Indoor positioning systems (IPS) are gaining higher attention recently due to the increased demand for indoor location aware services. Visible light communication (VLC) is a promising technology to use for IPS. In par...
详细信息
ISBN:
(数字)9798350303582
ISBN:
(纸本)9798350303599
Indoor positioning systems (IPS) are gaining higher attention recently due to the increased demand for indoor location aware services. Visible light communication (VLC) is a promising technology to use for IPS. In particular, received signal strength (RSS) based visible light positioning (VLP) systems are gaining high attention due to their low complexity and cost, in addition to higher positioning accuracy compared to their radio frequency (RF) counterparts. One of the main challenges in RSS based VLP systems is encountered when the receiver (the target) is tilted and not placed in parallel with the transmitters (the anchors). RSS based trilateration techniques require a computationally expensive and time-consuming process to solve the nonlinear problem of tilted receivers. Fingerprint based systems generally provide high positioning accuracy with short positioning time, and maybe used to circumvent the need to deal with the high complexity associated with tilted receivers. However, the design of a fingerprinting VLP system for tilted receiver has not been explored yet as far as receivers with a single photodetector (PD) are concerned. In this work, a fingerprint based VLP system for tilted receivers using artificial neural networks (ANN) is proposed, where different types of input features for training the positioning algorithm are studied. We show that using the components of the normal vector to the PD's surface in addition to RSS values provides an excellent positioning accuracy with an average positioning error of 25.41 cm and a remarkably low average positioning time less than
$\mathbf{5} \boldsymbol{\mu} \boldsymbol{s}$
. In addition, important research directions for future work are discussed.
Exact solutions of the Routing, Modulation, and Spectrum Allocation (RMSA) problem in Elastic Optical Networks (EONs), so that the number of admitted demands is maximized while those of regenerators and frequency slot...
详细信息
The advent of digital technology has contributed to experiencing liquid lifestyles and flexible work arrangements with different mobility routes and targets. Escaping the exhausting routine of commuting to and from wo...
详细信息
ISBN:
(数字)9798350354423
ISBN:
(纸本)9798350354430
The advent of digital technology has contributed to experiencing liquid lifestyles and flexible work arrangements with different mobility routes and targets. Escaping the exhausting routine of commuting to and from work has been a key driver of digital nomadism, a phenomenon that has become increasingly widespread across the globe and is often centered around cross-border travel and expatriate settlement. Due to their frequent mobility, digital nomads face unique challenges in fostering a sense of place-belongingness compared to most other types of workers. Despite the popularity of digital nomadic work/life in the current public discourse, there is no standardized guidebook for understanding how digital technology already supports or could potentially support the sense of place-belongingness among these voluntary migrants. Motivated by this line of research, in our paper, we propose an initial guide with practical methodological considerations on how to investigate this phenomenon using qualitative and quantitative materials. Such studies can assist strategists and organizations in attracting new talent and fostering more inclusive environments.
Depressive Disorders (DD) is one of the most prevalent mental disorders in the world that may lead to suicide cases. To prevent the latter, ubiquitous early detection systems may be effective. Recent studies have sinc...
Depressive Disorders (DD) is one of the most prevalent mental disorders in the world that may lead to suicide cases. To prevent the latter, ubiquitous early detection systems may be effective. Recent studies have since researched the development of such systems by exploiting several forms of data, including video, audio, Ecological Momentary Assessments (EMA), and passive sensing data using sensors embedded in mobile devices. To summarize the trends, opportunities, and existing challenges in this field, this study reviewed 15 papers to answer four research questions. EMA was the most popular data to be used in this task, but other approaches, such as using video, audio, and typing behaviors, may be considered due to the subjectivity of EMA. These data were typically recorded using smartphones and analyzed using Machine Learning (ML). However, most of the developed systems had yet to be implemented. Overall, it was concluded that further studies may need to explore usages of more objective data in multimodal approaches as well as consider using Mobile Cloud Computing (MCC) to deploy these systems to provide more effective and efficient diagnoses. Future studies must also take into account the existing challenges of the data and infrastructures, such as the weaknesses of several data types, limitations of mobile devices, as well as the challenges of diagnosis approaches.
An e-Commerce company has been using an Enterprise Resource Planning (ERP) system for several years, but is still constrained in its implementation, this is reflected in the number of issue/change request tickets subm...
详细信息
Due to the great advance in machine learning (ML) techniques, numerous ML models are expanding their application domains in recent years. To adapt for resource-constrained platforms such as mobile and Internet of Thin...
Due to the great advance in machine learning (ML) techniques, numerous ML models are expanding their application domains in recent years. To adapt for resource-constrained platforms such as mobile and Internet of Things (IoT) devices, pre-trained models are often processed to enhance their efficiency and compactness, using optimization techniques such as pruning and quantization. Similar to the optimization process in other complex systems, e.g., program compilers and databases, optimizations for ML models can contain bugs, leading to severe consequences such as system crashes and financial loss. While bugs in training, compiling and deployment stages have been extensively studied, there is still a lack of systematic understanding and characterization of model optimization bugs (MOBs). In this work, we conduct the first empirical study to identify and characterize MOBs. We collect a comprehensive dataset containing 371 MOBs from TensorFlow and PyTorch, the most extensively used open-source ML frameworks, covering the entire development time span of their optimizers (May 2019 to August 2022). We then investigate the collected bugs from various perspectives, including their symptoms, root causes, life cycles, detection and fixes. Our work unveils the status quo of MOBs in the wild, and reveals their features on which future detection techniques can be based. Our findings also serve as a warning to the developers and the users of ML frameworks, and an appeal to our research community to enact dedicated countermeasures.
The ability of robots to imitate human learning strategies-rapidly adapting to new tasks without large datasets-has garnered significant attention in meta-learning. Meta-reinforcement learning seeks to enhance robotic...
详细信息
ISBN:
(数字)9798331521554
ISBN:
(纸本)9798331521561
The ability of robots to imitate human learning strategies-rapidly adapting to new tasks without large datasets-has garnered significant attention in meta-learning. Meta-reinforcement learning seeks to enhance robotic agent flexibility across diverse tasks and contexts, offering promise where single-task learning often fails. Despite advancements like multi-task diffusion models and task-weighted optimization mechanisms, effectively training tasks with varying complexities simultaneously remains a major challenge. This paper introduces a novel meta-reinforcement learning method that addresses this issue by clustering the training tasks of robotic arms based on semantic and trajectory similarities, while leveraging adaptive learning rates and task-specific weights proposed by the multitask optimization techniques. Our approach, TEAM, emphasizes performance-driven semantic clustering, optimizing based on robotic task similarity, complexity, and convergence objectives. We also integrate fast adaptive and multi-task optimization of the diffusion model to enhance computational efficiency and adaptability. More specifically, we introduce a cluster-specific optimization technique, using specialized parameters for each group to allow more refined task handling. The experimental validation demonstrates the effectiveness of this scalable method in improving performance, adaptability, and efficiency in real-world, heterogeneous robotic tasks, further advancing robotic computing in meta-reinforcement learning.
In the digital transformation era, Metaverse offers a fusion of virtual reality (VR), augmented reality (AR), and web technologies to create immersive digital experiences. However, the evolution of the Metaverse is sl...
详细信息
While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing a...
详细信息
Multi-channel speech separation has been successfully applied in a complex real-world environment such as the far-field condition. The common solution to deal with the far-field condition is using a multi-channel sign...
详细信息
暂无评论