Independent Component Analysis Research Articles

Aberrant dynamic functional network connectivity in patients with diffuse axonal injury

Diffuse axonal injury (DAI) results in aberrant functional connectivity and is significantly linked to cognitive impairment. Nevertheless, the network mechanisms influencing neurocognitive function following DAI remain unclear. This study aimed to examine the characteristics of static and dynamic functional network connectivity (FNC) in patients with DAI. Resting-state functional magnetic resonance imaging data were collected from 26 patients with DAI and 27 healthy controls. Resting-state networks were extracted using independent component analysis. We evaluated the connectivity strength through spatial maps and static FNC, and then further dynamic properties were identified using a sliding time-window approach and k-means clustering, and investigated their associations with clinical variables. Patients with DAI showed stronger intra-network spatial maps in the default mode network and subcortical network than healthy controls, but static inter-network functional connectivity remained stable. Furthermore, three recurring states for dynamic connectivity were identified in all participants, and state 1 occurred most frequently in patients with DAI and exhibited higher fractional time, and as well as longer mean dwell time, which was positively associated with MMSE scores. Meanwhile, patients with DAI exhibited mostly increased functional connectivity strength of dynamic FNC in all states, particularly within the default mode network and visual network. These findings suggest that patients with DAI are characterized by altered dynamic FNC and temporal properties, which provide distinct complementary information different from static functional connectivity, and new insights into the neural pathophysiology of DAI associated with cognitive impairment.

Brain functional alternation in patients with systemic sclerosis: a resting-state functional magnetic resonance imaging study

BackgroundNeuropsychiatric manifestations, such as cognitive impairment, are relatively prevalent in systemic sclerosis (SSc) patients. This study aimed to investigate the resting state (RS) functional alternations of SSc patients and the potential influenced factors.MethodsForty-four SSc patients (mean age, 46.3 ± 11.4 years; 40 females) and 19 age and sex comparable healthy volunteers (mean age, 42.6 ± 11.3 years; 16 females) were recruited and underwent RS functional MR imaging (fMRI) and neuropsychological assessments. Functional segregation analysis was performed to calculate the amplitude of low frequency fluctuation (ALFF) and regional homogeneity (ReHo). Functional integration analysis was conducted using group independent component analysis to calculate intra-network and inter-network functional connectivity (FC). The fMRI measurements were compared between SSc patients and healthy volunteers using voxel-based pairwise two-sample t-tests. The correlations between clinical characteristics and fMRI measurements were also analyzed.ResultsCompared to healthy volunteers, SSc patients exhibited significantly decreased ALFF and increased ReHo (all P < 0.01, FWE corrected). SSc patients predominantly showed decreased intra-network and inter-network FC in the auditory network, visual network, default mode network, frontoparietal network and attention network (intra-network FC: P < 0.01, uncorrected, cluster size > 30; inter-network FC: P < 0.05, FDR correction). Furthermore, clinical characteristics including disease duration (r value ranged from − 0.31 to 0.36), elevated erythrocyte sedimentation rate (r = 0.35), Montreal Cognitive Assessment score (r = 0.43), and Hamilton Depression Scale score (r = -0.40) were significantly associated with fMRI measurements (all P < 0.05).ConclusionsSpontaneous activity and functional connectivity alternations can be seen in SSc patients, which are partially associated with neuropsychiatric manifestations and tend to aggravate with disease duration.

Intra- and inter-network connectivity abnormalities associated with surgical outcomes in degenerative cervical myelopathy patients: a resting-state fMRI study

Resting-state functional MRI (fMRI) has revealed functional changes at the cortical level in degenerative cervical myelopathy (DCM) patients. The aim of this study was to systematically integrate static and dynamic functional connectivity (FC) to unveil abnormalities of functional networks of DCM patients and to analyze the prognostic value of these abnormalities for patients using resting-state fMRI. In this study, we collected clinical data and fMRI data from 44 DCM patients and 39 healthy controls (HC). Independent component analysis (ICA) was performed to investigate the group differences of intra-network FC. Subsequently, both static and dynamic FC were calculated to investigate the inter-network FC alterations in DCM patients. k-means clustering was conducted to assess temporal properties for comparison between groups. Finally, the support vector machine (SVM) approach was performed to predict the prognosis of DCM patients based on static FC, dynamic FC, and fusion of these two metrics. Relative to HC, DCM patients exhibited lower intra-network FC and higher inter-network FC. DCM patients spent more time than HC in the state in which both patients and HC were characterized by strong inter-network FC. Both static and dynamic FC could successfully classify DCM patients with different surgical outcomes. The classification accuracy further improved after fusing the dynamic and static FC for model training. In conclusion, our findings provide valuable insights into the brain mechanisms underlying DCM neuropathology on the network level.

