Selection Scheme Research Articles

Differentially Private Stream Processing at Scale

We design, to the best of our knowledge, the first differentially private (DP) stream aggregation processing system at scale. Our system - Differential Privacy SQL Pipelines (DP-SQLP) - is built using a streaming framework similar to Spark streaming, and is built on top of the Spanner database and the F1 query engine from Google. Towards designing DP-SQLP we make both algorithmic and systemic advances, namely, we (i) design a novel (user-level) DP key selection algorithm that can operate on an unbounded set of possible keys, and can scale to one billion keys that users have contributed, (ii) design a preemptive execution scheme for DP key selection that avoids enumerating all the keys at each triggering time, and (iii) use algorithmic techniques from DP continual observation to release a continual DP histogram of user contributions to different keys over the stream length. We empirically demonstrate the efficacy by obtaining at least 16× reduction in error over meaningful baselines we consider. We implemented a streaming differentially private user impressions for Google Shopping with DP-SQLP. The streaming DP algorithms are further applied to Google Trends.

DAS: A DRL-Based Scheme for Workload Allocation and Worker Selection in Distributed Coded Machine Learning

DAS: A DRL-Based Scheme for Workload Allocation and Worker Selection in Distributed Coded Machine Learning

A pricing-based cooperative relay selection scheme for reliable communications

A pricing-based cooperative relay selection scheme for reliable communications

Cross-layer Design Based Common Data Channel Selection Scheme in Cognitive Radio Ad-hoc Network

Cross-layer Design Based Common Data Channel Selection Scheme in Cognitive Radio Ad-hoc Network

Location Selection Scheme of Smart Light Pole Based on Segmentation Optimization

Location Selection Scheme of Smart Light Pole Based on Segmentation Optimization

On the selection of aircraft-engine pairs for medium-haul Low-Cost Carriers operations

The selection of aircraft and engine models poses a significant challenge for Low-Cost Carriers (LCCs) striving for profitability. This decision is compounded by numerous subjective and objective variables and the vast array of available aircraft and engine configurations. Current methodologies, utilizing Multi-Criteria Decision Making (MCDM) and fuzzy logic, often simplify the problem, neglecting the engine consideration and limiting variables and alternatives. In this paper, we propose a novel methodology that circumvents these simplifications, considering engine configurations within the aircraft selection and addressing this problem for 27 parameters and real 51 selection alternatives. Through the consultation of different experts in the aeronautic field, we establish a comprehensive approach to assess the relative and overall performance of multiple variables, as well as their weights and hierarchy in the selection scheme. We apply this methodology to the aircraft selection problem in the medium-haul market, providing a framework and a solution for this currently unexplored literature domain. The results provide valuable insights for validating the devised methodology and providing relevant insights on the characteristics of the medium-haul market for LCCs.

Real-time analytical solution to energy management for hybrid electric vehicles using intelligent driving cycle recognition

For series hybrid electric vehicles, due to the limitation of engine operating characteristics, speed regulation is usually performed using discrete operating points. This leads to the problem of mixed integer programming when solving energy management problem. In this paper, an analytical method with strong real-time performance and small computational load is proposed. First, an intelligent cycle recognition system is designed. It can cluster driving cycles offline based on the probability distribution of the required power and efficiently recognize unknown driving cycles online. Then the analytical expression of power distribution is derived, and the selection scheme of engine operating point is given. Finally, the required power information obtained from the clustering is substituted into the analytical expression. The specific values of the corresponding analytical solutions for each type are computed offline. When facing unknown conditions, this method can match the power distribution scheme quickly once the driving cycle is recognized. The results of the simulation and hardware-in-loop experiments demonstrate that this method can effectively control the SOC trajectory and allocate power more optimally. Compared to the benchmark method, the proposed strategy improves the fuel economy by 5.52 % and 7.49 % in two cases, and the computational efficiency is significantly enhanced.

Method for selecting emergency material reserve bases in chemical industry parks under typhoon scenarios

Rationally selecting emergency material reserve bases (EMSBs) for chemical industry parks is crucial to ensure timely emergency responses during major accidents. To identify practical site selection schemes for EMSBs under typhoon scenarios, a prioritization/sorting site selection model considering typhoon disasters for EMSBs is developed. Firstly, an improved k-means clustering algorithm is employed to cluster typhoon paths and classify them into several critical typhoon scenarios, which are used to assess the risk of typhoon disasters affecting chemical industrial parks in specific areas. Then, according to the region's functional characteristics of EMSBs, candidate areas with emergency capabilities are identified through kernel density analysis, and safe candidate areas are further determined based on the identified typhoon scenarios. Finally, the safe candidate areas are ranked based on emergency path distances, and the preferred site selection areas are ultimately obtained through administrative planning analysis of the top-ranked areas. Furthermore, a case study is conducted based on data from Zhejiang Province, verifying the effectiveness of the decision-making method.

