the growing use of machine learning algorithms in decisions that significantly affect people necessitate interpretable and fair approaches. Mathematical programming based machine learning models have attracted attenti...
详细信息
ISBN:
(纸本)9783031779404;9783031779411
the growing use of machine learning algorithms in decisions that significantly affect people necessitate interpretable and fair approaches. Mathematical programming based machine learning models have attracted attention because of the flexibility they provide to integrate features like interpretability and fairness, combined with high accuracy. this work introduces a mathematical programming based classification tree that uses a game theoretic approach to address group fairness. the proposed mathematical formulation is a Mixed Integer Linear Programming model using a piecewise linearisation strategy based on special-ordered sets. the overall misclassification rate is the fairness metric examined and the Nash bargaining scheme is followed to balance the trade off between the misclassification error of the groups. the efficiency of the methodology is evaluated via three binary and multi-class literature datasets, which provide evidence for the fairness and accuracy of the predictions made by the model.
this paper presents a comprehensive approach to controlling a Parrot Mambo minidrone in a simulation environment using MATLAB. the primary objective is to guide the drone along a predefined path while maintaining stab...
详细信息
ISBN:
(数字)9798331515911
ISBN:
(纸本)9798331515928
this paper presents a comprehensive approach to controlling a Parrot Mambo minidrone in a simulation environment using MATLAB. the primary objective is to guide the drone along a predefined path while maintaining stability and precision. Optical flow technique and Inertial Measurement Unit sensor data are used for real-time position and velocity estimation. Path planning algorithms, coupled with control strategies such as Kalman filtering and dynamic error correction, ensure the drone follows the optimal path to reach its target. Simulation results demonstrate the effectiveness of the proposed system in successfully navigating the drone through complex maneuvers with minimal drift.
the proceedings contain 23 papers. the special focus in this conference is on Optimization and Learning. the topics include: HOTS: A Containers Resource Allocation Hybrid Method Using Machine Learning and Optimiz...
ISBN:
(纸本)9783031779404
the proceedings contain 23 papers. the special focus in this conference is on Optimization and Learning. the topics include: HOTS: A Containers Resource Allocation Hybrid Method Using Machine Learning and Optimization;optimisation-Based Classification Tree: A Game theoretic Approach to Group Fairness;jaxDecompiler: Redefining Gradient-Informed Software Design;adapted Q-Learning for the Blocking Job Shop Scheduling Problem;NeuroLGP-SM: A Surrogate-Assisted Neuroevolution Approach Using Linear Genetic Programming;Neural Architecture Tuning: A BO-Powered NAS Tool;a Multi-objective Clustering Algorithm Integrating Intra-Clustering and Inter-Clustering Measures;a Bayesian Optimization Approach to Algorithm Parameter Tuning in Constrained Multiobjective Optimization;evidence on the Regularisation Properties of Maximum-Entropy Reinforcement Learning;a Benchmark for Missing Data Imputation Techniques: Development Perspectives and Performance Comparative;approaching Single-Episode Survival Reinforcement Learning with Safety-threshold Q-Learning;feature Selection Based on Membrane Clustering;learning Insertion Patterns to Enhance Operational Efficiency in Large-Scale Dial-a-Ride Systems;a Constraint Programming Approach for the Preference Tourist Trip Design Problem;Solving a Shareable-Setup Time Prize Collection VRP Applied to an Electrical Maintenance Sector;biologically-Inspired algorithms for Adaptive Non-Player Character Behavior in Video Games;Optimization of Hydro Generation and Load Forecasting Based On LSTNet;patient Visits Forecasting in the Post-pandemic Era at Emergency Departments;nature-Inspired Techniques for Combinatorial Reverse Auctions in Electricity Consumption;robust Models for Learning Languages;advancing Road Safety Metrics: Exploring Index Construction.
Quadcopter drones have many advantages and are being used more and more in various fields. this requires a stronger performance of the UAV. this paper adds an expert system algorithm on the basis of the traditional PI...
详细信息
ISBN:
(纸本)9798400707087
Quadcopter drones have many advantages and are being used more and more in various fields. this requires a stronger performance of the UAV. this paper adds an expert system algorithm on the basis of the traditional PID controller. Firstly, the kinematic modeling of the quadrotor UAV is undertaken to improve its control performance, the basic framework of the traditional PID controller is used first, and then the expert algorithm is added, and the controller parameters are adjusted through the analysis of the deviation to achieve a more accurate control effect. In this paper, the control simulation experiments of pitch angle, roll angle and yaw angle were carried out for boththe traditional conventional PID controller and the optimised PID controller with additional expert algorithms, and it was shown by comparison that the expert PID controller takes less time to stabilise, has a smaller error and reduces the number of oscillations. It seems that the quadcopter UAV with expert PID control system has better control effect and stability.
the proceedings contain 72 papers. the topics discussed include: design and implementation of key word extraction system based on pre-training model and artificial intelligence algorithm;an overview of optimized inven...
