Classification Of Tasks Research Articles

LDER: a classification framework based on ERP enhancement in RSVP task

Objective. Rapid serial visual presentation (RSVP) based on electroencephalography (EEG) has been widely used in the target detection field, which distinguishes target and non-target by detecting event-related potential (ERP) components. However, the classification performance of the RSVP task is limited by the variability of ERP components, which is a great challenge in developing RSVP for real-life applications. Approach. To tackle this issue, a classification framework based on the ERP feature enhancement to offset the negative impact of the variability of ERP components for RSVP task classification named latency detection and EEG reconstruction was proposed in this paper. First, a spatial-temporal similarity measurement approach was proposed for latency detection. Subsequently, we constructed a single-trial EEG signal model containing ERP latency information. Then, according to the latency information detected in the first step, the model can be solved to obtain the corrected ERP signal and realize the enhancement of ERP features. Finally, the EEG signal after ERP enhancement can be processed by most of the existing feature extraction and classification methods of the RSVP task in this framework. Main results. Nine subjects were recruited to participate in the RSVP experiment on vehicle detection. Four popular algorithms (spatially weighted Fisher linear discrimination-principal component analysis (PCA), hierarchical discriminant PCA, hierarchical discriminant component analysis, and spatial-temporal hybrid common spatial pattern-PCA) in RSVP-based brain–computer interface for feature extraction were selected to verify the performance of our proposed framework. Experimental results showed that our proposed framework significantly outperforms the conventional classification framework in terms of area under curve, balanced accuracy, true positive rate, and false positive rate in four feature extraction methods. Additionally, statistical results showed that our proposed framework enables better performance with fewer training samples, channel numbers, and shorter temporal window sizes. Significance. As a result, the classification performance of the RSVP task was significantly improved by using our proposed framework. Our proposed classification framework will significantly promote the practical application of the RSVP task.

CGAN-rIRN: a data-augmented deep learning approach to accurate classification of mental tasks for a fNIRS-based brain-computer interface.

Functional near-infrared spectroscopy (fNIRS) is increasingly used to investigate different mental tasks for brain-computer interface (BCI) control due to its excellent environmental and motion robustness. Feature extraction and classification strategy for fNIRS signal are essential to enhance the classification accuracy of voluntarily controlled BCI systems. The limitation of traditional machine learning classifiers (MLCs) lies in manual feature engineering, which is considered as one of the drawbacks that reduce accuracy. Since the fNIRS signal is a typical multivariate time series with multi-dimensionality and complexity, it makes the deep learning classifier (DLC) ideal for classifying neural activation patterns. However, the inherent bottleneck of DLCs is the requirement of substantial-scale, high-quality labeled training data and expensive computational resources to train deep networks. The existing DLCs for classifying mental tasks do not fully consider the temporal and spatial properties of fNIRS signals. Therefore, a specifically-designed DLC is desired to classify multi-tasks with high accuracy in fNIRS-BCI. To this end, we herein propose a novel data-augmented DLC to accurately classify mental tasks, which employs a convolution-based conditional generative adversarial network (CGAN) for data augmentation and a revised Inception-ResNet (rIRN) based DLC. The CGAN is utilized to generate class-specific synthetic fNIRS signals to augment the training dataset. The network architecture of rIRN is elaborately designed in accordance with the characteristics of the fNIRS signal, with serial multiple spatial and temporal feature extraction modules (FEMs), where each FEM performs deep and multi-scale feature extraction and fusion. The results of the paradigm experiments show that the proposed CGAN-rIRN approach improves the single-trial accuracy for mental arithmetic and mental singing tasks in both the data augmentation and classifier, as compared to the traditional MLCs and the commonly used DLCs. The proposed fully data-driven hybrid deep learning approach paves a promising way to improve the classification performance of volitional control fNIRS-BCI.

