Search

Large language models (LLMs) are an exciting breakthrough in the rapidly growing field of artificial intelligence (AI), offering unparalleled potential in a variety of application domains such as finance, business, healthcare, cybersecurity, and so on. However, concerns regarding their trustworthiness and ethical implications have become increasingly prominent as these models are considered black-box and continue to progress. This position paper explores the potentiality of LLM from diverse perspectives as well as the associated risk factors with awareness. Towards this, we highlight not only the technical challenges but also the ethical implications and societal impacts associated with LLM deployment emphasizing fairness, transparency, explainability, trust and accountability. We conclude this paper by summarizing potential research scopes with direction. Overall, the purpose of this position paper is to contribute to the ongoing discussion of LLM potentiality and awareness from the perspective of trustworthiness and responsibility in AI. [ABSTRACT FROM AUTHOR]

My Turn is software used to manage several Covid-19 mass vaccination campaigns in California. The objective of this article is to describe the use of My Turn at two points of dispensing in California and comment on process improvements to reduce manual tasks of six identified processes of vaccination–registration, scheduling, administration, documentation, follow-up, and digital vaccine record–and paper. We reviewed publicly available documents of My Turn and patients vaccinated at George R. Moscone Convention Center in San Francisco and Oakland Coliseum Community Vaccination Clinic. For publicly available documents of My Turn, we examined videos of My Turn on YouTube, and documentation from EZIZ, the website for the California Vaccines for Children Program. For patients, we examined publicly available vaccination record cards on Instagram and Google. At the George R. Moscone Convention Center, 329,608 vaccines doses were given. At the Oakland Coliseum Community Vaccination Clinic, more than 500,000 vaccine doses were administered. The use of My Turn can be used to reduce manual tasks and paper for mass vaccinating patients against Covid-19. [ABSTRACT FROM AUTHOR]

This document is a foreword for a special issue of the journal Microsystem Technologies. The special issue features selected papers from the 5th International Conference on Energy Systems, Drives and Automations (ESDA2022) held in Kolkata, India. The conference covered various interdisciplinary areas such as electrical, mechanical, computer, electronics, and medical electronics. The papers included in this special issue have undergone a rigorous review process and were selected by guest editors. The foreword expresses the hope that readers will find the papers informative. [Extracted from the article]

In this paper, we propose that paper circuitry provides a productive space for exploring aspects of computational thinking, an increasingly critical 21st century skills for all students. We argue that the creation and operation of paper circuits involve learning about computational concepts such as rule-based constraints, operations, and defined states. Moreover, paper circuitry materials are low cost, provide a low threshold to entry, and draw upon the familiarity that already exists with respect to paper as a hands-on and interactive medium. Paper circuitry thus provides multiple points of entry for students who are unfamiliar with computational thinking ideas while also supporting creative, artistic and crafting activities. It also provides an important alternative to the typically steep learning curve associated with learning a programming language. We define paper circuitry and associated technologies, show how they afford key dimensions of computational thinking, and present examples of paper circuit projects created by students. [ABSTRACT FROM AUTHOR]

In a recent article, Madelaine Ley evaluates the future of work, specifically robotised workplaces, via the lens of care ethics. Like many proponents of care ethics, Ley draws on the approach and its emphasis on relationality to understand ethical action necessary for worker wellbeing. Her paper aims to fill a research gap by shifting away from the traditional contexts in which care ethics is employed, i.e., health and care contexts and instead appropriates the approach to tackle the sociotechnicity of robotics and how caring should be integrated into non-traditional contexts. This paper comments on that of Ley’s, making the case that the author does, in fact, achieve this end while still leaving areas of potential future research open to buttressing the approach she presents. [ABSTRACT FROM AUTHOR]

This paper presents the work that has gone into optimizing drilling performances on a laboratory-scale drilling rig, capable of drilling through rock samples in possible shortest time with preventing damages to devices for the sake of drilling costs and safety. The rig is fully functional, and we conducted successful experiments in both manual and autonomous modes. In this study, we focus on testings on drilling optimizations, failures, advancements of understanding of operational limits, and implementations of these boundaries to create a well-designed and controlled drilling rig. Case studies show that good results have been achieved in terms of optimizing drilling parameters and receiving the possible highest drilling speed when drilling different formations. [ABSTRACT FROM AUTHOR]

This review paper provides a literature survey of collaborative robots, or cobots, and their use in various industries. Cobots have gained popularity due to their ability to work with humans in a safe manner. The paper covers different aspects of cobots, including their design, control strategies, safety features, and human–robot interaction. The paper starts with a brief history and evolution of cobots, followed by a review of different control strategies and Safety features such as collision detection and avoidance, and safety-rated sensors are also examined. Further to this, a systematic review of Ergonomics is also taken into account. Additionally, the paper explores the challenges and opportunities presented by cobot's technology, including the need for standards and regulations, the impact on employment, and the potential benefits to industry. The latest research in human–robot interaction is also discussed. Finally, the paper highlights current limitations of cobot's technology and the need for further research to address technical and ethical challenges. This synthesis document is an invaluable resource for both academics and professionals interested while developing and application of cobot's technology. [ABSTRACT FROM AUTHOR]

Integrating artificial intelligence (AI) systems into administrative procedures can revolutionize the way processes are conducted and fundamentally change established forms of action and organization in administrative law. However, implementing AI in administrative procedures requires a comprehensive evaluation of the capabilities and limitations of different systems, including considerations of transparency and data availability. Data are a crucial factor in the operation of AI systems and the validity of their predictions. It is essential to ensure that the data used to train AI algorithms are extensive, representative, and free of bias. Transparency is also an important aspect establishing trust and reliability in AI systems, particularly regarding the potential for transparent representation in rule-based and machine-learning AI systems. This paper examines the potential and challenges that arise from integrating AI into administrative procedures. In addition, the paper offers a nuanced perspective on current developments in artificial intelligence and provides a conceptual framework for its potential applications in administrative procedures. Beyond this, the paper highlights essential framework conditions that require continuous monitoring to ensure optimal results in practice. [ABSTRACT FROM AUTHOR]

This paper examines the evolution of unemployment in a task-based model that allows for two types of technical change. One is automation, which turns labor tasks into mechanized ones. The second is addition of new labor tasks, which increases specialization, as in the expanding variety literature. The paper shows that in equilibrium the unemployment caused by automation converges to zero over time. [ABSTRACT FROM AUTHOR]

