Pre-trained Machine Learning Model Research Articles

Human activity recognition based on wrist PPG via the ensemble method

Human activity recognition via Electrocardiography (ECG) and Photoplethysmography (PPG) is extensively researched. While ECG requires less filtering and is less prone to disturbance and artifacts, nonetheless, PPG is cheaper and widely available in smart devices, making it a desired alternative. In this study, we explore the employment of the ensemble method with several pre-trained machine learning models namely Resnet50V2, MobileNetV2, and Xception for the classification of wrist PPG data of human activity, in comparison to its ECG counterpart. The study produced promising results with a test classification accuracy of 88.91% and 94.28% for PPG and ECG, respectively.

Front-end deep learning web apps development and deployment: a review.

Machine learning and deep learning models are commonly developed using programming languages such as Python, C++, or R and deployed as web apps delivered from a back-end server or as mobile apps installed from an app store. However, recently front-end technologies and JavaScript libraries, such as TensorFlow.js, have been introduced to make machine learning more accessible to researchers and end-users. Using JavaScript, TensorFlow.js can define, train, and run new or existing, pre-trained machine learning models entirely in the browser from the client-side, which improves the user experience through interaction while preserving privacy. Deep learning models deployed on front-end browsers must be small, have fast inference, and ideally be interactive in real-time. Therefore, the emphasis on development and deployment is different. This paper aims to review the development and deployment of these deep-learning web apps to raise awareness of the recent advancements and encourage more researchers to take advantage of this technology for their own work. First, the rationale behind the deployment stack (front-end, JavaScript, and TensorFlow.js) is discussed. Then, the development approach for obtaining deep learning models that are optimized and suitable for front-end deployment is then described. The article also provides current web applications divided into seven categories to show deep learning potential on the front end. These include web apps for deep learning playground, pose detection and gesture tracking, music and art creation, expression detection and facial recognition, video segmentation, image and signal analysis, healthcare diagnosis, recognition, and identification.

Machine learning modelling of a membrane capacitive deionization (MCDI) system for prediction of long-term system performance and optimization of process control parameters in remote brackish water desalination

Membrane Capacitive Deionization (MCDI) is a promising electrochemical technique for water desalination. Previous studies have confirrmed the effectiveness of MCDI in removing contaminants from brackish groundwaters, especially in remote areas where electricity is scarce. However, as with other water treatment technologies, performance deterioration of the MCDI system still occurs, hindering the stability of long-term operation. Herein, a machine learning (ML) modelling framework and various ML models were developed to (i) investigate the performance deterioration due particularly to insufficient charging/discharging of the electrode caused by accumulation of ions and electrode scaling and (ii) optimise MCDI operating parameters such that the impacts of these deleterious effects on unit performance were minimized. The ML models developed in this work exhibited a prediction accuracy of cycle time with average mean absolute percentage error (MAPE) values of 16.82% and 16.09% after 30-fold cross validation for Random Forest (RF) and Multilayer Perceptron (MLP) models respectively. The pre-trained ML model predicted different declining trends of water production for two different operating conditions and provided corresponding recommendations on frequencies of chemical cleaning. A case study on the adjustment of operating parameters using the results suggested by the optimization ML model was conducted. The model validation results showed that the overall water production and water recovery of the system using the cycle-based optimized process control parameters (SCN 1) exceeds the MCDI system performance under three fixed parameter settings that were used at each stage of SCN 1 by 1.78% to 4.48% and 2.95% to 9.46%, respectively. Permutation-based and Shapley additive explanation (SHAP) coefficients were also employed for variable importance (VIMP) analysis to uncover the “black-box” nature of the ML models and to better understand the various features’ contributions to overall MCDI system performance.

Sentiment analysis techniques, challenges, and opportunities: Urdu language-based analytical study.

Sentiment analysis in research involves the processing and analysis of sentiments from textual data. The sentiment analysis for high resource languages such as English and French has been carried out effectively in the past. However, its applications are comparatively few for resource-poor languages due to a lack of textual resources. This systematic literature explores different aspects of Urdu-based sentiment analysis, a classic case of poor resource language. While Urdu is a South Asian language understood by one hundred and sixty-nine million people across the planet. There are various shortcomings in the literature, including limitation of large corpora, language parsers, and lack of pre-trained machine learning models that result in poor performance. This article has analyzed and evaluated studies addressing machine learning-based Urdu sentiment analysis. After searching and filtering, forty articles have been inspected. Research objectives have been proposed that lead to research questions. Our searches were organized in digital repositories after selecting and screening relevant studies. Data was extracted from these studies. Our work on the existing literature reflects that sentiment classification performance can be improved by overcoming the challenges such as word sense disambiguation and massive datasets. Furthermore, Urdu-based language constructs, including language parsers and emoticons, context-level sentiment analysis techniques, pre-processing methods, and lexical resources, can also be improved.

