Digital Commons Network^™

Ai-Powered Synthetic Biology: Current Situation, Challenges, And Future Perspectives, Izem Olcay Sahin, Nuriye Gokce, Duygu T. Yildirim, A. Baki Yildirim, Hilal Akalın, Donald Martin, Tommaso Beccari, Oscar Vicente, Iza Radecka, Fideline Tchuenbou-Magaia, Robert S. Marks, Ratnesh Lal, Satya Prakash, Adam Mechler, Mario Petrov Milkov, Svetlana Fotkova Georgieva, Ilia Iliev, Kosi Gramatikoff, Ed Judge, Milica Markovic, Radka Kaneva, Galina Aleksieva Yaneva, Nadya Vasileva Agova, Nikoleta Dobromirova Ivanova, Mariya Kiryakova Tsvetkova, Ivelin Rosenov Iliev, Michel Salzet, Kisung Ko, Michele Maffia, Chiara Coppola, Matteo Bertelli

Research Outputs: 2025-Present

Synthetic biology has evolved from a set of engineering aspirations to an operationally sophisticated discipline, and artificial intelligence (AI) is its fastest-growing accelerant. This review traces that convergence across six interlocking domains: systems-level biological modeling, de novo protein engineering, metabolic and microbial programming, multi-omics data integration, regulatory element design, and clinical translation. For each domain, we survey established results, integrate findings from 2010–2026 literature, and articulate the trajectories that will define the next decade. Emerging themes include physics-informed neural networks for mechanistically constrained biological modeling, drug design, and federated learning architectures that allow global omics collaboration without centralizing sensitive data, …

Confidenceai: A Wearable And Predictive Ai Ecosystem, Denzil Paul, Xuejun Kong, Raymond Wang, Flora Fleith Lopes, Zhengjia Yang, Brain Chu, Weijian Wang, Leo Chen

Paul English Applied Artificial Intelligence (AI) Institute Publications

This group project presents ConfidenceAI, a conceptual wearable and predictive artificial intelligence ecosystem designed to help teenagers build confidence and manage stress in high-pressure situations such as classroom participation and public speaking. The system combines wrist-based biosensing with a personalized machine-learning model that uses physiological signals, including heart rate and heart rate variability, electrodermal activity, skin temperature, and movement, to learn an individual's baseline patterns and anticipate heightened stress responses. Rather than relying on universal thresholds, ConfidenceAI is designed to personalize the timing, method, and delivery of interventions based on each user's physiological patterns and prior responses. The proposed ecosystem …

Geospatial Assessment Of Urban Expansion And Green Area Decline In Karbala Using Machine Learning: Supporting The Achievement Of Sdgs, Doaa Taha Yaseen, Oday Zakariya Jasim

Iraqi Journal of Architecture and Planning

Urban sprawl is a major challenge to sustainable development. This research examines geospatial patterns of urban growth and vegetation cover reduction in the Karbala District between 2017 and 2024. Sentinel-2 satellite imagery classification using a Support Vector Machine (SVM) model was evaluated, and accuracy was assessed using confusion matrices and a comparative evaluation against the Esri Sentinel Land Cover dataset. The SVM approach provided better classification precision. The change-detection analysis shows that the conversion of green and cultivated lands into built-up areas is significant. Although there has been an expansion of pivot-irrigated areas in other districts of the Karbala Governorate, …

Artificial Intelligence Based Predictive Simulation And Decision-Support Framework For Full Scale Wastewater Treatment Systems, Muhammad Hassnain, Cameron Veal, Sarada M.W. Lee, Muhammad Rizwan Azhar

Research outputs 2022 to 2026

Full scale wastewater treatment plants (WWTPs) generate extensive sensor and laboratory datasets that remain challenging to translate into real-time operational insight, while increasing hydraulic variability, energy constraints, tightening effluent regulations, and events such as sensor faults, hydraulic shocks, and effluent-quality excursions require predictive decision-support tools beyond conventional mechanistic modelling. This study presents a full-scale, industry-deployed artificial intelligence (AI) framework integrating machine learning (ML), simulation, and operational boundary definition across a nitrogen-removal WWTP in Australia. Up to nine years of high-frequency online instrumentation data (≤419,000 records per target; 5–30 min resolution) and ~3000 laboratory samples were used to train and evaluate …

