Medical application of information gain based artificial immune recognition system (AIRS): Diagnosis of thyroid disease

In this paper, we have made medical application of a new artificial immune system named the information gain based artificial immune recognition system (IG-AIRS) which minimizes the negative effects of taking into account all attributes in calculating Euclidean distance in shape–space representation which is used in many artificial immune systems. For medical data, thyroid disease data set was applied in the performance analysis of our proposed system. Our proposed system reached 95.90% classification accuracy with 10-fold CV method. This result ensured that IG-AIRS would be helpful in diagnosing thyroid function based on laboratory tests, and would open the way to various ill diagnoses support by using the recent clinical examination data, and we are actually in progress.     

A new supervised classification algorithm in artificial immune systems with its application to carotid artery Doppler signals to diagnose atherosclerosis

Because of its self-regulating nature, immune system has been an inspiration source for usually unsupervised learning methods in classification applications of Artificial Immune Systems (AIS). But classification with supervision can bring some advantages to AIS like other classification systems. Indeed, there have been some studies, which have obtained reasonable results and include supervision in this branch of AIS. In this study, we have proposed a new supervised AIS named as Supervised Affinity Maturation Algorithm (SAMA) and have presented its performance results through applying it to diagnose atherosclerosis using carotid artery Doppler signals as a real-world medical classification problem. We have employed the maximum envelope of the carotid artery Doppler sonograms derived from Autoregressive (AR) method as an input of proposed classification system and reached a maximum average classification accuracy of 98.93% with 10-fold cross-validation method used in training-test portioning. To evaluate this result, comparison was done with Artificial Neural Networks and Decision Trees. Our system was found to be comparable with those systems, which are used effectively in literature with respect to classification accuracy and classification time. Effects of system's parameters were also analyzed in performance evaluation applications. With this study and other possible contributions to AIS, classification algorithms with effective performances can be developed and potential of AIS in classification can be further revealed.     

Stamping of Flexible,Coplanar Micro‐Supercapacitors Using MXene Inks

The fast growth of portable smart electronics and internet of things have greatly stimulated the demand for miniaturized energy storage devices. Micro‐supercapacitors (MSCs), which can provide high power density and a long lifetime, are ideal stand‐alone power sources for smart microelectronics. However, relatively few MSCs exhibit both high areal and volumetric capacitance. Here rapid production of flexible MSCs is demonstrated through a scalable, low‐cost stamping strategy. Combining 3D‐printed stamps with arbitrary shapes and 2D titanium carbide or carbonitride inks (Ti₃C₂T_x and Ti₃CNT_x, respectively, known as MXenes), flexible all‐MXene MSCs with controlled architectures are produced. The interdigitated Ti₃C₂T_x MSC exhibits high areal capacitance: 61 mF cm^?2 at 25 µA cm^?2 and 50 mF cm^?2 as the current density increases by 32 fold. The Ti₃C₂T_x MSCs also showcase capacitive charge storage properties, good cycling lifetime, high energy and power densities, etc. The production of such high‐performance Ti₃C₂T_x MSCs can be easily scaled up by designing pad or cylindrical stamps, followed by a cold rolling process. Collectively, the rapid, efficient production of flexible all‐MXene MSCs with state‐of‐the‐art performance opens new exciting opportunities for future applications in wearable and portable electronics.     

Classification of sleep stages using class-dependent sequential feature selection and artificial neural network

Several studies have been conducted for automatic classification of sleep stages to ease time-consuming manual scoring process that can involve a high degree of experience and subjectivity. But none of them has found a practical usage in medical area so far because of their under acceptable success rates. In this study, a different classification scheme is proposed to increase the success rate in automatic sleep stage scoring in which sleep stages were classified as Awake, Non-REM1, Non-REM2, Non-REM3 and REM stages. Using EEG, EMG and EOG recordings of five healthy subjects, a modified version of sequential feature selection method was applied to the sleep epochs in class by class basis and different artificial neural network (ANN) architectures were trained for each class. That is to say, sleep stages were classified with five ANN architectures each of which uses different features and different network parameters for classification. The highest classification accuracy was obtained for REM sleep as 95.13 % in addition to the lowest classification accuracy of 86.42 % for Non-REM3 sleep. The overall accuracy, on the other hand, was recorded as 90.93 %, which is a comparatively good result when the other studies using all stages are taken into account.     