Deep CNN‐based classification of motor imagery tasks from EEG signals using 2D wavelet transformed images of adaptively reconstructed signals from MVMD decomposed modes

AbstractBrain–computer interfaces (BCI) have begun to revolutionize many aspects of human life, ranging from health to smart living and communication devices. Therefore, BCI technologies require accurate recognition and classification systems of the brain responses to a variety of motor imagery (MI) movements through electroencephalogram (EEG) signals. Nowadays, deep learning models have received a lot of interest for learning features and classifying numerous kinds of data. However, it has not been thoroughly investigated for EEG signal classification. In this study, to reach an improved performance in MI‐EEG signal classification, we proposed a new strategy based on continuous wavelet transform (CWT)‐based time‐frequency maps to generate two‐dimensional (2D) EEG images of adaptively reconstructed signals from the extracted multivariate mode decomposition (MVMD) modes. In the next step, the extracted signals are projected in the new space using the proposed multiclass common spatial pattern (MCCSP) filtering. The resulting images are then fed to the convolutional neural network (CNN) architectures (AlexNet and LeNet). The proposed framework has the benefit of achieving high classification accuracy to be attained even with a significant amount of input data. LeNet and AlexNet reach the best average accuracy rates of 95.33% and 93.66% on dataset 1 from BCI competition IV and the results on dataset 2a from competition IV are more promising than the current state of the arts. Our results depict that MI‐EEG task recognition using image classification approaches, along with CNNs, is as comparable or even superior to other existing traditional approaches and provides high potential for upcoming research.

A neurophysiological approach to the distinction between motor and cognitive skills: a functional magnetic resonance imaging study.

This study investigated the neurophysiological differences underpinning motor and cognitive skills by measuring the brain activity via functional magnetic resonance imaging. Twenty-five healthy adults (11 women, 25.8 ± 3.5 years of age) participated in the study. We developed three types of tasks, namely, simple motor task (SMT), complex motor task (CMT), and cognitive task (CT), using two-dimensional images of Gomoku, a traditional game known as five in a row. When shown the stimulus, participants were instructed to identify the best spot to win the game and to perform motor imagery of placing the stone for the SMT and CMT but not for the CT. Accordingly, we found significant activation from the CMT minus SMT contrast in the dorsolateral prefrontal cortex, posterior parietal cortex, precentral gyrus, and superior frontal cortex, which reflected increased visuospatial attention, working memory, and motor planning. From the CT minus SMT contrast, we observed significant activation in the left caudate nucleus, right medial prefrontal cortex, and right primary somatosensory cortex, responsible for visuospatial working memory, error detection, and cognitive imagery, respectively. The present findings indicate that adopting a conventional classification of cognitive and motor tasks focused on the extent of decision making and motor control involved in task performance might not be ideal.

Deep Learning-Based Approach for Classification Of Mental Tasks From Electroencephalogram Signals

Background and Objective: Electroencephalography (EEG) analysis is an important tool for neuroscience, brain-computer interface studies, and biomedical studies. The primary purpose of Brain-Computer Interface (BCI) studies is to establish communication between disabled individuals, other individuals, and machines with brain signals. Interpreting and classifying the brain's response during different cognitive tasks will contribute to brain-computer interface studies. Therefore, in this study, five cognitive tasks were classified from EEG signals. Material and Methods: In this study, five neuropsychological tests (Öktem Verbal Memory Processes Test, WMS-R Visual Memory Subtest, Digit Span Test, Corsi Block Test, and Stroop Test) were administered to 30 healthy individuals. The tests assess the volunteers' abilities in verbal memory, visual memory, attention, concentration, working memory, and reaction time. The EEG signals were recorded while the tests were administered to the volunteers. The tests were classified using two different deep learning algorithms, 1D Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), from the recorded EEG signals. Results: When the success of the tests was evaluated, classification success was achieved with an accuracy of 88.53% in the CNN deep learning algorithm and 89.80% in the LSTM deep algorithm. Precision, recall, and F1-score values for CNN were calculated at 0.88, 0.87, and 0.87, respectively, while precision, recall, and f1-score values for the LSTM network were obtained at 0.90, 0.89, and 0.89. Conclusion: Following the findings of the present study, five different cognitive tasks were able to be classified with high accuracy from EEG signals using deep learning algorithms.

