Runtime Performance Research Articles

Enhancing cryo-EM structure prediction with DeepTracer and AlphaFold2 integration.

Understanding the protein structures is invaluable in various biomedical applications, such as vaccine development. Protein structure model building from experimental electron density maps is a time-consuming and labor-intensive task. To address the challenge, machine learning approaches have been proposed to automate this process. Currently, the majority of the experimental maps in the database lack atomic resolution features, making it challenging for machine learning-based methods to precisely determine protein structures from cryogenic electron microscopy density maps. On the other hand, protein structure prediction methods, such as AlphaFold2, leverage evolutionary information from protein sequences and have recently achieved groundbreaking accuracy. However, these methods often require manual refinement, which is labor intensive and time consuming. In this study, we present DeepTracer-Refine, an automated method that refines AlphaFold predicted structures by aligning them to DeepTracers modeled structure. Our method was evaluated on 39 multi-domain proteins and we improved the average residue coverage from 78.2 to 90.0% and average local Distance Difference Test score from 0.67 to 0.71. We also compared DeepTracer-Refine with Phenixs AlphaFold refinement and demonstrated that our method not only performs better when the initial AlphaFold model is less precise but also surpasses Phenix in run-time performance.

Investigation of the Effects of Caffeine Intake on Reaction Time, Acceleration, Speed and Balance in Short Distance Runners

The aims of this study is to examine the effects of caffeine intake in sprinters on reaction time, speed, acceleration and balance. A total of 31 sprinters (18 female, 13 male) from the athletics team of university faculty of sports sciences participated in the study. Sprinters were divided into two groups, caffeine and placebo, and their balance, reaction time, 30-meter running time and 15-meter acceleration performances were measured. The Wilcoxon t-Test and the Mann-Whitney U test were applied to the data obtained on the SPSS 23.0 package program. As a result of the study, the number of errors in the balance test decreased significantly in both the experimental group and the control group while a significant decrease was observed in block takeoff reaction time only in the experimental group. In conclusion, it was determined that while caffeine intake did not have a significant effect on acceleration and running times, block take off reaction time created a significant difference in the experimental group and could provide an advantage to the sprinters. Therefore, it can be said that caffeinated gum may be a good ergogenic aid to improve reaction performance in sprinters.

INFORMEDQX: Informed Conflict Detection for Over-Constrained Problems

Conflict detection is relevant in various application scenarios, ranging from interactive decision-making to the diagnosis of faulty knowledge bases. Conflicts can be regarded as sets of constraints that cause an inconsistency. In many scenarios (e.g., constraint-based configuration), conflicts are repeatedly determined for the same or similar sets of constraints. This misses out on the valuable opportunity for leveraging knowledge reuse and related potential performance improvements, which are extremely important, specifically interactive constraint-based applications. In this paper, we show how to integrate knowledge reuse concepts into non-instructive conflict detection. We introduce the InformedQX algorithm, which is a reuse-aware variant of QuickXPlain. The results of a related performance analysis with the Linux-2.6.3.33 configuration knowledge base show significant improvements in terms of runtime performance compared to QuickXPlain.

ConSequence: Synthesizing Logically Constrained Sequences for Electronic Health Record Generation

Generative models can produce synthetic patient records for analytical tasks when real data is unavailable or limited. However, current methods struggle with adhering to domain-specific knowledge and removing invalid data. We present ConSequence, an effective approach to integrating domain knowledge into sequential generative neural network outputs. Our rule-based formulation includes temporal aggregation and antecedent evaluation modules, ensured by an efficient matrix multiplication formulation, to satisfy hard and soft logical constraints across time steps. Existing constraint methods often fail to guarantee constraint satisfaction, lack the ability to handle temporal constraints, and hinder the learning and computational efficiency of the model. In contrast, our approach efficiently handles all types of constraints with guaranteed logical coherence. We demonstrate ConSequence's effectiveness in generating electronic health records, outperforming competitors in achieving complete temporal and spatial constraint satisfaction without compromising runtime performance or generative quality. Specifically, ConSequence successfully prevents all rule violations while improving the model quality in reducing its test perplexity by 5% and incurring less than a 13% slowdown in generation speed compared to an unconstrained model.

