Independent Features Research Articles

Further analysis of the statistical independence of the NIST SP 800-22 randomness tests

In multiple applications, from Statistics to Particle Physics and notably in Cryptography and Computer Security, it is necessary to obtain long sequences of random numbers. In order to verify the properties of these sequences, different statistical tests are commonly applied, which are usually included in the so-called test batteries or test suites. The batteries need to be both effective and efficient. Their effectiveness relates to how well they can spot non-randomness behaviour, the efficiency is related to the computational time they require. It is therefore essential for tests included in batteries to measure their independence features: Test independence is important for good effectiveness, as high correlations between tests could lead to a decreased efficiency (testing for the same features multiple times) and effectiveness (missing an opportunity to test for an orthogonal randomness property when we essentially measure the same twice). Moreover, the related study of test coverage is often based on the assumption that tests are independent. This paper describes a series of experiments aimed at scrutinizing dependencies among the statistical tests in the NIST SP 800-22 suite. In order to do so, sequences of varying lengths from sources of varying entropy have been generated and tested. Afterwards, an inferential study was carried out to find whether significant correlations exist and to present our findings in a statistically sound way.

Radiomics for the detection of diffusely impaired myocardial perfusion: A proof-of-concept study using 13N-ammonia positron emission tomography

AimThe current proof-of-concept study investigates the value of radiomic features from normal 13N-ammonia positron emission tomography (PET) myocardial retention images to identify patients with reduced global myocardial flow reserve (MFR). MethodsData from 100 patients with normal retention 13N-ammonia PET scans were divided into two groups, according to global MFR (i.e., < 2 and ≥ 2), as derived from quantitative PET analysis. We extracted radiomic features from retention images at each of five different gray-level (GL) discretization (8, 16, 32, 64, and 128 bins). Outcome independent and dependent feature selection and subsequent univariate and multivariate analyses was performed to identify image features predicting reduced global MFR. ResultsA total of 475 radiomic features were extracted per patient. Outcome independent and dependent feature selection resulted in a remainder of 35 features. Discretization at 16 bins (GL16) yielded the highest number of significant predictors of reduced MFR and was chosen for the final analysis. GLRLM_GLNU was the most robust parameter and at a cut-off of 948 yielded an accuracy, sensitivity, specificity, negative and positive predictive value of 67%, 74%, 58%, 64%, and 69%, respectively, to detect diffusely impaired myocardial perfusion. ConclusionA single radiomic feature (GLRLM_GLNU) extracted from visually normal 13N-ammonia PET retention images independently predicts reduced global MFR with moderate accuracy. This concept could potentially be applied to other myocardial perfusion imaging modalities based purely on relative distribution patterns to allow for better detection of diffuse disease.

A CT-based radiomics integrated model for discriminating pulmonary cryptococcosis granuloma from lung adenocarcinoma-a diagnostic test.

Chest computed tomography (CT) is a critical tool in the diagnosis of pulmonary cryptococcosis as approximately 30% of normal immunity individuals may not exhibit any significant symptoms or laboratory findings. Pulmonary cryptococcosis granuloma and lung adenocarcinoma can appear similar on noncontrast chest CT. This study evaluates the use of an integrated model that was developed based on radiomic features combined with demographic and radiological features to differentiate pulmonary cryptococcosis nodules from lung adenocarcinomas. Preoperative chest CT images for 215 patients with solid pulmonary nodules with histopathologically confirmed lung adenocarcinoma and cryptococcosis infection were collected from two clinical centers (108 cases in the training set and 107 cases in the test set divided by the different hospitals). Radiomics models were constructed based on nodular lesion volume (LV), 5-mm extended lesion volume (ELV), and perilesion volume (PLV). A demoradiological model was constructed using logistic regression based on demographic information (age, sex) and 12 radiological features (location, number, shape and specific imaging signs). Both models were used to build an integrated model, the performance of which was assessed using the test set. A junior and a senior radiologist evaluated the nodules. Receiver operating characteristic (ROC) curve analysis was conducted, and areas under the curve (AUCs), sensitivity (SEN), and specificity (SPE) of the models were calculated and compared. Among the radiomics models, AUCs of the LV, ELV, and PLV were 0.558, 0.757, and 0.470, respectively. Age, lesion number, and lobular sign were identified as independent discriminative features providing an AUC of 0.77 in the demoradiological model (SEN 0.815, SPE 0.642). The integrated model achieved the highest AUC of 0.801 (SEN 0.759, SPE 0.755), which was significantly higher than that obtained by a junior radiologist (AUC =0.689, P=0.024) but showed no significant difference from that of the senior radiologist (AUC =0.784, P=0.388). An integrated model with radiomics and demoradiological features improves discrimination of cryptococcosis granulomas from solid adenocarcinomas on noncontrast CT. This model may be an effective strategy for machine complementation to discrimination by radiologists, and whole-lung automated recognition methods might dominate in the future.