Mobile bed to move patients in hospitals is a critical aspect in a healthcare system. Typical hospital beds often require significant manpower and impose physical stresses on caregivers. This paper explores potential solutions to improve hospital bed mobility, focusing on the integration of robotic technologies. Existing literatures on the subject are reviewed, including studies on hospital bed design structures, ergonomic considerations, and implementations of robotics. Different types of wheels suitable for robot movements are discussed, covering conventional wheels, omniwheels, mecanum wheels, swerve drives, and powered fifth wheels. Each wheel type is described and its advantages and disadvantages are highlighted. The comparison of these wheel types helps identify the most suitable option for modifying hospital beds while maintaining their maneuverability. Furthermore, the paper draws inspiration from many applications of mobile robots in other industries, such as automated guided vehicles (AGVs) and autonomous mobile robots (AMRs), to explore potential innovations for the healthcare. By leveraging robotic technologies, hospitals can enhance efficiency and alleviate the burden on healthcare workers. [ABSTRACT FROM AUTHOR]

There is broad consensus that audio description (AD) is a modality of intersemiotic translation, but there are different views in relation to how AD can be more precisely conceptualised. While Benecke (Audiodeskription als partielle Translation. Modell und Methode, LIT, Berlin, 2014) characterises AD as 'partial translation', Braun (T 28: 302–313, 2016) hypothesises that what audio describers appear to 'omit' from their descriptions can normally be inferred by the audience, drawing on narrative cues from dialogue, mise-en-scène, kinesis, music or sound effects. The study reported in this paper tested this hypothesis using a corpus of material created during the H2020 MeMAD project. The MeMAD project aimed to improve access to audiovisual (AV) content through a combination of human and computer-based methods of description. One of the MeMAD workstreams addressed human approaches to describing visually salient cues. This included an analysis of the potential impact of omissions in AD, which is the focus of this paper. Using a corpus of approximately 500 audio described film extracts we identified the visual elements that can be considered essential for the construction of the filmic narrative and then performed a qualitative analysis of the corresponding audio descriptions to determine how these elements are verbally represented and whether any omitted elements could be inferred from other cues that are accessible to visually impaired audiences. We then identified the most likely source of these inferences and the conditions upon which retrieval could be predicated, preparing the ground for future reception studies to test our hypotheses with target audiences. In this paper, we discuss the methodology used to determine where omissions occur in the analysed audio descriptions, consider worked examples from the MeMAD500 film corpus, and outline the findings of our study namely that various strategies are relevant to inferring omitted information, including the use of proximal and distal contextual cues, and reliance on the application of common knowledge and iconic scenarios. To conclude, consideration is given to overcoming significant omissions in human-generated AD, such as using extended AD formats, and mitigating similar gaps in machine-generated descriptions, where incorporating dialogue analysis and other supplementary data into the computer model could resolve many omissions. [ABSTRACT FROM AUTHOR]

The digital twin (DT) technology is currently considered a key technology for the digital representation of real-world systems. The application of DT technology in smart manufacturing can provide accurate model support for the analysis of mechatronic equipment applications based on model simulations. However, for such a mechanics-electric-hydraulic-control coupled complex system of mechatronics equipment, how to quickly and effectively construct its consistent multi-domain DT mechanism model has become the biggest obstacle to the wide application of DT technology in this field. Therefore, based on the synthesis of existing model construction methods for mechatronics equipment, this paper proposes multi-domain, multi-level, parametric, and consistent mechatronics equipment DT mechanism model construction guidelines. Based on the proposed model construction guidelines, a DT mechanism model construction process for mechatronics equipment is given. Finally, a consistent multi-domain DT mechanism model of computer numerical control machine tools (CNCMT) is constructed by Simscape, to verify the feasibility of the proposed method. The solutions in this paper provide a reliable, rapid, and consistent mechanism model along with construction guidelines and theoretical systems for engineers or researchers that use DT technology to solve specific application problems. Also, the implementation of the virtual commissioning application case in this paper provides application guidance for service analysis based on the DT model. [ABSTRACT FROM AUTHOR]

The publication presents an introductory paper to the Special issue of the international journal Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications of the Russian Academy of Sciences. The main scientific results of the 8th International Workshop "Image Mining: Theory and Applications," held on August 21, 2022, Montreal, Canada, are presented. Historical information is given on this series of international workshops, and their significant role in the development of the theory and practice of automation of image analysis, pattern recognition, and artificial intelligence is emphasized. The list of papers of the Special issue of PRIA, prepared based on the invited and regular papers selected and recommended for publication by the Program Committee of the IMTA-VIII-2022, is presented. [ABSTRACT FROM AUTHOR]

Some economists now predict that technology will eliminate many millions of jobs and lead to a future without work. Much debate focuses on the accuracy of such a prediction—whether, or at what rate, jobs will disappear. But there is a wider question raised by this prediction, namely the merits or otherwise of automating work. Beyond estimating future job losses via automation, there is the normative issue of whether the quality of life would be enhanced in a world where machines replace humans in work. Economics makes particular assumptions about the value of work and the nature of well-being that can address this normative issue. But a deeper enquiry into the scope for living well in a possible automated future requires us to think beyond the limits of standard economic theory and to engage in matters of relevance to business ethicists. This paper shows how automation raises crucial concerns about work—its meaning and contribution to well-being—and how the ability to envisage a better future of work depends on bridging the gap between economics and business ethics. Overall, the paper aims to further understanding of automation as a possible mechanism to raise well-being within work and beyond it. [ABSTRACT FROM AUTHOR]

In this paper, the seismic performance and reliability of steel buildings with Chevron-Braced frames are studied integrating a novel probabilistic approach and the performance-based seismic design concept. The seismic response of models is extracted using response history analyses with the help the commercial software SAP2000. In this sense, three variables associated with the seismic response of the structure are studied: overall lateral displacement, rotation of connections, and inter-story drift. Those responses are evaluated by exciting the structure with eleven characteristic ground motions of the zone with respect to three performance levels: immediate occupancy, life safety, and collapse prevention. Once the seismic response is extracted for every performance level, the reliability of the models is calculated with respect to inter-story drift as described next. First, considering the seismic response in terms of inter-story drift for every ground motion, the associated histogram is constructed. Then, using 13 Probability Density Functions (PDFs), a Chi-square test is performed to identify the best-fitted PDF associated to the histogram of inter-story drift. Afterwards, with the best-fitted PDF of inter-story drift, the probability of failure and reliability index are extracted considering serviceability limits for every performance level. This represents a unique approach to extract the risk of structures subjected to ground motions associated to different performance levels. In addition to the structural reliability, a study about the cost of the structures with and without Chevron braces is developed, and then, it is documented the best option. Finally, based on the results reported in this paper, it is demonstrated that steel buildings with Chevron-braced frames present a better seismic performance than steel moment resisting frames without any bracing system. In summary, overall lateral drifts are reduced between 40 and 60% when Chevron braces are implemented in comparison to steel moment resisting frames without braces. On the other hand, if Chevron bracing systems are not used, i.e., in steel moment resisting frames, the inter-story drifts are about 300% higher than those of steel structures with Chevron braces. Hence, structural damages can be considerably reduced if Chevron-braced frames are implemented in steel structures that may be excited by characteristic ground motions of the zone where they are located. [ABSTRACT FROM AUTHOR]

