Adaptive Computation Research Articles

TAWFN: a deep learning framework for protein function prediction.

Proteins play pivotal roles in biological systems, and precise prediction of their functions is indispensable for practical applications. Despite the surge in protein sequence data facilitated by high-throughput techniques, unraveling the exact functionalities of proteins still demands considerable time and resources. Currently, numerous methods rely on protein sequences for prediction, while methods targeting protein structures are scarce, often employing convolutional neural networks (CNN) or graph convolutional networks (GCNs) individually. To address these challenges, our approach starts from protein structures and proposes a method that combines CNN and GCN into a unified framework called the two-model adaptive weight fusion network (TAWFN) for protein function prediction. First, amino acid contact maps and sequences are extracted from the protein structure. Then, the sequence is used to generate one-hot encoded features and deep semantic features. These features, along with the constructed graph, are fed into the adaptive graph convolutional networks (AGCN) module and the multi-layer convolutional neural network (MCNN) module as needed, resulting in preliminary classification outcomes. Finally, the preliminary classification results are inputted into the adaptive weight computation network, where adaptive weights are calculated to fuse the initial predictions from both networks, yielding the final prediction result. To evaluate the effectiveness of our method, experiments were conducted on the PDBset and AFset datasets. For molecular function, biological process, and cellular component tasks, TAWFN achieved area under the precision-recall curve (AUPR) values of 0.718, 0.385, and 0.488 respectively, with corresponding Fmax scores of 0.762, 0.628, and 0.693, and Smin scores of 0.326, 0.483, and 0.454. The experimental results demonstrate that TAWFN exhibits promising performance, outperforming existing methods. The TAWFN source code can be found at: https://github.com/ss0830/TAWFN.

Intelligent joint communication and computation scheme of UAV-assisted Offloading in high speed rail scenarios

With the continuous development of communication and computation technologies, large bandwidth services place higher demands on computing capacity and throughput in High-Speed Rail (HSR) scenarios. On the one hand, Millimetre-Wave enables high data transmission rates, but leads to high Doppler frequency deviation as well as large path loss. On the other hand, the development of Mobile Edge Computing greatly alleviates user computing congestion. In this paper, we propose the Adaptive Joint Communication and Computation Resource Allocation scheme to solve the energy optimization problem of a dual-band UAV and Mobile Relay relay-assisted HSR offloading system. This scheme works well to optimize the performance of the system through resource allocation. In addition, since the optimization problem is modeled as a Mixed-Integer Nonlinear Program, we propose the Pre- and Post-state connected Parameterized Deep Q-Network algorithm, which is based on Deep Reinforcement Learning approach, for offloading decision and bandwidth resource allocation. Simulation results show that the proposed algorithms result in lower system energy consumption, while ensuring a high task completion rate as well.

A Kernel Attention-based Transformer Model for Survival Prediction of Heart Disease Patients.

Survival analysis is employed to scrutinize time-to-event data, with emphasis on comprehending the duration until the occurrence of a specific event. In this article, we introduce two novel survival prediction models: CosAttnSurv and CosAttnSurv DyACT. CosAttnSurv model leverages transformer-based architecture and a softmax-free kernel attention mechanism for survival prediction. Our second model, CosAttnSurv DyACT, enhances CosAttnSurv with Dynamic Adaptive Computation Time (DyACT) control, optimizing computation efficiency. The proposed models are validated using two public clinical datasets related to heart disease patients. When compared to other state-of-the-art models, our models demonstrated an enhanced discriminative and calibration performance. Furthermore, in comparison to other transformer architecture-based models, our proposed models demonstrate comparable performance while exhibiting significant reduction in both time and memory requirements. Overall, our models offer significant advancements in the field of survival analysis and emphasize the importance of computationally effective time-based predictions, with promising implications for medical decision-making and patient care.

Survey of Cloud Computing Security and Privacy Issues

The world of computing and data management has completely changed as a result of cloud computing, which offers both consumers and enterprises scalable resources, on-demand services, and considerable cost savings. The demand for more adaptable and effective computer resources has prompted this paradigm change, and cloud computing provides it by enabling users to access and utilize computing resources over the internet. But using cloud computing also raises a number of security and privacy issues that must be properly handled. In order to assess the present status of cloud computing security and privacy problems, this article will examine key terms, the development of the technology, its significance, current research gaps, and the urgent need for more in-depth analysis.

