The research paper focuses on automating software development process by automating the team formation by extracting information from the software requirement specification (SRS) document of the project.

During COVID-19 and other pandemics, endotracheal intubation is an effective and common method to save patients as the virus causes lung fibrosis and thus patients are unable to breathe spontaneously. Medical staff need to insert a tube close to the patient’s mouth, thereby leading to a high risk of cross-infection. To protect medical staff, we propose an autonomous intubation robot system (AIRS). With the developed visual servoing and hybrid control method, the entire system can simulate doctors for satisfying repeatability and safety of intubation operations. This system includes a self-driving/teleoperation platform, two co-robot arms, a new multi-functional laryngoscope, force sensors, and several cameras. In the visual servoing part, we realize recognition and location of the patient’s face, medical devices, and main physiological structures to provide real-time navigation. In the hybrid control part, we establish an oral model, propose an offline planning method and PID controllers by combining force, vision, and motion, and apply Virtual Fixture to insert safely. AIRS’s validation is with a phantom model under a 2-min operation. Our proposed robot is original and promising in the area of emergent medical robots. We will further validate AIRS in clinical applications and extend the developed techniques in other general treatments.

We will look at the binary field $\mathbb F_2$.  The classical “hit problem” in algebraic topology, which is widely considered to be an important and fascinating open problem that has yet to be resolved, asks for a minimal set of generators for the polynomial algebra, $\mathcal P_m:=\mathbb F_2[x_1, x_2, \ldots, x_m]$, on $m$ variables $x_1, \ldots, x_m$, each of which has degree one, regarded as a connected unstable module over the 2-primary Steenrod algebra $\mathscr A.$ The algebra $\mathcal P_m$ is the cohomology with $\mathbb F_2$-coefficients of the product of $m$ copies of the Eilenberg-MacLan complex $K(\mathbb F_2, 1)$. Despite extensive study over the past three decades, the hit problem remains unresolved for $m\geq 5$. In this article, we develop our previous work [Commun. Korean Math. Soc. \textbf{35} (2020), 371-399] on the hit problem for the $\mathscr A$-module $\mathcal P_5$ in the generic degree $n_s = 5(2^{s}-1) + 18.2^{s}$ with $s$ an arbitrary non-negative integer. As a consequence, a localized variation  of the Kameko conjecture, which concerns the dimension of the cohit space $\mathbb F_2\otimes_{\mathscr A}\mathcal P_m$ in relation to parameter vectors, has been claimed to be veracious in the instance where $m = 5$ and the degree is $n_s.$ Also, we demonstrate that this conjecture remains valid for all $m\geq 1$ and degrees $\leq 12.$ This study has two important applications:  (1) it establishes the dimension result for the cohit space $\mathbb F_2\otimes_{\mathscr A}\mathcal P_m$ for $m = 6$ in the generic degree $5(2^{s+4}-1) + n_1.2^{s+4}$ with $s > 0;$ and (2) it describes the representations of the general linear group of rank $5$ over $\mathbb F_2.$ As a result, we prove that the algebraic transfer, defined by William Singer [Math. Z. \textbf{202} (1989), 493-523], is an isomorphism in bidegrees $(5, 5+n_s)$ with $s\geq 0.$ Besides, we obtain new results on the behavior of this algebraic transfer for all homological degrees $m$. Specifically, we show that Singer’s transfer is a trivial isomorphism in bidegree $(m, m+12)$ for any $m > 0$. At the end of this work, we discuss the hit problem for the symmetric polynomial algebra $\mathcal P_m^{\Sigma_m}.$ This topic has been previously studied by Ali Janfada and Reginald Wood for $m\leq 3.$

We present a novel graph convolutional method called star topology convolution (STC). This method makes graph convolution more similar to conventional convolutional neural networks (CNNs) in Euclidean feature spaces. STC learns subgraphs which have a star topology rather than learning a fixed graph like most spectral methods. Due to the properties of a star topology, STC is graph-scale free (without a fixed graph size constraint). It has fewer parameters in its convolutional filter and is inductive, so it is more flexible and can be applied to large and evolving graphs. The convolutional filter is learnable and localized, similar to CNNs in Euclidean feature spaces, and can share weights across graphs. To test the method, STC was compared with state-of-the-art graph convolutional methods in a supervised learning setting on nine node properties prediction benchmark datasets: Cora, Citeseer, Pubmed, PPI, Arxiv, MAG, ACM, DBLP, and IMDB. The experimental results showed that STC achieved state-of-the-art performance on all these datasets and maintained good robustness. In an essential protein identification task, STC outperformed state-of-the-art essential protein identification methods. An application of using pretrained STC as the embedding for feature extraction of some downstream classification tasks was introduced. The experimental results showed that STC can share weights across different graphs and be used as the embedding to improve the performance of downstream tasks.