Heri-Graphs: A Dataset Creation Framework for Multi-Modal Machine Learning on Graphs of Heritage Values and Attributes with Social Media

Values (why to conserve) and Attributes (what to conserve) are essential concepts of cultural heritage. Recent studies have been using social media to map values and attributes conveyed by the public to cultural heritage. However, it is rare to connect heterogeneous modalities of images, texts, geo-locations, timestamps, and social network structures to mine the semantic and structural characteristics therein. This study presents a methodological framework for constructing such multi-modal datasets using posts and images on Flickr for graph-based machine learning (ML) tasks concerning heritage values and attributes. After data pre-processing using pre-trained ML models, the multi-modal information of visual contents and textual semantics are modelled as node features and labels, while their social relationships and spatio-temporal contexts are modelled as links in Multi-Graphs. The framework is tested in three cities containing UNESCO World Heritage properties—Amsterdam, Suzhou, and Venice— which yielded datasets with high consistency for semi-supervised learning tasks. The entire process is formally described with mathematical notations, ready to be applied in provisional tasks both as ML problems with technical relevance and as urban/heritage study questions with societal interests. This study could also benefit the understanding and mapping of heritage values and attributes for future research in global cases, aiming at inclusive heritage management practices. Moreover, the proposed framework could be summarized as creating attributed graphs from unstructured social media data sources, ready to be applied in a wide range of use cases.

Study on electrical activity of grain boundaries in silicon through systematic control of structural parameters and characterization using a pretrained machine learning model

We report on the effects of grain boundary (GB) structures on the carrier recombination velocity at GB (vGB) in multicrystalline Si (mc-Si). The fabricated artificial GBs and an originally developed machine learning model allowed an investigation of the effect of three macroscopic parameters, misorientation angle α for Σ values, asymmetric angle β, and deviation angle θ from the ingot growth direction. Totally, 13 GBs were formed by directional solidification using multi-seeds with controlled crystal orientations. vGB was evaluated directly from photoluminescence intensity profiles across GBs using a pre-trained machine learning model, which allowed a quantitative and continuous evaluation along GBs. The evaluation results indicated that the impact of θ on vGB would be relatively large among the three macroscopic parameters. In addition, the results for the Σ5 and Σ13 GBs suggested that the minimum vGB would be related to the GB energy. These results were discussed in terms of the complexity of the local reconstruction of GB structures. The deviation would make a more complex reconstructed GB structure with local distortion, resulting in an increase in the electrical activity of GBs. The obtained knowledge will contribute to improving various polycrystalline materials through a comprehensive understanding of the relationship between GB structures and their properties.

Performance Analysis of Supervised Machine Learning Algorithms for Automatized Radiographical Classification of Maxillary Third Molar Impaction

Background: Oro-antral communication (OAC) is a common complication following the extraction of upper molar teeth. The Archer and the Root Sinus (RS) systems can be used to classify impacted teeth in panoramic radiographs. The Archer classes B-D and the Root Sinus classes III, IV have been associated with an increased risk of OAC following tooth extraction in the upper molar region. In our previous study, we found that panoramic radiographs are not reliable for predicting OAC. This study aimed to (1) determine the feasibility of automating the classification (Archer/RS classes) of impacted teeth from panoramic radiographs, (2) determine the distribution of OAC stratified by classification system classes for the purposes of decision tree construction, and (3) determine the feasibility of automating the prediction of OAC utilizing the mentioned classification systems. Methods: We utilized multiple supervised pre-trained machine learning models (VGG16, ResNet50, Inceptionv3, EfficientNet, MobileNetV2), one custom-made convolutional neural network (CNN) model, and a Bag of Visual Words (BoVW) technique to evaluate the performance to predict the clinical classification systems RS and Archer from panoramic radiographs (Aim 1). We then used Chi-square Automatic Interaction Detectors (CHAID) to determine the distribution of OAC stratified by the Archer/RS classes to introduce a decision tree for simple use in clinics (Aim 2). Lastly, we tested the ability of a multilayer perceptron artificial neural network (MLP) and a radial basis function neural network (RBNN) to predict OAC based on the high-risk classes RS III, IV, and Archer B-D (Aim 3). Results: We achieved accuracies of up to 0.771 for EfficientNet and MobileNetV2 when examining the Archer classification. For the AUC, we obtained values of up to 0.902 for our custom-made CNN. In comparison, the detection of the RS classification achieved accuracies of up to 0.792 for the BoVW and an AUC of up to 0.716 for our custom-made CNN. Overall, the Archer classification was detected more reliably than the RS classification when considering all algorithms. CHAID predicted 77.4% correctness for the Archer classification and 81.4% for the RS classification. MLP (AUC: 0.590) and RBNN (AUC: 0.590) for the Archer classification as well as MLP 0.638) and RBNN (0.630) for the RS classification did not show sufficient predictive capability for OAC. Conclusions: The results reveal that impacted teeth can be classified using panoramic radiographs (best AUC: 0.902), and the classification systems can be stratified according to their relationship to OAC (81.4% correct for RS classification). However, the Archer and RS classes did not achieve satisfactory AUCs for predicting OAC (best AUC: 0.638). Additional research is needed to validate the results externally and to develop a reliable risk stratification tool based on the present findings.

