Analysing Various Control Technics for Manipulator Robotic System (Robogymnast)

The Robogymnast is a highly complex, three-link system based on the triple-inverted pendulum and is modelled on the human example of a gymnast suspended by their hands from the high bar and executing larger and larger upswings to eventually rotate fully. The links of the Robogymnast correspond respectively to the arms, trunk, and lower limbs of the gymnast, and from its three joints, one is under passive operation, while the remaining two are powered. The passive top joint poses severe challenges in attaining the smooth movement control needed to operate the Robogymnast effectively. This study assesses four types of controllers used for systems operation and identifies how far response stabilisation is achieved with each. The system is simulated using MATLAB Simulink, with findings generated regarding rising and settling time, as well as overshoot. The research primarily seeks to examine the application of a linear quadratic regulator controller, proportionalintegral-derivative controller, fuzzy linear quadratic regulator controller and linear quadratic regulator- proportional-integral-derivative controller for this type of system and comparisons between the different controllers to demonstrate successful performance, which highlights the claimed advantages of the proposed system.     

Mechanically Robust Shape-Memory Organohydrogels Based on Silk Fibroin with Organogel Microinclusions of Various Sizes

Organohydrogels (OHGs) are soft materials with antagonistic hydrophilic and hydrophobic domains that have great interest for many different applications. This study presents the preparation of mechanically strong OHGs with shape-memory function by incorporating semicrystalline organo-microgels within the pores of silk fibroin (SF) scaffolds. In the first step, SF cryogels with various pore diameters between 26 ± 8 and 17 ± 4 µm are synthesized by cryogelation of aqueous SF solutions at concentrations between 5 and 20 w/v%. In the second step, the pores of SF scaffolds are filled with an organogel precursor solution containing n-octadecyl acrylate (C18A), acrylic acid, N,N'-methylene(bis)acrylamide, and an initiator. Once the free-radical polymerization took place inside the pores, OHGs containing organo-microgels of various sizes are obtained. The incorporation of the organogel component in the cryogels generates crystalline areas due to the side-by-side packed C18 side chains. OHGs' melting temperature and crystallinity level can be varied from 42 to 54 °C and from 2 to 16%, respectively. The stiffness of OHGs increases from 5.9 ± 0.5 to 18 ± 1 MPa with increasing SF concentration from 5 to 20 w/v%, which is attributed to the decreasing pore size of the cryogels and increasing thickness of the pore walls.     

Cyberattack Detection Framework Using Machine Learning and User Behavior Analytics

This paper proposes a novel framework to detect cyber-attacks using Machine Learning coupled with User Behavior Analytics. The framework models the user behavior as sequences of events representing the user activities at such a network. The represented sequences are then fitted into a recurrent neural network model to extract features that draw distinctive behavior for individual users. Thus, the model can recognize frequencies of regular behavior to profile the user manner in the network. The subsequent procedure is that the recurrent neural network would detect abnormal behavior by classifying unknown behavior to either regular or irregular behavior. The importance of the proposed framework is due to the increase of cyber-attacks especially when the attack is triggered from such sources inside the network. Typically detecting inside attacks are much more challenging in that the security protocols can barely recognize attacks from trustful resources at the network, including users. Therefore, the user behavior can be extracted and ultimately learned to recognize insightful patterns in which the regular patterns reflect a normal network workflow. In contrast, the irregular patterns can trigger an alert for a potential cyber-attack. The framework has been fully described where the evaluation metrics have also been introduced. The experimental results show that the approach performed better compared to other approaches and AUC 0.97 was achieved using RNN-LSTM 1. The paper has been concluded with providing the potential directions for future improvements.