Effects of an adaptive computer agent-based digital game on EFL students’ English learning outcomes

Effects of an adaptive computer agent-based digital game on EFL students’ English learning outcomes

Secured Computation Offloading in Multi-Access Mobile Edge Computing Networks through Deep Reinforcement Learning

Mobile edge computing (MEC) has emerged as a pivotal technology to address the computational demands of resource-constrained mobile devices by offloading tasks to nearby edge servers. However, ensuring the security and efficiency of computation offloading in multiaccess MEC networks remains a critical challenge. This paper proposes a novel approach that leverages deep reinforcement learning (DRL) for secure computation offloading in multi-access MEC networks. The proposed framework utilizes DRL agents to dynamically make offloading decisions based on the current network conditions, resource availability, and security requirements. The agents learn optimal offloading policies through interactions with the environment, aiming to maximize task completion efficiency while minimizing security risks. To enhance security, the framework integrates encryption techniques and access control mechanisms to protect sensitive data during offloading. The proposed approach undergoes comprehensive simulations to assess its performance in terms of security, efficiency, and scalability. The results demonstrate that the DRL-based approach effectively balances the tradeoffs between security and efficiency, achieving robust and adaptive computation offloading in multi-access MEC networks. This study contributes to advancing the state-of-the-art in secure and efficient mobile edge computing systems, fostering the development of intelligent and resilient MEC solutions for future mobile networks.

Using scalable computer vision to automate high-throughput semiconductor characterization

High-throughput materials synthesis methods, crucial for discovering novel functional materials, face a bottleneck in property characterization. These high-throughput synthesis tools produce 104 samples per hour using ink-based deposition while most characterization methods are either slow (conventional rates of 101 samples per hour) or rigid (e.g., designed for standard thin films), resulting in a bottleneck. To address this, we propose automated characterization (autocharacterization) tools that leverage adaptive computer vision for an 85x faster throughput compared to non-automated workflows. Our tools include a generalizable composition mapping tool and two scalable autocharacterization algorithms that: (1) autonomously compute the band gaps of 200 compositions in 6 minutes, and (2) autonomously compute the environmental stability of 200 compositions in 20 minutes, achieving 98.5% and 96.9% accuracy, respectively, when benchmarked against domain expert manual evaluation. These tools, demonstrated on the formamidinium (FA) and methylammonium (MA) mixed-cation perovskite system FA1−xMAxPbI3, 0 ≤ x ≤ 1, significantly accelerate the characterization process, synchronizing it closer to the rate of high-throughput synthesis.

Optimization of Sparse Matrix Computation for Algebraic Multigrid on GPUs

AMG is one of the most efficient and widely used methods for solving sparse linear systems. The computational process of AMG mainly consists of a series of iterative calculations of generalized sparse matrix-matrix multiplication (SpGEMM) and sparse matrix-vector multiplication (SpMV). Optimizing these sparse matrix calculations is crucial for accelerating solving linear systems. In this paper, we first focus on optimizing the SpGEMM algorithm in AmgX, a popular AMG library for GPUs. We propose a new algorithm called SpGEMM-upper, which achieves an average speedup of 2.02x on Tesla V100 and 1.96x on RTX 3090 against the original algorithm. Next, through experimental investigation, we conclude that no single SpGEMM library or algorithm performs optimally for most sparse matrices, and the same holds true for SpMV. Therefore, we build machine learning-based models to predict the optimal SpGEMM and SpMV used in the AMG calculation process. Finally, we integrate the prediction models, SpGEMM-upper, and other selected algorithms into a framework for adaptive sparse matrix computation in AMG. Our experimental results prove that the framework achieves promising performance improvements on the test set.

