Supervised Learning Mechanism Research Articles

Intelligent neural computing to investigate the heat and mass transmission in nanofluidic system between two rotating permeable disks: Supervised learning mechanism

The prime objective of the present study is to investigate the effectiveness and accuracy of a single-trained artificial neural network. The Levenberg-Marquardt Backpropagated networks are tested for heat and mass transmission in magnetized hybrid nanofluid flow between the rotating permeable system. The reference data to generate different cases for distinct scenarios has been obtained using the Adams method in Mathematica using the ND-Solver function. Additionally, the system of highly nonlinear PDE's is achieved and transformed into ODE's. The effect of body forces such as thermophoresis particle diffusion and Brownian motion are incorporated in the hybrid nanofluid system. Configuration under observation is permeable and under constant impact of the magnetic field. Rosseland thermal radiation approximation relation is utilized to investigate the linear impact of radiation on velocity and temperature profile. The accuracy and effectiveness of the proposed ANNLMB are depicted with performance demonstrations. Mean square error, histogram error, and regression plots are generated for all the scenarios to discuss the varying impact of different key study parameters on the performance of the proposed ANNLMB. Furthermore, the generated reference data is distributed in the following manner 82 %, 9 %, and 9 % for training, testing, and validation, respectively.

Attention‐based prohibited item detection in X‐ray images during security checking

AbstractThis paper focuses on the intelligent detection of prohibited items in X‐ray images during the security checking process. An intelligent semantic segmentation model of prohibited items in X‐ray images is proposed based on the attention‐based object localization method. Based on the pre‐trained CNN classification framework, the attention mechanism can map the high‐layer semantic information of objects into the input space, while generating energy saliency maps to locate the prohibited items. In order to make the obtained attention maps discriminative, the lateral and contrastive inhibition strategies are introduced and combined together which can highlight the responses of activated neurons. Under the guidance of attention responses, two traditional image segmentation algorithms are employed to achieve the semantic segmentation results for the prohibited items detection in X‐ray images. The proposed semantic segmentation model relies on weakly supervised learning mechanism, and only depends on the category labels of prohibited items, which greatly avoids the work cost of data semantic annotation. The experimental results based on the public SIXray baseline and the self‐built X‐ray image database demonstrate the proposed method can achieve about 65% IoU localization precise averagely. In addition, comparison experiments were carried out with the state‐of‐the‐arts and ablation experiments to verify the effectiveness of the proposed model.

A Sub-Second Method for SAR Image Registration Based on Hierarchical Episodic Control

For Synthetic Aperture Radar (SAR) image registration, successive processes following feature extraction are required by both the traditional feature-based method and the deep learning method. Among these processes, the feature matching process—whose time and space complexity are related to the number of feature points extracted from sensed and reference images, as well as the dimension of feature descriptors—proves to be particularly time consuming. Additionally, the successive processes introduce data sharing and memory occupancy issues, requiring an elaborate design to prevent memory leaks. To address these challenges, this paper introduces the OptionEM-based reinforcement learning framework to achieve end-to-end SAR image registration. This framework outputs registered images directly without requiring feature matching and the calculation of the transformation matrix, leading to significant processing time savings. The Transformer architecture is employed to learn image features, while a correlation network is introduced to learn the correlation and transformation matrix between image pairs. Reinforcement learning, as a decision process, can dynamically correct errors, making it more-efficient and -robust compared to supervised learning mechanisms such as deep learning. We present a hierarchical reinforcement learning framework combined with Episodic Memory to mitigate the inherent problem of invalid exploration in generalized reinforcement learning algorithms. This approach effectively combines coarse and fine registration, further enhancing training efficiency. Experiments conducted on three sets of SAR images, acquired by TerraSAR-X and Sentinel-1A, demonstrated that the proposed method’s average runtime is sub-second, achieving subpixel registration accuracy.

Bayesian self-supervised learning allying with Transformer powered compressed sensing imaging

Deep learning based compressed sensing imaging algorithms usually adopt supervised learning mechanism, which generally require massive high-quality images paired with the measured data in the training process. However, clear images are difficult to obtain in some specific application scenarios. In view of this, we propose a self-attention powered multi-scale compressed sensing imaging network named BNN-SANet with the Bayesian self-supervised learning manner in this paper. BNN-SANet can automatically learn effective feature representation from the measured data and reconstruct high-quality images without large-scale training samples. In particular, the self-attention based Transformer employed in BNN-SANet is effective to exploit global and long-range dependencies. Multi-scale dual path design in BNN-SANet performs well in extracting the semantic information at different scales to further improve the CS reconstruction quality. Experimental results illustrate that the proposed approach is substantially superior to previous compressed sensing imaging methods in terms of Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and visual metrics.