A new approach to eliminating EOG artifacts from the sleep EEG signals for the automatic sleep stage classification

Neural Computing and Applications - Interference between EEG and EOG signals has been studied heavily in clinical EEG signal processing applications. But, in automatic sleep stage classification...     

Enabling Flexible Heterostructures for Li‐Ion Battery Anodes Based on Nanotube and Liquid‐Phase Exfoliated 2D Gallium Chalcogenide Nanosheet Colloidal Solutions

2D metal chalcogenide (MC) nanosheets (NS) have displayed high capacities as lithium‐ion battery (LiB) anodes. Nevertheless, their complicated synthesis routes coupled with low electronic conductivity greatly limit them as promising LiB electrode material. Here, this work reports a facile single‐walled carbon nanotube (SWCNT) percolating strategy for efficiently maximizing the electrochemical performances of gallium chalcogenide (GaX, X = S or Se). Multiscaled flexible GaX NS/SWCNT heterostructures with abundant voids for Li⁺ diffusion are fabricated by embedding the liquid‐exfoliated GaX NS matrix within a SWCNT‐percolated network; the latter improves the electron transport and ion diffusion kinetics as well as maintains the mechanical flexibility. Consequently, high capacities (i.e., 838 mAh g^?1 per gallium (II) sulfide (GaS) NS/SWCNT mass and 1107 mAh g^?1 per GaS mass; the latter is close to the theoretical value) and good rate capabilities are achieved, which can be majorly attributed to the alloying processes of disordered Ga formed after the first irreversible GaX conversion reaction, as monitored by in situ X‐ray diffraction. The presented approach, colloidal solution processing of SWCNT and liquid‐exfoliated MC NS to produce flexible paper‐based electrode, could be generalized for wearable energy storage devices with promising performances.     

Influence of high-frequency cyclical stimulation on the bone fracture-healing process: mathematical and experimental models

Mechanical stimulation affects the evolution of healthy and fractured bone. However, the effect of applying cyclical mechanical stimuli on bone healing has not yet been fully clarified. The aim of the present study was to determine the influence of a high-frequency and low-magnitude cyclical displacement of the fractured fragments on the bone-healing process. This subject is studied experimentally and computationally for a sheep long bone. On the one hand, the mathematical computational study indicates that mechanical stimulation at high frequencies can stimulate and accelerate the process of chondrogenesis and endochondral ossification and consequently the bony union of the fracture. This is probably achieved by the interstitial fluid flow, which can move nutrients and waste from one place to another in the callus. This movement of fluid modifies the mechanical stimulus on the cells attached to the extracellular matrix. On the other hand, the experimental study was carried out using two sheep groups. In the first group, static fixators were implanted, while, in the second one, identical devices were used, but with an additional vibrator. This vibrator allowed a cyclic displacement with low magnitude and high frequency (LMHF) to be applied to the fractured zone every day; the frequency of stimulation was chosen from mechano-biological model predictions. Analysing the results obtained for the control and stimulated groups, we observed improvements in the bone-healing process in the stimulated group. Therefore, in this study, we show the potential of computer mechano-biological models to guide and define better mechanical conditions for experiments in order to improve bone fracture healing. In fact, both experimental and computational studies indicated improvements in the healing process in the LMHF mechanically stimulated fractures. In both studies, these improvements could be associated with the promotion of endochondral ossification and an increase in the rate of cell proliferation and tissue synthesis.     

Recovering the military Enigma using permutations—filling in the details of Rejewski's solution

During the last few months of 1932, the Polish mathematician Marian Rejewski solved the problem of finding the internal connections of the rotors and reflector of the Enigma cipher machine used by the German army at that time. This allowed the Polish Cipher Bureau to construct an analogue of the machine, and subsequently to find effective methods for deciphering secret messages. Rejewski performed this feat virtually alone using cryptographic material provided by the Polish secret services. His knowledge of the theory of permutation groups was essential in solving this problem.

This article describes in detail how to find the complete wiring of the rotors and reflector of Enigma, as well as other specifics, using data that Rejewski had at his disposal, by systematically presenting the resolution of all cases that could have been encountered. Similarly, we complete those stages of the procedure that were only outlined by Rejewski.