James E. Smith
YOU?
Author Swipe
View article: Fellowship Training After General Surgery Residency: Does it Pay?
Fellowship Training After General Surgery Residency: Does it Pay? Open
This analysis highlights the significant impact that fellowship training has on career earnings and underscores the opportunity cost of research years. These data offer a transparent financial analysis to help guide surgical residents in c…
View article: Evaluating a Decision-Making Architecture in Human-Robot Collaboration Experiments
Evaluating a Decision-Making Architecture in Human-Robot Collaboration Experiments Open
View article: A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack
A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack Open
Machine learning models can inadvertently expose confidential properties of their training data, making them vulnerable to membership inference attacks (MIA). While numerous evaluation methods exist, many require computationally expensive …
View article: A Multi-Language Toolkit for the Semi-Automated Checking of Research Outputs
A Multi-Language Toolkit for the Semi-Automated Checking of Research Outputs Open
View article: Edge Computing and Cloud Integration in SOA-Based Software-Defined Vehicles
Edge Computing and Cloud Integration in SOA-Based Software-Defined Vehicles Open
View article: Trends and Challenges in Data Analytics and Machine Learning Using Call Detail Records in Telecom Systems
Trends and Challenges in Data Analytics and Machine Learning Using Call Detail Records in Telecom Systems Open
As telecommunication networks continue to grow, the volume, variety, and velocity of such `big data' poses an immense challenge for security and service analysts. A primary data format in such networks are Call Detail Records (CDRs), and m…
View article: Analyst-Driven XAI for Time Series Forecasting: Analytics for Telecoms Maintenance
Analyst-Driven XAI for Time Series Forecasting: Analytics for Telecoms Maintenance Open
View article: Implementing Online Reinforcement Learning with Clustering Neural Networks
Implementing Online Reinforcement Learning with Clustering Neural Networks Open
An agent employing reinforcement learning takes inputs (state variables) from an environment and performs actions that affect the environment in order to achieve some objective. Rewards (positive or negative) guide the agent toward improve…
View article: Machine learning models in trusted research environments -- understanding operational risks
Machine learning models in trusted research environments -- understanding operational risks Open
IntroductionTrusted research environments (TREs) provide secure access to very sensitive data for research. All TREs operate manual checks on outputs to ensure there is no residual disclosure risk. Machine learning (ML) models require very…
View article: Neuromorphic Online Clustering and Classification
Neuromorphic Online Clustering and Classification Open
The bottom two layers of a neuromorphic architecture are designed and shown to be capable of online clustering and supervised classification. An active spiking dendrite model is used, and a single dendritic segment performs essentially the…
View article: In-situ gloveport glove leak tester
In-situ gloveport glove leak tester Open
The invention provides a system for detecting leaks in glovebox gloves, the system having a first seal within a glovebox aperture; a second seal contacting exterior surfaces of a glovebox, wherein the exterior surfaces define a periphery o…
View article: Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities
Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities Open
View article: A Novel Mirror Neuron Inspired Decision-Making Architecture for Human–Robot Interaction
A Novel Mirror Neuron Inspired Decision-Making Architecture for Human–Robot Interaction Open
Inspired by the role of mirror neurons and the importance of predictions in joint action, a novel decision-making structure is proposed, designed and tested for both individual and dyadic action. The structure comprises models representing…
View article: CITIZEN SCIENCE AND SOUNDSCAPE PERCEPTION DURING COVID RESTRICTION IN THE UK
CITIZEN SCIENCE AND SOUNDSCAPE PERCEPTION DURING COVID RESTRICTION IN THE UK Open
View article: A Decision-Making Architecture for Human-Robot Collaboration: Model Transferability
A Decision-Making Architecture for Human-Robot Collaboration: Model Transferability Open
In this paper, we aim to demonstrate the potential for wider-ranging capabilities and ease of transferability of our recently developed decision-making architecture for human-robot collaboration. To this end, a somewhat related but differe…
View article: A multi-language toolkit for the semi-automated checking of research outputs
A multi-language toolkit for the semi-automated checking of research outputs Open
This article presents a free and open source toolkit that supports the semi-automated checking of research outputs (SACRO) for privacy disclosure within secure data environments. SACRO is a framework that applies best-practice principles-b…
