Stand-alone Platform Research Articles

Deployment and validation of the CLL treatment infection model adjoined to an EHR system

Research algorithms are seldom externally validated or integrated into clinical practice, leaving unknown challenges in deployment. In such efforts, one needs to address challenges related to data harmonization, the performance of an algorithm in unforeseen missingness, automation and monitoring of predictions, and legal frameworks. We here describe the deployment of a high-dimensional data-driven decision support model into an EHR and derive practical guidelines informed by this deployment that includes the necessary processes, stakeholders and design requirements for a successful deployment. For this, we describe our deployment of the chronic lymphocytic leukemia (CLL) treatment infection model (CLL-TIM) as a stand-alone platform adjoined to an EPIC-based Danish Electronic Health Record (EHR), with the presentation of personalized predictions in a clinical context. CLL-TIM is an 84-variable data-driven prognostic model utilizing 7-year medical patient records and predicts the 2-year risk composite outcome of infection and/or treatment post-CLL diagnosis. As an independent validation cohort for this deployment, we used a retrospective population-based cohort of patients diagnosed with CLL from 2018 onwards (n = 1480). Unexpectedly high levels of missingness for key CLL-TIM variables were exhibited upon deployment. High dimensionality, with the handling of missingness, and predictive confidence were critical design elements that enabled trustworthy predictions and thus serves as a priority for prognostic models seeking deployment in new EHRs. Our setup for deployment, including automation and monitoring into EHR that meets Medical Device Regulations, may be used as step-by-step guidelines for others aiming at designing and deploying research algorithms into clinical practice.

Enhancing Online Accessibility of Digitized Artifacts from Small Museum Collections in Cyprus: An Empirical Evaluation of the CyprusArk Solution

Small museums play a pivotal role in the Cyprus cultural landscape by carefully safeguarding and curating historical artifacts, thereby showcasing the country's rich heritage. However, in order to enhance accessibility to a wider audience, it is crucial to make these objects available online. This research aims to explore the effectiveness of the CyprusArk solution (a high-fidelity prototype) in enhancing the online presence of digitized artifacts within Cypriot small museums. By collecting and analyzing qualitative data from six out of ten classified as small museums, the study aims to demonstrate the potential of such solutions, specifically designed for small museums in Cyprus. CyprusArk is a Content Management System, serving as a stand-alone platform for each museum. Instances of the solution will be hosted, supported, and maintained at a Cyprus national infrastructure in a high-performance computer facility (HPC), at The Cyprus Institute (CyI). The study has broader implications for the global museum sector, as it showcases the potential of new digital tools to enhance online access to cultural heritage resources and contribute to the dissemination of information “knowledge” among the broader population.

Direct Laser Processing and Functionalizing PI/PDMS Composites for an On-Demand, Programmable, Recyclable Device Platform.

Skin-interfaced high-sensitive biosensing systems to detect electrophysiological and biochemical signals have shown great potential in personal health monitoring and disease management. However, the integration of 3D porous nanostructures for improved sensitivity and various functional composites for signal transduction/processing/transmission often relies on different materials and complex fabrication processes, leading to weak interfaces prone to failure upon fatigue or mechanical deformations. The integrated system also needs additional adhesive to strongly conform to the human skin, which can also cause irritation, alignment issues, and motion artifacts. This work introduces a skin-attachable, reprogrammable, multifunctional, adhesive device patch fabricated by simple and low-cost laser scribing of an adhesive composite with polyimide powders and amine-based ethoxylated polyethylenimine dispersed in the silicone elastomer. The obtained laser-induced graphene in the adhesive composite can be further selectively functionalized with conductive nanomaterials or enzymes for enhanced electrical conductivity or selective sensing of various sweat biomarkers. The possible combination of the sensors for real-time biofluid analysis and electrophysiological signal monitoring with RF energy harvesting and communication promises a standalone stretchable adhesive device platform based on the same material system and fabrication process.