Video Compression Optimization Techniques Using Artificial Intelligence: Review/Review Article, Amal Abbas Kadhim, Wedad Abdul Khuder Naser, Nada Abdulkareem Hameed

Al-Esraa University College Journal for Engineering Sciences

Compressing video is an important and essential function in today's multimedia systems as it enables the efficient storage and transmission of large volumes of video data. The proliferation of high-resolution videos that are being used in various application areas such as video streaming, video conferencing, surveillance, and autonomous systems has caused the strong demand for more efficient compression algorithms. This paper presents an in-depth review of video compression techniques with particular focus on AI methods. It also discusses traditional video coding standards including H. 264/AVC, H. 265/HEVC, and AV1, including motion estimation, transform coding quantization entropy coding, and rate-distortion optimization. …

Global Trends And Research Landscape Of Metformin And Artificial Intelligence: Bibliometric Analysis, Raya Doraid Mohammed, Alaa Qasim Hayder, Hamza A. Saadallah, Ali Q Saeed, Alice Louis Yousif, Safa M Salim, Noor Mahmood Sultan, Mohammed Ahb. Al-Krdoshi

Al-Esraa University College Journal for Medical Sciences

This bibliometric study examines global research trends and key thematic areas in Artificial Intelligence (AI) applications related to Metformin, especially in diabetes treatment. A total of 227 articles were retrieved from the Science Citation Index Expanded (Web of Science Core Collection) from 2020 to 2024. VOSviewer and CiteSpace were used to analyze publications by year, country, institution, journal, citation impact, and keyword co-occurrence. The United States, Canada, and South Korea contributed over 85% of the output, with leading institutions including the University of California, Los Angeles. Keyword mapping identified ``machine learning,'' ``Metformin,'' and ``Type 2 Diabetes'' as the most influential …

A Systematic Literature Review Of Fraud Research Prevalence, Mohammed Khojah, Nawaf Alzahrani, Saed Eidow, Jawad Alamri, Ibrahim Albassam, Muath Alghamdi, Aseel Atawi, Osama Bayunus, Osama Alhodaly, Osama Rabie

Journal of King Abdulaziz University: Computing and Information Technology Sciences

Background: Fraud is a pervasive worldwide problem that is evolving rapidly along with the technological advances and causing significant financial losses in a variety of industries. Traditional detection techniques often fall short in the face of more complex and digitalized fraud schemes. The pressing need for more intelligent detection systems is what motivated this review, which attempts to systematically assess the body of research on fraud detection and pinpoint dominant fraud sectors, types, and methods. Methods: This study employed a Systematic Literature Review (SLR) approach to comprehensively assess the current landscape of fraud detection research across multiple domains. …

The Pivotal Role Of Artificial Intelligence In Optimizing Pharmaceutical Formulation And Delivery, Ali Khidher Abbas, Mustafa M. Noori, Ibtihal Abdulkadhim Dakhil, Mohammed Hussain Al-Mayahy

Al-Esraa University College Journal for Medical Sciences

Artificial intelligence (AI) has emerged as a transformative technological paradigm within the pharmaceutical sciences, offering innovative and forward-looking solutions to surmount the inherent limitations associated with conventional drug development, formulation design, and therapeutic delivery systems. Traditional pharmaceutical methodologies frequently entail protracted development timelines, extensive experimental procedures, and substantial financial expenditures, particularly within the domains of formulation optimization and drug delivery design. The integration of AI-driven technologies – encompassing machine learning (ML), deep learning (DL), artificial neural networks (ANNs), and predictive analytics – has considerably accelerated pharmaceutical research by refining decision-making processes, alleviating experimental burden, and enhancing formulation efficiency. The present …

Research On Mechanical Properties Of Concrete At High Temperatures Based On Machine Learning, Liu Junhua, Liu Bin, Cao Haifeng, Liu Zhiguang, Li Zhiyong

Journal of China & Foreign Highway

Structural safety is directly affected by the mechanical properties of concrete at high temperatures. Firstly, based on the existing compression and tension test data of concrete at high temperatures, the Abaqus finite element software was adopted for numerical simulation reproduction, and the reliability of the simulation method was verified. Secondly, by simulating the uniaxial tension-compression and confining pressure tests of normal concrete with different strength grades under high temperatures of 20‒800 ℃, the influence rules of temperature on the compressive strength, splitting tensile strength, elastic modulus, and stress ‒ strain relationship of concrete were elucidated. Finally, based on three commonly …