Fiber-reinforced polymers are highly demanding composites in aerospace and automotive areas because of their excellent mechanical properties such as stiffness and strength-to-weight ratio. The drilling remains the major machining operation applied to composites to provide high-quality holes for joints between parts. Due to composites plied structure, the drilling is accompanied with unusual form metal cutting defects such as delamination and uncut fibers around the drilled hole. Considering that the tool life of some drills reaches over thousands of holes, the research of composites machinability becomes difficult due to demanded labor intensity in manual inspection of the hole quality. Therefore, this paper develops the research solution for automatic analysis of the hole quality in drilled fiber-reinforced materials. The paper proposes a complex of solutions aimed to speed up the analysis of the hole quality when composites drilling. The solution consists of the developed vacuum table, robot arm with high-speed camera, developed top and bottom lightning systems, and Image Processing algorithms for defect detection from captured images. The paper results show how the developed solution can be used for high routine research activities. The output data, including tested 72 cutting data parameters and full-size tool life test, allowed identifying the operational window for high-speed steel drills and the range of tool life, where drill ensures a certain hole quality. The paper shows the efficiency of the developed research solution can reach 5 s per hole including drilling and full cycle of measurements having measurement error of 1–3%. [ABSTRACT FROM AUTHOR]

The growing uses of algorithm-based decision-making in human resources management have drawn considerable attention from different stakeholders. While prior literature mainly focused on stakeholders directly related to HR decisions (e.g., employees), this paper pertained to a third-party observer perspective and investigated how consumers would respond to companies' adoption of algorithm-based HR decision-making. Through five experimental studies, we showed that the adoption of algorithm-based (vs. human-based) HR decision-making could induce consumers' unfavorable ethicality inferences of the company (study 1); because implementing a calculative and data-driven approach (i.e. algorithm-based) to make employee-related decisions violates the deontological principles of respectful employee treatment (study 2). However, this effect was attenuated when consumers had high (vs. low) power distance beliefs (study 3); the algorithm served as assistance (vs. replacement) for human decisions (study 4); or the adoption was framed as employee-oriented (vs. company-oriented) motivated (study 5). Our findings suggested that consumers are aversive to algorithm-based HR decision-making because it is deontologically problematic regardless of its decision quality (i.e. accuracy). This paper contributes to the extant understanding of stakeholders' responses to algorithm-based HR decision-making and consumers' attitudes toward algorithm users. [ABSTRACT FROM AUTHOR]

Experiments at particle colliders are the primary source of insight into physics at microscopic scales. Searches at these facilities often rely on optimization of analyses targeting specific models of new physics. Increasingly, however, data-driven model-agnostic approaches based on machine learning are also being explored. A major challenge is that such methods can be highly sensitive to the presence of many irrelevant features in the data. This paper presents Boosted Decision Tree (BDT)-based techniques to improve anomaly detection in the presence of many irrelevant features. First, a BDT classifier is shown to be more robust than neural networks for the Classification Without Labels approach to finding resonant excesses assuming independence of resonant and non-resonant observables. Next, a tree-based probability density estimator using copula transformations demonstrates significant stability and improved performance over normalizing flows as irrelevant features are added. The results make a compelling case for further development of tree-based algorithms for more robust resonant anomaly detection in high energy physics. [ABSTRACT FROM AUTHOR]

Process knowledge reuse technology can improve the computer numerical control (CNC) programming efficiency and shorten the production cycle for similar parts. However, current process knowledge reuse methods focus on retrieving similar machining cases based on the machining features or topological structures of a part, which failed to deeply consider the close relationship between the 3D part geometry and CNC machining process, can result in incomplete matches between the reused knowledge and CNC process. It is more obvious for the similar complex surface parts that the most existing reuse methods are hardly to integrate 3D part geometry with CNC machining process. To overcome the problem, a reuse method for similar ruled surface blades is proposed through dual mapping mechanism in this paper, which is based on the 3D solid mapping model and spatial transformation relationship. First of all, a dual mapping mechanism is constructed to transfer process knowledge from the parameter domain to physical domain for similar ruled surface blades. Secondly, the acquired process knowledge of the ruled surface blade is characterized to the process knowledge template by the multi-vector function, followed by its inheritability is analyzed for the process knowledge reuse. Finally, two similar ruled surface blades are machined in an experiment, the machined surfaces of both blades are smooth without obvious pits in no violent vibration machining, furthermore, the surface roughness value is 4.314 µm and 4.933 µm of the two similar blades, which can meet the requirement of semi-fishing, this result indicates the correctness and validity of the process knowledge reuse method presented in this paper. [ABSTRACT FROM AUTHOR]

With the integration of connected devices, artificial intelligence, and heterogeneous networks in IoT-driven cyber-physical systems, our society is evolving as a smart, automated, and connected community. In such dynamic and distributed environments, various operations are carried out considering different contextual factors to support the automation of connected devices and systems. These devices often perform long-lived operations or tasks (referred to as activities) to fulfill larger goals in the connected environment. These activities are usually mutable (change states) and interdependent. They can influence the execution of other activities in the ecosystem, requiring active and real-time monitoring of the entire connected environment. Traditional access control models are designed to take authorization decisions at the time of access request and do not fit well in dynamic and connected environments, which require continuous active checks on dependent and mutable activities. Recently, a vision for activity-centric access control (ACAC) was proposed to enable security modeling and enforcement from the perspective and abstraction of interdependent activities. The proposed ACAC incorporates four decision parameters: Authorizations (A), oBligations (B), Conditions (C), and activity Dependencies (D) for an object agnostic continuous access control in smart systems. In this paper, we take a step further towards maturing ACAC by focusing on the mutability of activities (the ability of changing states of activities), activity dependencies (D) and developing a family of formal mathematically grounded models, referred to as ACAC D . We propose six practically suitable sub-models for ACAC D to support the state transition of a mutable activity incorporating the dependent activities' state-check and state-update procedures. These formal models consider the real-time mutability of activities as a critical factor in resolving active dependencies among various activities in the ecosystem. Activity dependencies can form a chain where it is possible to have dependencies of dependencies. In ACAC, we also consider the chain of dependencies while handling the mutability of an activity. We highlight the challenges (such as multiple dependency paths, race conditions, circular dependencies, and deadlocks) while dealing with a chain of dependencies, and provide solutions to resolve these challenges. We also present a proof of concept implementation of our proposed ACAC D models with performance analysis for a smart farming use case. This paper addresses the formal models' intended behavior while supporting activities' dependencies. Specifically, it focuses on developing and categorizing mathematically grounded activity dependencies into various ACAC sub-models without formal policy specification and analysis of theoretical complexities, which are intentionally kept out of the scope of this work. [ABSTRACT FROM AUTHOR]