Performance Evaluation of an Open Source Implementation of a 5G Standalone Platform

Performance Evaluation of an Open Source Implementation of a 5G Standalone Platform

A fully integrated, standalone stretchable device platform with in-sensor adaptive machine learning for rehabilitation

Post-surgical treatments of the human throat often require continuous monitoring of diverse vital and muscle activities. However, wireless, continuous monitoring and analysis of these activities directly from the throat skin have not been developed. Here, we report the design and validation of a fully integrated standalone stretchable device platform that provides wireless measurements and machine learning-based analysis of diverse vibrations and muscle electrical activities from the throat. We demonstrate that the modified composite hydrogel with low contact impedance and reduced adhesion provides high-quality long-term monitoring of local muscle electrical signals. We show that the integrated triaxial broad-band accelerometer also measures large body movements and subtle physiological activities/vibrations. We find that the combined data processed by a 2D-like sequential feature extractor with fully connected neurons facilitates the classification of various motion/speech features at a high accuracy of over 90%, which adapts to the data with noise from motion artifacts or the data from new human subjects. The resulting standalone stretchable device with wireless monitoring and machine learning-based processing capabilities paves the way to design and apply wearable skin-interfaced systems for the remote monitoring and treatment evaluation of various diseases.

Electroanalytical paper-based device for reliable detection and quantification of sugars in milk

Knowing the level of sugars in food and beverages is essential because they are related to diseases such as diabetes, and obesity, among others. In this regard, an approach has been designed, characterized, and applied to develop the first all-in-one paper-based microfluidic analytical device for the quantification of sugars in milk samples. In particular, the powerful combination of the paper-based platform, the facile manufacturing, and the on-demand customization, allowed to obtain a stand-alone platform that was capable to store all the reagents necessary for the assay, to treating the sample by removing major interferences due to lipids and proteins, and to visualize the results in minutes. A wax-patterned chromatographic paper was finely designed to provide a reagent-free platform for the use of non-specialists applied towards the analysis of sugars' content (lactose as the main sugar). Sugars were electrochemically quantified down to 0.16 g L−1 with a repeatability of 5%. To strengthen the efficacy of the novel platform, the electrochemical paper-based analytical device has been applied to commercial milk, including skimmed, semi-skimmed, whole, and lactose-free, confirming satisfactory performance with analytical reliability. This paper-based architecture opens novel avenues for portable (bio)sensing of other relevant species, not only in the agri-food field.

PIRET-A Platform for Treatment Planning in Electroporation-Based Therapies.

We developed PIRET, a platform to predict the treatment volume in electroporation-based therapies. The platform seamlessly integrates tools to build patient-specific models where the electric field is simulated to predict the treatment volume. Patient anatomy is segmented from medical images and 3D reconstruction aids in placing the electrodes and setting up treatment parameters. Four canine patients that had been treated with high-frequency irreversible electroporation were retrospectively planned with PIRET and with a workflow commonly used in previous studies, which uses different general-purpose segmentation (3D Slicer) and modeling software (3Matic and COMSOL Multiphysics). PIRET outperformed the other workflow by 65 minutes (× 1.7 faster), thanks to the improved user experience during treatment setup and model building. Both approaches computed similarly accurate electric field distributions, with average Dice scores higher than 0.93. A platform which integrates all the required tools for electroporation treatment planning is presented. Treatment plan can be performed rapidly with minimal user interaction in a stand-alone platform. This platform is, to the best of our knowledge, the most complete software for treatment planning of irreversible electroporation. It can potentially be used for other electroporation applications.

Revolutionizing IC Genset Operations with IIoT and AI: A Study on Fuel Savings and Predictive Maintenance

