Usage Scenarios Research Articles

Edge deep learning in computer vision and medical diagnostics: a comprehensive survey

Edge deep learning, a paradigm change reconciling edge computing and deep learning, facilitates real-time decision making attuned to environmental factors through the close integration of computational resources and data sources. Here we provide a comprehensive review of the current state of the art in edge deep learning, focusing on computer vision applications, in particular medical diagnostics. An overview of the foundational principles and technical advantages of edge deep learning is presented, emphasising the capacity of this technology to revolutionise a wide range of domains. Furthermore, we present a novel categorisation of edge hardware platforms based on performance and usage scenarios, facilitating platform selection and operational effectiveness. Following this, we dive into approaches to effectively implement deep neural networks on edge devices, encompassing methods such as lightweight design and model compression. Reviewing practical applications in the fields of computer vision in general and medical diagnostics in particular, we demonstrate the profound impact edge-deployed deep learning models can have in real-life situations. Finally, we provide an analysis of potential future directions and obstacles to the adoption of edge deep learning, with the intention to stimulate further investigations and advancements of intelligent edge deep learning solutions. This survey provides researchers and practitioners with a comprehensive reference shedding light on the critical role deep learning plays in the advancement of edge computing applications.

A General Framework for Comparing Embedding Visualizations Across Class-Label Hierarchies.

Projecting high-dimensional vectors into two dimensions for visualization, known as embedding visualization, facilitates perceptual reasoning and interpretation. Comparing multiple embedding visualizations drives decision-making in many domains, but traditional comparison methods are limited by a reliance on direct point correspondences. This requirement precludes comparisons without point correspondences, such as two different datasets of annotated images, and fails to capture meaningful higher-level relationships among point groups. To address these shortcomings, we propose a general framework for comparing embedding visualizations based on shared class labels rather than individual points. Our approach partitions points into regions corresponding to three key class concepts-confusion, neighborhood, and relative size-to characterize intra- and inter-class relationships. Informed by a preliminary user study, we implemented our framework using perceptual neighborhood graphs to defne these regions and introduced metrics to quantify each concept. We demonstrate the generality of our framework with usage scenarios from machine learning and single-cell biology, highlighting our metrics' ability to draw insightful comparisons across label hierarchies. To assess the effectiveness of our approach, we conducted an evaluation study with fve machine learning researchers and six single-cell biologists using an interactive and scalable prototype built with Python, JavaScript, and Rust. Our metrics enable more structured comparisons through visual guidance and increased participants' confdence in their fndings.

Ferry: Toward Better Understanding of Input/Output Space for Data Wrangling Scripts.

Understanding the input and output of data wrangling scripts is crucial for various tasks like debugging code and onboarding new data. However, existing research on script understanding primarily focuses on revealing the process of data transformations, lacking the ability to analyze the potential scope, i.e., the space of script inputs and outputs. Meanwhile, constructing input/output space during script analysis is challenging, as the wrangling scripts could be semantically complex and diverse, and the association between different data objects is intricate. To facilitate data workers in understanding the input and output space of wrangling scripts, we summarize ten types of constraints to express table space and build a mapping between data transformations and these constraints to guide the construction of the input/output for individual transformations. Then, we propose a constraint generation model for integrating table constraints across multiple transformations. Based on the model, we develop Ferry, an interactive system that extracts and visualizes the data constraints describing the input and output space of data wrangling scripts, thereby enabling users to grasp the high-level semantics of complex scripts and locate the origins of faulty data transformations. Besides, Ferry provides example input and output data to assist users in interpreting the extracted constraints and checking and resolving the conflicts between these constraints and any uploaded dataset. Ferry's effectiveness and usability are evaluated through two usage scenarios and two case studies, including understanding, debugging, and checking both single and multiple scripts, with and without executable data. Furthermore, an illustrative application is presented to demonstrate Ferry's flexibility.

Curio: A Dataflow-Based Framework for Collaborative Urban Visual Analytics.