Neural Signatures of Evidence Accumulation Encode Subjective Perceptual Confidence Independent of Performance

Confidence is an adaptive computation when environmental feedback is absent, yet there is little consensus regarding how perceptual confidence is computed in the brain. Difficulty arises because confidence correlates with other factors, such as accuracy, response time (RT), or evidence quality. We investigated whether neural signatures of evidence accumulation during a perceptual choice predict subjective confidence independently of these factors. Using motion stimuli, a central-parietal positive-going electroencephalogram component (CPP) behaves as an accumulating decision variable that predicts evidence quality, RT, accuracy, and confidence (Experiment 1, N = 25 adults). When we psychophysically varied confidence while holding accuracy constant (Experiment 2, N = 25 adults), the CPP still predicted confidence. Statistically controlling for RT, accuracy, and evidence quality (Experiment 3, N = 24 adults), the CPP still explained unique variance in confidence. The results indicate that a predecision neural signature of evidence accumulation, the CPP, encodes subjective perceptual confidence in decision-making independent of task performance.

Adaptable reservoir computing: A paradigm for model-free data-driven prediction of critical transitions in nonlinear dynamical systems.

A problem in nonlinear and complex dynamical systems with broad applications is forecasting the occurrence of a critical transition based solely on data without knowledge about the system equations. When such a transition leads to system collapse, as often is the case, all the available data are from the pre-critical regime where the system still functions normally, making the prediction problem challenging. In recent years, a machine-learning based approach tailored to solving this difficult prediction problem, adaptable reservoir computing, has been articulated. This Perspective introduces the basics of this machine-learning scheme and describes representative results. The general setting is that the system dynamics live on a normal attractor with oscillatory dynamics at the present time and, as a bifurcation parameter changes into the future, a critical transition can occur after which the system switches to a completely different attractor, signifying system collapse. To predict a critical transition, it is essential that the reservoir computer not only learns the dynamical "climate" of the system of interest at some specific parameter value but, more importantly, discovers how the system dynamics changes with the bifurcation parameter. It is demonstrated that this capability can be endowed into the machine through a training process with time series from a small number of distinct, pre-critical parameter values, thereby enabling accurate and reliable prediction of the catastrophic critical transition. Three applications are presented: predicting crisis, forecasting amplitude death, and creating digital twins of nonlinear dynamical systems. Limitations and future perspectives are discussed.

Fostering scientific methods in simulations through symbolic regressions

Two-dimensional computer and tablet PC physics simulations have proved to be effective in helping students understand the fundamental principles of physics and related natural processes. However, the current approach to using these simulations tends to follow a repetitive cognitive and procedural pathway, regardless of the specific physical concepts being explored or software environment being used. This approach involves manipulating the simulation interface and collecting data through interaction with controls, widgets, or other contextual elements. Students then attempt to determine how these experimental measurements align with established laws, interactions, or mechanisms, as the teacher might have previously explained. We believe that this approach, while appropriate for education, obscures scientific processes, mainly related to the hypothetico-deductive model. To address this issue, we have developed a simple and adaptable computer environment that makes use of genetic algorithms (GAs) and symbolic regression to derive many of the basic laws of nature from the data collected by students using the popular physics education technology (PhET) simulations environment. Our proposal enables learners to observe how the order and relationships of mathematical tokens are routinely refined as new data points are added to the simulation setting. This iterative distillation technique can also be augmented with the interplay of dimensional analysis. In contrast with other more sophisticated artificial intelligence patterns, GA fit into the realm of grey box machine learning models. These type of evolutionary algorithms achieve the sought results by evolving mathematical models on each stage in an understandable way, which mimics the way scientific breakthroughs are accomplished (over the course of generations of researchers and based of prior knowledge). By implementing this innovative approach, we can provide students with a more authentic empirical experience that fosters a deeper understanding of the principles of science and scientific discovery. Field tests with students supporting this claim have also been carried out.