Enhanced Two-Stream Bayesian Hyper Parameter Optimized 3D-CNN Inception-v3 Based Drop-ConvLSTM2D Deep Learning Model for Human Action Recognition

Human Action Recognition (HAR) has grown to be the toughest and most attractive concern in the domains of computer vision, communication between a person and the surroundings, and video surveillance. In variation to the conventional methods that usually make use of the Long Short Term Memory model (LSTM) for training, this work designed dropout variant Drop-ConvLSTM2D, to provide more effectiveness in regularization for deep Convolution Neural Networks (CNNs).In addition, to speed up the runtime performance of the Deep Learning model, Bayesian Hyper Parameter Optimization (BHPO) is also introduced to autonomously optimize, the hyperparameters of the trained architecture. In this study, a two-stream Bayesian Hyper Parameter optimized Drop-ConvLSTM2D model is designed for HAR to overcome the current research deficiencies. In one stream, an Inception-v3 model extracts the temporal characteristics from the optical frames which are generated through the dense flow process. In another stream, a 3D-CNN involves the mining of the spatial-temporal characteristics from the RGB frames. Finally, the features of Inception-v3 and 3D-CNN are fused using which the Drop-ConvLSTM2D model is trained to recognize human behavior. On perceptive public video datasets UCF-101, and HMDB51, the quantitative assessments are conducted on the Drop-ConvLSTM2D BHPO model. For all hyperparameters, the built model explicitly obtains optimized values in this process, which can save time and improve performance. The experimental outcome shows that with a precision of at least 3%, the designed model beats the traditional two-stream model.

LPLM: A Neural Language Model for Cardinality Estimation of LIKE-Queries

Cardinality estimation is an important step in cost-based database query optimization. The accuracy of the estimates directly affects the ability of an optimizer to identify the most efficient query execution plan correctly. In this paper, we study cardinality estimation of LIKE-queries, i.e., queries that use the LIKE-operator to match a pattern with wildcards against string-valued attributes. While both traditional and machine-learning-based approaches have been proposed to tackle this problem, we argue that they all suffer from drawbacks. Most importantly, many state-of-the-art approaches are not designed for patterns that contain wildcards in-between characters. Based on past research on neural language models, we introduce the LIKE-Pattern Language Model (LPLM) that uses a new language and a novel probability distribution function to capture the semantics of general LIKE-patterns. We also propose a method to generate training data for our model. We demonstrate that our method outperforms state-of-the-art approaches in terms of precision (Q-error), while offering comparable runtime performance and memory requirements.

GPU-accelerated Bloch simulations and MR-STAT reconstructions using the Julia programming language.

MR-STAT is a relatively new multiparametric quantitative MRI technique in which quantitative paramater maps are obtained by solving a large-scale nonlinear optimization problem. Managing reconstruction times is one of the main challenges of MR-STAT. In this work we leverage GPU hardware to reduce MR-STAT reconstruction times. A highly optimized, GPU-compatible Bloch simulation toolbox is developed as part of this work that can be utilized for other quantitative MRI techniques as well. The Julia programming language was used to develop a flexible yet highly performant and GPU-compatible Bloch simulation toolbox called BlochSimulators.jl. The runtime performance of the toolbox is benchmarked against other Bloch simulation toolboxes. Furthermore, a (partially matrix-free) modification of a previously presented (matrix-free) MR-STAT reconstruction algorithm is proposed and implemented using the Julia language on GPU hardware. The proposed algorithm is combined with BlochSimulators.jl and the resulting MR-STAT reconstruction times on GPU hardware are compared to previously presented MR-STAT reconstruction times. The BlochSimulators.jl package demonstrates superior runtime performance on both CPU and GPU hardware when compared to other existing Bloch simulation toolboxes. The GPU-accelerated partially matrix-free MR-STAT reconstruction algorithm, which relies on BlochSimulators.jl, allows for reconstructions of 68 seconds per two-dimensional (2D slice). By combining the proposed Bloch simulation toolbox and the partially matrix-free reconstruction algorithm, 2D MR-STAT reconstructions can be performed in the order of one minute on a modern GPU card. The Bloch simulation toolbox can be utilized for other quantitative MRI techniques as well, for example for online dictionary generation for MR Fingerprinting.