Over the past decade, several urban visual analytics systems and tools have been proposed to tackle a host of challenges faced by cities, in areas as diverse as transportation, weather, and real estate. Many of these tools have been designed through collaborations with urban experts, aiming to distill intricate urban analysis workflows into interactive visualizations and interfaces. However, the design, implementation, and practical use of these tools still rely on siloed approaches, resulting in bespoke systems that are difficult to reproduce and extend. At the design level, these tools undervalue rich data workflows from urban experts, typically treating them only as data providers and evaluators. At the implementation level, they lack interoperability with other technical frameworks. At the practical use level, they tend to be narrowly focused on specific fields, inadvertently creating barriers to cross-domain collaboration. To address these gaps, we present Curio, a framework for collaborative urban visual analytics. Curio uses a dataflow model with multiple abstraction levels (code, grammar, GUI elements) to facilitate collaboration across the design and implementation of visual analytics components. The framework allows experts to intertwine data preprocessing, management, and visualization stages while tracking the provenance of code and visualizations. In collaboration with urban experts, we evaluate Curio through a diverse set of usage scenarios targeting urban accessibility, urban microclimate, and sunlight access. These scenarios use different types of data and domain methodologies to illustrate Curio's flexibility in tackling pressing societal challenges. Curio is available at urbantk.org/curio.

Scenario-oriented data interoperability: maximising the connection between data and users in collaboration environments

ABSTRACT In large-scale collaborative environments, data interoperability faces challenges due to varying data standards, differences in time and space, and rising demands for data services. Traditional methods focus on integrating resources but often miss the need for interoperability between users and data. This research introduces a new approach to data interoperability, which emphasises scenario-based strategies. We use topic analysis and context fusion to handle industry-specific terminology, making it easier for users to understand cross-speciality data. Our approach includes a concept-extended metamodel to address business logic differences and connect data with user scenarios. We tested our model in a railway company and found it effective and useful based on survey feedback.

Исследование способов диспетчеризации видео на множестве конечных устройств в контексте языка программирования Rust

Abstract. The modern world is actively moving towards digitalization, which requires efficient distribution of video content on a variety of end devices. The problem is that different usage scenarios impose different requirements on security, quality, and latency when transmitting video. The aim of the study is to identify the most suitable protocols for video dispatching in educational and real-world applications using the Rust programming language, known for its security and performance. Protocols such as HTTPS (TCP), BitTorrent, HLS, WebRTC, SRT and DASH have been investigated and analyzed. The results show that HLS and DASH have advantages in adaptive streaming in a changing network environment, while SRT and WebRTC provide low latency and high reliability for applications requiring real-time operation. The practical significance of these findings is confirmed by successful integration into educational systems, which ensures stable work even with a change in workload. Discussion: in the future, it is recommended to explore the combined use of several protocols, such as HLS and SRT, to improve the overall efficiency and reliability of video data transmission, as well as integration with CDN to improve quality and reduce load.

Deconstruction and Empirical Insights into the Key Factors of Elderly Household Product Purchasing Decisions in Anhui Province

Against the backdrop of the accelerated aging process globally and in China, especially the significant increase in the elderly population in Anhui Province, the market for elderly household products presents both opportunities and problems. In this study, 518 elderly people from 16 prefecture-level cities in Anhui Province were sampled. Through methods such as questionnaire surveys and structural equation models, an in-depth analysis was conducted on the impacts of cognitive ability, product characteristics, usage scenarios, and product usability on the purchasing decisions of elderly household products. The results show that cognitive ability, product characteristics, and usage scenarios are significantly positively correlated with purchasing decisions, and product usability plays a crucial mediating role. Moreover, significant differences exist in these factors among elderly people with different demographic characteristics. This study innovatively reveals the internal mechanism of the purchasing decisions of elderly household products in Anhui Province and provides targeted strategies for enterprises and the government.

