Self-report on height and weight had huge result on the precision of a screen for overweight and corpulence. Real and reported body size each helps to find the underreporting body weight. Self-reports will stay significant wellbeing reconnaissance apparatus yet ought not to be depended on solely to identify weight issues. Exactness checks of self-report information might further develop reviews of weight issues in youngsters. This Classification helps to improve the understanding the underweight and the under height causes. We consider the dataset employed to isolate the underweight and under heightened individuals of both orientations as per individual levels and loads. To isolate individuals, this study utilized an assortment of regression approaches, including linear and logistic regression and classification approaches like decision tree and random Forest techniques with the help of these techniques we achieve the self-reported anthropometric measurements can be used to determine BMI for purposes of weight classification.

We propose a novel reconstruction scheme for reconstructing charged particles in digital tracking calorimeters using model-free reinforcement learning aiming to benefit from the rapid progress and success of neural network architectures for tracking without the dependency on simulated or manually labeled data. Here we optimize by trial-and-error a behavior policy acting as a heuristic approximation to the full combinatorial optimization problem, maximizing the physical plausibility of sampled trajectories. In modern data processing pipelines used in high energy physics experiments and related high energy physics driven applications tracking plays an essential role allowing to identify and follow charged particle trajectories traversing particle detectors. Due to the usual high multiplicity of charged particles as well as the occurring physical interactions, randomly deflecting the particles from their initial path, the reconstruction is a challenging undertaking, requiring fast, accurate and robust algorithms. Our approach works on graph-structured data, capturing possible track hypotheses through edge connections between particles in the sensitive detector layers. We demonstrate in a comprehensive study on simulated data generated for a particle detector used for proton computed tomography, the overall high potential as well as the competitiveness of our approach compared to a heuristic search algorithm and a model trained on ground truth information. Finally, we point out limitations of our approach, guiding towards a robust foundation for further development of reinforcement learning based tracking algorithms in high energy physics.

The article propose a framework for automatic diagnosis of breast cancer using mammogram images

Article proposed a framework for automatic diagnosis different type of glaucoma using 2D-FBSE-EWT

Article propose a framework for automatic diagnosis of breast cancer using ultrasound images

High spectral and energy efficiencies are vital for the implementation of smart cities. To this end, this paper investigates the performance of an amplify-and-forward (AF) relay-aided coordinated direct and relay transmission (CDRT) protocol in a downlink non-orthogonal multiple access (NOMA) based Internet-of-things (IoT) network in which source shares the direct as well as the relayed links to the IoT near-user (NU) and the far-user (FU). Different from existing literature, we exploit incremental relaying (IR) along with combining at the NU (and not just at the FU) to achieve a 20% increase in FU throughput while ensuring the desired performance at NU. Considering practical imperfect successive interference cancellation (SIC), we analyze the throughput performance. Both NU and FU accrue large throughput gains, and doubling of the energy efficiency (EE) is achieved over the non-incremental AF CDRT NOMA scheme and its relayed OMA counterpart. We accomplish this by intelligently exploiting feedback bits in the second phase of signalling to avoid unwanted relaying, which saves energy and improves EE, which is very much required from the perspective of IoT-based energy-efficient smart cities. It is seen that the proper choice of the power allocation coefficient and the target information rate is crucial for maximizing the sum throughput and EE of the considered IoT Network. Finally, we validate the correctness of the theoretical analysis and the superiority of the proposed scheme through Monte Carlo simulations.

Despite the prevalence and success of prediction algorithms in several areas, most notably medicine, climate and geology, their successes in the field of football are still very modest, and this is completely logical. The outcome of the match depends on a large and varied human effort, as it is not limited to the level of the two competing teams, but politics and economics play a very important role, especially in major tournaments such as the World Cup held in Qatar. In this paper, we will propose mathematical methods to predict the results of football matches in general, according to a number of data and information. Financial institutions including Goldman Sachs, UBS and ING have not been able to predict the winner of the last two World Cups, although Liberium Capital made an exception after Joachim Clement’s algorithm figured out the winner of the previous two World Cups. But Joachim Clement told the Financial Market Watch news site that his model determines only 45 percent of a team’s chances of winning the championship, while the remaining 55 percent is sheer luck. We do not seek in this paper to leave an opportunity for luck, we will develop a number of different mathematical equations, each of which serves a form of football matches. Then we will programmatically formulate these mathematical equations to create applications capable of picking the winning team. We believe that mathematics is the language of the universe and we will speak this language simply to determine the winning team in any football match. Note: our test case will be all matches in QATAR 2022 world-Cup.