Semi-supervised approach for tweet-level stress detection

Psychological stress detection through social media has caught the interest of researchers due to the emergence of social media platforms like Twitter as major data sources to solicit human emotions and interactions. The problem of tweet-level stress detection is solved using various supervised learning mechanisms described in the existing literature. Given the real-world scenario in which there is a scarcity of labeled data and an abundance of unlabeled data, the semi-supervised solutions form an ideal choice. In this work, a semi-supervised approach called “Self-training Method for Tweet-level Stress Detection (SMTSD)” is proposed to extend the self-training approach for utilizing the information from sarcasm in predicting the pseudo-labels. In SMTSD, logistic regression is used as the base classifier. The predicted pseudo-labels are then used to train and build supervised baseline models on all the datasets collected using Twitter’s Tweepy API. The proposed solution of SMTSD, with the usage of sarcasm in predicting the pseudo-label, surpasses the performance of the basic self-training approach. Moreover, the proposed model also outperforms the supervised models considered and also gives better performance than the state-of-the-art techniques like Bi-LSTM. It is demonstrated that as the sample size for combined data of tweets with predicted pseudo-labels increases, so does the performance of the supervised models trained on them.

Unsupervised Learning-Based Framework for Deepfake Video Detection

With the continuous development of computer hardware equipment and deep learning technology, it is easier for people to swap faces in videos by currently-emerging multimedia tampering tools, such as the most popular deepfake. It would bring a series of new threats of security. Although many forensic researches have focused on this new type of manipulation and achieved high detection accuracy, most of which are based on supervised learning mechanism with requiring a large number of labeled samples for training. In this paper, we first develop a novel unsupervised detection manner for identifying deepfake videos. The main fundamental behind our proposed method is that the face region in the real video is taken by the camera while its counterpart in the deepfake video is usually generated by the computer; the provenance of two videos is totally different. Specifically, our method includes two clustering stages based on Photo-Response Non-Uniformity (PRNU) and noiseprint feature. Firstly, the PRNU fingerprint of each video frame is extracted, which is used to cluster the full-size identical source video (regardless of its real or fake). Secondly, we extract the noiseprint from the face region of the video, which is used to identify (re-cluster for the task of binary classification) the deepfake sample in each cluster. Numerical experiments verify our proposed unsupervised method performs very well on our own dataset and the benchmark FF++ dataset. More importantly, its performance rivals that of the supervised-based state-of-the-art detectors.

Stepwise Adaptive Convolutional Network for Fault Diagnosis of High-Speed Train Bogie Under Variant Running Speeds

Fault diagnosis of high-speed train (HST) bogie plays an indispensable role in guaranteeing the safety and stability of the daily operation of HST. Up to now, the well-established fault diagnosis models of HST bogie, which are usually trained by supervised learning mechanism, require that the training and testing data satisfy the same probability distribution. Consequently, those methods could lose their efficacy when the probability distribution of the testing data is changed owing to the variation of HST running speed and the labeled data corresponding to the changed speed is absent. To address this, a stepwise adaptive convolutional network (SACN) is proposed to learn the domain-invariant features of vibration data in different speed domains. Moreover, a novel in-and-out stepwise transfer method is designed to deal with the scenario of continuous change in vehicle speed. The experimental tests of the proposed method are conducted using the dataset acquired by SIMPACK via the HST model CRH380 A, mainly addressing the single and compound failure classification problem of the three key components of HST bogie, namely, the air spring, antiyaw damper, and lateral damper. Overall, the proposed SACN achieves an average accuracy of 96.1%, demonstrating the remarkable performance of domain adaptation in performing fault diagnosis of HST bogie under variant running speeds.