In a world increasingly aware of its carbon footprint, the quest for sustainable energy production and consumption has never been more urgent. A key player in this monumental endeavor is fuel conservation, which helps curb greenhouse gas emissions and preserve our planet’s finite resources. In the realm of the Industrial Internet of Things (IIoT) and artificial intelligence (AI) technologies, Caterpillar (CAT) generator set (genset) operations have been revolutionized, unlocking unprecedented fuel savings and reducing environmental harm. Envision a system that not only enhances fuel efficiency but also anticipates maintenance needs with state-of-the-art technology. This standalone IIoT platform crafted with Visual Basic.Net (VB.Net) and the KEPware Object linking and embedding for Process Control (OPC) server gathers, stores, and analyzes data from CAT gensets, painting a comprehensive picture of their inner workings. By leveraging the Modbus Remote Terminal Unit (RTU) protocol, the platform acquires vital parameters such as engine load, temperature, pressure, revolutions per minute (RPM), and fuel consumption measurements, from a radar transmitter. However, the magic does not stop there. Machine Learning.Net (ML.Net) empowers the platform with machine learning capabilities, scrutinizing the generator’s performance over time, identifying patterns and forecasting future behavior. Equipped with these insights, the platform fine tunes its operations, elevates fuel efficiency, and conducts predictive maintenance, minimizing downtime and amplifying overall efficiency. The evidence is compelling: IIoT and AI technologies have the power to yield substantial fuel savings and enhance performance through predictive maintenance. This research offers a tangible solution for industries eager to optimize operations and elevate efficiency by embracing IIoT and AI technologies in CAT genset operations. The future is greener and smarter, and it starts now.

HPTLC-based fingerprinting: An alternative approach for fructooligosaccharides metabolism profiling

Fructans are categorized as fructose-based metabolites with no more than one glucose in their structure. Agave species possess a mixture of linear and ramified fructans with different degrees of polymerization. Among them, fructooligosaccharides are fructans with low degree of polymerization which might be approachable by high performance thin layer chromatography (HPTLC). Thus, this study used two emblematic Agave species collected at different ages as models to explore the feasibility of HPTLC-based fingerprinting to characterize fructooligosaccharides (FOS) production, accumulation, and behavior through time. To do so, high performance anion exchange was also used as analytical reference to determine the goodness and robustness of HPTLC data. The multivariate data analysis showed separation of samples dictated by species and age effects detected by both techniques. Moreover, linear correlations between the increase of the age in agave and their carbohydrate fraction was established in both species by both techniques. Oligosaccharides found to be correlated to species and age factors, these suggest changes in specific carbohydrate metabolism enzymes. Thus, HPTLC was proven as a complementary or stand-alone fingerprinting platform for fructooligosaccharides characterization in biological mixtures. However, the type of derivatizing reagent and the extraction color channel determined the goodness of the model used to scrutinize agavin fructooligosaccharides (aFOS).

The IAS-MEEG Package: A Flexible Inverse Source Reconstruction Platform for Reconstruction and Visualization of Brain Activity from M/EEG Data

We present a standalone Matlab software platform complete with visualization for the reconstruction of the neural activity in the brain from MEG or EEG data. The underlying inversion combines hierarchical Bayesian models and Krylov subspace iterative least squares solvers. The Bayesian framework of the underlying inversion algorithm allows to account for anatomical information and possible a priori belief about the focality of the reconstruction. The computational efficiency makes the software suitable for the reconstruction of lengthy time series on standard computing equipment. The algorithm requires minimal user provided input parameters, although the user can express the desired focality and accuracy of the solution. The code has been designed so as to favor the parallelization performed automatically by Matlab, according to the resources of the host computer. We demonstrate the flexibility of the platform by reconstructing activity patterns with supports of different sizes from MEG and EEG data. Moreover, we show that the software reconstructs well activity patches located either in the subcortical brain structures or on the cortex. The inverse solver and visualization modules can be used either individually or in combination. We also provide a version of the inverse solver that can be used within Brainstorm toolbox. All the software is available online by Github, including the Brainstorm plugin, with accompanying documentation and test data.