An annotated corpus of clinical trial publications supporting schema-based relational information extraction

BackgroundThe evidence-based medicine paradigm requires the ability to aggregate and compare outcomes of interventions across different trials. This can be facilitated and partially automatized by information extraction systems. In order to support the development of systems that can extract information from published clinical trials at a fine-grained and comprehensive level to populate a knowledge base, we present a richly annotated corpus at two levels. At the first level, entities that describe components of the PICO elements (e.g., population’s age and pre-conditions, dosage of a treatment, etc.) are annotated. The second level comprises schema-level (i.e., slot-filling templates) annotations corresponding to complex PICO elements and other concepts related to a clinical trial (e.g. the relation between an intervention and an arm, the relation between an outcome and an intervention, etc.).ResultsThe final corpus includes 211 annotated clinical trial abstracts with substantial agreement between annotators at the entity and scheme level. The mean Kappa value for the glaucoma and T2DM corpora was 0.74 and 0.68, respectively, for single entities. The micro-averaged F1 score to measure inter-annotator agreement for complex entities (i.e. slot-filling templates) was 0.81.The BERT-base baseline method for entity recognition achieved average micro- F1 scores of 0.76 for glaucoma and 0.77 for diabetes with exact matching.ConclusionsIn this work, we have created a corpus that goes beyond the existing clinical trial corpora, since it is annotated in a schematic way that represents the classes and properties defined in an ontology. Although the corpus is small, it has fine-grained annotations and could be used to fine-tune pre-trained machine learning models and transformers to the specific task of extracting information about clinical trial abstracts.For future work, we will use the corpus for training information extraction systems that extract single entities, and predict template slot-fillers (i.e., class data/object properties) to populate a knowledge base that relies on the C-TrO ontology for the description of clinical trials. The resulting corpus and the code to measure inter-annotation agreement and the baseline method are publicly available at https://zenodo.org/record/6365890.

MALMI: An Automated Earthquake Detection and Location Workflow Based on Machine Learning and Waveform Migration

Abstract Robust automatic event detection and location is central to real-time earthquake monitoring. With the increase of computing power and data availability, automated workflows that utilize machine learning (ML) techniques have become increasingly popular; however, ML-based classical workflows still face challenges when applied to the analysis of microseismic data. These seismic sequences are often characterized by short interevent times and/or low signal-to-noise ratio (SNR). Full waveform methods that do not rely on phase picking and association are suitable for processing such datasets, but are computationally costly and lack clear event identification criteria, which is not ideal for real-time processing. To leverage the advantages of both the methods, we propose a new workflow—MAchine Learning aided earthquake MIgration location (MALMI), which integrates ML and waveform migration to perform automated event detection and location. The new workflow uses a pretrained ML model to generate continuous phase probabilities that are then backprojected and stacked to locate seismic sources using migration. We applied the workflow to one month of continuous data collected in the Hengill geothermal area of Iceland to monitor induced earthquakes around two geothermal production sites. With a ML model (EQ-Transformer) pretrained using a global distribution of earthquakes, the proposed workflow automatically detects and locates 250 additional seismic events (accounting for 36% events in the obtained catalog) compared to a reference catalog generated using the SeisComP software. Most of the new events are microseismic events with a magnitude less than 0. Visual inspection of the waveforms of the newly detected events indicates that they are real seismic events of low SNR and are only reliably recorded by very few stations in the array. Further comparison with the conventional migration method based on short-term average over long-term average confirms that MALMI can produce much clearer stacked images with higher resolution and reliability, especially for events with low SNR. The workflow is freely available on GitHub, providing an automated tool for simultaneous event detection and location from continuous seismic data.