Wearable device data-driven athlete injury detection and rehabilitation monitoring algorithm

In recent years, sports wearable technology has completely changed the way athletes prepare, compete, and recover. Wearable technology has a lot to offer in the rehabilitation process, which is essential to an athlete’s return to their best performance. Wearable devices for athlete injury detection pose potential challenges like data quality, security, and privacy, impacting accuracy, reliability, and effectiveness. To solve these problems, an innovative injury detection and rehabilitation monitoring (IDRM) system was proposed for athletes. By employing an adjustable recurrent neural network (ARNN) to detect anomalies in injury risks such as abnormal joint movements in athletes. In this study, biomechanics data was collected from sports athletes through wearable devices, and the wearable system provided feedback to the user. A redefined convolutional neural network (RCNN) was utilized to monitor the rehabilitation process. This system tracks athlete’s rehabilitation progress and ensures that progress monitors were performed correctly, and the system, feasibility was evaluated on 10 healthy subjects performing 4 different rehabilitation exercises. Each exercise was performed four times monitoring and validation. The data was preprocessed using a Gaussian filter to remove noise from the obtained data. Then the features are extracted using independent component analysis (ICA) for dimensionality reduction from preprocessed data. The proposed method is implemented using Python software. In comparative analysis, the performance of ARNN showed high performance, with an F1-measure of 91.6%, accuracy of 93.5%, recall of 92.8%, and precision of 91.4%. With a 95% accuracy rate, 98% F1 measure, 94% precision, and 93% recall, the RCNN model functioned effectively. The result showed the proposed method achieved better performance in athlete injury detection and accurately recognizing all rehabilitation monitoring. This study provides a complete approach to athlete health management by highlighting the integration of rehabilitation monitoring and injury detection into an overall structure.

Distinct Neural Mechanisms Underlying Dual-Task Priority During Gait Across Cognitive and Motor Networks.

Background: Prioritization strategy during gait significantly influences gait performance and successful gait relies on interactions between cognitive and motor functions. This study aimed to examine the within- and between-network connectivities of cognitive and motor networks associated with dual-task priority during gait. Methods: Twenty-nine healthy individuals (66.86 ± 8.53 years) underwent the timed-up-and-go (TUG) test alone, TUG with a cognitive task, and the cognitive task alone. The cognitive task involved sequentially subtracting three from a random number between 50 and 100. The resting-state functional magnetic resonance imaging was acquired on the same day. Using independent component analysis, the dorsal attention network (DAN), frontoparietal network (FPN), primary motor network (PM), and lateral motor network were assessed. The participants were divided into cognitive and motor priority groups based on the modified attention allocation index (mAAI). Group comparisons of within- and between-network connectivity were conducted using permutation tests. Additionally, correlation analysis was employed to investigate the association between-network connectivity and task priority. Results: The cognitive priority group showed cognitive dual-task facilitation. In comparison to the motor priority group, they also showed comparable motor dual-task costs and lower combined dual-task costs. They exhibited increased within-network connectivity in the left FPN and enhanced between-network connectivity between the right FPN and both the DAN and PM. These between-network connectivities were negatively correlated with mAAI scores. Conclusion: The results suggest distinct neural mechanisms across cognitive and motor networks based on individuals' dual-task strategies. This may have implications for understanding gait performance in complex contexts.

Changes in resting-state functional connectivity of large-scale brain networks in bulimia nervosa: evidence from causal analysis.