Uncertainty Quantification of Machine Learning Model Performance via Anomaly-Based Dataset Dissimilarity Measures

The use of Machine Learning (ML) models as predictive tools has increased dramatically in recent years. However, data-driven systems (such as ML models) exhibit a degree of uncertainty in their predictions. In other words, they could produce unexpectedly erroneous predictions if the uncertainty stemming from the data, choice of model and model parameters is not taken into account. In this paper, we introduce a novel method for quantifying the uncertainty of the performance levels attained by ML classifiers. In particular, we investigate and characterize the uncertainty of model accuracy when classifying out-of-distribution data that are statistically dissimilar from the data employed during training. A main element of this novel Uncertainty Quantification (UQ) method is a measure of the dissimilarity between two datasets. We introduce an innovative family of data dissimilarity measures based on anomaly detection algorithms, namely the Anomaly-based Dataset Dissimilarity (ADD) measures. These dissimilarity measures process feature representations that are derived from the activation values of neural networks when supplied with dataset items. The proposed UQ method for classification performance employs these dissimilarity measures to estimate the classifier accuracy for unseen, out-of-distribution datasets, and to give an uncertainty band for those estimates. A numerical analysis of the efficacy of the UQ method is conducted using standard Artificial Neural Network (ANN) classifiers and public domain datasets. The results obtained generally demonstrate that the amplitude of the uncertainty band associated with the estimated accuracy values tends to increase as the data dissimilarity measure increases. Overall, this research contributes to the verification and run-time performance prediction of systems composed of ML-based elements.

MCMSTStream: applying minimum spanning tree to KD-tree-based micro-clusters to define arbitrary-shaped clusters in streaming data

Stream clustering has emerged as a vital area for processing streaming data in real-time, facilitating the extraction of meaningful information. While efficient approaches for defining and updating clusters based on similarity criteria have been proposed, outliers and noisy data within stream clustering areas pose a significant threat to the overall performance of clustering algorithms. Moreover, the limitation of existing methods in generating non-spherical clusters underscores the need for improved clustering quality. As a new methodology, we propose a new stream clustering approach, MCMSTStream, to overcome the abovementioned challenges. The algorithm applies MST to micro-clusters defined by using the KD-Tree data structure to define macro-clusters. MCMSTStream is robust against outliers and noisy data and has the ability to define clusters with arbitrary shapes. Furthermore, the proposed algorithm exhibits notable speed and can handling high-dimensional data. ARI and Purity indices are used to prove the clustering success of the MCMSTStream. The evaluation results reveal the superior performance of MCMSTStream compared to state-of-the-art stream clustering algorithms such as DenStream, DBSTREAM, and KD-AR Stream. The proposed method obtained a Purity value of 0.9780 and an ARI value of 0.7509, the highest scores for the KDD dataset. In the other 11 datasets, it obtained much higher results than its competitors. As a result, the proposed method is an effective stream clustering algorithm on datasets with outliers, high-dimensional, and arbitrary-shaped clusters. In addition, its runtime performance is also quite reasonable.

Field teams coordination for earthquake-damaged distribution system energization

The re-energization of electrical distribution systems in a post-disaster scenario is of grave importance as most modern infrastructure systems rely heavily on the presence of electricity. This paper introduces a method to coordinate the field teams for the optimal energization of an electrical distribution system after an earthquake-induced blackout. The proposed method utilizes a Markov Decision Process (MDP) to create an optimal energization strategy, which aims to minimize the expected time to energize each distribution system component. The travel duration of each team and the possible outcomes of the energization attempts are considered in the state transitions. The failure probabilities of the system components are computed using the fragility curves of structures and the Peak Ground Acceleration (PGA) values which are encoded to the MDP model via transition probabilities. Furthermore, the proposed solution offers several methods to determine the non-optimal actions during the construction of the MDP and eliminate them in order to improve the run-time performance without sacrificing the optimality of the solution.