Forensic Face Sketch Artist System

Abstract: In this modern age, the general crime rate is increasing day-by-day and to cope up with this the enforcement departments too should find ways in which would speed up the overall process and help them in bringing one to justice. One such way can be using face recognition technology for identifying and verifying the criminal. The traditional approach here is to use the hand-drawn face sketches drawn by forensic sketch artist tospot the criminal, modernizing this is able to mean using the hand-drawn sketch and then matching them with the enforcement departments database to spot the criminal. Using this approach would result in the various limitations with latest technologies andeven would be time consuming as there are very few forensic sketch artists available when compared to the increasing crime ratio. Our project is aimed on decreasing the time span and speeding up this process by providing a standalone platform to the law enforcement department which would allow users to create accurate face sketch of the suspect without the help of forensic sketch artist and no special training or artistic skills. The sketch can be created using drag and drop feature in the application with variety of face elements and can automatically match the drawn composite face sketch with the law enforcement departments database much faster and efficiently using deep learning and cloud infrastructure.

MiniDeep: A Standalone AI-Edge Platform with a Deep Learning-Based MINI-PC and AI-QSR System

In this paper, we present a new AI (Artificial Intelligence) edge platform, called “MiniDeep”, which provides a standalone deep learning platform based on the cloud-edge architecture. This AI-Edge platform provides developers with a whole deep learning development environment to set up their deep learning life cycle processes, such as model training, model evaluation, model deployment, model inference, ground truth collecting, data pre-processing, and training data management. To the best of our knowledge, such a whole deep learning development environment has not been built before. MiniDeep uses Amazon Web Services (AWS) as the backend platform of a deep learning tuning management model. In the edge device, the OpenVino enables deep learning inference acceleration at the edge. To perform a deep learning life cycle job, MiniDeep proposes a mini deep life cycle (MDLC) system which is composed of several microservices from the cloud to the edge. MiniDeep provides Train Job Creator (TJC) for training dataset management and the models’ training schedule and Model Packager (MP) for model package management. All of them are based on several AWS cloud services. On the edge device, MiniDeep provides Inference Handler (IH) to handle deep learning inference by hosting RESTful API (Application Programming Interface) requests/responses from the end device. Data Provider (DP) is responsible for ground truth collection and dataset synchronization for the cloud. With the deep learning ability, this paper uses the MiniDeep platform to implement a recommendation system for AI-QSR (Quick Service Restaurant) KIOSK (interactive kiosk) application. AI-QSR uses the MiniDeep platform to train an LSTM (Long Short-Term Memory)-based recommendation system. The LSTM-based recommendation system converts KIOSK UI (User Interface) flow to the flow sequence and performs sequential recommendations with food suggestions. At the end of this paper, the efficiency of the proposed MiniDeep is verified through real experiments. The experiment results have demonstrated that the proposed LSTM-based scheme performs better than the rule-based scheme in terms of purchase hit accuracy, categorical cross-entropy, precision, recall, and F1 score.

HSI-PP: A flexible open-source software for hyperspectral imaging-based plant phenotyping

Hyperspectral imaging has become one of the most popular techniques for high-throughput plant phenotyping. Extracting and analyzing useful plant phenotypic traits from hyperspectral images represents a major bottleneck for plant science and breeding communities. This study aims to present a stand-alone easy-to-use software platform called HSI-PP to process and analyze hyperspectral images for high-throughput plant phenotyping. The HSI-PP software integrates pre-processing, feature extraction, and modeling functions. The application of HSI-PP is exemplified by investigating the response of different Arabidopsis thaliana genotypes to drought stress, and the impact of various imaging angles on predicting the canopy nitrogen content (CNC) of oilseed rape (Brassica napus L.). The results showed that HSI-PP can process 10 GB on an ordinary PC in time ranging from 30 to 73 min according to image size and the complexity of the pipeline. HSI-PP extracted multiple phenotyping traits (spectral, textural, and morphological) of Arabidopsis thaliana from a large image dataset (104 GB) within five hours. The fusion of these features achieved higher accuracy (94%) than only using spectral information (85%) as early as day 4 after drought stress treatment. For oilseed rape, about 384 GB image data was processed within eighteen hours, and it was found that the tilted imaging angle of 75° had the optimized PLSR fitting (0.83) to the ground truth. The results demonstrate that HSI-PP is a stand-alone, automated, and open-source hyperspectral image processing platform adapted to various applications in plant phenotyping without requiring professional programming skills to serve the plant research community.

