Selection Scheme Research Articles

Adap-BDCM: Adaptive Bilinear Dynamic Cascade Model for Classification Tasks on CNV Datasets.

Copy number variation (CNV) is an essential genetic driving factor of cancer formation and progression, making intelligent classification based on CNV feasible. However, there are a few challenges in the current machine learning and deep learning methods, such as the design of base classifier combination schemes in ensemble methods and the selection of layers of neural networks, which often result in low accuracy. Therefore, an adaptive bilinear dynamic cascade model (Adap-BDCM) is developed to further enhance the accuracy and applicability of these methods for intelligent classification on CNV datasets. In this model, a feature selection module is introduced to mitigate the interference of redundant information, and a bilinear model based on the gated attention mechanism is proposed to extract more beneficial deep fusion features. Furthermore, an adaptive base classifier selection scheme is designed to overcome the difficulty of manually designing base classifier combinations and enhance the applicability of the model. Lastly, a novel feature fusion scheme with an attribute recall submoduleis constructed, effectively avoiding getting stuck in local solutions and missing some valuable information. Numerous experiments have demonstrated that our Adap-BDCM model exhibits optimal performance in cancer classification, stage prediction, and recurrence on CNV datasets. This study can assist physicians in making diagnoses faster and better.

A Semi-Automated Solution Approach Recommender for a Given Use Case: a Case Study for AI/ML in Oncology via Scopus and OpenAI

Nowadays, literature review is a necessary task when trying to solve a given problem. However, an exhaustive literature review is very time-consuming in today’s vast literature landscape. It can take weeks, even if looking only for abstracts or surveys. Moreover, choosing a method among others, and targeting searches within relevant problem and solution domains, are not easy tasks. These are especially true for young researchers or engineers starting to work in their field. Even if surveys that provide methods used to solve a specific problem already exist, an automatic way to do it for any use case is missing, especially for those who don’t know the existing literature. Our proposed tool, SARBOLD-LLM, allows discovering and choosing among methods related to a given problem, providing additional information about their uses in the literature to derive decision-making insights, in only a few hours. The SARBOLD-LLM comprises three modules: (1: Scopus search) paper selection using a keyword selection scheme to query Scopus API; (2: Scoring and method extraction) relevancy and popularity scores calculation and solution method extraction in papers utilizing OpenAI API (GPT 3.5); (3: Analyzes) sensitivity analysis and post-analyzes which reveals trends, relevant papers and methods. Comparing the SARBOLD-LLM to manual ground truth using precision, recall, and F1-score metrics, the performance results of AI in the oncology case study are 0.68, 0.9, and 0.77, respectively. SARBOLD-LLM demonstrates successful outcomes across various domains, showcasing its robustness and effectiveness. The SARBOLD-LLM addresses engineers more than researchers, as it proposes methods and trends without adding pros and cons. It is a useful tool to select which methods to investigate first and comes as a complement to surveys. This can limit the global search and accumulation of knowledge for the end user. However, it can be used as a director or recommender for future implementation to solve a problem.

Adaptive-Duplex Relay Selection for Cooperative Non-Orthogonal Multiple Access Networks

To further improve the spectral efficiency of the cooperative non-orthogonalmultiple access (NOMA) network with half-duplex (HD) relaying and avoid the zero diversity gain due to the imperfect self interference estimation at high signa-to-noise ratio (SNR) value with full-duplex (FD) relaying, this paper developed a novel two-stage relay selection for a two-user multi-relay cooperative NOMA systems with adaptive-duplex (AD) relaying which can switch opportunistically between HD and FD relaying modes. An adaptive duplexbased on a fixed power allocation factor relay selection (AD-FPA-RS) scheme for cooperative NOMA networks is proposed in this paper, the relay can switch the work mode to the FD or HD state adaptively according to the current channel state information and the result of decode at the relay. Furthermore, the exact outage probability for the proposed AD-FPA-RS scheme is obtained in a closed-form expression. The simulation and numerical results show that the proposed AD-FPA-RS scheme not only outperforms the existing HD-FPARS and FD-FPA-RS schemes in terms of outage behavior significantly but also can obtain full diversity gain without the floor outage performance at high SNR region.

