scholarly journals Discrete Multiple Kernel k-means

2021 ◽  
Author(s):  
Rong Wang ◽  
Jitao Lu ◽  
Yihang Lu ◽  
Feiping Nie ◽  
Xuelong Li
Keyword(s):  
Optimization Algorithm ◽  
Information Loss ◽  
Complementary Information ◽  
Two Stage ◽  
Practical Applications ◽  
Multiple Kernel ◽  
Proposed Model ◽  
Kernel Fusion ◽  
Indicator Matrix ◽  
Two Stages

The multiple kernel k-means (MKKM) and its variants utilize complementary information from different kernels, achieving better performance than kernel k-means (KKM). However, the optimization procedures of previous works all comprise two stages, learning the continuous relaxed label matrix and obtaining the discrete one by extra discretization procedures. Such a two-stage strategy gives rise to a mismatched problem and severe information loss. To address this problem, we elaborate a novel Discrete Multiple Kernel k-means (DMKKM) model solved by an optimization algorithm that directly obtains the cluster indicator matrix without subsequent discretization procedures. Moreover, DMKKM can strictly measure the correlations among kernels, which is capable of enhancing kernel fusion by reducing redundancy and improving diversity. What’s more, DMKKM is parameter-free avoiding intractable hyperparameter tuning, which makes it feasible in practical applications. Extensive experiments illustrated the effectiveness and superiority of the proposed model.

scholarly journals Analysis of Red-Light Violation Behavior of Pedestrian Two-Stage Crossing at a Signalized Intersection

2019 ◽  
Vol 5 (2) ◽  
pp. 429 ◽  
Author(s):  
Yongqing Guo ◽  
Xiaoyuan Wang ◽  
Xinqiang Meng ◽  
Jie Wang ◽  
Yaqi Liu
Keyword(s):  
Red Light ◽  
Video Recording ◽  
Signalized Intersections ◽  
Signal Timing ◽  
Two Stage ◽  
Proposed Model ◽  
Group A ◽  
Two Stages ◽  
User Friendly ◽  
Time Selection

Studying pedestrians’ twice-crossing behavior is of great significance to enhance safety and efficiency for pedestrians at signalized intersections. However, researchers have paid little attention to analyze and model pedestrians’ red-light running behavior on a two-stage crossing at signalized intersections. This paper focuses on analyzing the characteristics of pedestrian red-light violation behavior at the two stages, including the time distribution of violation behavior, the consistency of violation behavior, and the violation behavior in group.  A goal-oriented and time-driven red-light violation behavior model was proposed for pedestrian two-stage crossing. A video-recording method was used to collect field data, and the results show that pedestrians in the two directions present different red-light violation behaviors in time selection and violation count, as well as, pedestrians in the two stages of a direction present different red-light violation behaviors in time selection. The main reasons leading to the phenomena were analyzed, regarding from people’s cognitive psychology and visual perception. The results also show that the proposed model is effective in simulating pedestrian red-light violation behavior of twice crossing. This research provides a theoretical basis for optimizing signal timing, improving pedestrian safety and developing user-friendly transportation system.

scholarly journals A Novel Multi-Objective Nonlinear Discrete Binary Gaining-Sharing knowledge-based Optimization Algorithm Optimum Scheduling of Flights for Residual S

2022 ◽  
Vol 13 (1) ◽  
pp. 0-0
Keyword(s):  
Mathematical Programming ◽  
Decision Maker ◽  
Optimization Algorithm ◽  
Programming Model ◽  
Search Space ◽  
Mathematical Programming Model ◽  
Practical Applications ◽  
Knowledge Based ◽  
Two Stages

GSK algorithm is based on the concept of how humans acquire and share knowledge through their lifespan. Discrete Binary version of GSK named novel binary Gaining Sharing knowledge-based optimization algorithm (DBGSK) depends on mainly two binary stages: binary junior gaining sharing stage and binary senior gaining sharing stage with knowledge factor 1. These two stages enable BGSK for exploring and exploitation of the search space efficiently and effectively to solve problems in binary space. Besides, one of these practical applications is to optimally schedule the flights for residual stranded citizens due to COVID-19. The problem is defined for a decision maker who wants to schedule a multiple stepped trip for a subset of candidate airports to return the maximum number of residuals of stranded citizens remaining in listed airports while comprising the minimization of the total travelled distances for a carrying airplane. A nonlinear binary mathematical programming model for the problem is introduced with a real application case study, the case study is solved using (DBGSK).