Automated colonoscopy withdrawal phase duration estimation using cecum detection and surgical tasks classification.

Colorectal cancer is the third most common type of cancer with almost two million new cases worldwide. They develop from neoplastic polyps, most commonly adenomas, which can be removed during colonoscopy to prevent colorectal cancer from occurring. Unfortunately, up to a quarter of polyps are missed during colonoscopies. Studies have shown that polyp detection during a procedure correlates with the time spent searching for polyps, called the withdrawal time. The different phases of the procedure (cleaning, therapeutic, and exploration phases) make it difficult to precisely measure the withdrawal time, which should only include the exploration phase. Separating this from the other phases requires manual time measurement during the procedure which is rarely performed. In this study, we propose a method to automatically detect the cecum, which is the start of the withdrawal phase, and to classify the different phases of the colonoscopy, which allows precise estimation of the final withdrawal time. This is achieved using a Resnet for both detection and classification trained with two public datasets and a private dataset composed of 96 full procedures. Out of 19 testing procedures, 18 have their withdrawal time correctly estimated, with a mean error of 5.52 seconds per minute per procedure.

Locally private estimation of conditional probability distribution for random forest in multimedia applications

The application of artificial intelligence models to raw multimedia data is susceptible to various data inference attacks, posing a significant risk in terms of sensitive input information leakage. Most of the existing studies on privacy-preserving multimedia applications based on artificial intelligence, focus on a single intelligent model and thus have various limitations. In this paper, we attempt to directly perturb the core component of many multimedia intelligent models in Bayesian networks and deep learning. That is, we apply conditional probability distribution estimation to guarantee the privacy of the models. At first, we present the formal problem formulation of private conditional probability distribution estimation and apply it to random forest for task classification in multimedia applications. Then, we design a simple perturbation approach called NaivePrivDistEst, to add noise to all the elements of probability estimation in random forest. Next, we present an improved approach called FastLRG, that utilizes the taxonomy tree to discretize the continuous attributes, thereby combining the attribute features to improve the prediction accuracy of random forest. Finally, we perform extensive experiments to evaluate the performance of random forest based on the proposed estimation algorithms. The experimental results indicate that the proposed models have better performance compared with existing private decision trees.

Divergent Selection Task Offloading Strategy for Connected Vehicles Based on Incentive Mechanism

With the improvements in the intelligent level of connected vehicles (CVs), travelers can enjoy services such as self-driving, self-parking and audiovisual entertainment inside the vehicle, which place extremely high demands on the computing power of onboard systems (OBSs). However, the arithmetic power of a single CV often cannot meet the diverse service demands of the in-vehicle system. As a new computing paradigm, task offloading based on vehicular edge computing has significant advantages in remedying the shortcomings of single-CV computing power and balancing the allocation of computing resources. This paper studied the computational task offloading of high-speed connected vehicles without the help of roadside edge servers in certain geographic areas. User vehicles (UVs) with insufficient computing power offload some of their computational tasks to nearby CVs with abundant resources. We explored the high-speed driving model and task classification model of CVs to refine the task offloading process. Additionally, inspired by game theory, we designed a divergent selection task offloading strategy based on an incentive mechanism (DSIM), in which we balanced the interests of both the user vehicle and service vehicles. CVs that contribute resources are rewarded to motivate more CVs to join. A DSIM algorithm based on a divergent greedy algorithm was introduced to maximize the total rewards of all volunteer vehicles while respecting the will of both the user vehicle and service vehicles. The experimental simulation results showed that, compared with several existing studies, our approach can always obtain the highest reward for service vehicles and lowest latency for user vehicles.

A Systematic Review on the Visualization of Avatars and Agents in AR & VR displayed using Head-Mounted Displays.