Review And Development Of An Explicit Machine Learning Model For Pollutant Gas Solubility In Ionic Liquids As Green Solvents, Amir Dashti, Farid Amirkhani, Mojtaba Raji, John L. Zhou, Ali Altaee, Ali Braytee, Brett Turner, Hossein Ali Khonakdar, Amir Razmjou

Research outputs 2022 to 2026

The increasing release of greenhouse gases (GHGs) like CO₂, CH₄, N₂O, and industrial contaminants (indirect GHGs) such as SO₂ and H₂S has prompted significant global worries due to their role in climate change, air pollution, and harm to the environment. Ionic liquids (ILs) as green solvents have emerged as promising alternatives to traditional solvents because of their minimal volatility, high thermal stability, and adjustable physicochemical characteristics. Yet, limited gas solubility data in ILs is hindering their applications in carbon capture and air pollution control. Machine learning (ML) is a powerful tool for modeling and simulating the solubility of polluting gases …

Application Of Ai Risk Prediction Tools For Cardiovascular Care In Hong Kong: A Systematic Review With Insights From Clinicians, Celine Sze Ling Chui, Celia Jiaxi Lin, Ruibang Luo, Yekai Zhou, Nadeem Qureshi, Li Wah Tam, Carmen Chan, Ian Chi Kei Wong, Kai Hang Yiu, P-Cardiac Consortium

Journal of the Hong Kong College of Cardiology

Background: Cardiovascular diseases (CVD) present a substantial burden on global and local healthcare systems, particularly within Hong Kong's overstretched public secondary care settings coupled with an aging population. The Personalized CARdiovascular DIsease risk Assessment for Chinese (P-CARDIAC), a locally developed and validated artificial intelligence (AI) powered cardiovascular risk assessment tool, offers a transformative opportunity for enhancing care through systematic risk prediction and a multidisciplinary care approach. Implementation strategies for its application in secondary care remain undefined. Methods: We gathered local insights from one expert meeting and thirteen semi-structured interviews with cardiologists and pharmacists, matched these with barriers and respective facilitators …

Predicting Thoroughbred Yearling Auction Prices With Machine Learning: Evidence From The Keeneland September Sale, Yanchao Yang, John Clarke, Tapaan Madal '26, Thinh Nguyen '26, Trung Pham '25

Business Analytics Faculty Publications

We apply machine learning methods to predict Thoroughbred yearling auction prices at the Keeneland September Sale (2020–2024). Our sample includes 5,788 yearling prices with pedigree data. We use both linear and tree-based models to predict log prices. We use cross-validation to tune model hyperparameters and select Ridge regression (α = 1.451) as the primary model for interpretation given its stability and interpretability. The Ridge regression explains approximately 54% of out-of-sample variation (R2≈ 0.5403). Sire and Dam Reputation emerge as the dominant predictors. Results provide pricing benchmarks and show how reputation and session structure shape Thoroughbred yearling auction prices.

Advances In Research On Methods For Intelligent Identification Of Seismic Facies, Liu Xingye, Yu Peilin, He Hengjun

Coal Geology & Exploration

Background The intelligent identification of seismic facies can significantly improve the efficiency of sedimentary system characterization and hydrocarbon reservoir interpretation. However, influenced by factors such as non-stationary geological bodies, high costs of sample labeling, and limited training samples, conventional methods for intelligent identification are generally insufficient to achieve high identification accuracy and widespread application concurrently. Advances This study presents a systematic review of three types of technologies for the intelligent identification of seismic facies, namely unsupervised, supervised, and semi-supervised learning, with each type including deep learning methods. The three technological types are comparatively verified using 3D seismic data from a …

Algorithmic Monocultures In Hiring, Rishi Bommasani, Sarah H. Bana, Kathleen A. Creel, Dan Saul Jurafsky, Percy Liang

Economics Faculty Articles and Research

Many employers screen job applicants with algorithms built by the same few algorithm vendors. We hypothesize that algorithmic monoculture leads to the same individuals and members of the same racial groups facing rejection. We acquire and analyze a novel dataset of 3 million applicants submitting 4 million applications where all the applications are screened by algorithms built by the same vendor. We find clear racial disparities in applicant outcomes. Of all applications submitted by Asian and Black applicants, 14.74% and 25.87% are submitted to positions that adversely impact Asian and Black applicants, respectively, according to U.S. employment discrimination standards. Individuals …