Multi Disease-Prediction Framework Using Hybrid Deep Learning: An Optimal Prediction Model (Preprint)

2020 ◽  
Author(s):  
Anusha Ampavathi ◽  
Vijaya Saradhi T
Keyword(s):  
Feature Extraction ◽  
Big Data ◽  
Deep Learning ◽  
Weight Function ◽  
Optimization Algorithm ◽  
Large Scale ◽  
Heuristic Algorithms ◽  
Disease Prediction ◽  
Health Care Decisions ◽  
Proposed Model

UNSTRUCTURED Big data and its approaches are generally helpful for healthcare and biomedical sectors for predicting the disease. For trivial symptoms, the difficulty is to meet the doctors at any time in the hospital. Thus, big data provides essential data regarding the diseases on the basis of the patient’s symptoms. For several medical organizations, disease prediction is important for making the best feasible health care decisions. Conversely, the conventional medical care model offers input as structured that requires more accurate and consistent prediction. This paper is planned to develop the multi-disease prediction using the improvised deep learning concept. Here, the different datasets pertain to “Diabetes, Hepatitis, lung cancer, liver tumor, heart disease, Parkinson’s disease, and Alzheimer’s disease”, from the benchmark UCI repository is gathered for conducting the experiment. The proposed model involves three phases (a) Data normalization (b) Weighted normalized feature extraction, and (c) prediction. Initially, the dataset is normalized in order to make the attribute's range at a certain level. Further, weighted feature extraction is performed, in which a weight function is multiplied with each attribute value for making large scale deviation. Here, the weight function is optimized using the combination of two meta-heuristic algorithms termed as Jaya Algorithm-based Multi-Verse Optimization algorithm (JA-MVO). The optimally extracted features are subjected to the hybrid deep learning algorithms like “Deep Belief Network (DBN) and Recurrent Neural Network (RNN)”. As a modification to hybrid deep learning architecture, the weight of both DBN and RNN is optimized using the same hybrid optimization algorithm. Further, the comparative evaluation of the proposed prediction over the existing models certifies its effectiveness through various performance measures.

scholarly journals Solving knapsack problems using a binary gaining sharing knowledge-based optimization algorithm

2021 ◽  
Author(s):  
Prachi Agrawal ◽  
Talari Ganesh ◽  
Ali Wagdy Mohamed
Keyword(s):  
Life Span ◽  
Population Size ◽  
Linear Function ◽  
Optimization Algorithm ◽  
Optimization Problems ◽  
Search Space ◽  
Knapsack Problems ◽  
Local Optima ◽  
Knowledge Based ◽  
Two Stages

AbstractThis article proposes a novel binary version of recently developed Gaining Sharing knowledge-based optimization algorithm (GSK) to solve binary optimization problems. GSK algorithm is based on the concept of how humans acquire and share knowledge during their life span. A binary version of GSK named novel binary Gaining Sharing knowledge-based optimization algorithm (NBGSK) depends on mainly two binary stages: binary junior gaining sharing stage and binary senior gaining sharing stage with knowledge factor 1. These two stages enable NBGSK for exploring and exploitation of the search space efficiently and effectively to solve problems in binary space. Moreover, to enhance the performance of NBGSK and prevent the solutions from trapping into local optima, NBGSK with population size reduction (PR-NBGSK) is introduced. It decreases the population size gradually with a linear function. The proposed NBGSK and PR-NBGSK applied to set of knapsack instances with small and large dimensions, which shows that NBGSK and PR-NBGSK are more efficient and effective in terms of convergence, robustness, and accuracy.