Backpropagation of Levenberg Marquardt artificial neural networks for wire coating analysis in the bath of Sisko fluid

In the artificial neural networks domain, the Levenberg-Marquardt technique is novel with convergent stability and generates a numerical solution of the wire coating system for Sisko fluid flow (WCS-SFF) through regression plots, histogram representations, state transition measures, and means squared errors. In this paper, the analysis of fluid flow problem based on WCS-SFF is studied with a new application of intelligent computing system via supervised learning mechanism using the efficacy of neural networks trained by Levenberg-Marquardt algorithm (NN-TLMA). The original mathematical formulation in terms of PDEs for WCS-SFF is converted into dimensionless nonlinear ODEs. The data collection for the projected NN-TLMA is produced for parameters associated with the system model WCS-SFF influencing the velocity using the explicit Runge-Kutta technique. The training, validation, and testing processes of NN-TLMA are utilized to evaluate the obtained results of WCS-SFF for various cases, and a comparison of the obtained results is performed with reference data set to check the accuracy and effectiveness of the proposed algorithm NN-TLMA for the analysis of non-Newtonian fluid problem-related WCS-SFF. The proposed NN-TLMA for solving the WCS-SFF is effectively confirmed through state transition dynamics, mean square error, regression analyses, and error histogram studies. The powerful consistency of suggested outcomes with reference solutions indicates the validity of the framework, and the accuracy of 10-8 to 10-6 is also achieved.

Mining Likely Analogical APIs Across Third-Party Libraries via Large-Scale Unsupervised API Semantics Embedding

Establishing API mappings between third-party libraries is a prerequisite step for library migration tasks. Manually establishing API mappings is tedious due to the large number of APIs to be examined. Having an automatic technique to create a database of likely API mappings can significantly ease the task. Unfortunately, existing techniques either adopt supervised learning mechanism that requires already-ported or functionality similar applications across major programming languages or platforms, which are difficult to come by for an arbitrary pair of third-party libraries, or cannot deal with lexical gap in the API descriptions of different libraries. To overcome these limitations, we present an unsupervised deep learning based approach to embed both API usage semantics and API description (name and document) semantics into vector space for inferring likely analogical API mappings between libraries. Based on deep learning models trained using tens of millions of API call sequences, method names and comments of 2.8 millions of methods from 135,127 GitHub projects, our approach significantly outperforms other deep learning or traditional information retrieval (IR) methods for inferring likely analogical APIs. We implement a proof-of-concept website ( https://similarapi.appspot.com ) which can recommend analogical APIs for 583,501 APIs of 111 pairs of analogical Java libraries with diverse functionalities. This scale of third-party analogical-API database has never been achieved before.

Design and Implementation of an Efficient Rose Leaf Disease Detection using K Nearest Neighbours

Plants are prone to different diseases caused by multiple reasons like environmental conditions, light, bacteria, and fungus. These diseases always have some physical characteristics on the leaves, stems, and fruit, such as changes in natural appearance, spot, size, etc. Due to similar patterns, distinguishing and identifying category of plant disease is the most challenging task. Therefore, efficient and flawless mechanisms should be discovered earlier so that accurate identification and prevention can be performed to avoid several losses of the entire plant. Therefore, an automated identification system can be a key factor in preventing loss in the cultivation and maintaining high quality of agriculture products. This paper introduces modeling of rose plant leaf disease classification technique using feature extraction process and supervised learning mechanism. The outcome of the proposed study justifies the scope of the proposed system in terms of accuracy towards the classification of different kind of rose plant disease.

Adaptive Packet Padding Approach for Smart Home Networks: A Tradeoff Between Privacy and Performance

The presence of connected devices in homes introduces numerous threats to privacy via the analysis of the encrypted traffic these devices generate. Prior works have shown that traffic attributes such as packet size combined with machine learning techniques enable the inference of private information from Internet of Things users. One of the commonly used techniques to mitigate those privacy threats is traffic obfuscation, such as packet padding. Most padding mechanisms that were previously proposed statically select the number of bytes inserted in the packets, which incurs high overhead and ineffective privacy improvement. These static mechanisms are particularly unsuitable for networks whose traffic patterns are significantly dynamic, such as smart homes. This article proposes an adaptive packet padding approach based on software-defined networking (SDN) that adjusts the number of bytes inserted into packets in response to variations in the home network utilization. The proposed technique monitors the network to instruct a padding mechanism through a representational state transfer (REST) interface proposed in this article. This mechanism ensures that the length of packets generated by connected devices is modified. The evaluation includes four supervised learning mechanisms, random forest (RF), support vector machine (SVM), decision tree, and k-nearest neighbors (KNNs), to measure privacy improvement through the metrics accuracy, recall, and F1-score. Goodput, jitter, and packet loss induced by the proposal are also evaluated. Our proposal is shown to overcome the state-of-the-art solutions in privacy preservation with a significantly lower overhead. For instance, the accuracy of RF on identifying devices decreases from 96% to 4.96%.