Randomized greedy magic point selection schemes for nonlinear model reduction

An established way to tackle model nonlinearities in projection-based model reduction is via relying on partial information. This idea is shared by the methods of gappy proper orthogonal decomposition (POD), missing point estimation (MPE), masked projection, hyper reduction, and the (discrete) empirical interpolation method (DEIM). The selected indices of the partial information components are often referred to as “magic points.” The original contribution of the work at hand is a novel randomized greedy magic point selection. It is known that the greedy method is associated with minimizing the norm of an oblique projection operator, which, in turn, is associated with solving a sequence of rank-one SVD update problems. We propose simplification measures so that the resulting greedy point selection has the following main features: (1) The inherent rank-one SVD update problem is tackled in a way, such that its dimension does not grow with the number of selected magic points. (2) The approach is online efficient in the sense that the computational costs are independent from the dimension of the full-scale model. To the best of our knowledge, this is the first greedy magic point selection that features this property. We illustrate the findings by means of numerical examples. We find that the computational cost of the proposed method is orders of magnitude lower than that of its deterministic counterpart. Nevertheless, the prediction accuracy is just as good if not better. When compared to a state-of-the-art randomized method based on leverage scores, the randomized greedy method outperforms its competitor.

Multi-Scale Feature and Multi-Channel Selection toward Parkinson's Disease Diagnosis with EEG.

Motivated by Health Care 4.0, this study aims to reducing the dimensionality of traditional EEG features based on manual extracted features, including statistical features in the time and frequency domains. A total of 22 multi-scale features were extracted from the UNM and Iowa datasets using a 4th order Butterworth filter and wavelet packet transform. Based on single-channel validation, 29 channels with the highest R2 scores were selected from a pool of 59 common channels. The proposed channel selection scheme was validated on the UNM dataset and tested on the Iowa dataset to compare its generalizability against models trained without channel selection. The experimental results demonstrate that the proposed model achieves an optimal classification accuracy of 100%. Additionally, the generalization capability of the channel selection method is validated through out-of-sample testing based on the Iowa dataset Conclusions: Using single-channel validation, we proposed a channel selection scheme based on traditional statistical features, resulting in a selection of 29 channels. This scheme significantly reduced the dimensionality of EEG feature vectors related to Parkinson's disease by 50%. Remarkably, this approach demonstrated considerable classification performance on both the UNM and Iowa datasets. For the closed-eye state, the highest classification accuracy achieved was 100%, while for the open-eye state, the highest accuracy reached 93.75%.

A human-in-the-loop method for pulmonary nodule detection in CT scans

Automated pulmonary nodule detection using computed tomography scans is vital in the early diagnosis of lung cancer. Although extensive well-performed methods have been proposed for this task, they suffer from the domain shift issue between training and test images. Unsupervised domain adaptation (UDA) methods provide a promising means to mitigate the domain variance; however, their performance is still limited since no target domain supervision is introduced. To make the pulmonary nodule detection algorithm more applicable in clinical practice and further boost the performance across domains, we propose a human-in-the-loop method in a semi-supervised fashion to enhance the model generalization ability when transferred from source domain to target domain. Specifically, we first train a detector model on source domain, and then the pre-trained detector is utilized with our proposed uncertainty-guided sample selection scheme (USSS) to find a few target domain samples worth annotating most and obtain their human annotations. Finally, the annotated and the rest unlabeled target domain samples are used together to refine the pre-trained model via our proposed zoom-in and zoom-out constraint (ZZC) strategy. We evaluate our method on the Nodule Analysis 2016 (LUNA16) and TianChi datasets. Experimental results show that our method surpasses recent competitive methods on source domain and also achieves surprising performance on target domain.

Adaptive Radio Access Technology Selection Algorithm for Heterogeneous Wireless Networks

In Heterogeneous Wireless Networks (HWNs), Radio Access Technologies (RAT) can only consider the situation of one particular Radio Resource Management (RRM) which is unsuitable for managing multiple RATs. This study deployed an adaptive RAT selection scheme model to allocate users to the best RAT with the use of the cost function variable. The adopted model uses different input criteria like signal strength, network loads, service type and QoS requirement for the best access network selections. The adaptive RAT selection algorithm was executed in different service mixes (voice and data service) to access model suitability for users in Global System for Mobile Communications with Enhanced Data Rates for Global Evolution Radio Access Network (GERAN) and Universal Mobile Telecommunications System Radio Access Network (UTRAN). The proposed algorithm resulted in the call blocking probability reduction by 0.03 for GERAN and 0.14 for UTRAN as validated with the existing algorithm based on load balancing, service-based and priority-based. The drop implied an increased probability of ensuring session stability and high quality of the active service, leading to a high load distribution.