Newly Appearing Hepatic Lesion After Curative Surgery For Colorectal Cancer: Single-phase CT Findings Implying Metastasis.

In patients treated with curative surgery for colorectal cancer, the single-phase (portal phase) abdomen-pelvic computed tomography (CT) follow-up is routinely performed to detect any recurrent lesions. The objective of this study is to evaluate CT features implying metastasis in newly appearing hepatic lesions on single-phase CT after colorectal cancer surgery. Of 1,227 patients who underwent curative colorectal surgery between 2011 and 2014, 267 patients with new hepatic lesions on follow-up single-phase CT (metastasis, n=192; benign, n=75) were included. The CT features of the hepatic lesions were analyzed by two radiologists retrospectively, and clinical information, including carcinoembryonic antigen (CEA) level was also reviewed. The risk factors for hepatic metastasis were evaluated by multivariable logistic regression. In this study, independent CT features associated with metastasis were spherical shape (p < 0.001), circumscribed margin (p = 0.021), heterogeneous attenuation (p = 0.024) and bulging appearance (p = 0.007). Among the clinical factors, increased CEA level (p = 0.013), higher preoperative stage (p = 0.014) and lymphovascular invasion (p = 0.003) were associated with metastasis. However, on multivariable analysis, spherical shape was the only significant predictive factor for hepatic metastasis. The diagnostic performance of 'spherical shape' for detection of hepatic metastasis showed an accuracy of 84.6%, sensitivity of 83.9%, and specificity of 86.7%. Specific single-phase CT features could be useful in distinguishing hepatic metastasis from benign, resulting in continuing routine CT follow-up without liver magnetic resonance imaging (MRI) when metastasis is unlikely.

From IMU Measurement Sequence to Velocity Estimate Sequence: An Effective and Efficient Data-Driven Inertial Odometry Approach

We propose a novel deep learning-based inertial odometry framework to improve both localization accuracy and efficiency. The measured 3D accelerations and angular velocities are constructed as two independent channel 2D features. In each channel, the 3 axes of accelerations or angular velocities constitute the height dimension, whereas the temporal axis represents the width dimension. In the neural network module, we first employ 2D convolutional operations to convert the input features to 1D series with 4-fold downsampling along the temporal axis. We then apply the convolutional attention module to refine the generated 1D feature map and long short-term memory (LSTM) layers to generate the hidden state for each refined time index, which is followed by two separate 2-layer multilayer perceptrons (MLPs) to regress the velocity and the uncertainty. During backpropagation, we use the negative log-likelihood loss to optimize the velocity and the uncertainty objectives. Benefiting from the velocity sequence objective in a single network forward propagation procedure, we also add the average squared distance between the ground-truth relative position and that of the prediction to minimize the location error. Extensive experiments on both the RoNIN dataset and the real scenario collected data in the CUHK campus show higher localization accuracy with 10 times higher efficiency of the proposed framework than the comparing methods.

Coal Flow Foreign Body Classification Based on ESCBAM and Multi-Channel Feature Fusion.