Identification of Least Risk Path using GA-SVM for the Software Project Management

Risk management is an important part of the development cycles for high quality applications. Most specific threats are incidents that may adversely affect the plan or organizational climate growth. The major risk factors contains time, budget and resources can affect adversely by events. Important considerations such as plan, time and cost are generally impacted. Essentially, risk assessment includes recognizing, assessing, preparing and monitoring incidents that affect the atmosphere of the project. Risk is the danger of volatility, lack of knowledge regarding events, activities and lack of appropriate technologies for managing measures and activities. Therefore, both exogenous and endogenous influences contribute in the venture risks and uncertainties. The high task failure rates due to poor planning of project which can limit the teams and future wealth creation, while project managers should allow for the plan being to anticipate potential risks when preparing their project achievements based on their own past experiences. This paper addresses the Supervised Learning mechanism with multi-label Support Vector Classifier (SVC) to predict the project risks and apply Genetic algorithm for providing avoidance action as recommendation.

SOM-Based Direct Inverse Trajectory Control System for Double-Propeller Boat Maneuvers

This paper presents the development of neural-network-based control system using self-organizing-maps (SOMs) for the maneuvers of a double-propeller boat. The performance characteristics of the developed SOM controller system are compared with a widely-used supervised learning mechanism, the backpropagation neural network (BPNN) controller. The experimental results show that the proposed unsupervised SOM controller can control the boat model with very low error, although most artificial neural network (ANN)-based controllers are usually designed using supervised learning approaches. The important characteristic of the proposed SOM controller system is that it utilizes a mapping principle instead of an error calculation such as that in the BPNN controller system; consequently, the proposed SOM controller system is not very sensitive to non-ideal training data, which produces a low control error for the generated elliptical trajectory data. It is also confirmed in these experiments that when more mapping neurons are utilized in the SOM controller, a lower control error is achieved. It is expected that in a real implementation, the SOM controller could provide more robust control than the BPNN controller in handling small disturbances such as light winds and small waves.

A Stable Distributed Neural Controller for Physically Coupled Networked Discrete-Time System via Online Reinforcement Learning

The large scale, time varying, and diversification of physically coupled networked infrastructures such as power grid and transportation system lead to the complexity of their controller design, implementation, and expansion. For tackling these challenges, we suggest an online distributed reinforcement learning control algorithm with the one-layer neural network for each subsystem or called agents to adapt the variation of the networked infrastructures. Each controller includes a critic network and action network for approximating strategy utility function and desired control law, respectively. For avoiding a large number of trials and improving the stability, the training of action network introduces supervised learning mechanisms into reduction of long-term cost. The stability of the control system with learning algorithm is analyzed; the upper bound of the tracking error and neural network weights are also estimated. The effectiveness of our proposed controller is illustrated in the simulation; the results indicate the stability under communication delay and disturbances as well.

A study on the cognitive model of robot sensorimotor system1

A cognitive model for sensorimotor system of self-rebalancing robot is presented based on Skinner operant conditioning principle. The model mainly consists of three parts, which are cerebellum, basal ganglia and cerebral cortex. In the model, the cerebellum realizes the mapping from sensorimotor st ates to actions by supervised learning mechanism, the basal ganglia decides the proper action based on the operant conditioning theory and the results of action forecast evaluation, and the cerebral cortex sends collected information to cerebellum and basal ganglia and consequently forms the closed loop feedback sensorimotor system. The structure, function and algorithm of the proposed model are presented in this paper. Simulation and experimental results on a two-wheeled robot demonstrate that this model has better cognitive characters and it enables the robot to master the skill of balance control in movement through self-learning.

Fault Diagnosis of Supervision and Homogenization Distance Based on Local Linear Embedding Algorithm

In view of the problems of uneven distribution of reality fault samples and dimension reduction effect of locally linear embedding (LLE) algorithm which is easily affected by neighboring points, an improved local linear embedding algorithm of homogenization distance (HLLE) is developed. The method makes the overall distribution of sample points tend to be homogenization and reduces the influence of neighboring points using homogenization distance instead of the traditional Euclidean distance. It is helpful to choose effective neighboring points to construct weight matrix for dimension reduction. Because the fault recognition performance improvement of HLLE is limited and unstable, the paper further proposes a new local linear embedding algorithm of supervision and homogenization distance (SHLLE) by adding the supervised learning mechanism. On the basis of homogenization distance, supervised learning increases the category information of sample points so that the same category of sample points will be gathered and the heterogeneous category of sample points will be scattered. It effectively improves the performance of fault diagnosis and maintains stability at the same time. A comparison of the methods mentioned above was made by simulation experiment with rotor system fault diagnosis, and the results show that SHLLE algorithm has superior fault recognition performance.