Complete area-coverage path planners are essential for robots performing tasks like cleaning, inspection, and surveying. However, they often involve complex calculations, mapping, and determining movement directions, leading to high computational or processing overheads and the risk of deadlocks. This paper proposes an approach for cleaning, i.e., by linear wiping of generic and discontinuous surfaces in hospital settings using inhouse assembled mobile dual-arm (MDA) robotic system. The proposed framework introduces key features: (a) a less resource-intensive approach for MDA positioning and cleaning surface mapping, (b) Modified Glasius Bioinspired Neural Network through use of heuristics (GBNN+H) to optimize surface linear wiping while obstacle avoidance, and traversal across discontinuous surfaces. The advantages of the proposed algorithm are highlighted in simulation with GBNN+H significantly reduces the number of steps and flight time required for complete coverage compared to existing algorithms. The proposed framework is also experimentally demonstrated in a hospital setting, paving the way for improved automation in cleaning and disinfection tasks. Overall, this work presents a generic and versatile, applicable to various surface orientations and complexities. [ABSTRACT FROM AUTHOR]

Object detection is a key technology to realize the blind inspection of industrial products. To improve the automation degree of building deep convolutional neural networks (CNNs) for object detection and further improve the detection accuracy, this paper proposes an improved neural architecture search method using exclusive-OR (XOR)-based channel feature fusion. First, an XOR-based channel fusion module is designed; it can fuse the feature mapping of different scales at the channel level in the case of multibranch access complementarily. Then, an improved cell pruning strategy is proposed to efficiently prune the connections between cells by setting the architecture parameters of the candidate operations to 0 s, which are in the alignment layers of the subsequent cells. The cell pruning strategy can directly search the multibranch CNN models and narrow the neural network architectures' gap between the search stage and the evaluation stage. The experimental results show that the proposed method takes approximately 0.75 GPU days to search the optimal neural network on a dataset including six classes for blind inspection of industrial products, and the mean average precision (mAP) is approximately 99.1% on a test dataset, which is higher than those of state-of-the-art methods, e.g., DenseNAS and CSPDarknet53. [ABSTRACT FROM AUTHOR]

As automating technologies are increasingly integrated into workplaces, one concern is that many of the human workers who remain will be relegated to more dull and less positively impactful work. This paper considers two rival theories of meaningful work that might be used to evaluate particular implementations of automation. The first is achievementism, which says that work that culminates in achievements to workers' credit is especially meaningful; the other is the practice view, which says that work that takes the form of an open-ended practice is especially meaningful. Of the two, the practice view is the better tool for assessing the future of meaningful work, because achievementism is explanatorily inadequate in two ways. Moreover, the practice view can explain why the most meaningful forms of work cannot be automated. A procedure can only be automated as long as the steps are defined, whereas, in such work, which steps to take is indefinitely open to redefinition. This reveals the real threat to meaningful work to be a political-economic one. The relevant ethical questions there have to do with how much creative control workers retain in crafting their own jobs, when those jobs involve meaningful work in collaboration with machines; and how to liberate workers from jobs that do not involve meaningful work, which should be left to machines anyway. [ABSTRACT FROM AUTHOR]

Advances in artificial intelligence (AI) have led to its application in many areas of everyday life. In the context of control engineering, reinforcement learning (RL) represents a particularly promising approach as it is centred around the idea of allowing an agent to freely interact with its environment to find an optimal strategy. One of the challenges professionals face when training and deploying RL agents is that the latter often have to run on dedicated embedded devices. This could be to integrate them into an existing toolchain or to satisfy certain performance criteria like real-time constraints. Conventional RL libraries, however, cannot be easily utilised in conjunction with that kind of hardware. In this paper, we present a framework named LExCI, the Learning and Experiencing Cycle Interface, which bridges this gap and provides end-users with a free and open-source tool for training agents on embedded systems using the open-source library RLlib. Its operability is demonstrated with two state-of-the-art RL-algorithms and a rapid control prototyping system. [ABSTRACT FROM AUTHOR]

Accurate detection of tea buds plays a crucial role in achieving the automation and intelligence required for tea bud picking. Aiming at the problems that the current object detection algorithms have low detection accuracy for tea buds under occlusion scenarios and the model is too large which is not suitable for mobile deployment, this paper proposed an improved model Yolo-GSG based on Yolox for detecting tea buds. A global context mechanism (GC) was integrated into the feature fusion network to fuse global context information which was used to find tea buds in complex backgrounds. The separated and enhancement attention module (SEAM) was added to the detection head to gather information that was beneficial for tea bud classification while suppressing useless information. The α -IoU method was introduced to the post-processing stage to improve missed detection caused by occlusion. The ghost module was introduced to the CSPLayer, considerably reducing the computing and model size. Finally, a tea bud dataset was established for the experiment. The results of the ablation experiment demonstrated that implementing a suitable technique could lead to further enhancements in the model's performance. The proposed model outperformed models proposed in the previous study (SSD, Faster RCNN, Yolov3, Yolov4, Yolov5, Yolov7) as well as those introduced in subsequent research (Yolov8, RT-DETR, Yolov9), it obtained the best performance with a mAP of 92.71%. The floating-point operations and parameters were reduced to 23.437G and 8.782 M, respectively. In summary, this paper offered both theoretical research and technical support, serving as a foundation for intelligent tea bud picking in real-world scenarios. [ABSTRACT FROM AUTHOR]