Foreign bodies often cause belt scratching and tearing, coal stacking, and plugging during the transportation of coal via belt conveyors. To overcome the problems of large parameters, heavy computational complexity, low classification accuracy, and poor processing speed in current classification networks, a novel network based on ESCBAM and multichannel feature fusion is proposed in this paper. Firstly, to improve the utilization rate of features and the network's ability to learn detailed information, a multi-channel feature fusion strategy was designed to fully integrate the independent feature information between each channel. Then, to reduce the computational amount while maintaining excellent feature extraction capability, an information fusion network was constructed, which adopted the depthwise separable convolution and improved residual network structure as the basic feature extraction unit. Finally, to enhance the understanding ability of image context and improve the feature performance of the network, a novel ESCBAM attention mechanism with strong generalization and portability was constructed by integrating space and channel features. The experimental results demonstrate that the proposed method has the advantages of fewer parameters, low computational complexity, high accuracy, and fast processing speed, which can effectively classify foreign bodies on the belt conveyor.

RFMNet: Robust Deep Functional Maps for unsupervised non-rigid shape correspondence

In traditional deep functional maps for non-rigid shape correspondence, estimating a functional map including high-frequency information requires enough linearly independent features via the least square method, which is prone to be violated in practice, especially at an early stage of training, or costly post-processing, e.g. ZoomOut. In this paper, we propose a novel method called RFMNet (Robust Deep Functional Map Networks), which jointly considers training stability and more geometric shape features than previous works. We directly first produce a pointwise map by resorting to optimal transport and then convert it to an initial functional map. Such a mechanism mitigates the requirements for the descriptor and avoids the training instabilities resulting from the least square solver. Benefitting from the novel strategy, we successfully integrate a state-of-the-art geometric regularization for further optimizing the functional map, which substantially filters the initial functional map. We show our novel computing functional map module brings more stable training even under encoding the functional map with high-frequency information and faster convergence speed. Considering the pointwise and functional maps, an unsupervised loss is presented for penalizing the correspondence distortion of Delta functions between shapes. To catch discretization-resistant and orientation-aware shape features with our network, we utilize DiffusionNet as a feature extractor. Experimental results demonstrate our apparent superiority in correspondence quality and generalization across various shape discretizations and different datasets compared to the state-of-the-art learning methods.

Symmetries and spectral statistics in chaotic conformal field theories

We discuss spectral correlations in coarse-grained chaotic two-dimensional CFTs with large central charge. We study a partition function describing the dense part of the spectrum of primary states in a way that disentangles the chaotic properties of the spectrum from those which are a consequence of Virasoro symmetry and modular invariance. We argue that random matrix universality in the near-extremal limit is an independent feature of each spin sector separately; this is a non-trivial statement because the exact spectrum is fully determined by only the spectrum of spin zero primaries and those of a single non-zero spin (“spectral determinacy”). We then describe an argument analogous to the one leading to Cardy’s formula for the averaged density of states, but in our case applying it to spectral correlations: assuming statistical universalities in the near-extremal spectrum in all spin sectors, we find similar random matrix universality in a large spin regime far from extremality.

Low Complex CORDIC-based Hand Movement Recognition Design Methodology for Rehabilitation and Prosthetic Applications.

Hand movement recognition using Electromyography (EMG) signals have gained much significance lately and is extensively used for rehabilitation and prosthetic applications including stroke-driven disability and other neuromuscular disorders. Herein, quantitative analysis of EMG signals is very crucial. However, such applications are constrained by power consumption limitations due to the battery backup necessitating low-complex system design and the on-chip area requirement. Existing hand movement recognition methodologies using single-channel EMG signal involve computationally intensive stages, including Ensemble Empirical Mode Decomposition (EEMD), Fast Independent Component Analysis (FastICA), feature extraction, and Linear Discriminant Analysis (LDA) classification, which can not be mapped onto the low-complex architecture directly from the algorithmic level. The high computational complexity of LDA classification makes it difficult to be used for low-complex applications. In this paper, we introduce a low-complex CORDIC-based hand movement recognition design methodology targeting resource-constrained rehabilitation applications. This work explores replacing LDA classification with K-Means clustering due to its reduced complexity and efficient clustering algorithm. CORDIC-based K-Means clustering is used to further reduce the overall computational complexity of the system. The proposed low complex, K-Means clustering-based hand movement recognition for classifying seven hand movements using single-channel EMG data is found to be 99.77 % less complex and 1.28% more accurate than the conventional LDA-based classification.