Cough is an important defense mechanism of the respiratory system and is also a symptom of lung diseases, such as asthma. Acoustic cough detection collected by portable recording devices is a convenient way to track potential condition worsening for patients who have asthma. However, the data used in building current cough detection models are often clean, containing a limited set of sound categories, and thus perform poorly when they are exposed to a variety of real-world sounds which could be picked up by portable recording devices. The sounds that are not learned by the model are referred to as Out-of-Distribution (OOD) data. In this work, we propose two robust cough detection methods combined with an OOD detection module, that removes OOD data without sacrificing the cough detection performance of the original system. These methods include adding a learning confidence parameter and maximizing entropy loss. Our experiments show that 1) the OOD system can produce dependable In-Distribution (ID) and OOD results at a sampling rate above 750 Hz; 2) the OOD sample detection tends to perform better for larger audio window sizes; 3) the model’s overall accuracy and precision get better as the proportion of OOD samples increase in the acoustic signals; 4) a higher percentage of OOD data is needed to realize performance gains at lower sampling rates. The incorporation of OOD detection techniques improves cough detection performance by a significant margin and provides a valuable solution to real-world acoustic cough detection problems.

Cloud providers offer virtual machines (VM) located in physical machines (PM) using the “pay-as-you-go” model to satisfy emerging demand for online computational services. If the instantaneous utilized capacity requested by VMs exceeds a certain threshold of the total capacity a PM can offer, a hotspot happens and may cause unacceptable VM performance degradation. Hotspots can be resolved by relocating some VMs to other PMs using live migration. However, the problem of selecting which VM(s) to release is challenging because the utilized capacity demanded by VMs changes continuously over time. In this work, we propose a Predicted Mixed Integer Linear Programming (MILP) Robust Solver (PMRS), which predicts the utilized capacity range of each VM and applies the Γ-robustness theory to ensure that PM is hotspot-safe with desired probability. The latter allows us to formulate the hotspot resolution as a Γ-robust knapsack problem (Γ-RKP) that can be solved by a novel MILP model. Extensive experiments based on real-trace data and large-scale synthetic data demonstrate the effectiveness of the PMRS. More encouragingly, the application of the PMRS in the real-production environment benefits Huawei Cloud by resolving all existing and 94%+ potential future hotspots with minimal migration overhead.Cloud providers offer virtual machines (VM) located in physical machines (PM) using the “pay-as-you-go” model to satisfy emerging demand for online computational services. If the instantaneous utilized capacity requested by VMs exceeds a certain threshold of the total capacity a PM can offer, a hotspot happens and may cause unacceptable VM performance degradation. Hotspots can be resolved by relocating some VMs to other PMs using live migration. However, the problem of selecting which VM(s) to release is challenging because the utilized capacity demanded by VMs changes continuously over time. In this work, we propose a Predicted Mixed Integer Linear Programming (MILP) Robust Solver (PMRS), which predicts the utilized capacity range of each VM and applies the Γ-robustness theory to ensure that PM is hotspot-safe with desired probability. The latter allows us to formulate the hotspot resolution as a Γ- robust knapsack problem (Γ-RKP) that can be solved by a novel MILP model. Extensive experiments based on real-trace data and large-scale synthetic data demonstrate the effectiveness of the PMRS. More encouragingly, the application of the PMRS in the real-production environment benefits Huawei Cloud by resolving all existing and 94%+ potential future hotspots with minimal migration overhead.

Fast frequency response services, designed to quickly balance the electrical grid within seconds, have a critical importance for managing sudden anomalies in low-inertia power systems. Battery systems often serve as versatile prosumers on the demand side to facilitate fast frequency response services. However, the nature of the fast frequency response services leads to a highly fluctuating power profile for batteries, which can shorten their lifetime. In contrast, distributed air-source heat pumps in residential areas have a substantial untapped potential to support fast frequency response services. This paper seeks to integrate them into the existing services through a controller upgrade. We analyze the influence of air-source heat pumps' inherent complex thermal dynamics on fast frequency response services, revealing control challenges posed by unpredictable operating condition changes. Such a challenge is tackled with a decentralized control strategy based on H∞ and inverse-droop control, guaranteeing practical and stable operations within the permitted operating condition range. Finally, the proposed fast frequency response service scheme is tested through multiphysics simulations on a small-size low-inertia residential microgrid. The obtained results strongly supported the proposed new service.

Demand response (DR) is regarded as a solution to the issue of high electricity prices in the wholesale market, as the flexibility of the demand can be harnessed to lower the demand level for price reductions. As an across-the-board DR in a system is impractical due to the enrollment budget for instance, it is necessary to select a small group of nodes for DR implementing. Current studies resort to intuitive yet naive approaches for DR targeting, as price is implicitly associated with demand, though optimality cannot be ensured. In this paper, we derive such a relationship in the security-constrained economic dispatch via the multi-parametric programming theory, based on which the DR targeting problem is rigorously formulated as a mixed-integer quadratic programming problem aiming at reducing the averaged price to a reference level by efficiently reducing targeted nodes’ demand. A solution strategy is proposed to accelerate the computation. Numerical studies demonstrate compared with the benchmarking strategy, the proposed approach can reduce the price to the reference point with less efforts in demand reduction. Besides, we empirically show that the proposed approach is immune to inaccurate system parameters, and can be generalized to variants of DR targeting tasks.