Vine water status mapping with multispectral UAV imagery and machine learning

Optimizing water management has become one of the biggest challenges for grapevine growers in California, especially during drought conditions. Monitoring grapevine water status and stress level across the whole vineyard is an essential step for precision irrigation management of vineyards to conserve water. We developed a unified machine learning model to map leaf water potential ({psi }_{mathrm{leaf}}), by combining high-resolution multispectral remote sensing imagery and weather data. We conducted six unmanned aerial vehicle (UAV) flights with a five-band multispectral camera from 2018 to 2020 over three commercial vineyards, concurrently with ground measurements of sampled vines. Using vegetation indices from the orthomosaiced UAV imagery and weather data as predictors, the random forest (RF) full model captured 77% of {psi }_{mathrm{leaf}} variance, with a root mean square error (RMSE) of 0.123 MPa, and a mean absolute error (MAE) of 0.100 MPa, based on the validation datasets. Air temperature, vapor pressure deficit, and red edge indices such as the normalized difference red edge index (NDRE) were found as the most important variables in estimating {psi }_{mathrm{leaf}} across space and time. The reduced RF models excluding weather and red edge indices explained 52–48% of {psi }_{mathrm{leaf}} variance, respectively. Maps of the estimated {psi }_{mathrm{leaf}} from the RF full model captured well the patterns of both within- and cross-field spatial variability and the temporal change of vine water status, consistent with irrigation management and patterns observed from the ground sampling. Our results demonstrated the utility of UAV-based aerial multispectral imaging for supplementing and scaling up the traditional point-based ground sampling of {psi }_{mathrm{leaf}}. The pre-trained machine learning model, driven by UAV imagery and weather data, provides a cost-effective and scalable tool to facilitate data-driven precision irrigation management at individual vine levels in vineyards.

Machine Learning-Driven Clinical Image Analysis to Identify Craniosynostosis: A Pilot Study of Telemedicine and Clinic Patients.

The authors have developed pretrained machine learning (ML) models to evaluate neonatal head shape deformities using top-down and facial orthogonal photographs of the patient's head. In previous preliminary analysis, this approach was tested with images from an open-source data bank. To determine the accuracy of pretrained ML models in identifying craniosynostosis among patients seen in our outpatient neurosurgery clinic. We retrospectively reviewed top-down and facial orthogonal images of each patient's head and provider clinical diagnosis from the same encounters. Head shape classifications generated from 3 pretrained ML models (random forest, classification and regression tree, and linear discriminant analysis) were applied to each patient's photograph data set after craniometric extraction using a predefined image processing algorithm. Diagnoses were codified into a binary scheme of craniosynostosis vs noncraniosynostosis. Sensitivity, specificity, and Matthew correlation coefficient were calculated for software vs provider classifications. A total of 174 patients seen for abnormal head shape between May 2020 and February 2021 were included in the analysis. One hundred seven patients (61%) were seen in-person and 67 (39%) through telemedicine. Twenty-three patients (13%) were diagnosed with craniosynostosis. The best-performing model identified craniosynostosis with an accuracy of 94.8% (95% CI 90.4-97.6), sensitivity of 87.0% (95% CI 66.4-97.2), specificity of 96.0% (95% CI 91.6-98.5), and Matthew correlation coefficient of 0.788 (95% CI 0.725-0.839). Machine learning-driven image analysis represents a promising strategy for the identification of craniosynostosis in a real-world practice setting. This approach has potential to reduce the need for imaging and facilitate referral by primary care providers.

Data Augmentation and Transfer Learning for Data Quality Assessment in Respiratory Monitoring.