Bulimia nervosa (BN) has been observationally linked to the functional connectivity (FC) of large-scale brain networks, but the biological mechanisms remain unclear. This study used two-sample Mendelian randomization (MR) with genetic variations as instrumental variables (IVs) to explore potential causal relationships between FC and BN. Summary data from genome-wide association studies (GWAS) involving 2,564 individuals were analyzed to identify genetically predicted BN. Functional magnetic resonance imaging parameters and materials were sourced from the UK Biobank. The variables underwent independent component analysis processing by the database to generate the final GWAS dataset. Various methods, including MR Pleiotropy RESidual Sum and Outlier, MR Egger, and weighted median, were employed to detect heterogeneity and pleiotropy, with inverse variance weighting serving as the principal estimation method (P < 0.05). The FC imaging-derived phenotypes revealed that BN exerted a causal influence on the FC between large-scale networks, including the visual network, default mode network (DMN), frontoparietal network, somatosensory network (SSN), and ventral attention network. Additionally, BN had a causal impact on the within-network FC of both the DMN and SSN. The study provides evidence that BN leads to further changes in FC patterns within and between large-scale brain networks.

Altered gait speed and brain network connectivity in Parkinson's disease.

Slow gait speed and disrupted brain network connectivity are common in patients with Parkinson's disease (PD). This study aimed to clarify the relationship between gait speed and clinical characteristics in PD, and explore the underlying brain network mechanisms. Forty-two PD patients and 20 healthy controls (HC) were recruited. Statistical independent component analysis and correlation analysis were employed to investigate underlying neural mechanisms and relationships. PD patients exhibited significantly slower gait speed, which showed a significant negative correlation with postural instability and gait disturbance scores. Network connectivity analysis revealed decreased intranetwork functional connectivity (FC) within visual network (VN) and cerebellum network (CN), but increased internetwork FC between CN and both sensorimotor network (SMN) and frontoparietal network (FPN) in PD patients compared to HC. The slow gait speed PD subgroup demonstrated increased intranetwork FC within SMN and VN, along with decreased FC between VN and both FPN and default mode network. Correlation analyses revealed negative correlation between gait speed and FC of CN and positive correlation to FC of CN-SMN. Our study identified relationships between gait speed and clinical characteristics, and corresponding network connectivity alterations in PD patients, providing insights into the neural mechanisms underlying gait impairments in PD.

IModulonDB 2.0: dynamic tools to facilitate knowledge-mining and user-enabled analyses of curated transcriptomic datasets.

iModulons-sets of co-expressed genes identified through independent component analysis (ICA) of high-quality transcriptomic datasets-provide an unbiased, modular view of an organism's transcriptional regulatory network. Established in 2020, iModulonDB (iModulonDB.org) serves as a centralized repository of curated iModulon sets, enabling users to explore iModulons and download the associated transcriptomic data. This update reflects a significant expansion of the database-19 new ICA decompositions (+633%) spanning 8925 expression profiles (+1370%), 503 studies (+2290%)and 12 additional organisms (+400%)-and introduces new features to help scientists decipher the mechanisms governing prokaryotic transcriptional regulation. To facilitate comprehension of the underlying expression profiles, the updated user-interface displays essential information about each data-generating study (e.g. the experimental conditions and publication abstract). Dashboards now include condition-specific coloring and highlight data generated from genetically perturbed strains, enabling users to rapidly interpret disruptions in transcriptional regulation. New interactive graphs rapidly convey omics-derived indicators (e.g. the explained variance of ICA decompositions, genetic overlap between iModulons and regulons). Direct links to operon diagrams (BioCyc) and protein-protein interaction networks (STRING) provide users with seamless access to external resources for further assessment of iModulons. Lastly, a new suite of search-driven and species-wide analysis tools promotes user-engagement with iModulons, reinforcing iModulonDB's role as a dynamic, interactive knowledgebase of prokaryotic transcriptional regulation.