This paper introduces and underscores the automation of the E-vehicle charging process through optimization between the grid and the vehicle, incorporating real-time constraints in the charging and discharging processes. With the surge in E-vehicle usage and heightened electricity demand, automating the vehicle battery charging process becomes imperative to mitigate its impact on the grid. The research outlined in this paper focuses on automating electric vehicle charging and discharging based on real-time power demand considerations. The automation process, facilitated through a connection to the power grid, is managed by the interconnected network and algorithm-based monitoring of real-time parameters. These parameters include power, voltage, state of charge of the battery, charging cost, grid load demand, distance from the grid to the vehicle and vehicle demand. The actor-critic algorithm serves as a guide for electric vehicle charging automation, aligning with vehicle-specific data such as charging cost, vehicle demand, and grid demand to assess switching responses and enhance result accuracy. Load variations in real and reactive power for different configurations—domestic, industrial, and vehicle connections to the grid—throughout the day are considered using the IEEE 33 standard bus system. Frequency analysis of vehicle charging, grid stability analysis, and evaluation of voltage sag and swell during faulty conditions are conducted with MATLAB and the IEEE 33 standard bus system. The results provide insights into the switching time for the charging process based on algorithmic guidelines, ensuring the process follows the correct trajectory. The study demonstrates that charging time and cost are directly proportional to demand, even in time-varying processes. In the course of this research, an embedded hardware prototype model was developed to implement the proposed concept of E-vehicle charging automation. [ABSTRACT FROM AUTHOR]

Manual parsing of invoices is a tedious, arduous and error-prone task. Due to the academic and business importance of this problem, it has attracted the attention of machine learning enthusiasts. There are several complexities and challenges in the automated parsing of invoices. Some of them include a paucity of useful datasets, eclectic template formats, and poor performance of algorithms in real life scenarios. This problem can be solved by the automatic traversal of the invoices by object detection algorithms such as YOLO, SSD and R-CNN. These state-of-the-art algorithms will be trained to detect various fields or entities present in an invoice. In this paper, a dataset of 315 invoices has been generated using web testing tools. The dataset has been annotated for eight entities: billing address, shipping address, invoice date, invoice number, product name, price, quantity, and total amount. The text boxes detected by the models is converted to machine encoded text, using text extraction methods such as Optical Character Recognition (OCR). Hyperparameter tuning has been performed to improve model accuracy. The models have been evaluated on myriad metrics such as mean Average Precision (mAP), common objects in context (COCO) evaluation metrics and total loss during training and validation. The loss vs iteration graph has been visualized using Tensorboard. A front-end application encapsulates all the functions of the research paper and allows testing of various models. [ABSTRACT FROM AUTHOR]

While previous entrepreneurship research has only seldom drawn on organizational ambidexterity, the analysis of the important contemporary tensions among entrepreneurship, innovation management and strategic management issues may be facilitated by more closely analysing organizational ambidexterity in entrepreneurial settings. In this paper, we follow this thinking and more closely analyse an often applied form of corporate entrepreneurship: automation. Such automation is transferring work that was formerly conducted by humans to machines and may thus result in new tensions between corporate entrepreneurship, innovation management and the management of organizational stakeholders such as employees. The present paper investigates whether increased automation lowers the stability of firms' relationships with their employees. In addition, we expect that this relationship is moderated by organizational ambidexterity, as employees may have perceived ambidexterity as a signal that their firm will not overly invest in exploitation only, but maintain a balance between exploitation and exploration. Drawing on stakeholder theory, previous insights into corporate entrepreneurship and a survey of German Mittelstand firms, our findings show that highly ambidextrous firms are indeed more vulnerable to automation, leading to lower employee relational stability. Our findings thus suggest that in highly ambidextrous firms, novel tensions around automation-related corporate entrepreneurship will be detrimental to the stability of the firm's relations with one of its key stakeholder groups: employees. [ABSTRACT FROM AUTHOR]

Future automation and artificial intelligence technologies are expected to have a major impact on labour markets. There is a lack of analysis which considers the sub-national geographical implications of automation risk posed to employment. In this paper, we identify the proportion of jobs at risk of automation across all Irish towns, using the occupational methodology of Frey and Osborne (2017) and compare these results with those of the task-based methodology of Nedelkoska and Quintini (2018). The job risk of automation varies significantly across towns, and while there is a substantial difference in the magnitude of risk identified by the occupational and task-based approaches, the correlation between them is approximately 95% in our analysis. The proportion of jobs at high risk (> 70% probability of automation) across towns using the occupational based methodology varies from a high of 58% to a low of 25%. In comparison, the proportion of jobs at high risk using the task-based methodology varies from 26 to 11%. Factors such as education levels, age demographics, urban size, and industry structure are important in explaining job risk across towns. Our results have significant implications for local and regional urban policy development in the Irish case. [ABSTRACT FROM AUTHOR]

The paper considers the use of the graphical formalism of event trees when creating prototypes of knowledge bases for intelligent systems. Here, the knowledge is represented in a declarative form as logical rules describing the relationship between external signs of a malfunction, possible causes, and operations for their localization and elimination. The previously developed technology of prototyping the rule-based expert systems, implementing the principles of visual programming and model transformations, is used as a methodological basis. Its application is described in the creation of knowledge bases for aviation diagnostics, including the main models and stages, an example is given. Algorithms and software were developed in the form of a specialized event tree editor and an extension module for Personal Knowledge Base Designer. [ABSTRACT FROM AUTHOR]

Nowadays, there are many different industrial processes in which people spend several hours performing tedious and repetitive tasks. Furthermore, most of these processes involve the manipulation of dangerous materials or machinery, such as the toy manufacturing, where people handle ovens with high temperatures and make weary physical effort for a long period of time during the process. In this work, it is presented an automatic and innovative collaborative robotic system that is able to deal with the demoulding task during the manufacturing process of toy dolls. The intelligent robotic system is composed by an UR10e robot with a RealSense RGB-D camera integrated which detects the pieces in the mould using a developed vision-based algorithm and extracts them by means of a custom gripper located and the end of the robot. We introduce a pipeline to perform the demoulding task of different plastic pieces relying in the use of this intelligent robotic system. Finally, to validate this approach, the automatic method has been successfully implemented in a real toy factory providing a novel approach in this traditional manufacturing process. The paper describes the robotic system performance using different forces and velocities, obtaining a success rate of more than 90% in the experimental results. [ABSTRACT FROM AUTHOR]