Gene pyramiding for achieving enhanced disease and insect multiple resistance in Coffea arabica

AbstractDeveloping a new coffee cultivar can take up to 25 years using traditional approaches. The implementation of molecular tools into the coffee breeding pipeline can speed up the development of high‐yielding varieties with multiple resistance to pests and diseases. This study aimed to verify the presence of gene pyramiding for resistance to coffee berry disease (CBD) and coffee leaf rust and access the breeding potential of a breeding population of coffee (Coffea arabica L.) that presents partial phenotypic resistance to coffee leaf miner. A progeny of 128 individuals was evaluated in 2019 during the coffee maturation stage for 11 agronomic traits. The individuals were genotyped for four loci related to rust and CBD resistance. Gene pyramiding was verified based on the presence of markers linked with the resistance alleles. Genetic parameters were estimated, and a selection index was used to rank the individuals based on the phenotypic evaluation. Gene pyramiding for rust and CBD was detected in ∼82% of the individuals. Moreover, the phenotypic evaluation of rust indicated high levels of resistance, confirmed by the presence of the resistance alleles. Ninety‐five percent of the 38 top‐ranked individuals presented resistance alleles and could be used in an interpopulation recurrent selection scheme with marker‐assisted selection. The studied coffee population has the potential to be used in coffee breeding programs since it presents vigorous individuals with low levels of coffee leaf miner incidence (CLMI) and gene pyramiding for CBD and rust resistance, the main pest and diseases of this crop.

Adaptive projection plane and reference point strategy for multi-objective particle swarm optimization

Achieving a balance between convergence and diversity and their mutual enhancement is a complex task in the process of algorithm improvement. This is crucial because it is directly related to the effectiveness of the algorithm in obtaining accurate and uniformly distributed Pareto frontiers. Although significant progress has been made in particle swarm algorithms, exploring new approaches is necessary. In this paper, we construct a projection plane (projection line in 2D) based on the extreme values of the non-dominated solutions, select a set of uniform reference points on the projection plane, and then project the non-dominated solutions onto the constructed projection plane to form projection points. The reference points and projection points on the projection plane are thus utilized to guide the updating of the population as well as the maintenance of the external archive, a strategy that enhances the algorithm's global exploration and local exploitation capabilities. Secondly, we aggregate the target values of particles into a single scalar value and combine the idea of particle fusion to design a scheme for the particle selection of individual optimal particles. This paper further improves the algorithm's overall performance by using the information between populations to select individual optimal particles. Lastly, it is evaluated against a number of multi-objective algorithms that are currently in use and perform well on 22 test problems. The findings demonstrate that the algorithm this paper proposes performs better when solving multi-objective problems.

Exploring the Potential of Generative Adversarial Networks in Enhancing Urban Renewal Efficiency

As Chinese cities transition into a stage of stock development, the revitalization of industrial areas becomes increasingly crucial, serving as a pivotal factor in urban renewal. The renovation of old factory buildings is in full swing, and architects often rely on matured experience to produce several profile renovation schemes for selection during the renovation process. However, when dealing with a large number of factories, this task can consume a significant amount of manpower. In the era of maturing machine learning, this study, set against the backdrop of the renovation of old factory buildings in an industrial district, explores the potential application of deep learning technology in improving the efficiency of factory renovation. We establish a factory renovation profile generation model based on the generative adversarial networks (GANs), learning and generating design features for the renovation of factory building profiles. To ensure a balance between feasibility and creativity in the generated designs, this study employs various transformation techniques on each original profile image during dataset construction, creating mappings between the original profile images and various potential renovation schemes. Additionally, data augmentation techniques are applied to expand the dataset, and the trained models are validated and analyzed on the test set. This study demonstrates the significant potential of the GANs in factory renovation profile design, providing designers with richer reference solutions.

Multi-armed bandit algorithm for sequential experiments of molecular properties with dynamic feature selection.