Brain Inspired Computing (BIC) is an emerging research field that aims to build fundamental theories, models, hardware architectures, and application systems toward more general Artificial Intelligence (AI) by learning from the information processing mechanisms or structures/functions of biological nervous systems. It is regarded as one of the most promising research directions for future intelligent computing in the post-Moore era. In the past few years, various new schemes in this field have sprung up to explore more general AI. These works are quite divergent in the aspects of modeling/algorithm, software tool, hardware platform, and benchmark data, since BIC is an interdisciplinary field that consists of many different domains, including computational neuroscience, artificial intelligence, computer science, statistical physics, material science, microelectronics and so forth. This situation greatly impedes researchers from obtaining a clear picture and getting started in the right way. Hence, there is an urgent requirement to do a comprehensive survey in this field to help correctly recognize and analyze such bewildering methodologies. What are the key issues to enhance the development of BIC? What roles do the current mainstream technologies play in the general framework of BIC? Which techniques are truly useful in real-world applications? These questions largely remain open. To address the above issues, in this survey we first clarify the biggest challenge of BIC: how can AI models benefit from the recent advancements in computational neuroscience? With this challenge in mind, we will focus on discussing the concept of BIC and summarize four components of BIC infrastructure development: 1) modeling/algorithm; 2) hardware platform; 3) software tool; and 4) benchmark data. For each component, we will summarize its recent progress, main challenges to resolve, and future trends. On the basis of these studies, we present a general framework for the real-world applications of BIC systems, which is promising to benefit both AI and brain science. Finally, we claim that it is extremely important to build a research ecology to promote prosperity continuously in this field.

Despite numerous advantages, mobile phones cause serious health issues to people due to electromagnetic radiation. Various head models already exist to study the impact of radiation on a human head. The accuracy of the measurement of power absorbed by different layers of a head should be high. A new head model with six layers is proposed in this paper. Parameters such as dielectric constant, conductivity and mass density of different tissue layers skin, fat, bone, Dura, cerebrospinal fluid (CSF), and brain are extracted from the Federal Communications Commission (FCC) database. To study the impact of radiation in the proposed model, standard planar inverted F-antennas (PIFA) capable to radiate at 1.7 GHz and 2.4 GHz are used. Simulations are performed using ANSYS Electromagnetics Suite. The analysis shows that the specific absorption rate (SAR) in the brain layer decreased in the proposed model when compared to the existing model.

The continuous development of the Internet of Things (IoT) calls for innovative solutions and technologies to realize the IoT vision efficiently. One of the rising connectivity technologies that can potentially benefit the IoT deployment is Optical Wireless Communication (OWC) technology. In OWC, light beams from light sources are used to modulate information. The receiver demodulates the received light and processes the signal. The broad unlicensed spectrum of the OWC technology, along with its potential high bit-rate and increased physical link security, motivated researchers to consider OWC for IoT solutions. In this paper, we survey the existing literature related to using OWC technology in the IoT domain. We present the background and preliminaries of the IoT and OWC domains to understand how the OWC fits in the IoT architecture. Then we perform a comprehensive survey of literature related to the use of OWC technology in IoT applications. We highlight and summarize the major papers and experiments in the literature to provide researchers a jump-start to tap into the domain of OWC in IoT using the systemic and detailed survey presented in this paper.

Determining the number of groups or dimension of a feature space related to an initial dataset projected to null-space of the Laplace-Beltrami-type operators is a fundamental problem of applications exploiting a spectral clustering techniques. This paper theoretically focuses on generalizing and providing minor comments to a previous work by Bruneau et al., who proposed modification of the Bartlett test that is commonly used in the principal component analysis, to estimate the number of groups related to normalized spectral clustering approaches. The generalization is based on a relation between the distributions of the spectrum associated with a covariance matrix and graph Laplacian, which allows us to use the modified Bartlett test for unnormalized spectral clustering as well. Other comments follow previous works by Lawley and James, which allow us testing subsets of eigenvalues by involving likelihood ratio statistic and linkage factors. Solving issues arising from limits of floating-point arithmetic are demonstrated on benchmarks employing spectral clustering for $2$-phase volumetric image segmentation. On a same problem, analysing spectral clustering in divide-merge settings is presented.