The workpiece positioning and defect segmentation are two key steps in the workpiece detection process. This paper has designed a CPU-GPU parallel call algorithm based on real industrial quality inspection conditions to realize the high-speed workpiece defect detection. The algorithm can fully utilize all computing resources of the industrial control computer while simultaneously accomplishing the workpiece positioning and defect segmentation tasks. Moreover, to reduce the workpiece defect detection's scope and improve the defect segmentation algorithm's efficiency, the proposed method uses the workpiece positioning results. As for the positioning task, we have designed the double pyramid method to enhance the positioning speed. When it comes to the defect segmentation task, we have introduced the lightweight network to improve the workpiece segmentation speed. Considering that the current general data sets are of the workpiece local image(s) post cutting, we set up a new data set to reflect the situation in the industrial field. It consists of images taken from real industrial fields that can better verify the whole quality inspection algorithm process, including the positioning and segmentation algorithms. According to our experiment, our algorithm accomplished the positioning and defect segmentation tasks at a speed of 116FPS. Additionally, the segmentation accuracy reached 75.12% Mean IoU. [ABSTRACT FROM AUTHOR]

In this study, the authors describe the development of an automated system for controlling the technological process of obtaining a modifying concrete additive comprising spherical silicon dioxide nanostructures. The paper describes the automation object, outlines system development aims, as well as presenting the main process-specific parameters to be measured, adjusted, signaled, and / or blocked. A list of automation equipment of the field, lower, and upper levels of the automated process control system (APCS) is provided. As well as input signal processing, the automatic polling of sensors and instruments is achieved by employing a distributed system based on Siemens equipment for the collection of data, which interact via Ethernet. The paper considers software requirements for the APCS operation and analyzes its reliability. The maximum safety level of the APCS is SIL 3; the average service life is stated to be 12 years. The developed automated control system for the technological process of obtaining the silica-based modifying additive permits the development of its structure, specifically an increase in the number of measurement points using a 10% input-output margin. In addition, software and data support of the APCS allows the system configuration to be modified, as well as enabling its expansion through an upgrade and the input of new tasks (sets of tasks and algorithms). [ABSTRACT FROM AUTHOR]

There is a broad consensus that information and communication technology (ICT) development contributes to economic growth, but its environmental benefits have not been thoroughly studied. This paper explores the impact and mechanisms of ICT development on manufacturing carbon emissions. We first conducted empirical tests based on panel data from 18 manufacturing sectors in 42 countries from 2000 to 2014. The results show that domestic ICT development reduces manufacturing carbon emissions, but the effect is only significant in sectors with high ICT embedded. Second, technological progress, industrial internal structure upgrading, energy consumption intensification, and low carbonization are the main channels for ICT development and embedding to reduce manufacturing carbon emissions. Third, the carbon emissions from manufacturing, which are deeply embedded by ICT, will decrease as the position of ICT forward GVCs improves, and increase as the position of backward GVCs increases. In addition, ICT development has a more significant impact on reducing carbon emissions in high-tech manufacturing. This paper has enriched research on the environmental benefits of ICT development and has been informative and insightful for countries in formulating industrial development policies and implementing the Paris Agreement. [ABSTRACT FROM AUTHOR]

Modelling that exploits visual elements and information visualisation are important areas that have contributed immensely to understanding and the computerisation advancements in many domains and yet remain unexplored for the benefit of the law and legal practice. This paper investigates the challenge of modelling and expressing structures and processes in legislation and the law by using visual modelling and information visualisation (InfoVis) to assist accessibility of legal knowledge, practice and knowledge formalisation as a basis for legal AI. The paper uses a subset of the well-defined Unified Modelling Language (UML) to visually express the structure and process of the legislation and the law to create visual flow diagrams called lawmaps, which form the basis of further formalisation. A lawmap development methodology is presented and evaluated by creating a set of lawmaps for the practice of conveyancing and the Landlords and Tenants Act 1954 of the United Kingdom. This paper is the first of a new breed of preliminary solutions capable of application across all aspects, from legislation to practice; and capable of accelerating development of legal AI. [ABSTRACT FROM AUTHOR]

Critical (software) systems are all around us. These systems are typically characterised by stringent dependability requirements and demand elevated levels of robustness and fault tolerance. To assure that they function as intended and provide a number of quality guarantees, formal methods and automated verification techniques and tools have been in use in the engineering of such critical systems for many years now. In this introduction to the special issue FMICS-AVoCS on “Formal Methods and Automated Verification of Critical Systems”, we outline a number of recent achievements concerning the use of formal methods and automated verification techniques and tools for the specification and analysis of critical systems from a variety of application domains. These achievements are represented by six selected papers: five were selected from the joint 21st International Workshop on Formal Methods for Industrial Critical Systems and 16th International Workshop on Automated Verification of Critical Systems (FMICS-AVoCS 2016), while one of them was selected after an open call for papers. [ABSTRACT FROM AUTHOR]

Organs-at-risk contouring is time consuming and labour intensive. Automation by deep learning algorithms would decrease the workload of radiotherapists and technicians considerably. However, the variety of metrics used for the evaluation of deep learning algorithms make the results of many papers difficult to interpret and compare. In this paper, a qualitative evaluation is done on five established metrics to assess whether their values correlate with clinical usability. A total of 377 CT volumes with heart delineations were randomly selected for training and evaluation. A deep learning algorithm was used to predict the contours of the heart. A total of 101 CT slices from the validation set with the predicted contours were shown to three experienced radiologists. They examined each slice independently whether they would accept or adjust the prediction and if there were (small) mistakes. For each slice, the scores of this qualitative evaluation were then compared with the Sørensen-Dice coefficient (DC), the Hausdorff distance (HD), pixel-wise accuracy, sensitivity and precision. The statistical analysis of the qualitative evaluation and metrics showed a significant correlation. Of the slices with a DC over 0.96 (N = 20) or a 95% HD under 5 voxels (N = 25), no slices were rejected by the readers. Contours with lower DC or higher HD were seen in both rejected and accepted contours. Qualitative evaluation shows that it is difficult to use common quantification metrics as indicator for use in clinic. We might need to change the reporting of quantitative metrics to better reflect clinical acceptance. [ABSTRACT FROM AUTHOR]