Changes in respiratory rate have been found to be one of the early signs of health deterioration in patients. In remote environments where diagnostic tools and medical attention are scarce, such as deep space exploration, the monitoring of the respiratory signal becomes crucial to timely detect life-threatening conditions. Nowadays, this signal can be measured using wearable technology; however, the use of such technology is often hampered by the low quality of the recordings, which leads more often to wrong diagnosis and conclusions. Therefore, to apply these data in diagnosis analysis, it is important to determine which parts of the signal are of sufficient quality. In this context, this study aims to evaluate the performance of a signal quality assessment framework, where two machine learning algorithms (support vector machine–SVM, and convolutional neural network–CNN) were used. The models were pre-trained using data of patients suffering from chronic obstructive pulmonary disease. The generalization capability of the models was evaluated by testing them on data from a different patient population, presenting normal and pathological breathing. The new patients underwent bariatric surgery and performed a controlled breathing protocol, displaying six different breathing patterns. Data augmentation (DA) and transfer learning (TL) were used to increase the size of the training set and to optimize the models for the new dataset. The effect of the different breathing patterns on the performance of the classifiers was also studied. The SVM did not improve when using DA, however, when using TL, the performance improved significantly (p < 0.05) compared to DA. The opposite effect was observed for CNN, where the biggest improvement was obtained using DA, while TL did not show a significant change. The models presented a low performance for shallow, slow and fast breathing patterns. These results suggest that it is possible to classify respiratory signals obtained with wearable technologies using pre-trained machine learning models. This will allow focusing on the relevant data and avoid misleading conclusions because of the noise, when designing bio-monitoring systems.

Empowering digital pathology applications through explainable knowledge extraction tools

Exa-scale volumes of medical data have been produced for decades. In most cases, the diagnosis is reported in free text, encoding medical knowledge that is still largely unexploited. In order to allow decoding medical knowledge included in reports, we propose an unsupervised knowledge extraction system combining a rule-based expert system with pre-trained Machine Learning (ML) models, namely the Semantic Knowledge Extractor Tool (SKET). Combining rule-based techniques and pre-trained ML models provides high accuracy results for knowledge extraction. This work demonstrates the viability of unsupervised Natural Language Processing (NLP) techniques to extract critical information from cancer reports, opening opportunities such as data mining for knowledge extraction purposes, precision medicine applications, structured report creation, and multimodal learning.SKET is a practical and unsupervised approach to extracting knowledge from pathology reports, which opens up unprecedented opportunities to exploit textual and multimodal medical information in clinical practice. We also propose SKET eXplained (SKET X), a web-based system providing visual explanations about the algorithmic decisions taken by SKET.SKET X is designed/developed to support pathologists and domain experts in understanding SKET predictions, possibly driving further improvements to the system.

Unlocking Edge Intelligence Through Tiny Machine Learning (TinyML)

Machine Learning (ML) on the edge is key for enabling a new breed of IoT and autonomous system applications. The departure from the traditional cloud-centric architecture means that new deployments can be more power-efficient, provide better privacy and reduced latency for inference. At the core of this paradigm is TinyML, a framework allowing the execution of ML models on low-power embedded devices. TinyML allows importing pre-trained ML models on the edge for providing ML-as-a-Service (MLaaS) to IoT devices. This article presents a comprehensive overview of Tiny MLaaS (TMLaaS) architecture. The TMLaaS architecture inherently presents several design trade-offs in terms of energy consumption, security, privacy, and latency.We also present how TMLaaS architecture can be implemented, deployed, and maintained for large scale IoT deployment. The feasibility of implementation for the TMLaaS architecture has been demonstrated with the help of a case study.

Human Activity Recognition using CNN and Pretrained Machine Learning Models

People's lives are enriched by human activity recognition (HAR), which extracts action-level details about human behaviour from raw input data. There are a variety of uses for Human Activity Recognition, including elderly surveillance systems, abnormal behaviour, and so forth. However, deep learning models such as Convolutional Neural Networks have outperformed traditional machine learning methods. As a result of CNN, it is possible to extract features and reduce computational costs. Transfer Learning, on the other hand, refers to the use of pre-trained machine learning models that can be used to detect human activity using a special type of Artificial Neural Network known as Leveraging CNN. Resnet-34 Use of a CNN model can provide detection accuracy up to 96.95 percent for human activity recognition Numerous studies and research have been conducted on HAR. There are only a few models in the majority of the paper, however What we know is that the more data we have, the better the model and the more accurate the model will be.