Factors Impacting Defect Density in Software Development Projects

This study empirically examines the impact of technical and situational factors on the quality of software development. Defect density was used to measure the post-implementation quality of software projects. The non-parametric Kruskal-Wallis test and the parametric Welch T-test were used to test the differences in defect density for technological and situational factors related to these projects. Results suggest technological and situational factors significantly impact the quality of software. Empirical findings revealed the following factors result in lower defect density: (1) project enhancements versus new project development; (2) smaller projects versus larger projects; (3) using a development methodology; (4) using later generation programming languages; (5) developing projects with in-house teams; (6) using an iterative development methodology versus a waterfall development methodology; (7) using larger development teams versus smaller teams; (8) using CASE tools; and (9) developing projects on a standalone platform versus developing on a client\server multiplatform.

Forensic Face Sketch Recognition

In modern society, the overall crime rate is increasing day by day, and in order to overcome this, law enforcement department must also find ways to speed up the entire process and help bring justice. One such method is to use facial recognition technology to identify the criminal. The traditional approach here is to use a hand-drawn sketch of a face, drawn by forensic artist to identify the criminal. Upgrading it will allow us to identify the criminals using hand-drawn sketches and then matching it with law enforcement databases. This approach is time consuming as there are few forensic artists available compared to the increasing crime ratio which is subject to various limitations with the latest technology and increasing crime rates. Our project provides law enforcement department a standalone platform that allows users to create composite sketches of a suspect's face using the drag-and-drop feature without the aid of forensics, thereby reducing time gaps and speeding up the process. The application automatically matches complex face sketches with police database.

Abstract 2705: Detection and assembly of extrachromosomal DNA in tumors with nanopore sequencing

Abstract In cancer, parts of linear chromosomes containing coding and regulatory sequences can become excised and form novel circular extrachromosomal DNA (ecDNA) molecules. Because ecDNA lack centromeres, their replication and segregation during cell division is not limited by laws of Mendelian inheritance. This allows ecDNA to drive rapid oncogene amplification and intra-tumor heterogeneity, leading to better tumor adaption to changing microenvironments and increasing the potential for drug treatment resistance. Detection and assembly of ecDNA plays an important role in cancer research and can help inform treatment. We present a computational workflow capable of detecting and assembling ecDNA in tumors by processing long nanopore reads at shallow whole genome coverage levels. Briefly, the workflow first identifies reference genomic regions with sample-specific excess in read-depth coverage (i.e. focal amplifications). Then long nanopore reads overlapping these regions are extracted and used as input for local de-novo assembly. Resulting assemblies are then refined to have a reference-based representation of ecDNA-comprising fragments, highlighting their new relative order, orientation, and structural differences from canonical reference/matching normal sample, followed by reporting of non-reference inserted sequences for further analysis (e.g., viral integration detection). We evaluate the proposed approach on low-pass whole genome nanopore sequencing data from a variety of ecDNA-containing cell lines. We observe that the proposed nanopore-based workflow detects ecDNA presence and assembles its amplicon structure in concordance with previously published results. We further demonstrate the stability of obtained results with ≤1x target WGS coverage levels, suggesting that the output obtained from a MinION nanopore sequencer would be suitable for conducting multi-site tumor multiplex sequencing for analyzing intra-tumor ecDNA abundance and structural heterogeneity. We show that the real-time nature of nanopore sequencing allows for detection and assembly of ecDNA elements within just a few hours of sequencing, paving the way for a rapid turnaround ecDNA analysis. Notably, because of the unique ability of nanopore reads to retain single-molecule methylation signals, the proposed workflow allows for identification of differentially methylated regions both across intra-tumor multi-site samples, as well as in a tumor vs normal comparison, thus shedding light in acquisition/loss of DNA modifications in ecDNA. These results show how nanopore sequencing can be used as cost- and time-effective stand-alone platform to detect ecDNA presence and analyze its structure, while also revealing the dimension of ecDNA methylation in tumor samples. Oxford Nanopore Technologies products are not intended for use for health assessment or to diagnose, treat, mitigate, cure, or prevent any disease or condition. Citation Format: Sergey Aganezov, John Beaulaurier, Eoghan Harrington, Sissel Juul. Detection and assembly of extrachromosomal DNA in tumors with nanopore sequencing [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 2705.