A Supervised Classification Approach for Detecting Hate Speech in English Tweets

As social concerns about threats of hatred and harassment have grown on the internet, there has been a lot of attention paid to detecting hate speech. This research looks at how well SGD classifiers with hyper-parameter tuning perform at detecting hate speech in tweets. It describes the categorization of English tweets with stochastic gradient descent (SGD) classifiers. The categorization of text documents depends on their content, which is divided into groups based on predefined categories. The Term-Frequency (TF) and Inverse-Document Frequency (IDF) parameters are implemented in the proposed system. A Stochastic Gradient Descent method (SGD) is used to generate classifiers that learn independent features, and performance is assessed using Accuracy and F1-score.

A CT-based Deep Learning Radiomics Nomogram for the Prediction of EGFR Mutation Status in Head and Neck Squamous Cell Carcinoma

Accurately assessing epidermal growth factor receptor (EGFR) mutation status in head and neck squamous cell carcinoma (HNSCC) patients is crucial for prognosis and treatment selection. This study aimed to construct and validate a contrast-enhanced computed tomography (CECT)-based deep learning radiomics nomogram (DLRN) to predict EGFR mutation status of HNSCC. A total of 300 HNSCC patients who underwent CECT scans were enrolled in this study. Participants from two hospitals were separated into a training set (n=200, 56 EGFR-negative and 144 EGFR-positive) from one hospital and an external test set from the other hospital (n=100, 37 EGFR-negative and 63 EGFR-positive). The least absolute shrinkage and selection operator method was used to select the key features from CECT-based manually extracted radiomics (MER) features and features automatically extracted using a deep learning model (DL, extracted using a GoogLeNet model). The selected independent clinical factors, MER features, and DL features were then combined to construct a DLRN. The DLRN's performance was evaluated using receiver operating characteristics curves. Five MER and six DL features were finally chosen. The DLRN, which includes "gender" and "necrotic areas," along with the selected features, predicted EGFR mutation status of HNSCC (EGFR-negative vs. positive) well in both the training (area under the curve [AUC], 0.901) and test (AUC, 0.875) sets. A DLRN using CECT was built to predict EGFR mutation in HNSCC. The model showed high predictive ability and may aid in treatment selection and patient prognosis.

The significance of the predominant component in combined hepatocellular-cholangiocarcinoma: MRI manifestation and prognostic value.

To investigate the significance of the predominant component of combined hepatocellular-cholangiocarcinoma (cHCC-CC) in terms of MRI manifestation and its potential prognostic value compared to hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). A total of 300 patients with chronic liver disease from two centers were retrospectively enrolled, including 100 surgically proven cases of cHCC-CC, HCC, and ICC each. Univariate and multivariate regression analyses were performed to identify independent predictors for distinguishing HCC-predominant cHCC-CC and ICC-predominant cHCC-CC from HCC and ICC, respectively. Diagnostic models were constructed based on the independent features. Recurrence-free survival (RFS) was estimated and compared between groups. The predominant component was an independent predictor for RFS in cHCC-CC (hazard ratio = 1.957, P = 0.044). The presence of targetoid appearance (odds ratio(OR) = 10.907, P = 0.001), lack of enhancing capsule (OR = 0.072, P = 0.001) and arterial peritumoral enhancement (OR = 0.091, P = 0.003) were independent predictors suggestive of HCC-predominant cHCC-CC over HCC; their combination yielded an area under the curve of 0.756. No significant differences were observed in RFS between HCC-predominant cHCC-CC and HCC (P = 0.864). Male gender (OR = 4.049, P = 0.015), higher alpha fetoprotein (OR = 16.789, P < 0.001) and normal carbohydrate antigen 19-9 (OR = 0.343, P = 0.036) levels, presence of enhancing capsule (OR = 7.819, P < 0.001) and hemorrhage (OR = 23.526, P = 0.004), and lack of targetoid appearance (OR = 0.129, P = 0.005) and liver surface retraction (OR = 0.190, P = 0.021) were independent predictors suggestive of ICC-predominant cHCC-CC over ICC; their combination yielded an area under the curve value of 0.898. ICC-predominant cHCC-CC exhibited poorer survival with shorter RFS than ICC (P = 0.009). The predominant histopathological component is closely related to the imaging manifestation of cHCC-CC; and more importantly, it plays a significant prognostic role, which may alter the RFS prognosis of cHCC-CC.