H-CoFe2O4/Ti3C2Tx/BNC Hybrid Aerogels with Modulation Impedance Matching for Electromagnetic Wave Absorption and Health Monitoring.

Given the limitations of single-function electromagnetic wave-absorbing materials (EWAMs) in meeting the evolving demands of complex usage scenarios, there is a growing need for structure-function integrated composites that offer a combination of microwave absorption, human monitoring, and thermal insulation. This study successfully synthesized two-dimensional (2D) Ti3C2Tx MXene via selective etching of Al from the Ti3AlC2 MAX phase. By introducing MXene into a composite of hydroxylated CoFe2O4 nanoparticles (h-CFO NPs) and bacterial nanocellulose (BNC) to modulate the electromagnetic performance of the EWAMs. The optimized electromagnetic parameters and three-dimensional (3D) porous structure achieve enhanced impedance matching of the wave absorber. The h-CFO/BNC/MXene (h-CFO@CM73) hybrid aerogel demonstrates superior electromagnetic wave absorption (EMWA) performance due to the synergistic effects of conductive loss, magnetic loss, interfacial polarization, and dipole polarization, where a minimum reflection loss (RLmin) of -32.66 dB at a thickness of 4.5 mm, an effective absorption bandwidth (EAB) of 10.70 GHz within the test range, and an EMWA efficiency reaching up to 99.92% were realized. Moreover, the hybrid aerogel presents sensitive sensing capabilities, detecting human joint movements, breathing, and vocalizations. Additionally, the developed hybrid aerogels exhibit commendable thermal insulation and infrared camouflage properties. Consequently, the fabricated multifunctional hybrid aerogel has excellent potential for monitoring care of infants, children, and pregnant women.

Network Long-Term Evolution Quality of Service Assessment Using a Weighted Fuzzy Inference System

The United Nations has pushed for improved mobile connectivity, ensuring that 97% of the world’s population lives within reach of a mobile cellular signal. This is within the framework of objective nine regarding industry, innovation, and infrastructure for sustainable development. The next challenge is for users to know the quality of this service. The Long-Term Evolution (LTE) network’s quality of service (QoS) is evaluated with key performance indicators (KPI) that only specialists can interpret. This work aims to assess the QoS and effectiveness of the fourth-generation (4G) LTE network using a weighted fuzzy inference system. Analytic Hierarchy Process (AHP) is integrated to rank the fuzzy rules. The KPIs that are considered for the evaluation are download speed, upload speed, latency, jitter, packet loss rate, reference received signal power (RSRP), and reference received signal quality (RSRQ). The evaluated data were collected collaboratively with end-user equipment (UEs). Different usage scenarios are contemplated to define the importance according to the positive impact of the QoS of the LTE mobile network. The advantage of the weighted fuzzy inference system concerning the fuzzy inference system is that each KPI is assigned a different weight, which implies having rules with hierarchies. In this way, the weighted fuzzy inference system provides two indices of quality and effectiveness. It can be a valuable tool for end users and regulatory bodies to identify the quality of the LTE mobile network.

Evaluating Testing and Use of Photometric Stereo Applications for Riblet Inspection

Computer vision is vital for various applications like object tracking for autonomous driving or quality assurance. Hence, assuring that computer vision fulfills given quality criteria is essential and requires sufficient testing. In previous work, authors introduced a testing method relying on image modifications for a photometric stereo application. Image modifications include pixel errors or the rotation of images to be analyzed, revealing a substantial impact on the computed outcome of the photometric stereo application, depending on the applied modification. This paper focuses on two questions, i.e., (i) whether we can reproduce the impact of image modifications in a real-world setup and (ii) on the practicability of the application of photometric stereo in the application context of quality assurance of riblet surfaces. To answer the first question, we compare the impact of the rotation and light conditions of the analyzed sample with the rotation and light modification applied to the image of the sample. The comparison indicates a similar effect when using rotation and light modifications, showing that testing based on image modifications is valuable for verifying computer vision applications. For the second question, we outline a usage scenario, present experimental observations, and discuss a stochastical model, allowing us to confirm the experiments. Moreover, we outline what to expect when using the computer vision application for real quality assurance.