PIMGAVir and Vir-MinION: Two Viral Metagenomic Pipelines for Complete Baseline Analysis of 2nd and 3rd Generation Data.

The taxonomic classification of viral sequences is frequently used for the rapid identification of pathogens, which is a key point for when a viral outbreak occurs. Both Oxford Nanopore Technologies (ONT) MinION and the Illumina (NGS) technology provide efficient methods to detect viral pathogens. Despite the availability of many strategies and software, matching them can be a very tedious and time-consuming task. As a result, we developed PIMGAVir and Vir-MinION, two metagenomics pipelines that automatically provide the user with a complete baseline analysis. The PIMGAVir and Vir-MinION pipelines work on 2nd and 3rd generation data, respectively, and provide the user with a taxonomic classification of the reads through three strategies: assembly-based, read-based, and clustering-based. The pipelines supply the scientist with comprehensive results in graphical and textual format for future analyses. Finally, the pipelines equip the user with a stand-alone platform with dedicated and various viral databases, which is a requirement for working in field conditions without internet connection.

Diagnosis of hepatitis disease using machine learning techniques

Hepatitis is <span>an infection that causes inflammation of liver tissue. Many studies have developed machine learning models for hepatitis disease diagnosis. However, there has been little discussion about the relationship between hepatitis symptoms. The first objective of this study is to provide a brief description of a real-world hepatitis disease symptom dataset. Furthermore, the authors proposed a stand-alone classification platform using random forest, decision tree, and support vector machine into healthy people or hepatitis patients using adaptive wrapper feature selection. It was discovered that there is a strong link between certain characteristics and hepatitis diagnosis. The work presented here may help improve hepatitis diagnosis in the early stages, which may lead to a reduction in the acute effects of hepatitis on human life. It is worth noting that random forest (RF) gave the highest accuracy and stayed slightly consistent through all sets of features in comparison to decision tree (DT) and support vector machines (SVM).</span>

Travelogue: A Travel Application using MERN and Augmented Reality

Abstract: Now a days web application plays a vital role from ordering food from a restaurant, ordering any electronic stuff or anything from web apps, watching movies, book a seat for a movie theatre, for study, download pictures from the internet, etc. and MERN stack is one of the most popular JavaScript stacks used for easier and faster deployment of full-stack web application comprising backend, frontend and database components. Travel enthusiasts have always desired for traveling fascinating places and archiving their memorable experiences. Currently, there are a wide range of travel based web applications. This paper aims at exploring features that could be integrated with travel applications for offering customizable user experience. Further, the paper discusses the prevailing drawbacks of the existing travel applications and looks forward for embracing modern features to make travel applications accessible. Currently there’s no simple standalone platform where people can share their travel experiences, receive suggestions for places to travel and recommend travel places to their dear ones. So we came up with an idea to build a full stack web application where folks can share their journey through images and location. That way it won’t be a tedious process anymore to surf the web and head on to travel. Keywords: Augmented Reality, Chatbot, MERN Stack, Web Application

Onboard Orbit Determination for Deep-Space CubeSats

In this work, an orbit determination algorithm suitable for CubeSats onboard implementation is developed, which simulates optical autonomous navigation accomplished by a stand-alone platform. An extended Kalman filter featuring line-of-sight acquisitions of planets is selected as the state estimator, and its performances are tested on a Raspberry Pi, whose characteristics are comparable to a miniaturized onboard computer. An improvement of the solution accuracy is performed by correcting the planetary light-time and aberration effects as well as by exploiting the optimal beacons selection strategy to acquire the external observations. Moreover, the numerical precision of the estimator is improved through the implementation of factorization techniques and nondimensionalization strategies. The results are presented for a sample Earth–Mars transfer, where the time slot for the navigation campaign involves 2 h every 10 days. At final time, the probe position and velocity are estimated with a accuracy of 360 km and 0.04 m/s, respectively.