scholarly journals A Theoretical Model with Which to Safely Optimize the Configuration of Hydraulic Suspension of Modular Trailers in Special Road Transport

2020 ◽  
Vol 11 (1) ◽  
pp. 305
Author(s):  
Rubén Escribano-García ◽  
Marina Corral-Bobadilla ◽  
Fátima Somovilla-Gómez ◽  
Rubén Lostado-Lorza ◽  
Ash Ahmed
Keyword(s):  
Theoretical Model ◽  
Wind Turbine ◽  
Optimization Algorithm ◽  
Hydraulic Cylinder ◽  
Road Transport ◽  
Automatic Testing ◽  
Transport Systems ◽  
The Road ◽  
Proposed Model ◽  
On The Road

The dimensions and weight of machines, structures, and components that need to be transported safely by road are growing constantly. One of the safest and most widely used transport systems on the road today due to their versatility and configuration are modular trailers. These trailers have hydraulic pendulum axles that are that are attached in pairs to the rigid platform above. In turn, these modular trailers are subject to limitations on the load that each axle carries, the tipping angle, and the oil pressure of the suspension system in order to guarantee safe transport by road. Optimizing the configuration of these modular trailers accurately and safely is a complex task. Factors to be considered include the load’s characteristics, the trailer’s mechanical properties, and road route conditions including the road’s slope and camber, precipitation and direction, and force of the wind. This paper presents a theoretical model that can be used for the optimal configuration of hydraulic cylinder suspension of special transport by road using modular trailers. It considers the previously mentioned factors and guarantees the safe stability of road transport. The proposed model was validated experimentally by placing a nacelle wind turbine at different points within a modular trailer. The weight of the wind turbine was 42,500 kg and its dimensions were 5133 × 2650 × 2975 mm. Once the proposed model was validated, an optimization algorithm was employed to find the optimal center of gravity for load, number of trailers, number of axles, oil pressures, and hydraulic configuration. The optimization algorithm was based on the iterative and automatic testing of the proposed model for different positions on the trailer and different hydraulic configurations. The optimization algorithm was tested with a cylindrical tank that weighed 108,500 kg and had dimensions of 19,500 × 3200 × 2500 mm. The results showed that the proposed model and optimization algorithm could safely optimize the configuration of the hydraulic suspension of modular trailers in special road transport, increase the accuracy and reliability of the calculation of the load configuration, save time, simplify the calculation process, and be easily implemented.

scholarly journals MultiStep Ahead Forecasting for Hourly PM10 and PM2.5 Based on Two-Stage Decomposition Embedded Sample Entropy and Group Teacher Optimization Algorithm

Atmosphere ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 64
Author(s):  
Feng Jiang ◽  
Yaqian Qiao ◽  
Xuchu Jiang ◽  
Tianhai Tian
Keyword(s):  
Optimization Algorithm ◽  
Hybrid Approach ◽  
Forecast Accuracy ◽  
Ensemble Empirical Mode Decomposition ◽  
Sample Entropy ◽  
Air Pollutant ◽  
Intrinsic Mode Functions ◽  
Concentration Data ◽  
Two Stage ◽  
Pm10 And Pm2.5

The randomness, nonstationarity and irregularity of air pollutant data bring difficulties to forecasting. To improve the forecast accuracy, we propose a novel hybrid approach based on two-stage decomposition embedded sample entropy, group teaching optimization algorithm (GTOA), and extreme learning machine (ELM) to forecast the concentration of particulate matter (PM10 and PM2.5). First, the improvement complementary ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is employed to decompose the concentration data of PM10 and PM2.5 into a set of intrinsic mode functions (IMFs) with different frequencies. In addition, wavelet transform (WT) is utilized to decompose the IMFs with high frequency based on sample entropy values. Then the GTOA algorithm is used to optimize ELM. Furthermore, the GTOA-ELM is utilized to predict all the subseries. The final forecast result is obtained by ensemble of the forecast results of all subseries. To further prove the predictable performance of the hybrid approach on air pollutants, the hourly concentration data of PM2.5 and PM10 are used to make one-step-, two-step- and three-step-ahead predictions. The empirical results demonstrate that the hybrid ICEEMDAN-WT-GTOA-ELM approach has superior forecasting performance and stability over other methods. This novel method also provides an effective and efficient approach to make predictions for nonlinear, nonstationary and irregular data.

