measured at different stages of BEOL processing: post-lithography and post-Chemical-Mechanical-Planarisation (CMP). Our results show that a) reasonable predictive performance can be achieved for a reasonable area budget; b) ML model performance across target families varies significantly, thus justifying the need for careful selection of targets; c) longitudinal measurements of targets increases accuracy for no extra area penalty; d) increasing the number of targets gives some improvement in accuracy for a dataset of this size, but relatively small compared to the increase in area budget needed. Ultimately we aim to do die-level yield prediction using these techniques. We discuss how collecting a larger dataset with appropriate yield information is the logical next step to achieving this. [ABSTRACT FROM AUTHOR]

Accurate prediction of the remaining useful life (RUL) of an ion mill is vital for optimizing the overall performance of the ion mill etching (IME) process. However, due to the uneven distribution of important information, and the poorly understood failure mechanisms, fault prognosis in this process presents significant challenges. Deep neural networks have shown promising results for extracting, without domain knowledge, relevant features from condition monitoring data. This study proposes a multi-scale and multi-branch Transformer network based on the vanilla Transformer to predict the RUL of ion mills. To extract features on various scales, multi-scale feature extraction first generates receptive fields of various sizes, which are then integrated to obtain feature representations. The multi-branch Transformer uses the parallel attention mechanism and long short-term memory (LSTM) to capture both the adjacent location information and the crucial information of a given timestamp. Handcrafted features are also incorporated as additional input to enhance the prediction accuracy of the model. The proposed model is evaluated on a dataset from a semiconductor IME process. The experimental results demonstrate that the proposed model outperforms other deep neural network and further highlight the practical feasibility of the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a linear regression model for scalar-valued responses and two-way functional (bivariate) predictors. Our motivation stems from the quality evaluation of products based on optical emission spectroscopy data from virtual metrology of semiconductor manufacturing. We focus on multivariate cases where the smoothness and shapes of the data vary significantly across variables. We propose a two-step solution to this problem, consisting of decomposition and prediction. First, we decompose the two-way functional data into pairs of component functions using functional singular value decomposition. Next, we build functional linear models for the decomposed functional variables and obtain the final predictor by averaging the models. Results from numerical studies, including simulation studies and real data analysis, demonstrate the promising empirical properties of the proposed approach, especially when the number of predictors is large. [ABSTRACT FROM AUTHOR]

The patterning of silicon and silicon oxide nanocones onto the surfaces of devices introduces interesting phenomena such as anti-reflection and super-transmissivity. While silicon nanocone formation is well-documented, current techniques to fabricate silicon oxide nanocones either involve complex fabrication procedures, non-deterministic placement, or poor uniformity. Here, we introduce a single-mask dry etching procedure for the fabrication of sharp silicon oxide nanocones with smooth sidewalls and deterministic distribution using electron beam lithography. Silicon oxide films deposited using plasma-enhanced chemical vapor deposition are etched using a thin alumina hard mask of selectivity > 88, enabling high aspect ratio nanocones with smooth sidewalls and arbitrary distribution across the target substrate. We further introduce a novel multi-step dry etching technique to achieve ultra-sharp amorphous silicon oxide nanocones with tip diameters of ~10 nm. The processes presented in this work may have applications in the fabrication of amorphous nanocone arrays onto arbitrary substrates or as nanoscale probes. [ABSTRACT FROM AUTHOR]

Single-image super-resolution (SISR) techniques have found wide applications in semiconductor defect inspection. Enhancing image resolution to improve inspection sensitivity and accuracy holds great significance. A novel SISR algorithm, called cross-convolutional residual network (CCRN), is proposed in this study. CCRN comprises a cross-convolutional module (CCM), which incorporates a cross-sharing mechanism that facilitates the fusion of features from different stages, enabling the extraction of more information from the image. Moreover, a global residual aggregation structure (GRA) is introduced. GRA captures and transfers different levels of residual features acquired from learning each CCM to the reconstruction layer. Experimental results demonstrate that the proposed SR algorithm outperforms existing state-of-the-art SR algorithms in terms of both visual and quantitative metrics when applied to optical, SEM, and TEM images of microfluidic chips, CMOS image sensors, and quantum dots, respectively. Additionally, CCRN significantly improves the accuracy of defect classification and inspection of unpatterned wafers, as evaluated using the WM-811K dataset. Notably, an increase in local defection testing accuracy from 79.00% to 89.00% and an improvement in classification accuracy from 93.69% to 96.06% are achieved. These findings underscore the potential applications of the proposed algorithm in improving semiconductor defect inspection and classification accuracies. [ABSTRACT FROM AUTHOR]