Evidence for Cerebellar Contributions to Adaptive Plasticity in Speech Perception.

Human speech perception rapidly adapts to maintain comprehension under adverse listening conditions. For example, with exposure listeners can adapt to heavily accented speech produced by a non-native speaker. Outside the domain of speech perception, adaptive changes in sensory and motor processing have been attributed to cerebellar functions. The present functional magnetic resonance imaging study investigates whether adaptation in speech perception also involves the cerebellum. Acoustic stimuli were distorted using a vocoding plus spectral-shift manipulation and presented in a word recognition task. Regions in the cerebellum that showed differences before versus after adaptation were identified, and the relationship between activity during adaptation and subsequent behavioral improvements was examined. These analyses implicated the right Crus I region of the cerebellum in adaptive changes in speech perception. A functional correlation analysis with the right Crus I as a seed region probed for cerebral cortical regions with covarying hemodynamic responses during the adaptation period. The results provided evidence of a functional network between the cerebellum and language-related regions in the temporal and parietal lobes of the cerebral cortex. Consistent with known cerebellar contributions to sensorimotor adaptation, cerebro-cerebellar interactions may support supervised learning mechanisms that rely on sensory prediction error signals in speech perception.

An investigation into the application of ensemble learning for entailment classification

Textual entailment is a task for which the application of supervised learning mechanisms has received considerable attention as driven by successive Recognizing Data Entailment data challenges. We developed a linguistic analysis framework in which a number of similarity/dissimilarity features are extracted for each entailment pair in a data set and various classifier methods are evaluated based on the instance data derived from the extracted features. The focus of the paper is to compare and contrast the performance of single and ensemble based learning algorithms for a number of data sets. We showed that there is some benefit to the use of ensemble approaches but, based on the extracted features, Naïve Bayes proved to be the strongest learning mechanism. Only one ensemble approach demonstrated a slight improvement over the technique of Naïve Bayes.

Enabling cross-site interactions in social networks

Online social networks is one of the major technological phenomena on the Web 2.0. Hundreds of millions of people are posting articles, photos, and videos on their profiles and interacting with other people, but the sharing and interaction are limited within a same social network site. Although users can share some contents in a social network site with people outside of the social network site using a secret address of content, appropriate access control mechanisms are still not supported. To overcome this limitation, we propose a cross-site interaction framework x-mngr, allowing users to interact with users in other social network sites, with a cross-site access control policy, which enables users to specify policies that allow/deny access to their shared contents across social network sites. We also propose a partial mapping approach based on a supervised learning mechanism to map user’s identities across social network sites. We implemented our proposed framework through a photo album sharing application that shares user’s photos between Facebook and MySpace based on the cross-site access control policy that is defined by the content owner. Furthermore, we provide mechanisms to enable users to fuse user-mapping decisions that are provided by their friends or others in the social network. We implemented our framework and through extensive experimentation we prove the accuracy and precision of our proposed mechanisms.

Semantic real-world image classification for image retrieval with fuzzy-ART neural network

Image retrieval based on semantic learning has attracted considerable attention in recent years. Analyzing the contents of an image and retrieving corresponding semantics are important in semantic-based image retrieval systems. Region-based image retrieval systems attempt to reduce the gap between high-level semantics and low-level features by representing images at the object level. In this paper, we apply principal component analysis to extract significant region features and then incorporate them into the proposed two-phase fuzzy adaptive resonance theory neural network (Fuzzy-ARTNN) for real-world image content classification. In general, Fuzzy-ARTNN is an unsupervised classifier. The training patterns in image content analysis are labeled with corresponding categories. This category information is useful for supervised learning. Thus, a supervised learning mechanism is added to label the category of the cluster centers derived by the Fuzzy-ARTNN. Moreover, based on the content analysis by the proposed two-phase Fuzzy-ART, each region in an image is associated with a high-level semantic concept. The proposed system supports both query by keyword(s) with/without region size and query by specified region(s). Experimental results show that the proposed method has high accuracy for semantic-based photograph content analysis and that the results of photograph content analysis are similar to the perception of human eyes. In addition, the semantic-based image retrieval system has a high retrieval rate.