Combining Remote Sensing Data and Geochemical Properties of Ultramafics to Explore Chromite Ore Deposits in East Oltu Erzurum, Turkey

The present research’s main objective was to apply thorough exploration approaches that combine remote sensing data with geochemical sampling and analysis to predict and identify potential chromitite locations in a complex geological site, particularly in rugged mountainous terrain, and differentiate the ultramafic massif containing chromitite orebodies from other lithologies. The ultramafic massif forming the mantle section of the Kırdağ ophiolite, located within the Erzurum–Kars Ophiolite Zone and emerging in the east of Oltu district (Erzurum, NE Turkey), was selected as the study area. Optimum index factor (OIF), false-color composite (FCC), decorrelation stretch (DS), band rationing (BR), minimum noise fraction (MNF), and principal and independent component analyses (PCA-ICA) were performed to differentiate the lithological features and identify the chromitite host formations. The petrography, mineral chemistry, and whole-rock geochemical properties of the harzburgites, which are the host rocks of chromitites in the research area, were evaluated to verify and confirm the remote sensing results. In addition, detailed petrographic properties of the pyroxenite and chromitite samples are presented. The results support the existence of potential chromitite formations in the mantle section of the Kırdağ ophiolite. Our remote sensing results also demonstrate the successful detection of the spectral anomalies of this ultramafic massif. The mineral and whole-rock geochemical features provide clear evidence of petrological processes, such as partial melting and melt–peridotite interactions during the harzburgite formation. The chromian spinels’ Cr#, Mg#, Fe3+, Al2O3, and TiO2 concentrations indicate that the harzburgite formed in a fore-arc environment. The Al2O3 content and Mg# of the pyroxenes and the whole-rock Al2O3/MgO ratio and V contents of the harzburgite are also compatible with these processes. Consequently, the combined approaches demonstrated clear advantages over conventional chromitite exploration techniques, decreasing the overall costs and supporting the occurrence of chromite production at the site.

Reducing electrocardiographic interference in the multichannel electromyogram to help muscle fatigue assessment in low-intensity contractions.

Surface electromyography (EMG) can be used in the rehabilitation of musculoskeletal disorders, for evaluating the coordination of muscles that stabilize a joint, or as an objective tool in assessing muscle fatigue. This latter may be achieved by evaluating the low-frequency content of the EMG. However, the electrocardiogram (ECG) interference is also recorded when EMG is acquired close to the heart. It may mask or even modify the information of interest in the EMG. Different signal processing techniques have been proposed to eliminate ECG artifacts from the EMG signals, the high-pass filter being the most used one. Nevertheless, this classic filtering approach would also attenuate EMG activities below 30 Hz, which contain information from low-intensity muscle contractions. This work addresses the automatic ECG attenuation when multichannel EMG is collected on the left pectoralis major muscle during a muscle fatigue test. The proposed ECG artifact mitigation extends a successful automatic template subtraction (TS) approach, which does not require an extra reference channel and is now applied to independent EMG source signal components extracted using a blind source separation technique (ICA, Independent Component Analysis). The automatic detection of ECG components was performed through two alternative measures: entropy and Kullback-Leibler divergence. While the ECG interference seems to hamper the detection of muscle fatigue in the low-contraction regime, the association ICA+TS preserved better the EMG low-frequency content, and the entropy-based automatic detection was found to be more suitable, avoiding possible errors that might arise from manual detection procedures.

Characterising the contribution of auditory and somatosensory inputs to TMS-evoked potentials following stimulation of prefrontal, premotor, and parietal cortex

Abstract Transcranial magnetic stimulation (TMS) results in a series of deflections in electroencephalography (EEG) recordings known as a TMS-evoked potential (TEP). However, it remains unclear whether these responses reflect neural activity resulting from transcranial stimulation of the cortex, the sensory experiences of TMS, or a combination of the two. Across three experiments (total n = 135), we recorded EEG activity following TMS to the dorsolateral prefrontal cortex, premotor cortex, and parietal cortex as well as a sensory control condition (stimulation of the shoulder or electrical stimulation of the scalp with a click sound). We found that TEPs showed a stereotypical frontocentral N100/P200 complex following TMS of all cortical sites and control conditions, regardless of TMS intensity or the type of sensory control. In contrast, earlier TEPs (&amp;lt;60 ms) showed site-specific characteristics which were largest at the site of stimulation, although TEP topographies were distorted in a subgroup of individuals due to residual TMS-evoked muscle artefact despite cleaning with independent component analysis. Self-reported sensory experiences differed across sites, with prefrontal stimulation resulting in stronger auditory (click sound perception) and somatosensory input (scalp muscle twitch, discomfort) than premotor or parietal stimulation, a pattern that was reflected in the amplitude of later (N100/P200), but not earlier (&amp;lt;60 ms), TEP peak amplitudes. Later TEPs were also larger in individuals who experienced stronger click sound perception and, to a lesser extent, TMS-evoked scalp muscle twitches. Increasing click sound perception by removing auditory masking increased N100/P200 amplitudes without altering earlier peaks, an effect which was more prominent at sites with more successful masking. Together, these findings suggest that the frontocentral N100/P200 complex primarily represents a generalised sensory response resulting from TMS-related auditory and somatosensory input when present. In contrast, early TEP peaks likely primarily reflect activity resulting from transcranial stimulation of the cortex when artefacts were adequately accounted for. The results have important implications for designing and interpreting TEP studies, especially when comparing TEPs between stimulation sites and participant groups showing differences in sensory experiences following TMS.