Since the invention of transistors and integrated circuits, the development of semiconductor processes has advanced rapidly. Current microchips contain hundreds of millions of transistors. The remarkable development of semiconductors thus far has also led to difficulties in designing tightly packed lithography patterns without unwanted defects called hotspots in the manufacturing process. Therefore, research areas focusing on these problems have received much attention. In particular, predicting hotspots during the design stage is essential for high productivity in the semiconductor industry. In this study, we developed a deep learning-based SEM image generation model to predict hotspots from layout patterns at the design stage. Our model combines a segmentation network and an image-to-image translation network based on a conditional generative adversarial network in parallel. Our proposed model can predict and display potential hotspots in scanning electron microscopy images generated from given layouts. Additionally, the model leverages prior knowledge of the optical diameter to predict patterns that are prone to hotspots. Our model shows improved performance over baseline models when evaluated on real-world industrial data. [ABSTRACT FROM AUTHOR]

This paper addresses the quality control of the photolithography process in the semiconductor industry. Overlay errors in the process seriously affect the wafer yield, and cause the wafer to be forced to rework and affect the production efficiency of the equipment. We examine the current state of its process control, develop a novel overlay predict model, and verify the prediction results. This study proposes a Global Attention Generative Adversarial Networks (GAGAN) model to precisely predict the overlay error for the feed-forward data of the front layer, which is used as the important information and process parameters for the advanced process control of the current layer. Experiment results on a semiconductor shop-floor confirms that our proposed method achieves high predictive performance while maintaining extensibility and visual quality. [ABSTRACT FROM AUTHOR]

It has been a widely growing interest in using silicon carbide (SiC) in high-power electronic devices. Yet, SiC wafers may contain killer defects that could reduce fabrication yield and make the device fall into unexpected failures. To prevent these failures from happening, it is very important to develop inspection tools that can detect, characterize and locate these defects in a non-invasive way. Current inspection techniques such as Dark Field or Bright field microscopy are effectively able to visualize most such defects; however, there are some scenarios where the inspection becomes problematic or almost impossible, such as when the defects are too small or have low contrast or if the defects lie deep into the substrate. Thus, an alternative method is needed to face these challenges. In this paper, we demonstrate the application of coherent Fourier scatterometry (CFS) as a complementary tool in addition to the conventional techniques to overcome different and problematic scenarios of killer defects inspection on SiC samples. Scanning electron microscopy (SEM) has been used to assess the same defects to validate the findings of CFS. Great consistency has been demonstrated in the comparison between the results obtained with CFS and SEM. [ABSTRACT FROM AUTHOR]

Data and privacy laws, such as the GDPR, require mobile apps that collect and process the personal data of their citizens to have a legally-compliant policy. Since these mobile apps are hosted on app distribution platforms such as Google Play Store and App Store, the app publishers also require the app developers who wish to submit a new app or make changes to an existing app to be transparent about their app privacy practices regarding handling sensitive user data that requires sensitive permissions such as calendar, camera, microphone. To verify compliance with privacy regulators and app distribution platforms, the app privacy policies and permissions are investigated for consistency. However, little has been done to investigate GDPR completeness checking within the Android permission ecosystem. In this paper, we investigate the design and runtime approaches towards completeness checking of sensitive (‘dangerous’) Android permission policy declarations against GDPR. In this paper, we investigate the design and runtime approaches towards completeness checking of dangerous Android permission policy declarations against GDPR. Leveraging the MPP-270 annotated corpus that describes permission declarations in application privacy policies, six natural language processing and language modelling algorithms are developed to measure permission completeness during runtime while a proof of concept Class Unified Modeling Language Diagram (UML) tool is developed to generate GDPR-compliant permission policy declarations using UML diagrams during design time. This paper makes a significant contribution to the identification of appropriate permission policy declaration methodologies that a developer can use to target particular GDPR laws, increasing GDPR compliance by 12% in cases during runtime using BERT word embedding, measuring GDPR compliance in permission policy sentences, and a UML-driven tool to generate compliant permission declarations.

