Extreme learning machine and bayesian optimization-driven intelligent framework for IoMT cyber-attack detection

The Journal of Supercomputing - The Internet of Medical Things (IoMT) is a bionetwork of allied medical devices, sensors, wearable biosensor devices, etc. It is gradually reforming the healthcare...     

Elitist teaching–learning-based optimization (ETLBO) with higher-order Jordan Pi-sigma neural network: a comparative performance analysis

An adaptive p-step prediction model for nonlinear dynamic processes is developed in this paper and implemented with a radial basis function (RBF) network. The model can predict output for multi-step-ahead with no need for the unknown future process output. Therefore, the long-range prediction accuracy is significantly enhanced and consequently is especially useful as the internal model in a model predictive control framework. An improved network structure adaptation is also developed with the recursive orthogonal least squares algorithm. The developed model is online updated to adapt both its structure and parameters, so that a compact model structure and consequently a less computing cost are achieved with the developed adaptation algorithm applied. Two nonlinear dynamic systems are employed to evaluate the long-range prediction performance and minimum model structure and compared with an existing PSC model and a non-adaptive RBF model. The simulation results confirm the effectiveness of the developed model and superior over the existing models.

     

Intelligent system for COVID-19 prognosis: a state-of-the-art survey

Applied Intelligence - This 21st century is notable for experiencing so many disturbances at economic, social, cultural, and political levels in the entire world. The outbreak of novel corona virus...     

Follower Link Prediction Using the XGBoost Classification Model with Multiple Graph Features

Wireless Personal Communications - The Follower Link Prediction is an emerging application preferred by social networking sites to increase their user network. It helps in finding potential unseen...     

On Low Latency Uplink Scheduling for Cellular Haptic Communication to Support Tactile Internet

Haptic communication is a form of non-verbal communication involving touch and feel. Haptic communication is a major requirement for the Tactile Internet that deals with mechanism to transmit touch, feel, and skills between two geographically distant entities, in realtime. Lately, haptic communication has become an essential requirement for variety of realtime robotic and Augmented/Virtual Reality applications. With very stringent delay and reliability requirements, haptic communication poses significant challenges for network engineers. This becomes further complicated when the cellular technology is used as the access medium for haptic communication. Since cellular networks are resource constrained, accommodating haptic users along with existing non-haptic users become a hard scheduling problem. In this paper, we propose an efficient latency-aware uplink resource allocation scheme satisfying end-to-end delay requirements of haptic users in a Long Term Evolution based cellular network. The proposed scheme first predicts the downlink and processing delays for users’ transmission flows. Subsequently, the model apply an optimal scheduling scheme for the uplink transmissions which satisfies expected end-to-end latency constraint. Our extensive simulations indicate that the proposed algorithm outperforms some of the widely used state-of-the-art scheduling schemes.

     

Traceability Issue in PM2.5 and PM10 Measurements

Nowadays particle size and mass concentration measurements are the important parameter of the ambient air quality standards of several countries. The regulatory limits of mass concentration of particulate matter (PM) for the size classes of PM_2.5 and PM₁₀, i.e., particle sizes of less than or equal to 2.5 and 10 μm in aerodynamic diameter, respectively in air are defined on yearly and hourly time-weighted-average basis. However, these limits are different in different regulations of the countries. Both of the parameters relate with the human health, climate and other issues, therefore accurate and precise measurement of these parameters are very important. Despite this, so far not much work has progressed in national metrology institutes (NMIs) worldwide on calibration and traceability issue of PM measurements. In this paper in context of PM measurement traceability, we present systematically the (1) air quality regulation in different countries, (2) reference methods for size and mass measurements, (3) variation/error and limitations of PM measurements based on the current results in this study and previously published results, (4) current status of PM size and mass calibration facility, (5) expected uncertainty in PM measurements, (6) add-on uncertainty in other parameters of national ambient air quality standards due to PM measurements, (7) where does traceability of PM issue stand against other parameters of air quality standards and its impact on health and climate, (8) NMIs working on this issue, (9) status at Bureau International des Poids et Mesures (BIPM), France and (10) conclusion. The aim of this paper is to better understand the importance of international system of units (SI) traceability issue in PM measurements, so wherever and whenever it is measured, should be acceptable everywhere, and data should be comparable for improving air quality and thus the quality of life. Funding agencies should be aware of this issue, and accept the results from the principle investigators and team only when their results have the traceability link to SI. NMIs should make program to involve industries in gas and aerosol metrology work to fulfill the requirement of calibration and standards. The regulatory authorities/ministry should work together with NMIs to improve the data quality of ambient measurements. This will greatly help to better make the policies and decisions on the related impacts. These were also the ultimate goals of “one-day pre-AdMet workshop” organized at National Physical Laboratory, New Delhi, India on February 20th, 2013.     

A pragmatic ensemble learning approach for effective software effort estimation

Innovations in Systems and Software Engineering - The immense increase in software technology has resulted in the convolution of software projects. Software effort estimation is fundamental to...     

Special issue on “Soft computing techniques: applications and challenges” neural computing and applications

Neural Computing and Applications -