Measurement of Acoustic Parameters of the Multipurpose Alev Alatlı Conference Hall

Multi-purpose halls are used for a wide range of activities, from conferences to concerts, theatre performances to sporting events. The acoustic performance of such halls can vary greatly depending on the type of event, temperature variations and occupancy of the hall. Therefore, determining the acoustic characteristics of a multi-purpose hall is critical to ensure that the venue can provide the best acoustic performance in every usage scenario. A measurement survey is conducted in a multipurpose conference hall through 2 different stimuli and in 2 different temperatures. The response of the hall is recorded at 10 receiver locations using omnidirectional microphones and a dummy head. The reverberation time, early decay time, bass ratio, centre time, clarity, definition, rapid speech transmission index, and inter aural cross correlation are extracted from the raw data. The results are compared to the relevant standards and the literature to evaluate the acoustic performance.

Personalized zero‐watermark algorithm based on non‐uniform weighted reconstruction and WGAN

AbstractThe image protection of non‐fungible tokens based on zero‐watermark methods has received widespread attention. However, on the one hand, existing zero‐watermark methods are often limited to complex texture changes in the host image, and the features for constructing the zero‐watermark are vulnerable to geometric attacks. On the other hand, a single watermark image cannot adapt to the diverse usage scenarios of non‐fungible tokens. This paper proposes a robust personalized zero‐watermark scheme to address the challenges above. Firstly, the image regions suitable for constructing zero‐watermarks are highlighted by the non‐uniform weighted reconstruction, and the U‐Net is introduced for feature extraction against the geometric attacks. At the same time, the watermark images generated by generative models that are suitable for the usage scenario have achieved zero‐watermark addition and protection for non‐fungible token image content. The proposed method has been experimentally verified to have a certain degree of robustness in geometric and non‐geometric attacks.

AI-enabled thermal monitoring of commercial (PHEV) Li-ion pouch cells with Feature-Adapted Unsupervised Anomaly Detection

Distributed temperature profiling of lithium-ion batteries provides valuable insights, aiding thermal management and minimising risk of battery failures. Highlighted by Batteries Europe as crucial for battery safety, advances in thermal monitoring are imperative to continuous safe adoption of battery technology. Deep Learning techniques have recently emerged as powerful tools for anomaly detection (AD) in many thermal mapping applications. These data-driven methods can handle common challenges like data unavailability or environment variations. Our study devises a methodology to leverage Deep Learning with thermal data from commercially available pouch cells and an infrared camera. We explain the building blocks of FAUAD (Feature-Adapted Unsupervised Anomaly Detection), which models the normality of the input data and synthesizes anomalies in its feature space. The resulting model is benchmarked against some of the latest state-of-the-art methods and achieves high anomaly detection capability; Area Under the ROC Curve (AUROC) score of 0.971 on simulated data, 0.990 on contaminated real data, and a perfect score of 1.0 on real clean data. While maintaining a compact size of 15 MB. FAUAD offers a notable advancement in unsupervised anomaly detection for battery thermal monitoring. The proposed method is cell chemistry agnostic and open to usage scenarios beyond this works’ scope.

KGScope: Interactive Visual Exploration of Knowledge Graphs With Embedding-Based Guidance.

Knowledge graphs have been commonly used to represent relationships between entities and are utilized in the industry to enhance service qualities. As knowledge graphs integrate data from a variety of sources, they can also be useful references for data analysts. However, there is a lack of effective tools to make the most of the rich information in knowledge graphs. Existing knowledge graph exploration systems are ineffective because they did not consider various user needs and characteristics of knowledge graphs. Exploratory approaches specifically designed to uncover and summarize insights in knowledge graphs have not been well studied yet. In this article, we propose KGScope that supports interactive visual explorations and provides embedding-based guidance to derive insights from knowledge graphs. We demonstrate KGScope with usage scenarios and assess its efficacy in supporting the exploration of knowledge graphs with a user study. The results show that KGScope supports knowledge graph exploration effectively by providing useful information and helping explore the entire network.