Optimal control of large quantum systems: assessing memory and runtime performance of GRAPE

Gradient Ascent Pulse Engineering (GRAPE) is a popular technique in quantum optimal control, and can be combined with automatic differentiation (AD) to facilitate on-the-fly evaluation of cost-function gradients. We illustrate that the convenience of AD comes at a significant memory cost due to the cumulative storage of a large number of states and propagators. For quantum systems of increasing Hilbert space size, this imposes a significant bottleneck. We revisit the strategy of hard-coding gradients in a scheme that fully avoids propagator storage and significantly reduces memory requirements. Separately, we present improvements to numerical state propagation to enhance runtime performance. We benchmark runtime and memory usage and compare this approach to AD-based implementations, with a focus on pushing towards larger Hilbert space sizes. The results confirm that the AD-free approach facilitates the application of optimal control for large quantum systems which would otherwise be difficult to tackle.

Maintaining Symmetry between Convolutional Neural Network Accuracy and Performance on an Edge TPU with a Focus on Transfer Learning Adjustments

Transfer learning has proven to be a valuable technique for deploying machine learning models on edge devices and embedded systems. By leveraging pre-trained models and fine-tuning them on specific tasks, practitioners can effectively adapt existing models to the constraints and requirements of their application. In the process of adapting an existing model, a practitioner may make adjustments to the model architecture, including the input layers, output layers, and intermediate layers. Practitioners must be able to understand whether the modifications to the model will be symmetrical or asymmetrical with respect to the performance. In this study, we examine the effects of these adjustments on the runtime and energy performance of an edge processor performing inferences. Based on our observations, we make recommendations for how to adjust convolutional neural networks during transfer learning to maintain symmetry between the accuracy of the model and its runtime performance. We observe that the edge TPU is generally more efficient than a CPU at performing inferences on convolutional neural networks, and continues to outperform a CPU as the depth and width of the convolutional network increases. We explore multiple strategies for adjusting the input and output layers of an existing model and demonstrate important performance cliffs for practitioners to consider when modifying a convolutional neural network model.

Indexed Types for a Statically Safe WebAssembly

We present Wasm-prechk, a superset of WebAssembly (Wasm) that uses indexed types to express and check simple constraints over program values. This additional static reasoning enables safely removing dynamic safety checks from Wasm, such as memory bounds checks. We implement Wasm-prechk as an extension of the Wasmtime compiler and runtime, evaluate the run-time and compile-time performance of Wasm-prechk vs WebAssembly configurations with explicit dynamic checks, and find an average run-time performance gain of 1.71x faster in the widely used PolyBenchC benchmark suite, for a small overhead in binary size (7.18% larger) and type-checking time (1.4% slower). We also prove type and memory safety of Wasm-prechk, prove Wasm safely embeds into Wasm-prechk ensuring backwards compatibility, prove Wasm-prechk type-erases to Wasm, and discuss design and implementation trade-offs.

GRUPS-rs, a high-performance ancient DNA genetic relatedness estimation software relying on pedigree simulations