Sequential optimization is one of the promising approaches in identifying the optimal candidate(s) (molecules, reactants, drugs, etc.) with desired properties (reaction yield, selectivity, efficacy, etc.) from a large set of potential candidates, while minimizing the number of experiments required. However, the high dimensionality of the feature space (e.g., molecular descriptors) makes it often difficult to utilize the relevant features during the process of updating the set of candidates to be examined. In this article, we developed a new sequential optimization algorithm for molecular problems based on reinforcement learning, multi-armed linear bandit framework, and online, dynamic feature selections in which relevant molecular descriptors are updated along with the experiments. We also designed a stopping condition aimed to guarantee the reliability of the chosen candidate from the dataset pool. The developed algorithm was examined by comparing with Bayesian optimization (BO), using two synthetic datasets and two real datasets in which one dataset includes hydration free energy of molecules and another one includes a free energy difference between enantiomer products in chemical reaction. We found that the dynamic feature selection in representing the desired properties along the experiments provides a better performance (e.g., time required to find the best candidate and stop the experiment) as the overall trend and that our multi-armed linear bandit approach with a dynamic feature selection scheme outperforms the standard BO with fixed feature variables. The comparison of our algorithm to BO with dynamic feature selection is also addressed.

PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption

In the past decade, we have witnessed an exponential growth of deep learning models, platforms, and applications. While existing DL applications and Machine Learning as a service (MLaaS) frameworks assume fully trusted models, the need for privacy-preserving DNN evaluation arises. In a secure multi-party computation scenario, both the model and the data are considered proprietary, i.e., the model owner does not want to reveal the highly valuable DL model to the user, while the user does not wish to disclose their private data samples either. Conventional privacy-preserving deep learning solutions ask the users to send encrypted samples to the model owners, who must handle the heavy lifting of ciphertext-domain computation with homomorphic encryption. In this paper, we present a novel solution, namely, PrivDNN, which (1) offloads the computation to the user side by sharing an encrypted deep learning model with them, (2) significantly improves the efficiency of DNN evaluation using partial DNN encryption, (3) ensures model accuracy and model privacy using a core neuron selection and encryption scheme. Experimental results show that PrivDNN reduces privacy-preserving DNN inference time and memory requirement by up to 97% while maintaining model performance and privacy. Codes can be found at https://github.com/LiangqinRen/PrivDNN

Creation of 6G Communication System for VANETs via a Neuro-Fuzzy Forwarder Selection Scheme

Creation of 6G Communication System for VANETs via a Neuro-Fuzzy Forwarder Selection Scheme

Multi-Objective Distributed Client Selection in Federated Learning-Assisted Internet of Vehicles.

Federated learning is an emerging distributed machine learning framework in the Internet of Vehicles (IoV). In IoV, millions of vehicles are willing to train the model to share their knowledge. Maintaining an active state means the participants must update their state to the FL server in a fixed interval and participate in the next round. However, the cost of maintaining an active state is very large when there are a huge number of participating vehicles. In this paper, we propose a distributed client selection scheme to reduce the cost of maintaining the active state for all participants. The clients with the highest evaluation are elected among the neighbors. In the evaluator, four variables are considered, including the sample quantity, available throughput, computational capability, and the quality of the local dataset. We adopt fuzzy logic as the evaluator since the closed-form solution over four variables does not exist. Extensive simulation results show that our proposal approximates the centralized client selection in terms of accuracy and can significantly reduce the communication overhead.

Motion Branch Transformation of 3(Rc)PU Parallel Mechanism with Reconfigurable Joint and Kinematic Performance Index

A novel 3(Rc)PU parallel mechanism based on the reconfigurable circular groove cross joint (Rc joint) is proposed. The motion branch transformation relationship and constraint performance evaluation method for the mechanism are studied. According to constrained screw analysis, the (Rc)PU limb provides a constraint couple to the moving platform in one motion mode and no constraint to the platform in another motion mode. According to the two configurations of the limb, the 3(Rc)PU mechanism has four different motion branches, namely 3T, 1R3T, 2R3T, and 3R3T. Based on the input selection principle, the input selection scheme of the 3(Rc)PU mechanism is determined, and it is concluded that, to achieve stable motion, at least two input drive pairs need to be applied on each limb. A unified kinematic model with four motion branches is established, and the geometric constraint equations of the 3(Rc)PU parallel mechanism are derived. After selecting the input actuated joints, the local minimization transmission index (LMTI) of the reconfigurable mechanism under different motion branches is established to evaluate the motion/force transmission performance of the reconfigurable mechanism under different motion branches. The conclusion shows that the LMTI values satisfy the corresponding constraint conditions, and the 3(Rc)PU parallel mechanism has good motion/force transmission performance.