Since the start of industrialization, machine capabilities have increased in such a way that human control of processes has evolved from simple (with mechanization) to cognitive (with computerization), and even emotional (with semi/full automation). The processes have also evolved from simple to complicated, and now complex systems, in the emerging context of Industry 4.0. The objective of the special issue "Human and Industry 4.0" is to benefit from studies and results from current manufacturing projects to highlight clues and good practices to design intelligent manufacturing systems for Industry 4.0, then paying attention to human involvements in order to unsure what it looks like in practice and how to realize these systems, especially when it comes to maintenance and operations. This paper aims to summarize the scientific papers that contributed to the Special Issue "Human and Industry 4.0". [ABSTRACT FROM AUTHOR]

This scientific paper provides a comprehensive overview of the current state of research concerning the application of additive manufacturing (AM) technology, especially the fused filament fabrication (FFF) and fused granular fabrication (FGF) methods, where robotic manipulator systems are applied in fabrication processes. To achieve this, a Systematic Literature Review (SLR) was conducted to identify, select, and evaluate the most relevant research. A total of 63 papers sourced from the most relevant scientific database covering the period from 2019 to December 2023 were thoroughly analyzed and synthesized. The examination, analysis, and assessment of these papers provide insights about the integration of the AM processes with robot manipulator technology, presenting the types of polymers, blends, and polymeric matrix composites that are processed using this advanced technology. This paper highlights and discusses current gaps in this area and proposes future research directions, emphasizing the potential enhancements in flexibility, quality, consistency, productivity, safety, and cost-effectiveness in AM facilitated by robot-assisted systems. [ABSTRACT FROM AUTHOR]

Numerical approaches to computations typically reconstruct the numerators of Feynman diagrams in four dimensions. In doing so, certain rational terms arising from the (D − 4)-dimensional part of the numerator multiplying ultraviolet (UV) poles in dimensional regularisation are not captured and need to be obtained by other means. At one-loop these rational terms of UV origin can be computed from a set of process-independent Feynman rules. Recently, it was shown that this approach can be extended to two loops. In this paper, we show that to all loop orders it is possible to compute rational terms of UV origin through process-independent vertices that are polynomial in masses and momenta. [ABSTRACT FROM AUTHOR]

Background: In the last decade the development of new PSMA-ligand based radiopharmaceuticals for the imaging and therapy of prostate cancer has been a highly active and important area of research. The most promising derivative in terms of interaction with the antigen and clinical properties has been found to be "PSMA-617", and its lutetium-177 radiolabelled version has recently been approved by EU and USA regulatory agencies for therapeutic purposes. For the above reasons, the development of new derivatives of PSMA-617 radiolabelled with fluorine-18 may still be of great interest. This paper proposes the comparison of two different PSMA-617 derivatives functionalized with NODA and RESCA chelators, respectively, radiolabelled via [18F]AlF2+ complexation. Results: The organic synthesis of two PSMA-617 derivatives and their radiolabelling via [18F]AlF2+ complexation resulted to proceed efficiently and successfully. Moreover, stability in solution and in plasma has been evaluated. The whole radiosynthesis procedure has been fully automated, and the final products have been obtained with radiochemical yield and purity potentially suitable for clinical studies. The biodistribution of the two derivatives was performed both in prostate cancer and glioma tumour models. Compared with the reference [18F]F-PSMA-1007 and [18F]F-PSMA-617-RESCA, [18F]F-PSMA-617-NODA derivative showed a higher uptake in both tumors, faster clearance in non-target organs, and lower uptake in salivary glands. Conclusion: PSMA-617 NODA and RESCA derivatives were radiolabelled successfully via [18F]AlF2+ chelation, the former being more stable in solution and human plasma. Moreover, preclinical biodistribution studies showed that [18F]F-PSMA-617-NODA might be of potential interest for clinical applications. [ABSTRACT FROM AUTHOR]

In the food industry, the increasing use of automatic processes in the production line is contributing to the higher probability of finding contaminants inside food packages. Detecting these contaminants before sending the products to market has become a critical necessity. This paper presents a pioneering real-time system for detecting contaminants within food and beverage products by integrating microwave (MW) sensing technology with machine learning (ML) tools. Considering the prevalence of water and oil as primary components in many food and beverage items, the proposed technique is applied to both media. The approach involves a thorough examination of the MW sensing system, from selecting appropriate frequency bands to characterizing the antenna in its near-field region. The process culminates in the collection of scattering parameters to create the datasets, followed by classification using the Support Vector Machine (SVM) learning algorithm. Binary and multiclass classifications are performed on two types of datasets, including those with complex numbers and amplitude data only. High accuracy is achieved for both water-based and oil-based products. [ABSTRACT FROM AUTHOR]

Requirements Engineering (RE) has undergone several transitions over the years, from traditional methods to agile approaches emphasising increased automation. In many software development projects, requirements are expressed in natural language and embedded within large volumes of text documents. At the same time, RE activities aim to define software systems' functionalities and constraints. However, manually executing these tasks is time-consuming and prone to errors. Numerous research efforts have proposed tools and technologies for automating RE activities to address this challenge, which are documented in published works. This review aims to examine empirical evidence on automated RE and analyse its impact on the RE sub-domain and software development. To achieve our goal, we conducted a Systematic Literature Review (SLR) following established guidelines for conducting SLRs. We aimed to identify, aggregate, and analyse papers on automated RE published between 1996 and 2022. We outlined the output of the support tool, the RE phase covered, levels of automation, development approach, and evaluation approaches. We identified 85 papers that discussed automated RE from various perspectives and methodologies. The results of this review demonstrate the significance of automated RE for the software development community, which has the potential to shorten development cycles and reduce associated costs. The support tools primarily assist in generating UML models (44.7%) and other activities such as omission of steps, consistency checking, and requirement validation. The analysis phase of RE is the most widely automated phase, with 49.53% of automated tools developed for this purpose. Natural language processing technologies, particularly POS tagging and Parser, are widely employed in developing these support tools. Controlled experimental methods are the most frequently used (48.2%) for evaluating automated RE tools, while user studies are the least employed evaluation method (8.2%). This paper contributes to the existing body of knowledge by providing an updated overview of the research literature, enabling a better understanding of trends and state-of-the-art practices in automated RE for researchers and practitioners. It also paves the way for future research directions in automated requirements engineering. [ABSTRACT FROM AUTHOR]