Calculation and selection scheme of node reputation values for notary mechanism in cross-chain

Calculation and selection scheme of node reputation values for notary mechanism in cross-chain

An Efficient Attribute-Based Participant Selecting Scheme with Blockchain for Federated Learning in Smart Cities

In smart cities, large amounts of multi-source data are generated all the time. A model established via machine learning can mine information from these data and enable many valuable applications. With concerns about data privacy, it is becoming increasingly difficult for the publishers of these applications to obtain users’ data, which hinders the previous paradigm of centralized training through collecting data on a large scale. Federated learning is expected to prevent the leakage of private data by allowing users to train models locally. The existing works generally ignore architectures designed in real scenarios. Thus, there still exist some challenges that have not yet been explored in federated learning applied in smart cities, such as avoiding sharing models with improper parties under privacy requirements and designing satisfactory incentive mechanisms. Therefore, we propose an efficient attribute-based participant selecting scheme to ensure that only someone who meets the requirements of the task publisher can participate in training under the premise of high privacy requirements, so as to improve the efficiency and avoid attacks. We further extend our scheme to encourage clients to take part in federated learning and provide an audit mechanism using a consortium blockchain. Finally, we present an in-depth discussion of the proposed scheme by comparing it to different methods. The results show that our scheme can improve the efficiency of federated learning by enabling reliable participant selection and promote the extensive use of federated learning in smart cities.

Factor graph-based deep reinforcement learning for path selection scheme in full-duplex wireless multihop networks

A wireless multihop network (WMN) is set of wirelessly connected nodes without an aid of centralized infrastructure that can forward any packets via intermediate nodes by a multihop fashion. In the WMN, there are still some issues that need to be resolved, like due to any source node may choose an uncertainty path to send their packets through the multihop fashion and this leads to the performance of network capacity can degrade drastically. To solve this problem, in this research, we propose two novel path selection algorithms called SNR-based learning path selection (NLPS) algorithm and SINR-based learning path selection (INLPS) algorithm, which are incorporated with the deep reinforcement learning (DRL) to select the best multihop path from any source node to a destination node with highest end-to-end (E2E) throughput. Besides that, a factor graph (FG) approach and a nested lattice code (NLC) representation are used to reduce the computation time. According to the numerical studies with the NLC is applied, our simulation results reveal that the proposed NLPS and INLPS algorithms can improve the overall average network capacity up to 3.1 times and 10.5 times compared to FG, respectively. However, the overall average computation time are highly increased for NLPS and INLPS, i.e., about 0.627 s and 1.221 s, respectively compared to FG, which is about 0.006 s. In other words, both NLPS and INLPS algorithms can achieve high network capacity and moderate computation time.

Risk-Return Analysis of Select Tax Saving Mutual Funds

The Indian stock market has been in existence since 1875 bestowing lesser range of instruments from companies to invest their money through general public. Since then, the awareness of investment has gained momentum amongst the general public and investors have become curious and intuitive to park their funds in some instrument to attain or gain profit or handsome returns from companies and the market. With the advent of Unit Trust of India (UTI) being formed during 1964 by a special legislature to function under the regulatory and administrative control of Reserve Bank of India (RBI) , it brought an innovative financial thought to the mechanism of investment by investors. Mutual Fund industry boosted the investors’ confidence that upheld capital appreciation, protection, tax burden and promoted financial stability. The researcher attempted to analyse the risk and returns of select tax savings scheme of mutual funds and point out the best tax saving mutual fund amidst the 11 selected funds using parameters like standard deviation, beta, sharpe ratio and treynor ratios for a period of 90 months from 2016 to 2023 taking Net Asset Values published by AMFI and the closing values of Bombay Stock Exchange Standard & Poor (BSE S & P) Sensex and also by using MS Excel for computing all the parameters manually rather than the already published data by many other sources. It was examined that Quant Tax Direct Plan (Growth Option) has good indicators to prove its performance. The research findings can aide investors’ decision with numerous benefits ranging from savings, returns, gains and risk management.