View article: Safe machine learning model release from Trusted Research Environments: The SACRO-ML package
Safe machine learning model release from Trusted Research Environments: The SACRO-ML package Open
We present SACRO-ML, an integrated suite of open source Python tools to facilitate the statistical disclosure control (SDC) of machine learning (ML) models trained on confidential data prior to public release. SACRO-ML combines (i) a SafeM…
View article: GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs) Open
TREs are widely, and increasingly used to support statistical analysis of sensitive data across a range of sectors (e.g., health, police, tax and education) as they enable secure and transparent research whilst protecting data confidential…
View article: Generation of FOUR iPSC lines (CRICKi004-A; CRICKi005-A; CRICKi006-A, CRICKi007-A) from Spinal muscle atrophy patients with lower extremity dominant (SMALED) phenotype
Generation of FOUR iPSC lines (CRICKi004-A; CRICKi005-A; CRICKi006-A, CRICKi007-A) from Spinal muscle atrophy patients with lower extremity dominant (SMALED) phenotype Open
View article: GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
GRAIMATTER Public Summary: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs) Open
GRAIMATTER has developed a draft set of usable recommendations for TREs to guard against the additional risks when disclosing trained AI models from TREs. This report provides a summary of our recommendations for a general public audience.…
View article: GRAIMatter: Guidelines and Resources for AI Model Access from TrusTEd Research environments (GRAIMatter).
GRAIMatter: Guidelines and Resources for AI Model Access from TrusTEd Research environments (GRAIMatter). Open
ObjectivesTo assess a range of tools and methods to support Trusted Research Environments (TREs) to assess output from AI methods for potentially identifiable information, investigate the legal and ethical implications and controls, and pr…
View article: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs) Open
<p><strong>Consultation:</strong></p>\n\n<p>This is a working version of the GRAIMATTER recommendations for disclosure control of machine learning models from trusted research environments. The document has al…
View article: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs) Open
<p><strong>Consultation:</strong></p>\n\n<p>This is a working version of the GRAIMATTTER recommendations for disclosure control of machine learning models from trusted research environments. The document has a…
View article: Preliminary Material
Preliminary Material Open
View article: A Macrocolumn Architecture Implemented with Spiking Neurons
A Macrocolumn Architecture Implemented with Spiking Neurons Open
The macrocolumn is a key component of a neuromorphic computing system that interacts with an external environment under control of an agent. Environments are learned and stored in the macrocolumn as labeled directed graphs where edges conn…
View article: Implementing Online Reinforcement Learning with Temporal Neural Networks
Implementing Online Reinforcement Learning with Temporal Neural Networks Open
A Temporal Neural Network (TNN) architecture for implementing efficient online reinforcement learning is proposed and studied via simulation. The proposed T-learning system is composed of a frontend TNN that implements online unsupervised …
View article: Temporal Computer Organization
Temporal Computer Organization Open
This document is focused on computing systems implemented in technologies that communicate and compute with temporal transients. Although described in general terms, implementations of spiking neural networks are of primary interest. As ba…
View article: Inter-annotator Agreement Using the Conversation Analysis Modelling Schema, for Dialogue
Inter-annotator Agreement Using the Conversation Analysis Modelling Schema, for Dialogue Open
We present the Conversation Analysis Modeling Schema (CAMS), a novel dialogue labeling schema that combines the Conversation Analysis concept of Adjacency Pairs, with Dialogue Acts. The aim is to capture both the semantic and syntactic str…
View article: Machine Learning Models Disclosure from Trusted Research Environments (TRE), Challenges and Opportunities
Machine Learning Models Disclosure from Trusted Research Environments (TRE), Challenges and Opportunities Open
Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research environments (TREs) provide safe and secure environments in which researchers can acce…
View article: Machine Learning Models Disclosure from Trusted Research Environments\n (TRE), Challenges and Opportunities
Machine Learning Models Disclosure from Trusted Research Environments\n (TRE), Challenges and Opportunities Open
Artificial intelligence (AI) applications in healthcare and medicine have\nincreased in recent years. To enable access to personal data, Trusted Research\nenvironments (TREs) provide safe and secure environments in which researchers\ncan a…