The distal tibiofibular joint effusion may be a reliable index for diagnosing the distal tibiofibular syndesmosis instability in ankle

PurposeTo analyze the accuracy of MRI in diagnosis of distal tibiofibular syndesmosis instability (DTSI) and construct new diagnostic parameters.Materials and methodsThis retrospective study evaluated 212 patients with history of ankle sprains and 3 T MRI and received a final diagnosis of distal tibiofibular syndesmosis instability by ankle arthroscopic surgery from October 2017 and December 2021. We compared the accuracy of syndesmotic injury, qualitative index of distal tibiofibular joint effusion (DTJE), and quantitative index of distal tibiofibular joint effusion (DTJE) in diagnosing distal tibiofibular syndesmosis instability. The criteria for syndesmotic injury were consistent with previous literature, and DTJE was grouped according to the pre-experimental results.ResultsA total of 212 patients (mean age, 35.64 ± 11.79, 74 female and 138 male) were included. Independent predictive MRI features included syndesmotic injury, qualitative index of distal tibiofibular joint effusion, and quantitative index of DTJE including the height, projected area of equal-point method, and projected area of incremental-value method. The quantitative index of DTJE showed a higher area under the receiver operating characteristic curve (0.805/0.803/0.804/0.811/0.817/0.805 > 0.8, P < 0.05; in comparison with all other method). The height measurement method was simpler and easier to operate, that could be gotten only by measuring the DTJE distance of a MRI independent layer, and the cut-off value of the effusion height was 8.00 mm and the Youden index (0.56) was the best.ConclusionsOur research translated a complicated string of MRI multi-dimensional spatial measurements into a simple measuring process, and established the significance of quantifying DTJE in the diagnosis of DTSI. We found that the 8-mm height of DTJE was a more specific indicator for DTSI and could serve as a novel MRI diagnostic cutoff in clinical practice.

A new method for the extraction of tailing ponds from very high-resolution remotely sensed images: PSVED

ABSTRACT Automatic extraction of tailing ponds from Very High-Resolution (VHR) remotely sensed images is vital for mineral resource management. This study proposes a Pseudo-Siamese Visual Geometry Group Encoder-Decoder network (PSVED) to achieve high accuracy tailing ponds extraction from VHR images. First, handcrafted feature (HCF) images are calculated from VHR images based on the index calculation algorithm, highlighting the tailing ponds’ signals. Second, considering the information gap between VHR images and HCF images, the Pseudo-Siamese Visual Geometry Group (Pseudo-Siamese VGG) is utilized to extract independent and representative deep semantic features from VHR images and HCF images, respectively. Third, the deep supervision mechanism is attached to handle the optimization problem of gradients vanishing or exploding. A self-made tailing ponds extraction dataset (TPSet) produced with the Gaofen-6 images of part of Hebei province, China, was employed to conduct experiments. The results show that the proposed method achieves the best visual performance and accuracy for tailing ponds extraction in all the tested methods, whereas the running time of the proposed method maintains at the same level as other methods. This study has practical significance in automatically extracting tailing ponds from VHR images which is beneficial to tailing ponds management and monitoring.