On the Performance of the Relay Selection in Multi-hop Cluster-based Wireless Networks with Multiple Eavesdroppers Under Equally Correlated Rayleigh Fading

The performance of multi-hop cluster-based wireless networks under multiple eavesdroppers is investigated in the present work. More precisely, we derive the outage probability (OP) of the considered networks under two relay selection schemes: the channel-gain-based scheme and the random scheme. Although equally correlated Rayleigh fading is taken into consideration, the derived mathematical framework remains tractable. Specifically, we represent the exact expression of the OP under the channel-based scheme in series form, while the OP under the random scheme is computed in a closed-form expression. Additionally, we propose a novel power allocation for each transmitter that strictly satisfies the given intercept probability. Numerical results based on the Monte Carlo method are provided to verify the correctness of the derived framework. These results are also used to identify the influences of various parameters, such as the number of clusters, the number of relays per cluster, and the transmit power.

Defect Prediction via Tree-Based Encoding with Hybrid Granularity for Software Sustainability

Defects in software may result in system crashes, sluggish performance, or even deadlock, leading to the depletion of valuable resources. Implementing defect prediction can assist quality assurance teams in identifying potential software issues and rationalizing the allocation of testing resources, thereby decreasing the elimination of resources and enhancing software sustainability. Researchers have recently incorporated deep learning into defect prediction, extracting structural-semantic features from codes' abstract syntax trees (ASTs). However, inappropriate node granularity in ASTs may adversely impact the effectiveness of the extracted features. In addition, converting AST nodes into integer vectors may lead to the loss of structure information, resulting in poor model predictive capability. This paper proposes a tree-based encoding method with hybrid granularity for defect prediction to address these challenges. Specifically, five granularity selection schemes are extended to generate various ASTs from codes. Subsequently, a tree-based continuous bag-of-words model is utilized to map nodes of ASTs into numeric vector representations that conform to the tree-like structure of codes. The matrices converted from ASTs are then fed into a convolutional neural network to extract program features automatically. Experiments involving 24 versions of open-source projects demonstrate that our method can improve the effectiveness of extracted features in defect prediction tasks.

AI BASED FEATURE SELECTION MODEL FOR SOCCER SPORTS MANAGEMENT

Due to swift development of data mining as well as machine-learning technology and the flare- up of big sports data mining expansion challenges, sports data mining cannot merely use data statistical methods such as how to club machine learning and data mining technology for efficient mining and analysis of the sports data, to supply useful advice for the public physical exercise, and this is an vital need to study. It is a kind of effective sports data mining work through feature selection algorithm. Around the tricky problems existing in the study of the sports effect, given the drawback of existing data sets and conventional research methods, this paper begins from data mining algorithm, construct the sports effect evaluation database, based on the feature selection scheme, using elastic system network algorithm, random forest algorithm, and the impact of sports on the outcome of physical gauges. The evaluation algorithm presents machine learning techniques and the feature selection algorithm to guide sports effect evaluation research. When studying this evaluation problem of the sports effect, according to created sports effect evaluation database, elastic system algorithm is appended to regularize, realize and optimize the feature selection. When selecting features of different sports skills using the information gains marked to rank the significance of characteristics, which can systematically and accurately provide the influence degree of the sports on diverse physical indicators, bring the physical fitness research little more scientific, and can uncover the effect of the sports as much as possible. Experimental results demonstrate that the selected features as well as ground-truth both have good accuracy and good evaluation as match up to the baseline method.

Joint Optimization of Measurement Point Intelligent Selection and End-to-End Network Traffic Calculation in Datacenters

