The proceedings contain 50 papers. The special focus in this conference is on Data Science, Machine Learning and Blockchain Technology. The topics include: An unsupervised approach to creating a restaurant recommendat...
ISBN:
(纸本)9781032426853
The proceedings contain 50 papers. The special focus in this conference is on Data Science, Machine Learning and Blockchain Technology. The topics include: An unsupervised approach to creating a restaurant recommendation system;Classification of alzheimer’s disease using D-DEMNET framework;comparison of machine learning and deep learning methods for detection of liver abnormality;soil micronutrient detection using machine learning;a review of tracking concept drift detection in machine learning;wearable electrogastrogram perspective for healthcare applications;computer vision based home automation;Early autism detection using ML on behavioural pattern;implementation of application prototypes for human-to-computer interactions;recommendation system for anime using machine learning algorithms;predicting bitcoin price fluctuation by Twitter sentiment analysis;microarchitecture design and verification of co-processor for floating point operation;blockchain based higher education ecosystem;document verification using blockchain;blockchain-based traceability system for readymade food products;a cloud based interactive framework for emergency medical data sharing;the analysis and interpretation of higher education teachers based on student and teachers feedback;Implementing AI on microcontrollers in fog and edge architectures;abnormality detection in chest radiograph using deep learning models;a comprehensive review on hate speech recognition utilizing natural language processing and machine learning;prevalence of migraine among collegiate students in greater Noida;Indoor navigation using BLE beacons;strategic health planner and exercise suggester;perspective of deep learning strategies for analysis of 1D biomedical signals;revolution in agriculture sector using blockchain technology;customer churn prediction using ensemble learning with neural networks;Securing crime case summary and E-FIR using blockchain concept.
Precise short-term load forecasting is crucial in the electric power industry, which serves a vital purpose in maintaining a balance between demand and supply. Maintaining this equilibrium is essential for ensuring th...
详细信息
ISBN:
(数字)9798331534400
ISBN:
(纸本)9798331534417
Precise short-term load forecasting is crucial in the electric power industry, which serves a vital purpose in maintaining a balance between demand and supply. Maintaining this equilibrium is essential for ensuring the stability and efficiency of power systems. This forecasting task, however, poses significant challenges due to its inherent complexity. This paper presents a new approach for short-term load forecasting through the combination of convolutional neural networks (CNN) and extreme gradient boosting (XGBoost) algorithms. The model incorporates the feature extraction skills of CNN with the sequential learning strength of XGBoost. Both the techniques are ensembled with gradient boosting, which functions as a meta-learner. Gradient boosting combines the individual predictions done by the CNN and XGBoost and enhances the accuracy. The research used the daily load consumption data of Queensland, Australia. This proposed ensemble method is evaluated on the dataset and compared with other forecasting techniques. The outcomes indicated that the suggested ensemble model surpasses the existing forecasting algorithms in terms of various evaluation metrics.
A cable-driven space manipulator has great application potential in space operations due to its advantages of flexible movement and slender body. However, the pose accuracy of its end-effector is worse than that of tr...
详细信息
Deep learning-based grasp prediction models have become an industry standard for robotic bin-picking systems. To maximize pick success, production environments are often equipped with several end-effector tools that c...
Deep learning-based grasp prediction models have become an industry standard for robotic bin-picking systems. To maximize pick success, production environments are often equipped with several end-effector tools that can be swapped on-the-fly, based on the target object. Tool-change, however, takes time. Choosing the order of grasps to perform, and corresponding tool-change actions, can improve system throughput; this is the topic of our work. The main challenge in planning tool change is uncertainty - we typically cannot see objects in the bin that are currently occluded. Inspired by queuing and admission control problems, we model the problem as a Markov Decision Process (MDP), where the goal is to maximize expected throughput, and we pursue an approximate solution based on model predictive control, where at each time step we plan based only on the currently visible objects. Special to our method is the idea of void zones, which are geometrical boundaries in which an unknown object will be present, and therefore cannot be accounted for during planning. Our planning problem can be solved using integer linear programming (ILP). However, we find that an approximate solution based on sparse tree search yields near optimal performance at a fraction of the time. Another question that we explore is how to measure the performance of tool-change planning: we find that throughput alone can fail to capture delicate and smooth behavior, and propose a principled alternative. Finally, we demonstrate our algorithms on both synthetic and real world bin picking tasks.