Reliable and adaptive computation offload strategy with load and cost coordination for edge computing

There are several important factors to consider in edge computing systems including latency, reliability, power consumption, and queue load. Task replication requires additional energy costs in mobile edge offloading scenarios based on master-slave replication for fault tolerance. Excessive task offloading may lead to a sharp increase in the total energy consumption of the system including replication costs. Conversely, new tasks cannot enter the waiting queue and are lost, resulting in reliability issues. This paper proposes an adaptive task offloading strategy for balancing the edge node queue load and offloading cost (Lyapunov and Differential Evolution based Offloading schedule strategy, LDEO). The LDEO strategy innovatively customizes the Lyapunov drift-plus-penalty function by incorporating replication redundancy offloading costs to establish a balance model between the queue load and offloading cost. The LDEO strategy computes the optimal offloading decisions with dynamic adjustment characteristics by integrating a low-complexity differential evolution method, aiming to find the optimal balance point that minimizes the offloading cost while maintaining reliability performance. The experimental results show that compared with the existing strategies, LDEO strategy effectively reduces the redundancy of fault tolerance cost and the waiting time under the condition of ensuring that the task will not be discarded over time. It stabilizes the queue length in a reasonable range, controls the waiting time and loss rate of tasks, reduces the extra energy consumption paid by replication redundancy, and effectively realizes the optimal balance under multiple conditions.

Retraction Note: An adaptive QoS computation for medical data processing in intelligent healthcare applications

Retraction Note: An adaptive QoS computation for medical data processing in intelligent healthcare applications

Erratum: “Adaptive Computations to Pressure Profile for Creeping Flow of a Non-Newtonian Fluid With Fluid Non-Constant Density Effects,” [ASME J. Heat Mass Transfer-Trans. ASME, 2022, 144(10), p. 103601; DOI: 10.1115/1.4055092

Abstract There are some typesetting errors on the Adaptive computations to pressure profile for creeping flow of a non-Newtonian fluid with fluid non-constant density effects, which proposed as follows:

Diffusion MRI harmonization via personalized template mapping.

One fundamental challenge in diffusion magnetic resonance imaging (dMRI) harmonization is to disentangle the contributions of scanner-related effects from the variable brain anatomy for the observed imaging signals. Conventional harmonization methods rely on establishing an atlas space to resolve anatomical variability and generate a unified inter-site mapping function. However, this approach is limited in accounting for the misalignment of neuroanatomy that still widely persists even after registration, especially in regions close to cortical boundaries. To overcome this challenge, we propose a personalized framework in this paper to more effectively address the confounding from the misalignment of neuroanatomy in dMRI harmonization. Instead of using a common template representing site-effects for all subjects, the main novelty of our method is the adaptive computation of personalized templates for both source and target scanning sites to estimate the inter-site mapping function. We integrate our method with the rotation invariant spherical harmonics (RISH) features to achieve the harmonization of dMRI signals between sites. In our experiments, the proposed approach is applied to harmonize the dMRI data acquired from two scanning platforms: Siemens Prisma and GE MR750 from the Adolescent Brain Cognitive Development dataset and compared with a state-of-the-art method based on RISH features. Our results indicate that the proposed harmonization framework achieves superior performance not only in reducing inter-site variations due to scanner differences but also in preserving sex-related biological variability in original cohorts. Moreover, we assess the impact of harmonization on the estimation of fiber orientation distributions and show the robustness of the personalized harmonization procedure in preserving the fiber orientation of original dMRI signals.

HARNESSING CLOUD OF THING AND FOG COMPUTING IN IRAQ: ADMINISTRATIVE INFORMATICS SUSTAINABILITY

This article provides an overview of cloud computing and fog computing, as well as a discussion of the potential applications of these technologies in Iraq. The ability of cloud computing to provide scalable and adaptable computer resources on demand has led to a significant uptick in interest in this computing model all around the world. However, fog computing improves cloud computing by moving computation to devices that are positioned on the edge of a network. This research investigates the up-to-date applications of cloud computing and fog computing in Iraq, as well as the challenges that have been faced and the potential applications of these technologies in the future, particularly in the areas of agriculture, transportation, and healthcare. The use of questionnaires in research will be the topic of discussion in this study. This is made up of two different parts that work separately. In the first part of our survey, we ask respondents questions about their level of expertise with direct and indirect cloud on object and fog computing. The remaining aspects of the investigation are dissected in Part 2 of the study. These inquiries are in accordance with concerns regarding the complexity of the implementation process, the size and culture of an organization, practicability, compliance with legislation, compatibility with current systems, and support from the government. The final open-ended inquiry of the survey will assist us in compiling a wide variety of opinions on the types of cloud-on-object and fog computing services that are required by the Iraqi government.