Extracellular volume fraction using contrast-enhanced CT is useful in differentiating intrahepatic cholangiocellular carcinoma from hepatocellular carcinoma.

To evaluate whether tumor extracellular volume fraction (fECV) on contrast-enhanced computed tomography (CT) aids in the differentiation between intrahepatic cholangiocarcinoma (ICC) and hepatocellular carcinoma (HCC). In this retrospective study, 113 patients with pathologically confirmed ICC (n = 39) or HCC (n = 74) who had undergone preoperative contrast-enhanced CT were enrolled. Enhancement values of the tumor (Etumor) and aorta (Eaorta) were obtained in the precontrast and equilibrium phase CT images. fECV was calculated using the following equation: fECV [%] = Etumor/Eaorta × (100 - hematocrit [%]). fECV values were compared between the ICC and HCC groups using Welch's t-test. The diagnostic performance of fECV for differentiating ICC and HCC was assessed using receiver-operating characteristic (ROC) analysis. fECV and the CT imaging features of tumors were evaluated by two radiologists. Multivariate logistic regression analysis was performed to identify factors predicting a diagnosis of ICC. Mean fECV was significantly higher in ICCs (43.8% ± 13.2%) than that in HCCs (31.6% ± 9.0%, p < 0.001). The area under the curve for differentiating ICC from HCC was 0.763 when the cutoff value of fECV was 41.5%. The multivariate analysis identified fECV (unit OR: 1.10; 95% CI: 1.01-1.21; p < 0.05), peripheral rim enhancement during the arterial phase (OR: 17.0; 95% CI: 1.29-225; p < 0.05), and absence of washout pattern (OR: 235; 95% CI: 14.03-3933; p < 0.001) as independent CT features for differentiating between the two tumor types. A high value of fECV, peripheral rim enhancement during the arterial phase, and absence of washout pattern were independent factors in the differentiation of ICC from HCC.

Sound-based sleep assessment with controllable subject-dependent embedding using Variational Domain Adversarial Neural Network

AbstractSleep quality assessment as an indicator of daily health care plays an important role in our physiological and mental activity. Sound during sleep contains rich information on biological activities, such as body movement, snoring, and sleep bruxism. However, sound features differ depending on individual and environmental differences. In order to develop a wide-rage applicable daily sleep assessment, this paper utilizes deep learning to ease individual and environmental differences of sound features. Firstly, by Variational Domain Adversarial Neural Network (VDANN) encodes sound events into latent representation, simultaneously eliminates subject-dependent features. Then, sleep pattern in the obtained latent space is trained by Long Short-Term Memory (LSTM) with associated sleep assessment of one night. We performed age group estimation from normal sleep as an objective indicator of sleep comparing to their age group. The experiment with more than 100 subjects showed that VDANN is able to extract subject independent features, and the proposed method outperforms the conventional method for age group estimation from sleep sound even for new subjects. In addition, our model is able to personalize by controlling subject-dependent embedding when after data accumulation of the subject.

HIDR: A Hierarchical Independent Detection and Recognition strategy for underwater acoustic multi-target recognition

This paper proposed HIDR (Hierarchical Independent Detection and Recognition), a novel strategy for underwater acoustic multi-target recognition. HIDR adopts a hierarchical architecture instead of the single-step traditional target recognition task, which is a relatively challenging task especially for the multi-target recognition. HIDR would firstly distinguish target signals from non-target signals as a detection stage, then pinpoint the specific target from all possible types of target signals as a recognition stage. This hierarchical architecture cannot only sharply reduce the difficulty of feature extraction, but also benefit for the higher recognition accuracy. A universal feature extraction strategy is utilized to extract two independent feature sets for the two stages respectively, which include auditory parameters especially adaptive to detection/recognition stages, as well as other common time/frequency domain features. Experiments with real sea trial data are conducted to compare HIDR with existing high-quality multi-target recognition schemes. Experimental results show that the proposed strategy can reach up to 88.71% of recognition accuracy in four-class recognition task, which is more than 5.25% higher than that of mainstream methods.