ANALYZING EEG SIGNALS FOR STRESS DETECTION USING RANDOM FOREST ALGORITHM

Detection of stress using EEG signals has gained much interest because of monitoring and early intervention. As for the contribution of this research, a reliable method for stress identification has been suggested, using a random forest model to categorize stress levels from EEG signals. Data were filtered using a bandpass filter, Independent Component Analysis, and more so using the Z-score to remove outliers and poor signals. Data that has been cleaned from noise and outliers will go through a feature extraction process using Power Spectral Density (PSD). The result of PSD is the power of each frequency of the EEG signal. The number of features used is 20. Random Forest was chosen due to its high accuracy and robustness in handling complex, high-dimensional data, which is common in EEG analysis. Thus, the model obtained an accuracy level of 0.8571, thereby approving the tool’s efficiency in distinguishing between different degrees of stress. The computational efficiency of the model, with a classification time of 0.2762 seconds, demonstrates its feasibility for practical applications. Based on these findings, it can be concluded that the Random Forest algorithm can be used to integrate wearable technology and for offering suggestions and timely interventions for better mental health.

Multimodal Operation Data Mining for Grid Operation Violation Risk Prediction

With the continuous expansion of the power grid, the issue of operational safety has attracted increasing attention. In power grid operation control, unauthorized operations are one of the primary causes of personal accidents. Therefore, preventing and monitoring unauthorized actions by power grid operators is of critical importance. First, multimodal violation data are integrated through information systems, such as the power grid management platform, to construct a historical case database. Next, word vectors for three types of operation-related factors are generated using natural language processing techniques, and key vectors are selected based on generalized correlation coefficients using mutual information, enabling effective dimensionality reduction. Independent component analysis is then employed for feature extraction and further dimensionality reduction, allowing for the effective characterization of operational scenarios. For each historical case, a risk score is derived from a violation risk prediction model constructed using the Random Forests (RF) algorithm. When a high-risk score is identified, the K-Nearest Neighbor (KNN) algorithm is applied to locate similar scenarios in the historical case database where violations may have occurred. Real-time violation risk assessment is performed for each operation, providing early warnings to operators, thereby reducing the likelihood of violations, and enhancing the safety of power grid operations.

Food freshness and composition evaluated by Colorimetry, TPA, and spectroscopy through ICA-based ComDim: A case study of a peanut-based protein-enriched food

This study aimed to apply Common Components and Specific Weights Analysis (CCSWA or ComDim) to explore the relations between colorimetry (color), Texture Profile Analysis (TPA), and Near-Infrared Spectroscopy (NIR) besides determining which of these techniques is most effective in differentiating the freshness and composition of the studied samples. ComDim-ICA, a recent modification of ComDim based on Independent Components Analysis (ICA) decomposition, was used. This approach was chosen to provide more straightforward and interpretable scores and loadings compared to the classical ComDim, which is based on Principal Components Analysis (PCA). The experiment was performed on a peanut-based food enriched with powdered proteins derived from pumpkin seed, rice, pea, sunflower seed, water lentil (duckweed), flaxseed, soybean, and whey. Measurements (Color, NIR, and TPA) were taken on the day of the food preparation, after seven days, and after fourteen days. The global scores indicated that CC2 carried information regarding freshness, while CC3, CC4, and CC5 were associated with food composition. According to the saliences, NIR and color were the most important techniques for determining food freshness (the most important in CC2). Additionally, in CC3, NIR was responsible for distinguishing lentil and rice proteins from the other protein sources. The best differentiation regarding food composition was found in CC4 and CC5, where colorimetry and TPA were most significant. These findings may encourage new applications of multiblock analysis to elucidate differences in food quality based on diverse evaluation techniques.