An Ensemble Learning-Based Approach To Quantify Post-Earthquake Functional Recovery Of A Steel Moment-Resisting Frame Inventory, Mohsen Zaker Esteghamati, Shiva Baddipalli

Civil and Environmental Engineering Faculty Publications

The quest for seismic resiliency requires designing for performance objectives beyond life safety. Functional recovery is an emerging objective often defined as the time required to restore a building’s basic functionality to the pre-event level. Nevertheless, quantifying functional recovery is a complex, computationally intensive process that is challenging to integrate into a standard design workflow. This study develops a machine learning (ML) model to map design and geometric features of steel special moment-resisting frames (SMRFs) to their functional recovery under two hazard levels: design-basis (DBE) and maximum considered (MCE) earthquakes. First, functional recovery time was quantified for an inventory of …

Artificial Intelligence For Predictive Maintenance In Renewable Energy Assets: Wind Turbines, Solar Farms, And Energy Storage Systems, Bassam Rafea Hani, Ayman Abdulmajeed Radhi

Al-Farahidi Expert Systems Journal

The integration of Artificial Intelligence (AI) into predictive maintenance for renewable energy assets represents a significant advancement in modern energy management. This study reviews and analyzes AI applications in predictive maintenance across wind turbines, solar farms, and energy storage systems. It emphasizes the role of machine learning and deep learning algorithms in predicting failures before they occur, enhancing operational efficiency, and reducing maintenance costs. The paper also discusses challenges related to data quality, scalability, and system integration within renewable energy environments. Findings indicate that AI-based predictive maintenance significantly improves equipment reliability and system performance, paving the way toward smarter, more …

Machine Learning Based Approaches To Survey Elderly Adults About The Perception Of The Coronavirus Crisis, Ouban Wannous

Al-Farahidi Expert Systems Journal

The rapid digital transformation of society in recent years has resulted in the creation of vast databases available online, particularly benefiting businesses. The main challenge now is to effectively access and utilize this data to make informed business decisions. Artificial intelligence techniques, such as natural language processing and machine learning, have proven highly effective across various domains and present valuable opportunities for developing automated models to extract insights and uncover new information. This paper demonstrates the effectiveness of machine learning techniques in the field of social and economic sciences, focusing specifically on the task of classifying open-ended survey questions. We …

Integration Of Intraoperative Data In Interpretable Machine Learning Models To Predict Postoperative Aki In Noncardiac Surgery Patients, Justin Do, Karan H. Shah, Melissa Xu, Andrew Hyunwoo Kim, Vivaswat Suresh, Nidhir Guggilla, Michael Li, Rishi Kothari

Department of Anesthesiology Faculty Papers

OBJECTIVES: We aimed to (1) quantify changes in discrimination when adding intraoperative data to preoperative data and (2) compare tabular machine learning with feature engineering against a time-aware LSTM-based model.

MATERIALS AND METHODS: Retrospective cohort of 46 204 adults undergoing 57 055 eligible noncardiac surgery in the INSPIRE database. We extracted 38 preoperative and 49 intraoperative variables; acute kidney injury (AKI) was defined by KDIGO serum creatinine criteria and modeled as stage 2/3 postoperative AKI. Models were trained on preoperative-only and combined pre- and intraoperative data. Intraoperative series were summarized using eight statistical features for tabular models or integrated directly …

Data-Driven Electrochemistry Reveals The Impact Of Hydrophobicity On Aptamer Cross-Reactivity, Emily Carroll, Michael A. Pence, Elizabeth Winterholler, Taylor D. Sparks, Shelley D. Minteer

Chemistry Faculty Research & Creative Works

Electrochemical aptamer-based (E-AB) biosensors offer a promising platform for reagentless detection of molecular targets, yet aptamer recognition can be limited by cross-reactivity, particularly for hydrophobic analytes such as steroid hormones. To investigate how cross-reactivity influences E-AB sensor performance, we use automation and machine learning to screen a library of possible interferent molecules against a steroid-binding aptamer, with progesterone serving as a physiologically relevant test case. Here, we develop a label-free E-AB sensor for progesterone detection using a methylene blue-modified aptamer anchored with a hexanethiol linker. We then used an automated electrochemistry platform to perform reproducible and high-throughput characterization of our …