Hybrid solutions for agricultural vehicles: a comparative life cycle analysis from the users’ standpoint

In recent years, the need to reduce fossil fuel consumption has triggered a push towards alternative solutions for more sustainable vehicles. This trend is stimulated by increasingly stringent regulations aimed at reducing greenhouse gas (GHG) emissions in the transportation sector. However, in agriculture, the adoption of zero-emission vehicles (ZEVs) is not aligned with the trends seen in other sectors due to technological barriers. Currently, only a few prototypal solutions for hybrid tractors have emerged due to their advantages in battery size, weight, and cost compared to fully electric solutions. In the literature, few studies have examined the environmental performance of hybrid electric tractors (HETs), mainly comparing them to conventional models in terms of work performance. Conversely, the user perspective is scarcely addressed although users' needs vary significantly depending on farm dimensions and cultivation types. The study proposes an analysis of the environmental impact of a hybrid solution by comparing it with a diesel engine Stage V and one produced under the Stage IIIb requirements. The novelty of this paper results from combining the life cycle assessment (LCA) outputs with a scenario modelling framework to uncover the potential environmental impact of the three models considering different use scenarios. Such an approach goes beyond traditional LCA analyses by providing more detailed information on the practical environmental implications related to these propulsion units. The results show that depending on the user scenario, the hybrid solution is not always the least pollutant, thus requiring further research in the HET sector to better tailor technical solutions based on the target customer.

Non-Myopic Sensor Scheduling for Linear Systems with Colored Noise

This paper addresses the task of sensor selection over a finite time horizon for systems modeled via discrete-time, linear state-space representations. Our method for this general linear setting accommodates both spatial and temporal noise correlations. To our best knowledge, this is the first work to do so. Scheduling policies are designed to limit sensor usage and minimize a minimum-mean-square-error-based criterion with time-varying weights to accommodate different user scenarios (e.g., prioritizing certain state elements at certain times or performing linear quadratic Gaussian control). The approach is also nonmyopic since the effects of sensor activations on all time steps are incorporated. A new but algebraically equivalent formulation of the scheduling model is introduced that readily accounts for colored noise sequences. This lends a closed-form expression for the error covariance that is explicit in all scheduling variables. Such an expression had been considered intractable for filtering in both white and colored noise regimes. This expression is leveraged to develop a well-motivated surrogate objective function that is shown to be submodular, thus enabling the use of an efficient greedy algorithm accompanied by performance guarantees with respect to the surrogate objective. Numerical examples are provided to demonstrate the effectiveness of the proposed methodology.

Pembuatan Sistem Pencatatan Pinjaman Kelompok Wanita Tani Berbasis Web Menggunakan Metode V-Model

This research focuses on designing a web-based loan recording system for the Jati Mekar Women Farmers Group (KWT) in Sindanglaut Village. KWT Jati Mekar is an organization consisting of women farmers in Sindanglaut Village who have joined together to improve their welfare and productivity through various agricultural and economic activities.The main objective of the research is to develop a system that can increase efficiency and accuracy in recording group members' loans. The methodology used is the V-Model, which allows for structured and systematic system development through stages of requirements analysis, design, implementation, testing, and maintenance.This system is designed to facilitate the process of recording, monitoring, and reporting loans, as well as increasing transparency in the group's financial management. During the development process, blackbox testing was conducted to evaluate the system's functionality without examining the internal code structure. This testing focuses on the system's inputs and outputs, ensuring that each feature functions according to expected specifications.The research results show that the implementation of this web-based system can address problems that often occur in manual recording, such as inaccurate data and difficulties in tracking loan status. Blackbox testing verifies that the system can handle various usage scenarios correctly, including member data management, loan recording, and report generation.