Link prediction in complex networks is a critical process aimed at uncovering hidden or potential connections among nodes. This technique is widely utilized in areas such as knowledge graphs. Current Graph Neural Networks (GNNs) often focus exclusively on determining whether nodes are connected or assessing the strength of these links by leveraging node attributes. They typically use network structure and attributes to develop node representations through neighborhood aggregation. However, these methods often overlook the intrinsic importance of the links themselves. This paper thoroughly examines the significance of link value based on network structure and introduces an innovative approach for estimating this value, and proposes a method that incorporates link value into both the formulation and training of a link prediction graph attention network. This integration not only boosts the accuracy of link predictions but also provides a theoretical basis for understanding the prediction results. We conducted extensive experiments in link prediction employing widely recognized benchmark datasets. The findings reveal that our proposed framework for link prediction exhibits commendable performance and generalization capabilities, and overall performance improved by an average of 1.2%, thereby establishing it as an effective baseline model.

The limited size of existing datasets and signal variability have hindered EEG-based emotion recognition. In this paper, we present a solution that simultaneously addresses both problems. Generative Adversarial Networks (GANs) have recently shown notable data augmentation (DA) success. Therefore, we leverage a GAN-based DA technique to enhance the robustness of our proposed emotion recognition model by synthetically increasing the size of our datasets. Moreover, we employ contrastive learning to improve the quality of the learned representations from EEG signals and mitigate the adverse impact of inter-subject and intra-subject variability in signals corresponding to the same stimuli or emotions. We do so by maximizing the similarity in the representation of such EEG signals. We perform EEG-based emotion classification using a Graph Neural Network (GNN), which learns the relationship between the extracted EEG features. We compare the proposed model with several recent state-of-the-art emotion recognition models on the DEAP and MAHNOB datasets. The experimental results demonstrate that the proposed model outperforms previous models with a 64.84% and 66.40% emotion classification accuracy on the test set of the DEAP dataset and a 66.98% and 71.69% emotion classification accuracy on the test set of the MAHNOB-HCI dataset for the valence and arousal emotional dimensions, respectively. We perform an ablation study to demonstrate how contrastive learning, GAN, and GNN contribute to improving the proposed solution’s performance.

Cognitive agents make systems autonomous through the process of decision automation by mining an existing knowledge repository at run time. These processes can often be highly compute intensive, and would thus run slowly on the low-power computing platforms typically seen in autonomous systems. This paper examines how knowledge be represented in a Q-table and proposes a novel fast algorithm to mine that knowledge based on constraints. We evaluate this approach for the knowledge mining process of a specific agent: Cognitively Enhanced Complex Event Processing (CECEP). Within CECEP, knowledge is represented using Cognitive Domain Ontologies (CDO), and is mined using situational inputs and constraints. This is a novel approach to store information and is able to accommodate CDOs with millions of solutions. To show that the approach can run on low power hardware in real-time, this algorithm was executed on two low-power minicomputing platforms - Intel’s NUC and Asus’s Tinker Board. At present, no other optimized CDO solvers can generate solutions on these platforms. The algorithm generated the same amount of solutions as a GPU-enabled optimized path-based forward checking CDO solver, while consuming around 7.7 and 5.15 times less energy (Joules) on the NUC and Tinker Board respectively.

The Partial Element Equivalent Circuit (PEEC) method has gained significant recognition as an electromagnetic computational technique known for its ability to represent electromagnetic phenomena using equivalent circuits. This feature makes it particularly valuable for addressing mixed EM-circuit problems. However, PEEC models often exhibit large dimensions, necessitating modeling techniques that can effectively reduce their size while preserving accuracy. Model order reduction (MOR) serves as a highly effective approach to accomplish this objective. This paper presents two MOR techniques based on proper orthogonal decomposition (POD) for PEEC models described by neutral delayed differential equations (NDDEs). The unique characteristics of NDDEs demand specialized MOR approaches, as their formulation is inherently more complex compared to standard quasi-static PEEC models described by non-delayed differential equations. In addition to a traditional one-shot singular value decomposition (SVD), this paper also presents an incrementally computed SVD to evaluate the orthogonal matrix needed to generate the reduced order matrices. The accuracy and efficiency of the proposed PEEC-MOR methods are demonstrated through multiple relevant numerical results in both the frequency-domain and time-domain.