The effective design and management of data centers needs to follow the end-to-end traffic characteristics of data center networks (DCNs). However, directly measuring the end-to-end traffic of the network requires huge software and hardware costs. Since the particularity of the structure of DCNs, the flow estimation method used in the traditional computer network cannot be applied to existing DCNs. In this paper, we study the end-to-end traffic calculation of cloud computing DCNs. We propose <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> , which is an intelligent end-to-end traffic inference algorithm based on network tomography. Only using SNMP (simple network management protocol) data generally supported by switches, end-to-end traffic information can be calculated quickly and accurately. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> first devices a network traffic measurement point intelligent selection scheme based on node weighting. It first assigns weight to nodes through node criticality, and then uses node weighted incidence matrix approximation algorithm to calculate initial solution. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> then designs a network tomography method suitable for cloud computing network traffic calculation. It uses the time correlation of data center traffic to model the algorithm problem into a linear state space model, and finally calculates the traffic carried by each path through the improved Kalman filtering algorithm. Our evaluation and analysis demonstrate that <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LLS-TC</b> can effectively use the extracted coarse-grained traffic characteristics, and greatly improve the accuracy of the calculation on the premise of ensuring the computational efficiency.

Emotion recognition with reduced channels using CWT based EEG feature representation and a CNN classifier

Objective. Although emotion recognition has been studied for decades, a more accurate classification method that requires less computing is still needed. At present, in many studies, EEG features are extracted from all channels to recognize emotional states, however, there is a lack of an efficient feature domain that improves classification performance and reduces the number of EEG channels. Approach. In this study, a continuous wavelet transform (CWT)-based feature representation of multi-channel EEG data is proposed for automatic emotion recognition. In the proposed feature, the time-frequency domain information is preserved by using CWT coefficients. For a particular EEG channel, each CWT coefficient is mapped into a strength-to-entropy component ratio to obtain a 2D representation. Finally, a 2D feature matrix, namely CEF2D, is created by concatenating these representations from different channels and fed into a deep convolutional neural network architecture. Based on the CWT domain energy-to-entropy ratio, effective channel and CWT scale selection schemes are also proposed to reduce computational complexity. Main results. Compared with previous studies, the results of this study show that valence and arousal classification accuracy has improved in both 3-class and 2-class cases. For the 2-class problem, the average accuracies obtained for valence and arousal dimensions are 98.83% and 98.95%, respectively, and for the 3-class, the accuracies are 98.25% and 98.68%, respectively. Significance. Our findings show that the entropy-based feature of EEG data in the CWT domain is effective for emotion recognition. Utilizing the proposed feature domain, an effective channel selection method can reduce computational complexity.

Communication efficient federated learning with data offloading in fog-based IoT environment

Federated Learning (FL) has become a popular distributed machine learning technique that preserves privacy of data set generated by the Internet of Things (IoT) devices. However, straggler effect, and communication delay are the two major issues that should be properly taken care during model preparation of any FL process. In this study, we propose a novel and efficient scheme, called Fog Cloud Assisted Federated Learning (FCAFL) in IoT platform that address these issues. Specifically, the proposed scheme is shown to reduce the overall communication delay of the global model preparation in the FL process. It is also able to resolve straggler effect by employing clustering of the IoT devices with an efficient scheme of cluster head (CH) selection based on minimum intra-cluster distance and maximum residual energy. In order to reduce communication delay further, we also propose an efficient scheme of fog node selection using Genetic Algorithm (GA) by formulating the data offloading as a single objective problem with latency as an offloading parameter. There are some existing schemes which address straggler effect and communication delay. However, none of their approaches incorporate explicit clustering technique utilizing residual energy and minimum intra-cluster distance of the CHs to select clients, aiming to address the straggler effect. Additionally, their works do not involve any data offloading as a means to reduce communication delay in the FL process. The simulation results demonstrate better performance of the proposed FCAFL as compared to the traditional FL and existing approaches, namely, Hierarchical Federated Edge Learning (HFEL) and FedFog with respect to communication cost. The FCAFL also outperform traditional FL and HFEL with respect to training and testing accuracy of the produced FL model. The validity of the result is additionally proved through a widely recognized statistical technique, the analysis of variance (ANOVA), followed by a least significant difference (LSD) post-hoc analysis.

Selective signatures in composite MONTANA TROPICAL beef cattle reveal potential genomic regions for tropical adaptation.