Augmented Reality (AR) and Virtual Reality (VR) are pushing from the labs towards consumers, especially with social applications. These applications require visual representations of humans and intelligent entities. However, displaying and animating photo-realistic models comes with a high technical cost while low-fidelity representations may evoke eeriness and overall could degrade an experience. Thus, it is important to carefully select what kind of avatar to display. This article investigates the effects of rendering style and visible body parts in AR and VR by adopting a systematic literature review. We analyzed 72 papers that compare various avatar representations. Our analysis includes an outline of the research published between 2015 and 2022 on the topic of avatars and agents in AR and VR displayed using head-mounted displays, covering aspects like visible body parts (e.g., hands only, hands and head, full-body) and rendering style (e.g., abstract, cartoon, realistic); an overview of collected objective and subjective measures (e.g., task performance, presence, user experience, body ownership); and a classification of tasks where avatars and agents were used into task domains (physical activity, hand interaction, communication, game-like scenarios, and education/training). We discuss and synthesize our results within the context of today's AR and VR ecosystem, provide guidelines for practitioners, and finally identify and present promising research opportunities to encourage future research of avatars and agents in AR/VR environments.

Classification of Educational Tasks From the Mother Language

In the article, the priority of the development of practical speech skills in language education today, the inclusion of pragmatic competence in the composition of speech competences, starting from school education in students, the ability to speak in accordance with the speech situation, becoming a participant in dialogue, polylogues, being able to engage in polemics with interlocutors and justifying one's opinion it is thought about training competence.

Task Scheduling Scheme for Mobile Edge Computing via Bayesian Classifier

The enormous computing tasks in the Mobile Edge Computing (MEC) beget challenges correlated with cost, energy consumption and quality of service. However, existing studies are not optimized enough for MEC in terms of the selection of task classification and scheduling schemes. Inspired by spam classification idea, a novel task scheduling scheme is proposed for MEC via Bayesian Classifier. The MEC tasks are first categorized into three priority categories using Naive Bayes. In addition, the priority-based classification task scheduling (PCTS) scheme is proposed to schedule the classified tasks with different priorities. Finally, the experimental evaluation is conducted using three metrics that include latency, processing time, and energy consumption. Simulation results show that the proposed scheme outperforms the baseline schemes in accordance with completion time and throughout rate.

Examining whether adults with autism spectrum disorder encounter multiple problems in theory of mind: a study based on meta-analysis.

Theory of mind (ToM) represents a complex ability, while persons with autism spectrum disorder (ASD) encounter difficulties in the processing of ToM. The present ToM-focused studies on adults with ASD report inconsistent results, possibly owing to the differences between tasks. For instance, different ToM-related tasks involve different cognitive abilities, but the development of these cognitive abilities is different among adults with ASD, thereby leading to different behaviors by the same individual with ASD in different tasks. Therefore, it is of vital significance to explore the potential reasons for inconsistencies in the existing studies based on the task classification perspective. Hence, this study primarily reviews the existing ToM tasks used in studies on adults with ASD; afterward, based on the forms and characteristics of the task, the current ToM tasks are classified into four categories-reading comprehension, perceptual scene comprehension, comprehensive scene comprehension , and self-other processing. Subsequently, a meta-analysis is undertaken to determine the difference in each ToM task category between the ASD group and the typically developing (TD) group. As a result, 110 research papers (including 3,205 adults with ASD and 3,675 TD adults) that fulfilled the stated criteria are examined in this study. The study findings suggest that adults with ASD demonstrate worse performance in terms of all four ToM task categories as compared to TD adults. Furthermore, compared with tasks of self-other processing and perceptual scene comprehension, adults with ASD perform worse in reading comprehension and comprehensive scene comprehension. This shows that the differences between tasks may exert a potential influence on the study results. Future studies should focus on different abilities involved in ToM processing and the choice of ToM tasks, in order to elucidate the critical problems of ToM in adults with ASD.

