Visually impaired people encounter several challenges in their mobility and navigation. Their daily activities are obstructed due to their inability to adapt or recognize accurately their surroundings, especially outs...
Visually impaired people encounter several challenges in their mobility and navigation. Their daily activities are obstructed due to their inability to adapt or recognize accurately their surroundings, especially outside their house which they are more familiar with. Thus, it becomes the main reason of accidents, falling off, getting lost in unknown areas, etc. Furthermore, one of the sensory systems that helps the body to process data about the external environment is the visual system. Blind people also lose touch with the outside world, develops poor motor habits, which results in postural problems as a result. This project will assist visually impaired people in their daily life and simplify normal tasks through a system combining two previously designed projects, “Smart Shoes for Blind and Visually Impaired People”, and “Human posture monitoring device”. The multifunctional system is developed with the goal of securing safe movements for visually impaired people as well as maintaining a good back posture by detecting leaning postures (LP). The purpose of the smart shoe is to identify obstacles and protect the user from unintended accidents. A compatible Android application has been developed to alert the user when there is an obstruction or when he is walking on a wet surface. Voice alarms will be used to acoustically alert the user. If the user collapses, a message with their position will be sent right away to a relative. On the other hand, the smart vest will identify the position of the user's back and alert him to maintain a straight posture through the same application as well. As the system is dealing with human health, some safety measurements would be taken into consideration to implement a safe electrical system in order to reduce error and to increase accuracy.
This paper introduces a novel Sliding Mode-Based Observer tailored for a specific subset of nonlinear systems of order $\boldsymbol n$ featuring Lipschitz nonlinearities. The study establishes stability conditions t...
详细信息
ISBN:
(数字)9798331518493
ISBN:
(纸本)9798331518509
This paper introduces a novel Sliding Mode-Based Observer tailored for a specific subset of nonlinear systems of order
$\boldsymbol n$
featuring Lipschitz nonlinearities. The study establishes stability conditions that ensure convergence of the estimation error (s) in finite time until order
$\boldsymbol n$
, thus, providing an accurate state (s) estimation without the necessity for disturbance matching conditions. Furthermore, the study presents an extension of the scope of application of the proposed method to tackle a unique scenario characterized by a time-varying and non-invertible function of the output dynamics of the system model. The effectiveness of the proposed observer is showcased through simulation examples.
As the Metaverse develops, it is becoming more crucial to prioritize the safety of users, especially regarding the potential risks, such as users experiencing dizziness or making incorrect movements that may lead to f...
详细信息
ISBN:
(数字)9798350387445
ISBN:
(纸本)9798350387452
As the Metaverse develops, it is becoming more crucial to prioritize the safety of users, especially regarding the potential risks, such as users experiencing dizziness or making incorrect movements that may lead to falls. With more virtual environments becoming increasingly available and immersive, detecting and preventing falls within the Metaverse is required. Given the constrained resources of wearable sensors, precise fall prediction models are critical to efficiently analyzing data gathered by these devices. Traditional fall detection systems require centralizing data collection, which raises privacy concerns over the collected data. Resource-aware Split Federated Learning (RSFL) enables collaboration among multiple devices within the Metaverse to train a fall detection model, all while preserving individual data privacy. The approach also leverages parallelism in Federated Learning (FL) and Split Learning (SL) by decomposing training tasks between clients and servers. Moreover, we devise an efficient client selection mechanism to ensure timely training and model convergence performance. We implemented our architecture and assessed its performance using a sensory dataset. The evaluation results with the baseline demonstrate our architecture's superiority in terms of convergence time. Our approach mitigates data heterogeneity and privacy concerns, creating secure and efficient fall detection systems for the Metaverse.
The sports betting industry has experienced rapid growth, driven largely by technological advancements and the proliferation of online platforms. Machine learning (ML) has played a pivotal role in the transformation o...
详细信息
In this paper,we elaborate on residual-driven Fuzzy C-Means(FCM)for image segmentation,which is the first approach that realizes accurate residual(noise/outliers)estimation and enables noise-free image to participate ...