At present, all superconductivity techniques are carried out at ultra-low temperature. The aim of this study is to design a novel vacuum tube at room temperature, which can move electrons without resistance to achieve zero resistance and superconductivity properties. superconductor; vacuum tube; electronics; electrostatic shielding; zero resistance

Using capacitive sensors at long ranges (10-20x their plate diameter) for long term environmental sensing can be limited by slow but significant measurement drifts that can often far exceed the small capacitance variations of interest, which can be around 0.01% or less. We propose a differential capacitance measurement method that rejects the quasi-constant drift currents for single plate capacitive sensors by averaging the absolute slope values of adjacent charge-discharge voltage ramps of the plate capacitance, under constant current. Compared analytically and in simulations with period modulation techniques using astable multivibrators, our method shows much better rejection of drifts due to quasi-constant charge migration and improved random noise attenuation, while preserving the measurement sensitivity. We also provide an implementation example that avoids errors caused by some types of ramp distortions and improves noise reduction.

In the proposed research work; the COVID-19 is detected using transfer learning from CT scan images decomposed to three-level using stationary wavelet. A three-phase detection model is proposed to improve the detection accuracy and the procedures are as follows; Phase1- data augmentation using stationary wavelets, Phase2- COVID-19 detection using pre-trained CNN model and Phase3- abnormality localization in CT scan images. This work has considered the well known pre-trained architectures, such as ResNet18, ResNet50, ResNet101, and SqueezeNet for the experimental evaluation. In this work, 70% of images are considered to train the network and 30% images are considered to validate the network. The performance of the considered architectures is evaluated by computing the common performance measures.

Control barrier function (CBF) based Quadratic Programs (QPs) were introduced in early 2014 as a means to guarantee safety in affine control systems in conjunction with stability/tracking. However, due to the presence of model-based terms, they fail to provide guarantees under model perturbations. Therefore, in this paper, we propose a new class of CBFs for robotic systems that augment kinetic energy with the traditional forms. We show that with torque limits permitting, and with the kinematic models accurately known, forward invariance of safe sets generated by kinematic constraints (position and velocity) can be guaranteed. The proposed methodology is motivated by the control Lyapunov function (CLF) based QPs that use the kinetic energy function. By the property of CBF-QPs, we show that the pointwise min-norm control laws obtained are feasible and Lipschitz continuous, and can be derived analytically via the KKT conditions. In order to include stability with safety, we also augment CLF based constraints in the CBF-QPs to realize a unified control law that allows tracking with safety irrespective of the inertial parameters of the robot. We will demonstrate the robustness of this class of CBF-QPs in two robotic platforms: a 1-DOF and a 2-DOF manipulator, by scaling the masses by up to 100, and then simulating the resulting dynamics.

The paper discusses about a symmetric encryption process called Fernet which is used for encrypting and decrypting the data. It also describes various types of attacks on encrypted data and why encryption is never 100% secure from attacks.

Surrogate-assisted multi-objective evolutionary algorithms have advanced the field of computationally expensive optimization, but their progress is often restricted to low-dimensional problems. This manuscript presents a multiple classifiers-assisted evolutionary algorithm based on decomposition, which is adapted for high-dimensional expensive problems in terms of the following two insights. Compared to approximation-based surrogates, the accuracy of classification-based surrogates is robust for few high-dimensional training samples. Further, multiple local classifiers can hedge the risk of over-fitting issues. Accordingly, the proposed algorithm builds multiple classifiers with support vector machines on a decomposition-based multi-objective algorithm, wherein each local classifier is trained for a corresponding scalarization function. Experimental results statistically confirm that the proposed algorithm is competitive to the state-of-the-art algorithms and computationally efficient as well.

Walking gait data measured using force platforms is a promising means for person re-identification in authentication and surveillance scenarios. We aimed to determine the most discriminant components of force platform data using a two-stream Convolutional Recurrent Neural Network (KineticNet). Each network in the two-stream architecture extracts features pertaining to a single stance phase and then these features are fused to represent the entire gait cycle. Over two sessions, ground reaction forces (Fx, Fy, Fz), moments (Mx, My, Mz), and center of pressure coordinates (Cx, Cy) were acquired from 118 participants as they walked our laboratory five times at preferred speed. For each participant and each session, up to three samples were reserved for network training, leaving one sample for network validation and one sample for network testing. KineticNet’s performance was evaluated using both individual component and multi-component inputs before ablation studies were conducted on its architecture. Fz was the most discriminant individual component, and re-identification using Fz, Fy, and Cy together was the most accurate overall at 96.02%. These results warrant further investigation into the utility of force platforms as an accessory or alternative to video cameras for gait based person re-identification.