Investigating Feature Selection Techniques to Enhance the Performance of EEG-Based Motor Imagery Tasks Classification

Analyzing electroencephalography (EEG) signals with machine learning approaches has become an attractive research domain for linking the brain to the outside world to establish communication in the name of the Brain-Computer Interface (BCI). Many researchers have been working on developing successful motor imagery (MI)-based BCI systems. However, they still face challenges in producing better performance with them because of the irrelevant features and high computational complexity. Selecting discriminative and relevant features to overcome the existing issues is crucial. In our proposed work, different feature selection algorithms have been studied to reduce the dimension of multiband feature space to improve MI task classification performance. In the procedure, we first decomposed the MI-based EEG signal into four sets of the narrowband signal. Then a common spatial pattern (CSP) approach was employed for each narrowband to extract and combine effective features, producing a high-dimensional feature vector. Three feature selection approaches, named correlation-based feature selection (CFS), minimum redundancy and maximum relevance (mRMR), and multi-subspace randomization and collaboration-based unsupervised feature selection (SRCFS), were used in this study to select the relevant and effective features for improving classification accuracy. Among them, the SRCFS feature selection approach demonstrated outstanding performance for MI classification compared to other schemes. The SRCFS is based on the multiple k-nearest neighbour graphs method for learning feature weight based on the Laplacian score and then discarding the irrelevant features based on the weight value, reducing the feature dimension. Finally, the selected features are fed into the support vector machines (SVM), linear discriminative analysis (LDA), and multi-layer perceptron (MLP) for classification. The proposed model is evaluated with two benchmark datasets, namely BCI Competition III dataset IVA and dataset IIIB, which are publicly available and mainly used to recognize the MI tasks. The LDA classifier with the SRCFS feature selection algorithm exhibits better performance. It proves the superiority of our proposed study compared to the other state-of-the-art BCI-based MI task classification systems.

Effect of Local Network Characteristics on the Performance of the SSVEP Brain-Computer Interface

ObjectiveFor decades, a great deal of interest in investigating brain network functional connective features has arisen in brain-computer interfaces (BCIs) based on steady-state visual evoked potentials (SSVEPs). Traditional decoding algorithms, for example, canonical correlation analysis (CCA), only consider the inherent properties of each channel in terms of feature extraction for the single channel electroencephalogram (EEG) signal, with inadequate features that cannot fully utilize the information transmitted by the brain. Material and methodsThis paper proposes a fused feature extraction method, CCA-DTF, which combines CCA with a direct transfer function (DTF) to construct local brain network features with seven leads in the occipital region. First, the features extracted by the CCA algorithm were combined with these features extracted by DTF to analyze the EEG data from 20 subjects. Then, two methods, support vector machine (SVM) and random forest (RF), were used in constructing the classifiers for the four tasks classification of the SSVEP-BCI. ResultsThe experimental results showed that incorporating local network features (extracted from DTF or Pearson correlation coefficient) can effectively improve the classification average accuracy and the information transfer rate (ITR) of SSVEP, not only for SVM but also for the ensemble method RF. In particular, CCA-DTF plus SVM obtained a 94.52% classification average accuracy and a 49.23 bits/min ITR in a time window of 2 seconds. The performance was 5.57% and 8.01 bits/min higher than those of traditional CCA plus SVM, respectively. ConclusionThe proposed feature extraction method based on local network features is robust for improving the performance of SSVEP-BCI significantly, which has a perspective of being used in neural rehabilitation engineering field.

Learning Implicit and Explicit Multi-task Interactions for Information Extraction