Detection Of Early Browning Inside Fragrant Pears Based On Time-Frequency Images Of Acoustic And Vibration Signals, Zhang Feng, Yu Junyang, Xiao Ping, Zhang Hui, Wang Kai

Food and Machinery

［Objective］ To explore the detection efficacy of models constructed by combining time-frequency image features of the fragrant pears in acoustic and vibration with machine learning algorithms.［Methods］ Acoustic and vibration signals are collected from fragrant pears exhibiting varying degrees of internal browning using a custom-built non-destructive detection device. Time-frequency images are transformed using the short-time Fourier transform (STFT),continuous wavelet transform (CWT), and the S-transform. Then, texture feature parameters in 15 time-frequency domains are extracted, respectively, from 3 types of time-frequency images using the Gray-Gradient Co-occurrence Matrix (GGCM). Additionally, correlation analysis is performed between these feature parameters and the fragrant pear browning …

Comparative Analysis Of Random Forest And Artificial Neural Networks For Predicting In-Situ Soil Density, Eng. Jinan Ali Abd Al-Kareem Al-Maliki, Dr Ammar Salman Dawood, Dr. Ihsan Al-Abboodi

HBRC Journal

This study suggests that RF and ANN are proven to be robust algorithms in predicting in-situ soil density, which is considered a significant geotechnical parameter. The research is based on 86 soil samples and focuses on five main input parameters: Gravel Percentage (G%), Plastic Limit (PL%), Sand Percentage (S%), Fines Percentage (F%), and Liquid Limit (LL%). The models developed here utilize five commonly recorded index properties (G%, S%, F%, LL, and PL) for all field samples taken from the Basra-Faw Road project. The influence of moisture content and compressive energy was ignored, as all field samples acquired the same moisture …

Energy Efficient Load Balancing In Multi-Band Cellular Networks Via Reinforcement Learning, Ahmed Shoukry El Soukkary

Theses and Dissertations

This thesis investigates energy-efficient load balancing in homogeneous multi-band cellular networks through the joint design of user association (UA) and transmit power allocation (PA). The original mixed-integer nonlinear formulation is decomposed into two coupled yet tractable subproblems: a UA stage and a PA stage for high-frequency bands. For UA, a SINR-ratio-based heuristic is proposed to prioritize users that are most sensitive to suboptimal band assignments, and it is benchmarked against a Max- SINR baseline. For PA, the high-band power control problem is addressed using reinforcement learning, where a Proximal Policy Optimization (PPO) agent learns power levels and band-activation decisions under …

Discovery Of Bmi-Associated Gut Microbiome Signatures In The Awi-Gen 2 Cohort, Meriem Yagoubi

Theses and Dissertations

Obesity is increasing across sub-Saharan Africa amid rapid dietary, environmental, and urbanization transitions, yet the gut microbiome features associated with adiposity in African populations remain under-characterized. This study investigated whether species-level gut microbiome composition is associated with body mass index (BMI) in the AWI-Gen 2 cohort, and whether BMI-associated microbial signals remain detectable after accounting for the dominant geographic structure of the microbiome. Gut microbiome community structure and diversity were characterized across 1,665 participants, and differential abundance analysis was used to identify taxa associated with BMI after controlling for study site. Machine learning models were then trained to assess how …

Performance Comparison Of Machine Learning Across Metal, Cuda, And Software-Based Neuromorphic Simulation, Ryan Saini, William B. Andreopoulos

Faculty Research, Scholarly, and Creative Activity

Machine learning’s computational demands necessitate optimal performance and utilization across diverse hardware architectures. This research compares computing as spiking neural networks (CSNNs, or simulated neuromorphic computing) and regular CNNs on Apple Silicon M3 Pro with Metal Performance Shaders (MPS), and NVIDIA RTX 3070 GPU with CUDA. We run Convolutional Spiking Neural Networks (CSNNs) and traditional CNNs on two datasets (frame-based CIFAR-10; and sequential event-based DVS) to evaluate the suitability of neural net architectures and platforms for different data problems. For both CSNNs and traditional CNNs, Apple Silicon with MPS delivers better energy efficiency but longer processing times for training and …