With the development of cyber technology, the intelligence of power systems has increased, and cyber-physics is highly integrated and mutually constrained. In this paper, a globalized cyber-physical cooperative recovery strategy based on node importance is proposed for the failure of a cyber-physical power system under communication failure. First, the static importance of communication nodes and the importance of services are comprehensively analyzed based on the structural business transmission function characteristics of the network. Secondly, based on the fault characteristics of generators, power lines, and loads, the recovery model of the physical system is constructed by considering the safety constraints such as system frequency, node voltage, and line capacity. Finally, considering the possible delay caused by the cyber system failure to the generator output regulation, power line commissioning, and load recovery, the interaction model of physical system recovery and cyber system recovery is established and solved by using the solver after linearizing it. The results show that the cyber-physical recovery strategy can effectively reduce outage losses and improve recovery efficiency.

The goal of music genre classification is to identify the genre of given feature vectors representing certain characteristics of music clips. In addition, to improve the accuracy of music genre classification, considerable research has been conducted on extracting spectral features, which contain critical information for genre classification, from music clips and feeding these features into training models. In particular, recent studies argue that classification accuracy can be enhanced by employing multiple spectral features simultaneously. Consequently, fusing information from multiple spectral features is a critical consideration in designing music genre classification models. Hence, this paper provides a short survey of recent studies on music genre classification and compares the performance of the most recent CNN-based models with a newly devised model that employs a late fusion strategy for the multiple spectral features. Our empirical study of 12 public datasets, including Ballroom, ISMIR04, and GTZAN, showed that the late fusion CNN model outperforms other compared methods. Additionally, we performed an in-depth analysis to validate the effectiveness of the late fusion strategy in music genre classification.

Text-conditioned outfit recommendation aims to recommend a whole fashion outfit that satisfies the compatibility between the recommended items and given items and adheres to the text condition like “Paradise Tropical Vacation” or “60s Style”. Using text description as a condition can provide users with a flexible and accurate way to retrieve and recommend fashion items but this problem is underexplored by existing studies. A challenge of text-conditioned outfit recommendation is how to encode and fuse the outfit text description and fashion item images and text. To solve this, this paper proposes a framework for this task which features a hybrid attention layer that constructs the relationship between outfit text description and fashion items for condition compliance, and the relationship between fashion items for internal compatibility. To encode fashion item features, our method uses pre-trained FashionCLIP as an extractor which significantly reduces the trainable parameters compared to previous methods training CNN from scratch. The whole outfits are generated by iteratively adding compatible items based on a given partial outfit. Compared with state-of-the-art methods on polyvore disjoint and non-disjoint datasets, our approach can achieve 3% relative improvement in compatibility prediction AUC, achieve 5% relative improvement in fill-in-the-blank accuracy; achieve 19% relative improvement on complementary item retrieval recall at different ranks in average. Besides, We demonstrate that our approach can recommend a whole outfit with inner compatibility and adhere to the text description.

In a rapidly advancing world of technology, information security studies have become the backbone of the digital age, and steps in this area are critical. In this context, cryptography, in particular, plays a key role in ensuring the confidentiality, integrity and authentication of data. s-box structures provide a certain diversity and security layer in encryption algorithms, forming one of the key elements in this area. This study focuses on the design and analysis of s-box structures, examining the potential impact of chaos theory-based structures on encryption systems. First, it provides a comprehensive classification of existing s-box design proposals in the literature, and explores the contribution of chaos theory to the security features of these structures. The original contribution of the study is the results obtained with the help of the developed analysis and design program. The program optimizes levels of complexity, randomness, and resistance, and demonstrates the resistance of these new structures to cryptanalysis attacks. The paper also draws attention to open issues in the field of chaos-based s-box design and provides a road map for future research. It is estimated that all these findings will provide a common motivation for researchers in the relevant literature and constitute the basis for many practical practices.