Information extraction aims at extracting entities, relations, and so on, in text to support information retrieval systems. To extract information, researchers have considered multitask learning (ML) approaches. The conventional ML approach learns shared features across tasks, with the assumption that these features capture sufficient task interactions to learn expressive shared representations for task classification. However, such an assumption is flawed in different perspectives. First, the shared representation may contain noise introduced by another task; tasks coupled for multitask learning may have different complexities but this approach treats all tasks equally; the conventional approach has a flat structure that hinders the learning of explicit interactions. This approach, however, learns implicit interactions across tasks and often has a generalization ability that has benefited the learning of multitasks. In this article, we take advantage of implicit interactions learned by conventional approaches while alleviating the issues mentioned above by developing a Recurrent Interaction Network with an effective Early Prediction Integration (RIN-EPI) for multitask learning. Specifically, RIN-EPI learns implicit and explicit interactions across two different but related tasks. To effectively learn explicit interactions across tasks, we consider the correlations among the outputs of related tasks. It is, however, obvious that task outputs are unobservable during training, so we leverage the predictions at intermediate layers (referred to as early predictions) as proxies as well as shared features across tasks to learn explicit interactions through attention mechanisms and sequence learning models. By recurrently learning explicit interactions, we gradually improve predictions for the individual tasks in the multitask learning. We demonstrate the effectiveness of RIN-EPI on the learning of two mainstream multitasks for information extraction: (1) entity recognition and relation classification and (2) aspect and opinion term co-extraction. Extensive experiments demonstrate the effectiveness of the RIN-EPI architecture, where we achieve state-of-the-art results on several benchmark datasets.

Deep reinforcement learning for resource allocation of mobile communication systems with device‐to‐device underlay

SummaryOver the past few decades, the number of users and services of the mobile communications system has considerably increased, and since its essential resources such as spectrum and energy are limited, their optimization has drawn particular interest. Concomitantly, artificial intelligence (AI) techniques have advanced and their applications have been expanded, including problems of classification, regression, and optimization of tasks of mobile communications systems. Regarding fifth and sixth generations of such systems, the insertion of AI is foreseen toward the allocation of available resources. The present study applied two recently proposed techniques based on deep reinforcement learning algorithms (viz., deep deterministic policy gradient [DDPG] and twin‐delayed DDPG [TD3]), for the power control and spectrum allocation of a mobile communications system with device‐to‐device (D2D) underlay communications. The results show that both algorithms have superior performance to the three algorithms used for comparison: A random algorithm, a greedy algorithm, and REINFORCE, a classical reinforcement learning algorithm. Furthermore, the results show the proposed algorithms have good generalization capability and performed the allocation intelligently, taking into account the relationship between distances separating devices and interference between communications. The results also proved robust in terms of small variations in input data and noise.

Behavior and Task Classification Using Wearable Sensor Data: A Study across Different Ages.

In this paper, we face the problem of task classification starting from physiological signals acquired using wearable sensors with experiments in a controlled environment, designed to consider two different age populations: young adults and older adults. Two different scenarios are considered. In the first one, subjects are involved in different cognitive load tasks, while in the second one, space varying conditions are considered, and subjects interact with the environment, changing the walking conditions and avoiding collision with obstacles. Here, we demonstrate that it is possible not only to define classifiers that rely on physiological signals to predict tasks that imply different cognitive loads, but it is also possible to classify both the population group age and the performed task. The whole workflow of data collection and analysis, starting from the experimental protocol, data acquisition, signal denoising, normalization with respect to subject variability, feature extraction and classification is described here. The dataset collected with the experiments together with the codes to extract the features of the physiological signals are made available for the research community.

An integrated evaluation approach of wearable lower limb exoskeletons for human performance augmentation

Wearable robots have been growing exponentially during the past years and it is crucial to quantify the performance effectiveness and to convert them into practical benchmarks. Although there exist some common metrics such as metabolic cost, many other characteristics still needs to be presented and demonstrated. In this study, we developed an integrated evaluation (IE) approach of wearable exoskeletons of lower limb focusing on human performance augmentation. We proposed a novel classification of trial tasks closely related to exoskeleton functions, which were divided into three categories, namely, basic trial at the preliminary phase, semi-reality trial at the intermediate phase, and reality trial at the advanced phase. In the present study, the IE approach has been exercised with a subject who wore an active power-assisted knee (APAK) exoskeleton with three types of trial tasks, including walking on a treadmill at a certain angle, walking up and down on three-step stairs, and ascending in 11-storey stairs. Three wearable conditions were carried out in each trial task, i.e. with unpowered exoskeleton, with powered exoskeleton, and without the exoskeleton. Nine performance indicators (PIs) for evaluating performance effectiveness were adopted basing on three aspects of goal-level, task-based kinematics, and human–robot interactions. Results indicated that compared with other conditions, the powered APAK exoskeleton make generally lesser heart rate (HR), Metabolic equivalent (METs), biceps femoris (BF) and rectus femoris (RF) muscles activation of the subject at the preliminary phase and intermediate phase, however, with minimal performance augmentation at advanced phase, suggesting that the APAK exoskeleton is not suitable for marketing and should be further improved. In the future, continuous iterative optimization for the IE approach may help the robot community to attain a comprehensive benchmarking methodology for robot-assisted locomotion more efficiently.