Background Knee osteoarthritis (OA) remains a leading aetiology of disability worldwide. Clinical assessment of such knee-related conditions has improved with recent advances in gait analysis. Despite being a gold standard method, gait data acquired by motion capture (mocap) technology are highly non-linear and dimensional, which make traditional gait analysis challenging. Thus, extrinsic algorithms need to be used to make sense of gait data. Supervised Machine Learning (ML)-based classifiers outperform conventional statistical methods in revealing intrinsic patterns that can discern gait abnormalities when using mocap data, making them a suitable tool for aiding diagnosis of knee OA. Research question Studies have demonstrated the accuracy of supervised ML-based classifiers in gait analysis. However, these techniques have not gained wide acceptance amongst biomechanists for two reasons: the reliability of such methods has not been assessed and there is no consensus on which classifier or group of classifiers to select. Specifically, it is not clear whether classifiers that leverage optimal separating hyperplanes (OSH) or artificial neural networks (ANN) are more accurate and reliable. Methods A systematic review and meta-analysis were conducted to assess the capability of such algorithms to predict pathological kinematic and kinetic gait patterns as indicators of knee OA. With 153 eligible studies, 6 studies met the inclusion criteria for a subsequent meta-analysis, accounting for 273 healthy subjects and 313 patientswith symptomatic knee OA. The classification performance of supervised ML classifiers (OSH- or ANN-based) used in these studies was quantitatively assessed and compared across four following performance metrics: classification accuracy on the test set (ACC), sensitivity (SN), specificity (SP), and area under the receiver operating characteristic curve (AUC). Results There was no statistically significant discrepancy in the ACC between OSH- and ANN-based classifiers when dealing with kinetic and kinematic data concurrently, as well as when considering only kinematic data. However, there was a statistically significant difference in their SN and SP, with the ANN-based classifiers having higher SN and SP than OSH-based algorithms. As only one of the eligible studies reported AUC, this metric could not be assessed statistically across studies. Significance This study supports the use of ANN-based algorithms for classifying knee OA-related gait patterns as having a higher sensitivity and specificity than OSH-based classifiers. Considering their higher reliability, leveraging supervised ANN-based methods can aid biomechanists to diagnose knee OA objectively.

Passive shoulder supports show large potential for a wide range of applications, such as assisting activities of daily living and supporting work-related tasks. The rigid architectures of currently available devices, however, may pose an obstacle to finding designs that offer low protrusion and close-to-the-body alignment. This study explores the use of mechanisms that employ a flexible element which connects the supported arm to an attachment at the back and acts as energy storage, transmission and part of the load bearing structure. Based on the synthesis method explained in this paper, we conducted a large scope investigation into possible flexure-based mechanism topologies. Many potential designs were discovered and are presented, categorized and compared. Two promising designs were developed into prototypes that were built and tested on a dedicated test bench. These mechanisms reduce the necessary moment to lift the arm by more than 80 % throughout 85 % of the range of motion, while staying within 18 cm and 10 cm distance from the body, respectively. Our study indicates that, due to its lower protrusion and interface loads, a design with a tapered flexure connecting the upper arm via a hinge to a spring loaded slider at the back offers the most promising solution.

Abstract The integration of cognitive radio with e-healthcare systems assisted by wireless body sensor networks (WBSNs) has been regarded as an enabling approach for a new generation of pervasive healthcare services, to provide differentiated quality of service requirements and avoid harmful electromagnetic interference to primary medical devices (PMDs) over the crowded radio spectrum. Due to the sharing spectrum bands with PMDs in e-healthcare scenario using cognitive WBSNs (CWBSNs), efficient transmit power control and optimization strategies for resource-constrained secondary wearable biosensors (SWBs) play a key role in controlling the inter-network interference and improving the energy efficiency. This paper investigates the problem of dynamic power optimization for SWBs in e-healthcare leveraging CWBSNs with practical limitations, e.g., imperfect spectrum sensing and quality of physiological data sampling. We develop a distributed optimization framework of dynamic power optimization via the theory of differential game, by jointly considering utility maximization and quality of physiological data sampling for every SWB, while satisfying the evolution law of energy consumption in SWB’s battery. With the non-cooperation and cooperation relations for all SWBs in mind, we transform the differential game model into two subproblems, namely, utility maximization problem and total utility maximization problem. Utilizing Bellman’s dynamic programming, we derive a non-cooperative optimal solution for power optimization as a Nash equilibrium point for the utility maximization problem posed by competitive scenario. By exploiting Pontryagin’s maximum principle, a cooperative optimal solution is obtained for the total utility maximization problem, wherein all SWBs fully cooperate to obtain the highest total utilities. Building upon the analytical results, the actual utility distributed to each SWB is compared between the non-cooperative and cooperative schemes. Extensive simulations show that the proposed optimization framework is indeed an efficient and practical solution for power control compared with the benchmark algorithm.