ISBN:
(纸本)9798331529314
the proceedings contain 72 papers. the topics discussed include: design and implementation of key word extraction system based on pre-training model and artificial intelligence algorithm;an overview of optimized inventory management models in technology companies: historical developments, practical applications, and ai-driven approaches;multi-subpopulation artificial bee colony algorithm based on individual classification;terrain image classification based on vision transformer deep learning algorithm;optimized service function deployment in edge computing networks using deep reinforcement learning;new parallelized greedy soup algorithm in the end-to-end automatic speech recognition;and a local-mean based pseudo nearest neighbor method.
the proceedings contain 207 papers. the topics discussed include: low cost 3D-printed biosensor arrays for protein-based cancer diagnostics based on electrochemiluminescence;a robust multichannel lung sound recording ...
ISBN:
(纸本)9789897581700
the proceedings contain 207 papers. the topics discussed include: low cost 3D-printed biosensor arrays for protein-based cancer diagnostics based on electrochemiluminescence;a robust multichannel lung sound recording device;automated breastmass segmentation using pulse-coupled neural network and distance regularized level set evolution: a coarse-to-fine approach;SynapCountJ: a tool for analyzing synaptic densities in neurons;highly robust classification: a regularized approach for omics data;combinatorial identification of broad association regions with ChIP-seq data;quantitative estimation of long-living fluorescent molecules from temporal fluorescence intensity data corrupted by nonzero-mean noise;epileptic seizure prediction in scalp EEG using one dimensional local binary pattern based features;achieving patient-centered fine-grained access control in hospital information systems - using business process management systems;and intelligent robotic approach for after-stroke hand rehabilitation.
the proceedings contain 316 papers. the topics discussed include: early screening for Alzheimer’s disease based on OCT image classification;AUV 3D path planning based on improved sparrow search algorithm;a new offloa...
ISBN:
(纸本)9798350361445
the proceedings contain 316 papers. the topics discussed include: early screening for Alzheimer’s disease based on OCT image classification;AUV 3D path planning based on improved sparrow search algorithm;a new offloading method in cloud platforms: reducing latency based on data compression;optimization study of variable spray technology in dust removal systems;a filtering non-discriminative features method for person re-identification based on transformer;measurement of water content in oil-water two-phase system based on optimized EWT-FK algorithm;RRT-trained DDQN algorithm for pathfinding problem of automated guided vehicle;patient's emotion computing under robot vision;an estimation method for state of charge of lithium-ion batteries based on adaptive multi-innovation fractional order unscented Kalman filtering;apple detection and yield estimation based on YOLOv5;and optimization of multi-UUV cooperative detection formation based on particle swarm optimization.
the proceedings contain 24 papers. the topics discussed include: automated algorithm for multi-variate data synthesis with Cholesky decomposition;large matrix multiplication algorithms: analysis and comparison;benchma...
ISBN:
(纸本)9798400709098
the proceedings contain 24 papers. the topics discussed include: automated algorithm for multi-variate data synthesis with Cholesky decomposition;large matrix multiplication algorithms: analysis and comparison;benchmarking classifiers for loan default prediction using archetypal analysis;enhancing banking security through intelligent models for advanced fraud prevention;innovative predictive modeling of property appraisal: emphasizing coastline proximity as a key factor;improved grey wolf optimization algorithm based on local derivative inertia weights;ensemble deep transfer learning approaches for sales forecasting;an improved teaching-learning-based optimization with adaptive moment estimation for global optimization;preprocessing-based adversarial defense for object detection via feature filtration;and person attributes recognition based on hierarchical classification.
the proceedings contain 11 papers. the topics discussed include: overcoming load imbalance for irregular sparse matrices;optimizing Word2Vec performance on multicore systems;parallel depth-first search for directed ac...
ISBN:
(纸本)9781450351362
the proceedings contain 11 papers. the topics discussed include: overcoming load imbalance for irregular sparse matrices;optimizing Word2Vec performance on multicore systems;parallel depth-first search for directed acyclic graphs;progressive load balancing of asynchronous algorithms;a case for migrating execution for irregular applications;pressure-driven hardware managed thread concurrency for irregular applications;an efficient data layout transformation algorithm for locality-aware parallel sparse FFT;spherical region queries on multicore architectures;evaluation of knight landing high bandwidth memory for HPC workloads;enabling work-efficiency for high performance vertex-centric graph analytics on GPUs;and accelerating energy games solvers on modern architectures.
the proceedings contain 33 papers. the topics discussed include: an exact algorithm for connected red-blue dominating set;maximizing PageRank with new Backlinks;enumerating rooted graphs with reflectional block struct...
ISBN:
(纸本)3642130720
the proceedings contain 33 papers. the topics discussed include: an exact algorithm for connected red-blue dominating set;maximizing PageRank with new Backlinks;enumerating rooted graphs with reflectional block structures;improved approximations for TSP with simple precedence constraints;polynomial space algorithms for counting dominating sets and the domatic number;parameterized complexity of even/odd subgraph problems;popular matchings in the marriage and roommates problems;bounding the number of tolerable faults in majority-based systems;testing computability by width-2 OBDDs where the variable order is unknown;graph unique-maximum and conflict-free colorings;strategic coloring of a graph;multicut algorithms via tree decompositions;and the steiner tree reoptimization problem with sharpened triangle inequality.
暂无评论