Combining contextuality and causality: a game semantics approach.

We develop an approach to combining contextuality with causality, which is general enough to cover causal background structure, adaptive measurement-based quantum computation and causal networks. The key idea is to view contextuality as arising from a game played between Experimenter and Nature, allowing for causal dependencies in the actions of both the Experimenter (choice of measurements) and Nature (choice of outcomes). This article is part of the theme issue 'Quantum contextuality, causality and freedom of choice'.

Multivariate adaptive regression splines-assisted approximate Bayesian computation for calibration of complex hydrological models

Abstract Approximate Bayesian computation (ABC) relaxes the need to derive explicit likelihood functions required by formal Bayesian analysis. However, the high computational cost of evaluating models limits the application of Bayesian inference in hydrological modeling. In this paper, multivariate adaptive regression splines (MARS) are used to expedite the ABC calibration process. The MARS model is trained using 6,561 runoff simulations generated by the soil and water assessment tool (SWAT) model and subsequently replaces the SWAT model to calculate the objective functions in ABC and multi-objective evolutionary algorithm (MOEA). In experiments, MARS can successfully reproduce the runoff time series simulations of the SWAT model at a low time cost, with a runoff variance determination coefficient of 0.90 as compared to the Monte Carlo method. MARS-assisted ABC can quickly and accurately estimate the parameter distributions of the SWAT model. The comparison of ABC with non-Bayesian MOEAs helps in the selection of an appropriate calibration approach.

Grouping Boundary Proposals for Fast Interactive Image Segmentation.

Geodesic models are known as an efficient tool for solving various image segmentation problems. Most of existing approaches only exploit local pointwise image features to track geodesic paths for delineating the objective boundaries. However, such a segmentation strategy cannot take into account the connectivity of the image edge features, increasing the risk of shortcut problem, especially in the case of complicated scenario. In this work, we introduce a new image segmentation model based on the minimal geodesic framework in conjunction with an adaptive cut-based circular optimal path computation scheme and a graph-based boundary proposals grouping scheme. Specifically, the adaptive cut can disconnect the image domain such that the target contours are imposed to pass through this cut only once. The boundary proposals are comprised of precomputed image edge segments, providing the connectivity information for our segmentation model. These boundary proposals are then incorporated into the proposed image segmentation model, such that the target segmentation contours are made up of a set of selected boundary proposals and the corresponding geodesic paths linking them. Experimental results show that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.

An Adaptive Hybrid Brain Computer Interface for Hand Function Rehabilitation of Stroke Patients.

Motor imagery (MI) based brain computer interface (BCI) has been extensively studied to improve motor recovery for stroke patients by inducing neuroplasticity. However, due to the lower spatial resolution and signal-to-noise ratio (SNR) of electroencephalograph (EEG), MI based BCI system that involves decoding hand movements within the same limb remains lower classification accuracy and poorer practicality. To overcome the limitations, an adaptive hybrid BCI system combining MI and steady-state visually evoked potential (SSVEP) is developed to improve decoding accuracy while enhancing neural engagement. On the one hand, the SSVEP evoked by visual stimuli based on action-state flickering coding approach significantly improves the recognition accuracy compared to the pure MI based BCI. On the other hand, to reduce the impact of SSVEP on MI due to the dual-task interference effect, the event-related desynchronization (ERD) based neural engagement is monitored and employed for feedback in real-time to ensure the effective execution of MI tasks. Eight healthy subjects and six post-stroke patients were recruited to verify the effectiveness of the system. The results showed that the four-class gesture recognition accuracies of healthy individuals and patients could be improved to 94.37 ± 4.77% and 79.38 ± 6.26%, respectively. Moreover, the designed hybrid BCI could maintain the same degree of neural engagement as observed when subjects solely performed MI tasks. These phenomena demonstrated the interactivity and clinical utility of the developed system for the rehabilitation of hand function in stroke patients.