This paper explores the consequences of automation for public finance. We find that as the automation rate increases, the government size, measured as the fiscal revenues to output ratio, declines. This is due to the substitution of traditional inputs, which bear the burden of taxes, by the new automatic technology. These results are explained by the effects of automation on labor, where taxation of labor income (including social security contributions) represents the most important source of fiscal revenues in most advanced economies. The paper conducts two additional counterfactual experiments. First, we calculate how individual tax rates should be changed in response to automation in order to maintain constant fiscal revenues from the different sources of taxes. This experiment reveals that this fiscal policy would have significantly detrimental effects on output and labor, and indicates that a comprehensive reform of the current tax mix is necessary to counterbalance the effects of automation on public finance. Second, we calculate the tax rate on capital, without modifying the other tax rates, required to keep constant the size of the government, resulting in a capital income tax rate of around 0.77 for an automation rate of 45 % . [ABSTRACT FROM AUTHOR]

Due to impacts and constant stress, the leading edges of aircraft engine blades often lose their shape, while the other parts of the blade are still functional. This results in unnecessary performance losses. Currently, there is no method for a fast and effective repair process as the initial shape of the blade cannot be restored. This paper presents an automated re-contouring process chain for leading edges without prior material application. Thus, it is a sustainable approach to extend the lifespan until an energy-consuming welding process can be performed. It consists of an in-machine scanning process to obtain information about the worn shape, a subsequent target model generation based on the worn shape, and an automated process planning. The process chain is evaluated using a universal, leading edge workpiece. The results show that the target requirements for shape and smoothness are fulfilled. [ABSTRACT FROM AUTHOR]

Advances in artificial intelligence and robotics stand to change many aspects of our lives, including our values. If trends continue as expected, many industries will undergo automation in the near future, calling into question whether we can still value the sense of identity and security our occupations once provided us with. Likewise, the advent of social robots driven by AI, appears to be shifting the meaning of numerous, long-standing values associated with interpersonal relationships, like friendship. Furthermore, powerful actors' and institutions' increasing reliance on AI to make decisions that may affect how people live their lives may have a significant impact on privacy while also raising issues about algorithmic transparency and human control. In this paper, building and expanding on previous works, we will look at how the deployment of Artificial Intelligence technology may lead to changes in identity, security, and other crucial values (such as friendship, fairness, and privacy). We will discuss what challenges we may face in the process, while critically reflecting on whether such changes may be desirable. Finally, drawing on a series of considerations underlying virtue ethics, we will formulate a set of preliminary suggestions, which—we hope—can be used to more carefully guide the future roll out of AI technologies for human flourishing; that is, for social and moral good. [ABSTRACT FROM AUTHOR]

The verification of model transformations is important for realizing robust model-driven engineering technologies and quality-assured automation. Many approaches for checking properties of model transformations have been proposed. Most of them have focused on the effective and efficient detection of property violations by contract checking. However, there remains the fault localization step between identifying a failing contract for a transformation based on verification feedback and precisely identifying the faulty rules. While there exist fault localization approaches in the model transformation verification literature, these require the creation and maintenance of test cases, which imposes an additional burden on the developer. In this paper, we combine transformation verification based on symbolic execution with spectrum-based fault localization techniques for identifying the faulty rules in DSLTrans model transformations. This fault localization approach operates on the path condition output of symbolic transformation checkers instead of requiring a set of test input models. In particular, we introduce a workflow for running the symbolic execution of a model transformation, evaluating the defined contracts for satisfaction, and computing different measures for tracking the faulty rules. We evaluate the effectiveness of spectrum-based analysis techniques for tracking faulty rules and compare our approach to previous works. We evaluate our technique by introducing known mutations into five model transformations. Our results show that the best spectrum-based analysis techniques allow for effective fault localization, showing an average EXAM score below 0.30 (less than 30% of the transformation needs to be inspected). These techniques are also able to locate the faulty rule in the top-three ranked rules in 70% of all cases. The impact of the model transformation, the type of mutation and the type of contract on the results is discussed. Finally, we also investigate the cases where the technique does not work properly, including discussion of a potential pre-check to estimate the prospects of the technique for a certain transformation. [ABSTRACT FROM AUTHOR]

The investigation into intelligent acceptance systems for distribution automation terminals has spanned over a decade, furnishing indispensable assistance to the power industry. The integration of cutting-edge edge computing technologies into these systems has presented efficacious, low-latency, and energy-efficient remedies. This paper provides a comprehensive review and synthesis of research achievements in the field of intelligent acceptance systems for distribution automation terminals over the past few years. Firstly, this paper introduces the definition, composition, functions, and significance of distribution automation terminals, analyzes the advantages of employing edge computing in this domain, and elaborates on the design and implementation of intelligent acceptance systems based on edge computing technology. Additionally, this paper examines the technical challenges, security, and privacy issues associated with the application of edge computing in intelligent acceptance systems and proposes practical solutions. Finally, this paper summarizes the contributions and significance of this paper and provides an outlook on future research directions. It is evident from the review that the integration of edge computing has effectively alleviated these challenges, but new issues await resolution. [ABSTRACT FROM AUTHOR]

In the blockchain environment, smart contracts are computer programs that run on the blockchain platform. However, the development of smart contracts is a major challenge for developers, since blockchain platforms are still evolving. Owing to the inherited nature of blockchain, developing smart contracts without introducing vulnerabilities is not an easy task, as the deployed code is immutable and can be invoked by anyone with access to the network. Smart contracts have proved to be error-prone in practice due to the complexity of programming. Additionally, non-functional requirements, such as service cost, security, performance, authorization, and authentication, should be well implemented and defined in computer systems. In this paper, we aim to present a systematic literature review to outline in detail different approaches of smart contracts generation. Furthermore, we present a comparison of the existing approaches based on a classification according to automation paradigm and a set of defined criteria. Finally, we discuss the gaps in the literature, as well as identify a set of potential challenges which can significantly strengthen the existing work. The study shows that the examined works focused only on a limited number of specific features, such as authorization, asset control, and security. Additionally, formal verification of smart contracts and data privacy are poorly addressed. [ABSTRACT FROM AUTHOR]

Education is a fundamental right that enriches everyone's life. However, physically challenged people often debar from the general and advanced education system. Audio-Visual Automatic Speech Recognition (AV-ASR) based system is useful to improve the education of physically challenged people by providing hands-free computing. They can communicate to the learning system through AV-ASR. However, it is challenging to trace the lip correctly for visual modality. Thus, this paper addresses the appearance-based visual feature along with the co-occurrence statistical measure for visual speech recognition. Local Binary Pattern-Three Orthogonal Planes (LBP-TOP) and Grey-Level Co-occurrence Matrix (GLCM) is proposed for visual speech information. The experimental results show that the proposed system achieves 76.60 % accuracy for visual speech and 96.00 % accuracy for audio speech recognition. [ABSTRACT FROM AUTHOR]