Forewarn Traffic Signal with Ambulance Detection By GPS and Light Standard Signal Using Machine Learning

People's lives are enriched by human activity recognition (HAR), which extracts action-level details about human behaviour from raw input data. There are a variety of uses for Human Activity Recognition, including elderly surveillance systems, abnormal behaviour, and so forth. However, deep learning models such as Convolutional Neural Networks have outperformed traditional machine learning methods. As a result of CNN, it is possible to extract features and reduce computational costs. Transfer Learning, on the other hand, refers to the use of pre-trained machine learning models that can be used to detect human activity using a special type of Artificial Neural Network known as Leveraging CNN. Resnet-34 Use of a CNN model can provide detection accuracy up to 96.95 percent for human activity recognition Numerous studies and research have been conducted on HAR. There are only a few models in the majority of the paper, however What we know is that the more data we have, the better the model and the more accurate the model will be.

TOWARD DATA-DRIVEN FILTERS IN PARAVIEW

Recent progress in scientific visualization has expanded the scope of visualization from being merely a way of presentation to an analysis and discovery tool. A given visualization result is usually generated by applying a series of transformations or filters to the underlying data. Nowadays, such filters use deterministic algorithms to process the data. In this work, we aim at extending this methodology towards data-driven filters, thus filters that expose the abilities of pre-trained machine learning models to the visualization system. The use of such data-driven filters is of particular interest in fields like segmentation, classification, etc., where machine learning models regularly outperform existing algorithmic approaches. To showcase this idea, we couple Paraview, the well-known flow visualization tool, with PyTorch, a deep learning framework. Paraview is extended by plugins that allow users to load pre-trained models of their choice in the form of newly developed filters. The filters transform the input data by feeding it into the model and then provide the model's output as input to the remaining visualization pipeline. A series of simplistic use cases for segmentation and classification on image and fluid data is presented to showcase the technical applicability of such data-driven transformations in Paraview for future complex analysis tasks.

End-to-End Synthesis of Dynamically Controlled Machine Learning Accelerators

Edge systems are required to autonomously make real-time decisions based on large quantities of input data under strict power, performance, area, and other constraints. Meeting these constraints is only possible by specializing systems through hardware accelerators purposefully built for machine learning and data analysis algorithms. However, data science evolves at a quick pace, and manual design of custom accelerators has high non-recurrent engineering costs: general solutions are needed to automatically and rapidly transition from the formulation of a new algorithm to the deployment of a dedicated hardware implementation. Our solution is the SOftware Defined Architectures (SODA) Synthesizer, an end-to-end, multi-level, modular, extensible compiler toolchain providing a direct path from machine learning tools to hardware. The SODA Synthesizer frontend is based on the multilevel intermediate representation (MLIR) framework; it ingests pre-trained machine learning models, identifies kernels suited for acceleration, performs high-level optimizations, and prepares them for hardware synthesis. In the backend, SODA leverages state-of-the-art high-level synthesis techniques to generate highly efficient accelerators, targeting both field programmable devices (FPGAs) and application-specific circuits (ASICs). In this paper, we describe how the SODA Synthesizer can also assemble the generated accelerators (based on the finite state machine with datapath model) in a custom system driven by a distributed controller, building a coarse-grained dataflow architecture that does not require a host processor to orchestrate parallel execution of multiple accelerators. We show the effectiveness of our approach by automatically generating ASIC accelerators for layers of popular deep neural networks (DNNs). Our high-level optimizations result in up to 74x speedup on isolated accelerators for individual DNN layers, and our dynamically scheduled architecture yields an additional 3x performance improvement when combining accelerators to handle streaming inputs.

Quantitative Content Analysis of Maps on Twitter using network visualization and pre-trained machine learning models

Quantitative Content Analysis of Maps on Twitter using network visualization and pre-trained machine learning models

Comparing the Expense and Accuracy of Methods to Simulate Atomic Vibrations in Rubrene.

Atomic vibrations can inform about materials properties from hole transport in organic semiconductors to correlated disorder in metal-organic frameworks. Currently, there are several methods for predicting these vibrations using simulations, but the accuracy-efficiency tradeoffs have not been examined in depth. In this study, rubrene is used as a model system to predict atomic vibrational properties using six different simulation methods: density functional theory, density functional tight binding, density functional tight binding with a Chebyshev polynomial-based correction, a trained machine learning model, a pretrained machine learning model called ANI-1, and a classical forcefield model. The accuracy of each method is evaluated by comparison to the experimental inelastic neutron scattering spectrum. All methods discussed here show some accuracy across a wide energy region, though the Chebyshev-corrected tight-binding method showed the optimal combination of high accuracy with low expense. We then offer broad simulation guidelines to yield efficient, accurate results for inelastic neutron scattering spectrum prediction.