Genomic regions related to tropical adaptability are of paramount importance for animal breeding nowadays, especially in the context of global climate change. Moreover, understanding the genomic architecture of these regions may be very relevant for aiding breeding programs in choosing the best selection scheme for tropical adaptation and/or implementing a crossbreeding scheme. The composite MONTANA TROPICAL® population was developed by crossing cattle of four different biological types to improve production in harsh environments. Pedigree and genotype data (51962 SNPs) from 3215 MONTANA TROPICAL® cattle were used to i) characterize the population structure; ii) identify signatures of selection with complementary approaches, i.e. Integrated Haplotype Score (iHS) and Runs of Homozygosity (ROH); and iii) understand genes and traits related to each selected region. The population structure based on principal components had a weak relationship with the genetic contribution of the different biological types. Clustering analyses (ADMIXTURE) showed different clusters according to the number of generations within the composite population. Considering results of both selection signatures approaches, we identified only one consensus region on chromosome 20 (35399405-40329703 bp). Genes in this region are related to immune function, regulation of epithelial cell differentiation, and cell response to ionizing radiation. This region harbors the slick locus which is related to slick hair and epidermis anatomy, both of which are related to heat stress adaptation. Also, QTLs in this region were related to feed intake, milk yield, mastitis, reproduction, and slick hair coat. The signatures of selection detected here arose in a few generations after crossbreeding between contrasting breeds. Therefore, it shows how important this genomic region may be for these animals to thrive in tropical conditions. Further investigations on sequencing this region can identify candidate genes for animal breeding and/or gene editing to tackle the challenges of climate change.

Low-Complexity User Scheduling Framework for mmWave Hybrid Beam-forming OFDM System under Non-Ideal CSI

Introduction: User scheduling in millimeter-wave (mmWave) multi-user hybrid beam-forming Orthogonal Frequency Division Multiplexing (OFDM) systems involves the joint optimization of resource block group (RBG) allocation, beam pairing, and user selection. However, choosing the optimal scheduled User Equipment (UE), allocated RBGs, and communicating beams in practical mmWave hybrid beam-forming systems with non-ideal Channel State Information (CSI) remains challenging. Method: In this paper, we propose a low-complexity user scheduling framework. On one hand, two user classification methods are proposed under non-ideal CSI, assisted by beam search and RBG allocation respectively. On the other hand, in order to ensure both the throughput and fairness performance, a novel user selection scheme, called weighted user selection based on feedback threshold (WUSFT) scheme is proposed, and approximate closed-form expression of fairness index for both full feedback and feedback based on threshold are derived. Our proposed methods consist of three steps. First, RBGs are allocated based on the maximum received signal power (MRSP) of each user on each RBG, utilizing quasi-omnidirectional beams. In the second step, the communicating beams are further searched to achieve the MRSP with the allocated RBG. Result: Finally, the allocated RBG, or the determined beam information obtained through the beam search, is used to represent the correlation of user channels and classify the UEs into groups. Only UEs whose reported factor is not less than the feedback threshold will report received information. This simplifies the operation of user scheduling. Moreover, simulation results demonstrate that our proposed schemes can achieve more than 92.3% of the sum rate performance of exhaustive search methods while maintaining relatively low complexity. Conclusion: In addition, the user feedback overhead (FO) reduces obviously, especially with large UE number.

Dynamic Node Selection Approach for 6G Heterogeneous Cellular Networks (HCN) to Enhance QoS and Low Latency

A wireless multi-hop network is a group of nodes that can interact directly with one another or across longer distances by using other nodes as relay points and routers. 6G heterogeneous cellular network support several transmission modalities, such as single hop, multi-hop transmission and device-to-any device transmission. These transmission services can greatly increase 6G cellular network capacity, spectral efficiency, power efficiency, Quality of Service (QoS) and Ultra Reliable Low Latency Communication (URLLC). According to current research, Heterogeneous Cellular Networks (HCN) can benefit even more from the integration of demand-driven opportunistic networking into HCN. Devices can search look for the connections between nodes that are most efficient. in Proactive HCN connections by taking advantage of the URLLC acceptability of many mobile data services. Multiple Transmission modes necessitate node selection schemes that can determine the best node for each transmission. Previous proposals for node selection schemes have taken into account the introduction of D2X and HCN. Proactive HCN connections, however, cannot be incorporated into the selection process by current node selection schemes. By implementing outward the first node selection scheme that can incorporate Proactive HCN sharing information within 6G and beyond networks, this research work enhances the existing work. The analysis that was carried out shows the potential for Proactive HCN communications as well as the ability of the suggested node selection scheme to choose the best communication node to enhance QoS and Low Latency.

