Network-based Learning Model Research Articles

CHL-DTI: A Novel High-Low Order Information Convergence Framework for Effective Drug-Target Interaction Prediction.

Recognizing drug-target interactions (DTI) stands as a pivotal element in the expansive field of drug discovery. Traditional biological wet experiments, although valuable, are time-consuming and costly as methods. Recently, computational methods grounded in network learning have demonstrated great advantages by effective topological feature extraction and attracted extensive research attention. However, most existing network-based learning methods only consider the low-order binary correlation between individual drug and target, neglecting the potential higher-order correlation information derived from multiple drugs and targets. High-order information, as an essential component, exhibits complementarity with low-order information. Hence, the incorporation of higher-order associations between drugs and targets, while adequately integrating them with the existing lower-order information, could potentially yield substantial breakthroughs in predicting drug-target interactions. We propose a novel dual channels network-based learning model CHL-DTI that converges high-order information from hypergraphs and low-order information from ordinary graph for drug-target interaction prediction. The convergence of high-loworder information in CHL-DTI is manifested in two key aspects. First, during the feature extraction stage, the model integrates both high-level semantic information and low-level topological information by combining hypergraphs and ordinary graph. Second, CHL-DTI fully fuse the innovative introduced drug-protein pairs (DPP) hypergraph network structure with ordinary topological network structure information. Extensive experimentation conducted on three public datasets showcases the superior performance of CHL-DTI in DTI prediction tasks when compared to SOTA methods. The source code of CHL-DTI is available at https://github.com/UPCLyy/CHL-DTI .

Thermal Control Performance of a Network-based Learning Controller in a Very Hot and Humid Area

Purpose: In order to improve the energy strategies for a building space, various control methods of supply air have been examined in aspects of its energy efficiency and users’ thermal satisfaction. This simulation study examines the network-based learning model’s capability to maintain the thermal comfort without compromising on its energy efficiency especially in a very hot and humid area. Method: A network-based learning controller is proposed to optimize the supply air conditions to meet desired values of set-point temperature and comfort levels by regulating the amount of air and its temperature elaborately. Result: In a comparison with two other types of controllers, the proposed model improves the thermal comfort by about 29.3% than the conventional thermostat controller, and increases the energy efficiency by about 17.2% than the fuzzy-based controller. It is concluded that the network-based learning algorithm properly works to manage its supply air condition to improve spatial thermal quality in a very hot and humid area.

NMDA Receptor Alterations After Mild Traumatic Brain Injury Induce Deficits in Memory Acquisition and Recall.

Mild traumatic brain injury (mTBI) presents a significant health concern with potential persisting deficits that can last decades. Although a growing body of literature improves our understanding of the brain network response and corresponding underlying cellular alterations after injury, the effects of cellular disruptions on local circuitry after mTBI are poorly understood. Our group recently reported how mTBI in neuronal networks affects the functional wiring of neural circuits and how neuronal inactivation influences the synchrony of coupled microcircuits. Here, we utilized a computational neural network model to investigate the circuit-level effects of N-methyl D-aspartate receptor dysfunction. The initial increase in activity in injured neurons spreads to downstream neurons, but this increase was partially reduced by restructuring the network with spike-timing-dependent plasticity. As a model of network-based learning, we also investigated how injury alters pattern acquisition, recall, and maintenance of a conditioned response to stimulus. Although pattern acquisition and maintenance were impaired in injured networks, the greatest deficits arose in recall of previously trained patterns. These results demonstrate how one specific mechanism of cellular-level damage in mTBI affects the overall function of a neural network and point to the importance of reversing cellular-level changes to recover important properties of learning and memory in a microcircuit.

Network Energy Optimization of IOTs in Wireless Sensor Networks Using Capsule Neural Network Learning Model