Longitudinal functional brain connectivity maturation in premature newborn infants: modulatory influence of early music enrichment

Abstract Premature birth affects brain maturation, illustrated by altered brain functional connectivity at term equivalent age (TEA) and alters neurobehavioral outcome. To correct early developmental differences and improve neurological outcome, music during the NICU stay has been proposed as an auditory enrichment with modulatory effects on functional and structural brain development, but longitudinal effects of such interventions have not been studied so far. We longitudinally investigated resting-state functional connectivity (RS-FC) maturation in preterm infants (n=43). Data-driven Independent Component Analyses (ICA) were performed on scans obtained at 33- and 40-weeks gestational age (GA), determining the presence of distinct RSNs. Connectome analysis ´accordance measure´ quantitively examined the RS-FC both at 33- and 40-weeks GA. Further comparing the internetwork RS-FC at 33- and 40 weeks GA provided a circuitry of interest (COI) for significant maturational changes in which the effects on the RS-FC of a music intervention was tested. The connectome analyses resulted in a COI of RS-FC connections significantly maturing from 33 to 40 weeks GA, namely between the thalamic/brainstem and prefrontal-limbic, salience, sensorimotor, auditory and prefrontal cortical networks; between the prefrontal-limbic and cerebellar, visual and left hemispheric precuneus networks; between the salience and visual, and cerebellar networks; and between the sensorimotor and auditory, and posterior cingulate/precuneus networks. The infants exposed to music exhibited significantly increased maturation in RS-FC between the thalamic/brainstem and salience networks, compared to controls. This study exemplifies that preterm infant RS-FC maturation is modulated through NICU music exposure, highlighting the importance of environmental enrichment for neurodevelopment in premature newborns.

Online Recursive Independent Component Analysis based equalization for Orbital Angular Momentum Mode Division Multiplexed Transmission

Online Recursive Independent Component Analysis based equalization for Orbital Angular Momentum Mode Division Multiplexed Transmission

OB-TSASA Guided Soft Voting Ensemble Classifier for Breast Cancer Classification Using Thermal Infrared Images

Nowadays, the use of thermal infrared images has become more popular in breast cancer detection. Thermal image analysis with machine learning algorithms allows physicians to make accurate decisions on cancer diagnostics. Hence, this paper introduces a novel automated breast cancer classifier using thermal infrared images. Initially, the features from the DMR – IR dataset are extracted by an integrated approach of Kernel Principle Fast Independent-Component Analysis (KPFICA) and deep object-centric pooling convolution neural network (DOCP-CNN). Additionally, the DOCP-CNN hyperparameters are tuned by the Harris Hawks Optimization (HHO) algorithm. Next, the proposed oppositional based tunicate swarm algorithm with simulated annealing (OB-TSASA) optimization is used to select the relevant features from the extracted features. Finally, the OB-TSASA guided soft voting ensemble classifier is proposed to detect and classify cancerous patients. The experiment is conducted on the DMR – IR dataset to estimate the effectiveness of the proposed method. Furthermore, the proposed method produces outstanding classification results in terms of AUC, accuracy, F1-score, sensitivity, MCC, and kappa statistics. It is observed that the classification accuracy is 97.73% which is superior to other classifiers and the error rate is 2.27% which is very low compared to other methods.

Constructing a Supplementary Benchmark Suite to Represent Android Applications with User Interactions by using Performance Counters