Classification of primitive manufacturing tasks from filtered event data

Collaborative robots are increasingly present in industry to support human activities. However, to make the human–robot collaborative process more effective, there are several challenges to be addressed. Collaborative robotic systems need to be aware of the human activities to (1) anticipate collaborative/assistive actions, (2) learn by demonstration, and (3) activate safety procedures in shared workspace. This study proposes an action classification system to recognize primitive assembly tasks from human motion events data captured by a Dynamic and Active-pixel Vision Sensor (DAVIS). Several filters are compared and combined to remove event data noise. Task patterns are classified from a continuous stream of event data using advanced deep learning and recurrent networks to classify spatial and temporal features. Experiments were conducted on a novel dataset, the dataset of manufacturing tasks (DMT22), featuring 5 classes of representative manufacturing primitives (PickUp, Place, Screw, Hold, Idle) from 5 participants. Results show that the proposed filters remove about 65% of all events (noise) per recording, conducting to a classification accuracy up to 99,37% for subjects that trained the system and 97.08% for new subjects. Data from a left-handed subject were successfully classified using only right-handed training data. These results are object independent.

Low-complex resource mapping heuristics for mobile and iot workloads on NoC-HMPSoC architecture

Network-on-chip-based heterogeneous multiprocessor system-on-a chip (NoC-HMPSoC) a single board computer is extensively utilized in many real-time applications such as mobile edge computing (MEC), cyber-physical systems, smart phones, driverless vehicles, and real-time embedded systems due to its flexible communication architecture, switching network, excellent performance, and energy efficiency. Despite its benefits, task scheduling and appropriate resource allocation is still an non-polynomial hard problem. NoC-HMPSoC includes heterogeneous processors along with interconnected communication routing structure which creates more complexity in task and resource scheduling. In this paper, a new task classification and low-complex resource mapping heuristics are developed to deal with mixed-critical workloads execution targeted on NoC-HMPSoC architecture. MethodologyTo minimize runtime scheduling cost, the deadline-based task classification (DBTC) heuristic divides the workload into three distinct classes depending on their deadline and inter-arrival limitations. The mixed-integer linear programming (MILP) statistical model, which improved task miss ratio with greater time complexity, is used to schedule the categorized task sets. Static resource mapping (SRM) and load-based dynamic resource mapping (LBDRM) heuristics are created to allocate mixed-critical activities into NoC-HMPSoC in order to overcome this. The suggested framework is a list-based scheduler that processes tasks on an unchanging processor using the SRM algorithm and prioritizes them depending on the tasks' earliest finish times. The LBDRM technique is then used to dynamically reallocate mixed-critical task groups among heterogeneous processors based on the load factor and task utilization factor. The time complexity of DBTC algorithm is O(log n) where 'n' is the task nodes, and the time complexity of the proposed scheduling heuristics are O(n2 * m) for larger graphs. The proposed framework performs classification, mapping, and scheduling in an integrated manner that is experimentally evaluated on the Samsung Exynos 5422 NoC-HMPSoC and Intel Xeon cloud server for E3S sysmark mobile benchmark workloads. Averagely 65%, 33%, is improved in execution time reduction and 45%, 36% reduction in energy consumption and 56%, 32% than JRFS-HRFS and ARSH-FATI methods.