In this paper, an effective network energy optimization is carried out for the internet of things (IoTs) sensor nodes in respect of the wireless sensor networks. A capsule neural network architectural model is proposed here to achieve better performance by minimizing the network energy overhead for the wireless sensor network (WSN) aided internet of things. In WSN models, each sensor nodes gets communicated in a diversified manner for transferring the information from the cloud IoT to the virtual modules. Basically, the process of clustering in sensor networks aids in improving the network quality by controlling the energy consumption rate and improving the rate of data accuracy. Optimization of internet of things in wireless sensor networks that aims in managing the energy and accuracy rate involves highly complex clustering algorithms. Due to which, this research paper is intended to develop a new capsule neural network based learning model that takes care in maintaining the network energy in an optimal level thereby maintaining a better throughput and accuracy with network overhead been taken care off. Capsule neural network (CNN) architecture is a plausible neural model and is proven to be effective for routing and for optimization operations wherein the capsule’s activation is calculated at the time of forward pass. The main contribution of this paper is to model a novel neural network architectural model for improving the sensor network performance and as well to carry out optimization of network overhead that is present between the cloud storage space and the wireless sensor network model. Also, the designed neural network architecture aims to optimize the network energy utilization by selecting the optimal nodes in the wireless sensor environment. Simulation results attained establishes the reliability and effectiveness of the proposed CNN learning for energy optimization of IOTs in sensor networks in comparison with that of the existing methods from literature.

SHVC CU Processing Aided by a Feedforward Neural Network

The development of multimedia and hardware technologies has led to a great number of industrial video applications, such as virtual reality, high-definition video surveillance, and remote monitoring. As complex communication environments and heterogeneous networks are common in industrial applications, industrial videos are required to support a diverse range of display resolutions and transmission channel capacities. Scalable high-efficiency video coding (SHVC) standards provide the tools to meet this requirement. However, it is highly computationally expensive. Coding complexity has a great impact on SHVC performance in industrial applications. Many of these applications are sensitive to time delay and have limited power. Thus, improvements are required to ensure the practical usability of SHVC encoders. In SHVC encoders, intra/interprediction of variable coding unit (CU) sizes is independently performed for the base and enhancement layers (ELs). There are many interlayer similarities that can be exploited to speed up the procedure for EL coding. In this paper, we propose a feedforward neural network aided model for CU size and mode decisions for SHVC, which utilizes base layer coding information and the coding data of spatiotemporal neighboring CUs to decide which CU sizes or prediction modes can be bypassed for certain EL CUs. Two feedforward neural network based learning models are built for CU classification, which are introduced in the procedures for CU size and mode decisions, respectively. According to the analysis from a large number of video sequences, the representative features are directly extracted from the coding information of previously coded neighboring CUs to avoid computational overheads. After the training is finished, these two models are designed and integrated to build classifiers. Then, two online classification approaches are designed for the CU size and mode decision procedures to classify each CU's type. Finally, different candidate CU sizes and prediction modes are adaptively assigned for each type of CU. This approach outperforms the state-of-the-art fast SHVC/high-efficiency video coding (HEVC) algorithms with approximately 19–42% coding time savings or better compression efficiency, which will be beneficial for the realization of real-time scalable video coding.

A Sigmoid based Learning in Heterogeneous Distortion for Data Privacy

Neural network-based learning models along with an access to huge data have made a remarkable outcome in recent years. These models are contributing a lot to improvise the working dimensions of various domains like Speech recognition, Image processing, Text analysis and many more. The well represented data is the main resource in the current research, but this data is often privacy sensitive and it definitely needs a proper attention failing which leads to serious privacy concerns. The proposed work demonstrates how learning models can be applied to analyze the data sensitivity and classify them to various privacy classes. Once the privacy class distribution is performed the model applies Inverse laplacian query model to check the data utility. The data should not get compromised on utility with the curse of privacy. With this intention the given experimental study succeeded in training the network to perform privacy analysis under a modest privacy budget, complexity training efficiency and data utility.

Hybrid Model for Passive Locomotion Control of a Biped Humanoid:The Artificial Neural Network Approach

Developing a correct model for a biped robot locomotion is extremely challenging due to its inherently unstable structure because of the passive joint located at the unilateral foot-ground contact and varying configurations throughout the gait cycle, resulting variation of dynamic descriptions and control laws from phase to phase. The present research describes the development of a hybrid biped model using an Open Dynamics Engine (ODE) based analytical three link leg model as a base model and, on top of it, an Artificial Neural Network based learning model which ensures better adaptability, better limits cycle behaviors and better generalization while negotiating along a down slope. The base model has been configured according to the individual subjects and data have been collected using a novel technique through an android app from those subjects while walking down a slope. The pattern between the deviation of the actual trajectories and the base model generated trajectories has been found using a back propagation based artificial neural network architecture. It has been observed that this base model with learning based compensation enables the biped to better adapt in a real walking environment, showing better limit cycle behaviors. We also observed the bounded nature of deviation which led us to conclude that the strategy for biped locomotion control is generic in nature and largely dominated by learning.