We find existing benchmark suites for smartphone CPU micro-architecture design such as Geekbench 5.0 fail to authentically represent the micro-architecture level performance behavior of widely used real Android applications with interactive operations such as screen sliding. It is therefore crucial to systematically construct a benchmark suite as a supplementary to Geekbench to represent the user interaction behavior of Android applications for CPU micro-architecture design. The key is to identify a small number of representative programs from a large number of real applications. To this end, a set of features used to represent a program need to be constructed, and these features should be fair for different micro-architectures and can be collected efficiently. However, this is extremely difficult for Android applications. For example, the feature collection tools for Android applications are unavailable for benchmark selection. In this paper, we propose a novel benchmark suite construction approach dubbed BEMAP to efficiently build a supplementary benchmark suite from real-world Android applications to represent their user interaction behavior. 1 BEMAP innovates four techniques. The first technique, called two-stage RFC (representative feature construction), constructs program features from performance counters (events) to represent a program for selecting benchmarks from a large number of real Android applications in two stages. The first stage identifies a set of important performance events in terms of IPC (instructions per cycle) by employing a machine learning algorithm named SGBRT (Stochastic Gradient Boosted Regression Tree). The second stage constructs representative features based on the important performance events by using ICA (independent component analysis). The second technique, named SPC-MMA (source performance counters from multiple micro-architectures), collects the performance events from multiple mobile CPUs with different micro-architectures and mixes them as the source of RFC. The goal of these two innovations is to make the program features fair to different mobile CPU micro-architectures. The third technique, called ES (Elbow-Silhouette) approach, artfully leverages the synergy between the elbow method and the silhouette method to determine an optimal K when we use K-Means to group Android applications. The fourth technique is that we design a new tool named AutoProfiler to automatically profile the micro-architecture events (e.g., IPC, L1 Icache misses) of Android applications with interactive operations. Using the proposed BEMAP methodology 2 , we constructed SPBench, a novel benchmark suite supplementary to traditional mobile benchmark suites like Geekbench, for mobile CPU micro-architecture design. It consists of fifteen benchmarks selected from one hundred real Android applications with three common user interaction operations, which is the fifth innovation of this paper. The experimental results on four significantly different micro-architectures show that SPBench can represent the micro-architecture performance behaviors of the one hundred real-world applications with three common user interactive operations on each micro-architecture with significantly higher accuracy than benchmark suites produced by the state-of-the-art approaches.

A Novel Dictionary Learning Algorithm Based on Prior Knowledge for fMRI Data Analysis

ABSTRACTTask‐based functional magnetic resonance imaging (fMRI) has been widely utilized for brain activation detection and functional network analysis. In recent years, the K‐singular value decomposition (K‐SVD) algorithm has gained increasing attention in the research of fMRI data analysis methods. In this study, we propose a novel temporal feature region‐growing constrained K‐SVD algorithm that incorporates task‐based fMRI temporal prior knowledge and utilizes a region‐growing algorithm to infer potential activation locations. The algorithm incorporates temporal and spatial constraints to enhance the detection of brain activation. Specifically, this paper improves the three stages of the traditional K‐SVD algorithm. First, in the dictionary initialization stage, the automatic target generation process with an independent component analysis algorithm is utilized in conjunction with prior knowledge to enhance the accuracy of initialization. Second, in the sparse coding stage, the region‐growing algorithm is employed to infer potential activation locations based on temporal prior knowledge, thereby imposing spatial constraints to limit the extent of activation regions. Finally, in the dictionary learning stage, soft constraints and low correlation constraints are applied to reinforce the consistency with prior knowledge and enhance the robustness of learning for task‐related atoms. The proposed method was validated on simulated and real fMRI data, showing superior performance in detecting brain activation compared with traditional methods. The results indicate that the algorithm accurately identifies activated brain regions, providing an effective approach for studying brain function in clinical applications.

3D Fluorescence Spectroscopy Combined With Chemometrics as a Tool for Control of Imprinted Protein Purification From Template Molecules

ABSTRACTImprinted proteins (IPs) are promising alternatives to natural recognition systems, such as biological receptors or antibodies. One of the crucial stages during development of IPs is removal of the template molecules from its complex with the protein. In this study, bovine serum albumin was imprinted in the presence of 4‐hydroxycoumarin (4‐HC); purification of IPs were carried out by dialysis, and fluorescence 3D spectroscopy was used to monitor the IP purification process. Excitation–emission matrix (EEM) was further investigated via several chemometric algorithms (principal component analysis [PCA], parallel factor analysis [PARAFAC], and independent components analysis [ICA]). We found that the models using PARAFAC and ICA worked better than those of PCA. It was shown that PARAFAC and ICA analyses allow not only to recognize IP sample with signal close to nonimprinted protein, but also to provide recommendations on the optimal dialysis time.