scholarly journals Diversity Balancing for Two-Stage Collaborative Filtering in Recommender Systems

2020 ◽  
Vol 10 (4) ◽  
pp. 1257 ◽  
Author(s):  
Liang Zhang ◽  
Quanshen Wei ◽  
Lei Zhang ◽  
Baojiao Wang ◽  
Wen-Hsien Ho
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Social Relationships ◽  
Two Stage ◽  
Proposed Model ◽  
The Social ◽  
Item List ◽  
Ranking Strategy ◽  
High Prediction ◽  
Optimization Mechanism

Conventional recommender systems are designed to achieve high prediction accuracy by recommending items expected to be the most relevant and interesting to users. Therefore, they tend to recommend only the most popular items. Studies agree that diversity of recommendations is as important as accuracy because it improves the customer experience by reducing monotony. However, increasing diversity reduces accuracy. Thus, a recommendation algorithm is needed to recommend less popular items while maintaining acceptable accuracy. This work proposes a two-stage collaborative filtering optimization mechanism that obtains a complete and diversified item list. The first stage of the model incorporates multiple interests to optimize neighbor selection. In addition to using conventional collaborative filtering to predict ratings by exploiting available ratings, the proposed model further considers the social relationships of the user. A novel ranking strategy is then used to rearrange the list of top-N items while maintaining accuracy by (1) rearranging the area controlled by the threshold and by (2) maximizing popularity while maintaining an acceptable reduction in accuracy. An extensive experimental evaluation performed in a real-world dataset confirmed that, for a given loss of accuracy, the proposed model achieves higher diversity compared to conventional approaches.

scholarly journals A deep learning approach to multiple kernel fusion

2017 ◽  
Author(s):  
Huan Song ◽  
Jayaraman J. Thiagarajan ◽  
Prasanna Sattigeri ◽  
Karthikeyan Natesan Ramamurthy ◽  
Andreas Spanias
Keyword(s):  
Deep Learning ◽  
Learning Approach ◽  
Multiple Kernel ◽  
Kernel Fusion

Cuckoo optimization algorithm in reverse logistics: A network design for COVID-19 waste management

2021 ◽  
pp. 0734242X2110039
Author(s):  
Elham Shadkam
Keyword(s):  
Waste Management ◽  
Network Design ◽  
Optimization Algorithm ◽  
Reverse Logistics ◽  
Heuristic Algorithms ◽  
Programming Model ◽  
Fixed Costs ◽  
Logistics System ◽  
Cuckoo Optimization Algorithm ◽  
Proposed Model

Today, reverse logistics (RL) is one of the main activities of supply chain management that covers all physical activities associated with return products (such as collection, recovery, recycling and destruction). In this regard, the designing and proper implementation of RL, in addition to increasing the level of customer satisfaction, reduces inventory and transportation costs. In this paper, in order to minimize the costs associated with fixed costs, material flow costs, and the costs of building potential centres, a complex integer linear programming model for an integrated direct logistics and RL network design is presented. Due to the outbreak of the ongoing global coronavirus pandemic (COVID-19) at the beginning of 2020 and the consequent increase in medical waste, the need for an inverse logistics system to manage waste is strongly felt. Also, due to the worldwide vaccination in the near future, this waste will increase even more and careful management must be done in this regard. For this purpose, the proposed RL model in the field of COVID-19 waste management and especially vaccine waste has been designed. The network consists of three parts – factory, consumers’ and recycling centres – each of which has different sub-parts. Finally, the proposed model is solved using the cuckoo optimization algorithm, which is one of the newest and most powerful meta-heuristic algorithms, and the computational results are presented along with its sensitivity analysis.

Sign in / Sign up

Export Citation Format

Share Document