Background: The study of fine-grain genetic kinship ties (parents, siblings, cousins, etc.) from ancient remains is now gaining significant interest within the field of paleogenetics, as a means of deciphering the social organization of past societies. However, kinship analyses are in practice often quite difficult to apply within paleogenetic studies, and may carry a high degree of uncertainty in the results they provide, especially when applied on low coverage and/or highly degraded samples, or when studying poorly characterized populations. To overcome these challenges, most of the available kinship estimation methods either refrain from inferring ties beyond the second degree (e.g., half-siblings), and/or rely on the use of a cohort of individuals to obtain a satisfactory statistical significance. Thus, the current state of the art remains intrinsically limited when attempting to estimate kinship on a small number of individuals, or when trying to detect more distant relationships (e.g., cousins). Methods:Here, we present GRUPS-rs:an update and complete reimplementation of GRUPS (Get Relatedness Using Pedigree Simulations), an ancient DNA kinship estimation software based on the methods originally developed in (Martin et al. 2017).GRUPS-rs both computes an estimate of relatedness from randomly sampled pseudo-haploidized variant calls, and leverages high-definition pedigree simulations to bypass the use of a cohort of individuals. Results: We highlight that GRUPS and GRUPS-rs are especially suitable to perform kinship analysis on a restricted number of ancient samples, and can provide a sufficient statistical significance to estimate genetic relatedness past the second degree, while taking into account user-defined contamination and sequencing error estimates. Importantly, GRUPS-rs offers an estimated 14000-fold speed-up in runtime performance compared to its predecessor — allowing the joint estimation of kinship between dozens of individuals in a matter of minutes — and is now bundled with a user-friendly Shiny interface, in which users can interactively visualize their results. Conclusions: The GRUPS kinship estimation method is now fully operational in its "GRUPS-rs" implementation, whose use is particularly recommended when analyzing a restricted number of low coverage DNA samples.

Q-Seg: Quantum Annealing-Based Unsupervised Image Segmentation.

We present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixel- wise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology of the D-Wave Advantage device, offering superior scalability over existing quantum approaches and outperforming several tested state-of-the-art classical methods. Empirical evaluations on synthetic datasets have shown that Q-Seg has better runtime performance than the state-of-the-art classical optimizer Gurobi. The method has also been tested on earth observation image segmentation, a critical area with noisy and unreliable annotations. In the era of noisy intermediate-scale quantum, Q-Seg emerges as a reliable contender for real-world applications in comparison to advanced techniques like Segment Anything. Consequently, Q-Seg offers a promising solution using available quantum hardware, especially in situations constrained by limited labeled data and the need for efficient computational runtime.

Orthogonal Capsule Networks With Positional Information Preservation and Lightweight Feature Learning.

Both transformer and convolutional neural network (CNN) models require supplementary elements to acquire positional information. To address this issue, we propose a novel orthogonal capsule network (OthogonalCaps) that preserves location information during lightweight feature learning. The proposed network simplifies complex training processes and enables end-to-end training for object detection tasks. Specifically, there is no need to solve the regression problem of positions and the classification problem of objects separately, nor is there a need to encode the positional information as an additional token, as in transformer models. We generate the next capsule layer via orthogonality-based dynamic routing, which reduces the number of parameters and preserves positional information via its voting mechanism. Moreover, we propose Capsule ReLU as an activation function to avoid the problem of gradient vanishing and to facilitate capsule normalization across various scales, thus empowering OrthogonalCaps to better adapt to objects of diverse scales. The orthogonal capsule network (CapsNet) demonstrates an accuracy and run-time performance on a par with those of Faster R-CNN on the VOC dataset. Our network outperforms the baseline approach in detecting small-scale samples. The simulation results suggest that the proposed network surpasses other capsule network models in achieving a favorable balance between parameters and accuracy. Furthermore, an ablation experiment indicates that both Capsule ReLU and orthogonality-based dynamic routing play essential roles in enhancing the classification performance. The training code and pretrained models are available at https://github.com/l1ack/OrthogonalCaps.

YOLOH: You Only Look One Hourglass for Real-Time Object Detection.

Multi-scale detection based on Feature Pyramid Networks (FPN) has been a popular approach in object detection to improve accuracy. However, using multi-layer features in the decoder of FPN methods entails performing many convolution operations on high-resolution feature maps, which consumes significant computational resources. In this paper, we propose a novel perspective for FPN in which we directly use fused single-layer features for regression and classification. Our proposed model, You Only Look One Hourglass (YOLOH), fuses multiple feature maps into one feature map in the encoder. We then use dense connections and dilated residual blocks to expand the receptive field of the fused feature map. This output not only contains information from all the feature maps, but also has a multi-scale receptive field for detection. The experimental results on the COCO dataset demonstrate that YOLOH achieves higher accuracy and better run-time performance than established detector baselines, for instance, it achieves an average precision (AP) of 50.2 on a standard 3× training schedule and achieves 40.3 AP at a speed of 32 FPS on the ResNet-50 model. We anticipate that YOLOH can serve as a reference for researchers to design real-time detection in future studies. Our code is available at https://github.com/wsb853529465/YOLOH-main.

RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation.

Scene Graph Generation (SGG) has achieved significant progress recently. However, most previous works rely heavily on fixed-size entity representations based on bounding box proposals, anchors, or learnable queries. As each representation's cardinality has different trade-offs between performance and computation overhead, extracting highly representative features efficiently and dynamically is both challenging and crucial for SGG. In this work, a novel architecture called RepSGG is proposed to address the aforementioned challenges, formulating a subject as queries, an object as keys, and their relationship as the maximum attention weight between pairwise queries and keys. With more fine-grained and flexible representation power for entities and relationships, RepSGG learns to sample semantically discriminative and representative points for relationship inference. Moreover, the long-tailed distribution also poses a significant challenge for generalization of SGG. A run-time performance-guided logit adjustment (PGLA) strategy is proposed such that the relationship logits are modified via affine transformations based on run-time performance during training. This strategy encourages a more balanced performance between dominant and rare classes. Experimental results show that RepSGG achieves the state-of-the-art or comparable performance on the Visual Genome and Open Images V6 datasets with fast inference speed, demonstrating the efficacy and efficiency of the proposed methods.

Faster abnormality localization and recognition in a secured video bitstream by implementation of video encryption techniques

Cloud video storage uses an encrypted format to protect user data. It means encrypted video processing is an essential part of secured cloud storage. In order to detect suspicious or anomalous behavior, video surveillance must have encrypted cloud access. The primary goals of this research are to estimate parameters and detect abnormalities in an encrypted video bitstream. Various typical properties of video encoding frameworks and format-compliant encryption algorithms are investigated to identify abnormalities in an encrypted video bitstream using format-compliant encryption. The encrypted bitstream is decrypted to get three different kinds of enhancement features: the sizes of macroblocks, partitions of macroblocks, and the magnitude of the motion vector. The identification and localization methods now do not include video decryption or complete decompression. The proposed strategy has been created to implement the video encryption scheme efficiently and is compatible with various video encryption techniques. The experimental findings demonstrate that, in comparison to other methods, the proposed approach provides optimal running time and detection rate performance.

Validity and Impact of Methods for Collecting Training Data for Myoelectric Prosthetic Control Algorithms.

Intuitive regression control of prostheses relies on training algorithms to correlate biological recordings to motor intent. The quality of the training dataset is critical to run-time regression performance, but accurately labeling intended hand kinematics after hand amputation is challenging. In this study, we quantified the accuracy and precision of labeling hand kinematics using two common training paradigms: 1) mimic training, where participants mimic predetermined motions of a prosthesis, and 2) mirror training, where participants mirror their contralateral intact hand during synchronized bilateral movements. We first explored this question in healthy non-amputee individuals where the ground-truth kinematics could be readily determined using motion capture. Kinematic data showed that mimic training fails to account for biomechanical coupling and temporal changes in hand posture. Additionally, mirror training exhibited significantly higher accuracy and precision in labeling hand kinematics. These findings suggest that the mirror training approach generates a more faithful, albeit more complex, dataset. Accordingly, mirror training resulted in significantly better offline regression performance when using a large amount of training data and a non-linear neural network. Next, we explored these different training paradigms online, with a cohort of unilateral transradial amputees actively controlling a prosthesis in real-time to complete a functional task. Overall, we found that mirror training resulted in significantly faster task completion speeds and similar subjective workload. These results demonstrate that mirror training can potentially provide more dexterous control through the utilization of task-specific, user-selected training data. Consequently, these findings serve as a valuable guide for the next generation of myoelectric and neuroprostheses leveraging machine learning to provide more dexterous and intuitive control.