Prediction of postoperative reintervention risk for uterine fibroids using clinical-imaging features and T2WI radiomics before high-intensity focused ultrasound ablation

Objective To predict the risk of postoperative reintervention for uterine fibroids using clinical-imaging features and T2WI radiomics before high-intensity focused ultrasound (HIFU) ablation. Methods Among patients with uterine fibroids treated with HIFU from 2019 to 2021, 180 were selected per the inclusion and exclusion criteria (42 reintervention and 138 non-reintervention). All patients were randomly assigned to either the training (n = 125) or validation (n = 55) cohorts. Multivariate analysis was used to determine independent clinical-imaging features of reintervention risk. The Relief and LASSO algorithm were used to select optimal radiomics features. Random forest was used to construct the clinical-imaging model based on independent clinical-imaging features, the radiomics model based on optimal radiomics features, and the combined model incorporating the above features. An independent test cohort of 45 patients with uterine fibroids tested these models. The integrated discrimination index (IDI) was used to compare the discrimination performance of these models. Results Age (p < .001), fibroid volume (p = .001) and fibroid enhancement degree (p = .001) were identified as independent clinical-imaging features. The combined model had AUCs of 0.821 (95% CI: 0.712–0.931) and 0.818 (95% CI: 0.694–0.943) in the validation and independent test cohorts, respectively. The predictive performance of the combined model was 27.8% (independent test cohort, p < .001) and 29.5% (independent test cohort, p = .001) better than the clinical-imaging and radiomics models, respectively. Conclusion The combined model can effectively predict the risk of postoperative reintervention for uterine fibroids before HIFU ablation. It is expected to help clinicians to develop accurate, personalized treatment and management plans. Future studies will need to be prospectively validated.

Gated Multi-task Learning for QoS-aware Service Recommendation

In the ever-increasing diversity of cloud environment, the recommendation of web service-related applications based on service quality is a basic tasks that both service providers and web developers are very interested in. A key challenge is how to get personalized and accurate QoS values of web services from the multi-source information of users/services. In addition, complex contexts and multi-tasking attributes also make the collaborative services quality prediction difficult to meet. Inspired by the progress of multi-task deep learning, this paper proposes a new framework of service quality prediction called multi-task gated expert network (MGEN), which is based on gating mechanism and multi-task learning. The MGEN consists of three parts: expert-based context-source feature extraction, gated interaction learning and information fusion. First, multiple expert networks are used to capture the latent representation in raw data of web services, including both implicit features in the QoS matrix and explicit features of service descriptions. In the process, several independent experts extract features from different dimensions. Second, output embedding of different expert networks is transmitted to each task layer through different weights, learning both global and local high-order feature interactions. Third, the interactive information of different tasks is fused by embedding splicing, and then fed back to the prediction module for final service recommendation. Results of the comparative experiment demonstrate that the proposed MGEN significantly outperforms the state-of-the-art models of service recommendation, where both the implicit and explicit information of various multi-source features and interaction sequences are effectively extracted. In addition, the gating mechanism performs well in the QoS prediction by independently modeling each task.

Prinsip-Prinsip Praktis Bersikap dalam Mendampingi Orang Dewasa Belajar

With the special conditions of adults, teaching them needs to be based on appropriate practical principles. Although not the dominant determinant, educators still need to master it properly to be successful in accompanying adults in learning. Therefore it is necessary to study practical principles for the teacher in teaching adults. Through a literature review, an analysis and synthesis of previous findings has been carried out. At least there are six affective principles that need to be considered, namely recognizing them as adults, paying attention to their experiences, understanding their needs, understanding their goals, strengthening their motivation, appreciating the uniqueness of each individual, and giving roles in the main group. Teachers manage adult study groups keeping in mind their independent, personal and experienced features. If the practical principles of the application will increase the effectiveness of interpersonal relationships that respect each other and a conducive adult learning atmosphere.