Green building interior design based on digital image processing and thermal environment simulation

With the increasingly severe global climate change and energy crisis, this study aims to explore effective strategies for green building interior design, especially in terms of thermal environment control, through digital image processing and thermal environment simulation. The study simulates indoor scenes based on image processing technology, using methods such as image acquisition, localization, and object detection to improve the accuracy of scene reconstruction, and conducts in-depth analysis of detection effects, laying the foundation for subsequent thermal environment simulations. In the design of the thermal energy environment control system, the calculation of indoor cooling load was studied and compared with existing thermal environment models to determine the impact of user activities on the indoor thermal environment. By establishing a thermal energy environment control model and implementing precise environmental regulation for different usage scenarios, indoor comfort and energy efficiency have been significantly improved. The experimental results show that the use of digital image processing simulation technology can effectively improve the accuracy and flexibility of indoor thermal environment control in green buildings, optimize energy efficiency, emphasize the importance of thermal factors in interior design, and provide theoretical basis and practical guidance for future building design practices.

Optimizing epidermal growth factor receptor-tyrosine kinase inhibitor treatment in lung cancer: a systematic review and meta-analysis of the influence of gastric acid suppressants.

The introduction of epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs) has revolutionized advanced non-small cell lung cancer (NSCLC) treatment. However, their efficacy can be compromised by concurrent use of gastric acid suppressants (GASs), such as proton pump inhibitors (PPIs) and histamine 2 receptor antagonists (H2RAs). This study aimed to update the evidence on the impact of GASs on the overall survival (OS) and progression-free survival (PFS) in patients on EGFR-TKI treatment. A systematic review and meta-analysis were conducted using data from PubMed, Embase, Cochrane Library, Web of Science, Scopus, KoreaMed, and preprint repositories. Data from 13 retrospective studies, involving 10,814 patients, were analyzed. Overall, 34.6% of the patients used GASs, with most being Asian females and non-smokers. Most patients had EGFR-mutated adenocarcinoma, reflecting typical EGFR-TKI usage scenarios. Concurrent use of GASs was significantly associated with reduced OS [hazard ratio (HR) =1.34, 95% confidence interval (CI): 1.26-1.42], and PFS (HR =1.52, 95% CI: 1.25-1.86). In subgroup analysis, PPIs had a more negative impact on OS (HR =1.64, 95% CI: 1.51-1.79) than did H2RAs (HR =1.11, 95% CI: 0.95-1.31). Longer overlap times of GASs correlated with a higher trend in HRs for OS. However, the results for PFS were not significant in both subgroup analyses. Concurrent use of GASs with EGFR-TKIs is linked to poorer OS and PFS in patients with advanced NSCLC. Careful consideration is advised when prescribing GASs, including adjusting administration timing, minimizing overlap duration, or opting for H2RAs over PPIs. Further research is needed to optimize treatment protocols, specifically addressing the duration of overlap time, to improve patient outcomes.

Intelligent Agent and NPC Behavior Modeling: From Traditional Methods to AI Driven Interactive Game Design

In recent years, artificial intelligence (AI) related technologies have been widely applied in the gaming industry, bringing enormous commercial value. Research has shown that non-player characters (NPCs) embedded with AI technology are more intelligent, popular among players, and can make them feel challenged and amused. Major game companies have established their own AI studios to invest energy in designing more intelligent NPCs, making the NPCs deployed in games increasingly superior. However, there is still a lack of comprehensive induction and summary of the behavior modeling design methods for NPCs. Therefore, this article focuses on providing a more comprehensive summary of this field, by searching and comparing relevant examples in existing game and research results of NPC design, summarizing and generalizing different types of methods, then analyzing and comparing the advantages and disadvantages of traditional algorithms and AI algorithms, as well as their usage scenarios, and proposing potential methods for the future in the end.