Bi-level programming optimization method of rural integrated energy system based on coupling coordination degree of energy equipment

Promoting energy transformation in rural areas, building a Rural Integrated Energy System, and developing multi-energy complementary and comprehensive utilization of rural energy in accordance with local conditions are important paths to support global low-carbon transformation and rural revitalization. However, how to consider the coupling synergy of multiple devices and plan the capacity of multiple devices in rural energy systems in an economical, low-carbon, and reliable manner is an urgent issue facing the development of Rural Integrated Energy System. This paper proposes a bi-level programming optimization method of Rural Integrated Energy System based on coupling coordination degree of energy equipment. Firstly, a multi-dimensional rural user energy utilization framework is designed that comprehensively considers agriculture, animal husbandry, industry, and lifestyle. Secondly, the bi-level optimization model of the Rural Integrated Energy System based on the coupling coordination degree of energy equipment is constructed. The upper-level planning model puts forward the equipment coupling coordination degree, and determines the equipment selection scheme for different types of Rural Integrated Energy System planning. The lower-level planning model considers economy, low carbon, and reliability, and uses the improved multi-objective Harris Hawk optimization algorithm to solve the capacity of different energy equipment in the Rural Integrated Energy System. Finally, the effectiveness and scientific nature of the model and method proposed in this paper are verified by the Integrated Energy Systems of a rural area in the north of China. In addition, by comparing the equipment selection scheme with the traditional method, it can be found that the optimization scheme in this paper that considers the coupling coordination of energy equipment reduces the annualized total cost by 29.34 %, reduces the annual carbon emissions by 60.43 %, and increases the reliability by 15.85 %. The collaborative planning of energy economy, low carbon energy and reliable energy has been realized.

A Subarray Selection Scheme for Cellular-Connected UAV With Conformal Phased Array Antenna

A Subarray Selection Scheme for Cellular-Connected UAV With Conformal Phased Array Antenna

Outage performance analysis of antenna selection schemes in UAV-assisted networks

In this paper, we investigate the performance of various antenna selection (AS) techniques in an unmanned aerial vehicle (UAV)-assisted relay communication system, wherein a UAV is deployed as a flying relay to establish and sustain a communication link between source and destination nodes. The AS schemes under study encompass transmit antenna selection/maximal ratio combining (TAS/MRC), joint transmit and receive antenna selection (JTRAS), and maximum ratio transmission/receive antenna selection (MRT/RAS). We present a unified outage probability (OP) performance analysis of AS techniques in UAV relay networks. We initially derive a closed-form expression for the OP under Nakagami-m fading channels. Subsequently, an asymptotic expression elucidating the array and diversity gain is derived to offer deeper insights into the performance of the studied system. Finally, Monte Carlo simulations are conducted to validate the theoretical results.

Experimental study of flake graphite large-area explosion electron emission cathode performance based on particle size discrepancy

Graphite is the most commonly used large-area cathode material in the high-power vacuum electron device for its long life and good repetitive-frequency performance, but its particle size selection scheme has not been elucidated. Therefore, in the present work, the explosive electron emission properties of flake graphite large area explosive electron emission cathodes with varied particle sizes are studied. The 320 mesh flake graphite has a current delay reduction of 0.2–0.9 ns compared to other samples at the same peak voltage. According to the Murphy–Good equation, the emission performance of each sample during the priming stage was calculated, and the threshold characteristics of 320 mesh flake graphite were significantly better than the other samples. After the space charge limited current is formed, the plasma expansion rate of all samples is 1.2±0.2cm/μs with a difference not exceeding 4% between samples. Our research provides a strong basis for the selection of raw materials for graphite based large area explosive electron emission cathodes and contributes to the development of cross-field high-power vacuum devices.