Human Kinesiology analysis is essential for understanding biomechanical loads in rehabilitation, injury prevention, and diagnosis. However, traditional marker-based motion capture systems are suboptimal due to high eq...
详细信息
Estimating the pose information on moving vehi-cles is one of the most fundamental functions of autonomous driving for detecting and tracking moving objects. The current methods are often based on the prior informatio...
详细信息
We study how to design learning-based adaptive controllers that enable fast and accurate online adaptation in changing environments. In these settings, learning is typically done during an initial (offline) design pha...
详细信息
ISBN:
(数字)9798350384574
ISBN:
(纸本)9798350384581
We study how to design learning-based adaptive controllers that enable fast and accurate online adaptation in changing environments. In these settings, learning is typically done during an initial (offline) design phase, where the vehicle is exposed to different environmental conditions and disturbances (e.g., a drone exposed to different winds) to collect training data. Our work is motivated by the observation that real-world disturbances fall into two categories: 1) those that can be directly monitored or controlled during training, which we call "manageable"; and 2) those that cannot be directly measured or controlled (e.g., nominal model mismatch, air plate effects, and unpredictable wind), which we call "latent". Imprecise modeling of these effects can result in degraded control performance, particularly when latent disturbances continuously vary. This paper presents the Hierarchical Meta-learning-based Adaptive Controller (HMAC) to learn and adapt to such multi-source disturbances. Within HMAC, we develop two techniques: 1) Hierarchical Iterative Learning, which jointly trains representations to caption the various sources of disturbances, and 2) Smoothed Streaming Meta-Learning, which learns to capture the evolving structure of latent disturbances over time (in addition to standard meta-learning on the manageable disturbances). Experimental results demonstrate that HMAC exhibits more precise and rapid adaptation to multi-source disturbances than other adaptive controllers.
1
Image clustering is a fundamental problem in computer vision domains. In this survey, we provide a comprehensive overview of image clustering. Specifically, we first discuss the applications of image clustering across...
详细信息
This study presents a method for constructing metric depth maps based on relative depth maps for a 4-DOF manipulator with a single RGB camera, which is attached to an end effector. To create a relative depth map of a ...
详细信息
ISBN:
(数字)9798331509231
ISBN:
(纸本)9798331509248
This study presents a method for constructing metric depth maps based on relative depth maps for a 4-DOF manipulator with a single RGB camera, which is attached to an end effector. To create a relative depth map of a scene, we utilize the Depth Anything V2 model along with a system of twelve ArUco markers positioned at varying distances from one another. Unlike traditional methods for determining distances to objects using ArUco markers, the proposed approach does not require a continuous presence of markers within a camera's field of view; it only necessitates measuring a distance to a few markers in an initial frame. The proposed method enables the robot to perform object localization using a relative depth map concurrently with an object search process.
The main purpose of the article is to develop an effective algorithm for solving applied problems of global optimization of multidimensional unimodal and multimodal functions. Such functions are encountered in issues ...
详细信息
ISBN:
(数字)9798350349818
ISBN:
(纸本)9798350349825
The main purpose of the article is to develop an effective algorithm for solving applied problems of global optimization of multidimensional unimodal and multimodal functions. Such functions are encountered in issues of engineering design, image processing and computer vision, energy and energy management, data analysis and machine learning, robotics. To achieve this goal, the article proposes a computational model of the collective behavior of a group of animals and an effective algorithm for differential vector movement. The algorithm was experimentally tested on known multidimensional unimodal and multimodal functions. The results were compared with competing algorithms. The obtained results using Wilcoxon rank-sum test for independent samples showed that the results of the algorithm are statistically significant.
暂无评论