Social media sites are gaining popularity day by day. They are best for communication, business, entertainment, and many other things. After more than a decade, social media have become very influential. On the flip side, fake news, hate speech, and online trolls are the biggest concerns because of social media. So, a solution to curb this issue is needed, especially in regional languages. Many social media platforms support regional languages. This paper will provide a machine learning-based solution to this problem. The focus of this paper is to classify comments written in regional languages. Firstly, a dataset has been created in Gujarati, Hindi, English, Marathi, and Punjabi languages. After that, different machine learning and deep learning models are applied to the multilingual dataset. At last, a comparison of all model performances was made.

Kuramoto model based analysis of Josephson junction array in series and comparison with small numbers of junctions as compared to higher number as proposed in the Kuramoto model.

Evolutionary sequential transfer optimization (ESTO), which attempts to enhance the evolutionary search of a target task using the knowledge captured from several previously-solved source tasks, has been receiving increasing research attention in recent years. Despite the tremendous approaches developed, it is worth noting that existing benchmark problems for ESTO are not well designed, as they are often simply extended from other benchmarks in which the relationships between the source and target tasks are not well analyzed. Consequently, the comparisons conducted on these problems are not systematic and can only provide numerical results without a deeper analysis of how an ESTO algorithm performs on problems with different properties. Taking this clue, this two-part paper revisits a large body of solution-based ESTO algorithms on a group of newly developed test problems, to help researchers and practitioners gain a deeper understanding of how to better exploit optimization experience towards enhanced optimization performance. Part A of the series designs a problem generator based on several newly defined concepts to generate benchmark problems with diverse properties, which are competitive in resembling real-world problems. Part B of the series empirically revisits various algorithms by answering five key research questions related to knowledge transfer. The results demonstrated that the performance of many ESTO algorithms is highly problem-dependent, which suggest the necessity of more research efforts on transferability measurement and enhancement in ESTO algorithm design. The source code of the benchmark suite developed in part A is available at https://github.com/XmingHsueh/Revisiting-S-ESTOs-PartA.

Federated learning (FL) allows a large number of users to collaboratively train machine learning (ML) models by sending only their local gradients to a central server for aggregation in each training iteration, without sending their raw training data. The main security issues of FL, that is, the privacy of the gradient vector and the correctness verification of the aggregated gradient, are gaining increasing attention from industry and academia. To protect the privacy of the gradient, a secure aggregation was proposed; to verify the correctness of the aggregated gradient, a verifiable secure aggregation that requires the server to provide a verifiable aggregated gradient was proposed. In 2021, Hahn et al. proposed VERSA, a verifiable secure aggregation (DOI:10.1109/TDSC.2021.3126323). However, in this paper, we will point out a flaw in VERSA, which indicates that VERSA does not work. To address the flaw, we present several approaches with different advantages and disadvantages. We hope that by identifying the flaw, similar errors can be avoided in future designs for verifiable secure aggregation.

This paper proposes two distinct approaches, namely Piece-by-Piece MNA and General MNA, for construction of Modified Nodal Analysis (MNA) matrices in order to be used in Model Order Reduction (MOR) techniques. In this work, we successfully applied the proposed approaches to construct MNA matrices of a multi-port network with several sub-circuits, then, reduced order of network using obtained MNA matrices in each approach. As a numerical example, the Y-parameters of full-order and reduced-order networks for a 4-port optical network, operating in frequency range 175-215 THz, are obtained through the proposed approaches, validated through simulating in Advanced Design System (ADS) software, and compared in terms of order of system (or matrix dimensions), execution time, Root Mean Square Error (RMSE), reduction controllability, reduction efficiency, and passivity point of view.

The chat application is something that allows users to get in touch directly. People can interact using this online application. People can interact using this online application effectively even far apart. To be utilized by many people, this web-based application is supposed to be real-time and multiplatform. Chatterbox is a real-time chat application developed using MERN stack development thus it is easily extendible and developed with recent technologies. Also, it has features like voice calls, video calls, screen sharing, chatting, and much more for users in one application. Particularly the application is more secure and comes with the option of screenshare which other applications mostly don’t have making it handy and easily reliable as well.  Also, with further system demands for running higher ends of the project, multiple features can be added to the application due to the extensible code and the application can be extended.

This is the era of internet and there are a lot of Social Media platforms out there that facilitate the sharing a vast variety of user generated content. LinkedIn is a business and employment oriented social platform whereas Twitter is used to share recent news trends and updates. Pinterest is about discovering new content and ideas while Facebook is more about catching up with friends and family. These networks and virtual communities cast a tremendous amount of influence on their users. Here we have a similar content-oriented platform called Social. It is designed and built for the users to connect and share digital content (like text, images and/or gifs) related to community, social, healthcare and welfare services. MERN stands for MongoDB, ExpressJS, ReactJS and NodeJS (the four key technologies that make the stack) and is used to built this fully responsive web application in conjugation with other APIs and tools.