PEACE-Home: Probabilistic estimation of abnormal clinical events using vital sign correlations for reliable home-based monitoring

The objective of this study is to develop a probabilistic model for predicting the future clinical episodes of a patient using observed vital sign values prior to the clinical event. Vital signs (e.g. heart rate, blood pressure) are used to monitor a patient’s physiological functions of health and their simultaneous changes indicate a transition of a patient’s health status. If such changes are abnormal then it may lead to serious physiological deterioration. Chronic patients living alone at home die of various diseases due to the lack of an efficient automated system having prior prediction ability. Our developed system can make probabilistic predictions of future clinical events of an unknown patient in real-time using the learned temporal correlations of multiple vital signs from many similar patients. In this paper, Principal Component Analysis (PCA) is used to separate patients with known medical conditions into multiple categories and then Hidden Markov Model (HMM) is adopted for probabilistic classification and prediction of future clinical states. The advantage of using dynamic probabilistic model over static predictor model for solving our problem is analysed by comparing the results obtained from HMM with a neural network based learning model. Both the learning models are trained and evaluated using six vital signs data of 1023 patient records collected from the MIMIC-II database of MIT physiobank archive. The best HMM models are selected using maximum likelihood probabilities and further used in personalized remote monitoring system to forecast the most probable forthcoming clinical states of a continuously monitored patient. The scalable power of cloud computing is utilized for fast learning of various clinical events from large samples. Our results suggest that the developed technique using multiple physiological parameter trends can significantly enhance the traditional home-based monitoring systems in terms of clinical abnormality detections and predictions.

On modeling microscopic vehicle fuel consumption using radial basis function neural network

Energy conservation is one of the central challenges for the transportation system today. A variety of microscopic vehicle fuel consumption models have been developed to support eco-friendly transport strategies. However, most existing models are regression based and are sensitive to the vehicle-specific parameters and the operating conditions, therefore, an expensive and time-consuming calibration procedure is always indispensable in these models' application. In this paper, we propose an artificial neural network-based model to avoid the calibration problem. The main works include: (1) collect extensive field datasets such as large-scale controller area network bus to reflect the local transportation environment's fuel consumption characteristics; (2) conduct correlational analysis to identify the key fuel consumption influence factors; (3) develop a radial basis function neural network-based learning model to capture the nonlinear relationship between the key factors and the corresponding fuel consumption values based on the collected training datasets. The proposed model can give a reasonable prediction of instantaneous fuel consumption without calibration. The effectiveness of the proposed model is validated from a combination of both in-lab and field experiments.

Research on applying the network-based learning model into public PE courses in a university

After studying a number of literature references and applying theories into practice, the author explores the application of the network-based learning model into public physical education (PE) courses in a university. Based on the 3a (three-year online courses) teaching reform practice, the study result shows that the students who use the network-based learning mode in the experimental group increase their physical quality more significantly than the control group after the second year. Also, the students in the experimental group participate in more extra-curricular activities. In addition, the students show great interest in the network-based learning mode. The result indicate that, for the teaching reform of college public PE courses, creating a teaching website based on the campus network and changing two-year public PE compulsory face-to-face courses to three-year online courses can be a future direction and a feasible trend; and class hours can be better managed by using the network and information technology. It has practical values and universal guiding significance for the current college PE course reform in the context of China and other similar developing countries.

A Proposed Collaborative Computer Network-Based Learning Model for Undergraduate Students with Different Learning Styles

In this information and communication technology age, computer network-based learning is widely used for expanding learning opportunities and facilitating learning activities to students separated by time and distance as well as for delivering effective content to students and instructors interacting with each other in a face-to-face classroom. Collaborative Computer Network Based Learning (CCNBL), in particular, is appropriate for learner center, constructivist, and problems-solving activities in that it uses computer network technologies for effective communication in learning activities. However, differences in student learning styles are one of the major problems that affect all students who prefer not use the same style of activity for effective learning. With that in mind, the best method is to use specific activities designed for each student learning style but this is difficult to do because there are a wide variety of student characteristics in virtual classroom. This research shows a way to solve this problem by developing Collaborative Computer Network Based Learning model for all student learning styles to receive effective learning at the same level by using KOLB’s learning styles. By supporting learning activities for this developing prototype model, designers can integrate collaborative learning technologies and collaborative learning strategies in the design and development process. The result from this process is an appropriate Collaborative Computer Network Based Learning model for higher education level.