详细信息
In this paper,we elaborate on residual-driven Fuzzy C-Means(FCM)for image segmentation,which is the first approach that realizes accurate residual(noise/outliers)estimation and enables noise-free image to participate in *** propose a residual-driven FCM framework by integrating into FCM a residual-related regularization term derived from the distribution characteristic of different types of *** on this framework,a weighted?2-norm regularization term is presented by weighting mixed noise distribution,thus resulting in a universal residual-driven FCM algorithm in presence of mixed or unknown ***,with the constraint of spatial information,the residual estimation becomes more reliable than that only considering an observed image *** experiments on synthetic,medical,and real-world images are *** results demonstrate the superior effectiveness and efficiency of the proposed algorithm over its peers.
The paper presents a combined observer and lateral control design approach for autonomous vehicles. The goal of the observer design is to estimate the front and rear slip angles of the vehicle together with the corner...
详细信息
ISBN:
(数字)9798350316339
ISBN:
(纸本)9798350316346
The paper presents a combined observer and lateral control design approach for autonomous vehicles. The goal of the observer design is to estimate the front and rear slip angles of the vehicle together with the cornering stiffness. The observer is based on the combination of the polytopic LPV approach and the ultra-local model. The ultra-local model is used to update the cornering stiffness and, in this way, improve the performance level of the LPV observer. Then, the resulted observer is exploited during the LPV-based lateral control design. The improved lateral control can adapt to different circumstances such as low adhesion coefficient. The proposed observer and LPV controller is implemented and tested in MATLAB/Simulink environment and using the high-fidelity simulation software, CarMaker.
This paper proposes an energy efficient resource allocation design algorithm for an intelligent reflecting surface (IRS)-assisted downlink ultra-reliable low-latency communication (URLLC) network. This setup features ...
This paper proposes an energy efficient resource allocation design algorithm for an intelligent reflecting surface (IRS)-assisted downlink ultra-reliable low-latency communication (URLLC) network. This setup features a multi-antenna base station (BS) transmitting data traffic to a group of URLLC users with short packet lengths. We maximize the total network's energy efficiency (EE) through the optimization of active beamformers at the BS and passive beamformers (a.k.a, phase shifts) at the IRS. The main non-convex problem is divided into two sub-problems. An alternating optimization (AO) approach is then used to solve the problem. Through the use of the successive convex approximation (SCA) with a novel iterative rank relaxation method, we construct a concave-convex objective function for each sub-problem. The first sub-problem is a fractional program that is solved using the Dinkelbach method and a penalty-based approach. The second sub-problem is then solved based on semi-definite programming (SDP) and the penalty-based approach. The iterative solution gradually approaches the rank-one for both the active beamforming and unit modulus IRS phase-shift sub-problems. Our results demonstrate the efficacy of the proposed solution compared to existing benchmarks.
Depth estimation is one of the crucial tasks for autonomous systems, which provides important information about the distance between the system and its surroundings. Traditionally, Light Detection and Ranging and ster...
详细信息
In this paper we deal with stochastic optimization problems where the data distributions change in response to the decision variables. Traditionally, the study of optimization problems with decision-dependent distribu...
详细信息
In this paper, we focus on distributed learning over peer-to-peer networks. In particular, we address the challenge of expensive communications (which arise when e.g. training neural networks), by proposing a novel lo...
详细信息
ISBN:
(数字)9798350316339
ISBN:
(纸本)9798350316346
In this paper, we focus on distributed learning over peer-to-peer networks. In particular, we address the challenge of expensive communications (which arise when e.g. training neural networks), by proposing a novel local training algorithm, LTADMM. We extend the distributed ADMM enabling the agents to perform multiple local gradient steps per communication round (local training). We present a preliminary convergence analysis of the algorithm under a graph regularity assumption, and show how the use of local training does not compromise the accuracy of the learned model. We compare the algorithm with the state of the art for a classification task, and in different set-ups. The results are very promising showing a great performance of LT-ADMM, and paving the way for future important theoretical developments.
暂无评论