A Systematic Review Of Intrusion Detection Systems For Internet Of Medical Things: Performance, Efficiency, Explainability, And Generalization, Oswald Adohinzin, Youssef Harrath

Research & Publications

The Internet of Medical Things (IoMT) has transformed health care delivery through medical devices, remote patient monitoring, and real-time clinical decision support. However, the proliferation of IoMT devices introduces security vulnerabilities that put patient safety and data privacy at risk. Intrusion Detection Systems (IDS) have emerged as essential components for protecting IoMT networks from cyberattacks. This article presents a systematic review of IoMT-IDS research, analyzing 53 high-quality papers published between 2020 and 2025, identified through database searches spanning 2016–2025 across IEEE Xplore, Springer, ScienceDirect, and ACM Digital Library. We organize the literature through a comprehensive taxonomy spanning classical machine learning …

What Makes A Modern Attention Implementation?, Brian H. Slonim

Master's Theses

Since the seminal assertion by Vaswani et al. in 2017 that “Attention Is All You Need,” transformer models have risen to ubiquity due to their ability to learn extremely complex patterns from sequence data, culminating in the unprecedented generative capabilities of large language models. These models’ strength lies in their scale: hundreds of millions (e.g., BERT-LARGE) to billions or trillions of learned parameters. Running inference with these models, let alone training them, would be intractable without significant innovations in the hardware and software that support them. This need has driven an enormous demand for GPU compute and associated software ecosystems, …

Object Detection And Classification For Man-Made Structures To Aid In Search And Rescue (Sar), Mio A. Nakagawa

Master's Theses

This project explores the use of various object detection and classification models to identify permanent man-made structures, specifically cell towers, water towers, watch towers as well as its corresponding shadows (attributes), from aerial imagery. The goal is to evaluate those models and test the feasibility of current models to detect man-made structures in aerial images, in an effort to support search and rescue operations as well as update network infrastructure databases. Multiple object detection models, as well as classification models, including YOLOv8 and VGG19 are implemented and trained on annotated aerial images to determine the presence or absence of man-made …

Development Of A Video-Based Tool To Measure Motor Asymmetry In Infants At Risk For Hemiparesis, Roha Ali

Master's Theses

Congenital hemiparesis is a unilateral motor impairment stemming from brain injury in utero or early postnatally. Hemiparesis can be difficult to detect in early infancy with current clinical tools. Yet, early identification of motor asymmetry could play a key role in the design of effective early intervention and rehabilitation strategies. This thesis presents the development and validation of a video-based tool designed to extract infant limb movement data using DeepLabCut’s (DLC) machine learning network. The pipeline was developed using videos of typically developing (TD) infants and infants with Asymmetric Perinatal Brain Injury (APBI), all at or under 3 months corrected …

Multimodal Machine Learning For Soil Burn Severity Mapping Across California Wildfires, Sanjana Checker

Master's Theses

Accurate mapping of soil burn severity (SBS) is critical for post-fire watershed management, erosion risk assessment, and ecological recovery planning, yet traditional field-based approaches remain costly, time-intensive, and spatially limited. This thesis presents a machine learning pipeline for wall-to-wall SBS classification across California wildfires using multi-sensor satellite imagery, terrain derivatives, and bioclimatic covariates. Field-collected SBS observations (n = 2,180) from 52 wildfires occur- ring between 2013 and 2025, sourced from the U.S. Forest Service and CAL FIRE, were used to train and evaluate multiple classification architectures within a Google Earth Engine and Google Cloud-based prediction framework. After upsampling the unburned …

Reproducing And Evaluating Charger Surfing: Robustness Of Smartphone Charging-Line Side-Channels, Colby M. Watts

Master's Theses

Smartphones are frequently connected to external, untrusted charging hardware, creating opportunities for side-channel attacks that do not require malware or direct access to device data. Charger Surfing, a recently proposed charging-line power analysis side-channel attack, reported high accuracy in inferring touchscreen input from voltage measurements collected from a smartphone’s charging cable; however, the reproducibility and robustness of these results under different conditions remain unclear. This thesis presents an independent replication and evaluation of Charger Surfing, including the development of an end-to-end data collection pipeline consisting of a modified charging cable, oscilloscope-based recordings, custom Android app, automated trace processing, and convolutional …