Digital Machine Research Articles

Enhancing Financial Inclusion and Regulatory Challenges: A Critical Analysis of Digital Banks and Alternative Lenders Through Digital Platforms, Machine Learning, and Large Language Models Integration

Enhancing Financial Inclusion and Regulatory Challenges: A Critical Analysis of Digital Banks and Alternative Lenders Through Digital Platforms, Machine Learning, and Large Language Models Integration

Development and application of building intercom products

The article mainly describes the development of building intercom products and the overview of current products. It elaborates on the popularization of economical and practical network cable products, as well as the advantages and disadvantages of face brushing and door opening in terms of cost, performance, and construction. It is believed that network cable products still belong to the category of analogue intercom products. The clever combination of digital doorstep machines that support mobile WeChat mini programs and network cable products has led the use of building intercom into a new field.

A Framework for Monitoring Stability of Tailings Dams in Realtime Using Digital Twin Simulation and Machine Learning

Tailings dam failures cause catastrophic impact on the environment and surrounding communities. Incidences of failure in the recent past have caused industrialists and researchers to seek innovative ways for proactively managing their safety and disaster mitigation. Given Industry 4.0 technologies now available, researchers are looking to develop digital tools for cost-effective, realtime monitoring of tailings dams. However, published literature indicates that a reliable framework is still lacking. This paper proposes a framework for developing a data-driven system for monitoring tailings dam stability and early warning detection. The framework relies upon digital twin simulation and machine-learning (ML) techniques, and comprises four main components: realtime data collection, digital twin modelling, ML-based early detection and prediction, and intelligence-driven decision-support. Sensors gather real-time geophysical data from monitored structure, and the digital twin uses this data to simulate dam behaviour. ML algorithms analyse the data and simulations to enable early detection of instability and failure prediction. Literature suggests that digital twin and ML-based approaches may have advantages over traditional monitoring techniques and other AI-based methods. The paper concludes with a discussion of the framework's limitations, opportunities for improvement, and potential for application in mining and geotechnical engineering. The paper serves as a basis for model development and future research.

Transcriptome analysis reveals the pathogenesis of spontaneous tibial dyschondroplasia in broilers.

Tibial dyschondroplasia (TD) is a severe bone disease that affects fast-growing broiler chickens and causes economic loss. Despite previous studies, the regulatory mechanism of TD remains unclear and is thought to be primarily based on thiram induction, which may differ from that of naturally occurring diseases. To better understand TD, a digital X-ray machine was used in the present study to determine its incidence in four hundred yellow-feathered broiler chickens. The results showed that the incidence of TD was 22% after 6weeks and gradually decreased after 8 and 10weeks. The body weight of broilers with TD decreased significantly compared to that of NTD broilers. In addition, the length and density of the tibia were reduced after eight and 10weeks, and the density of the tibia was reduced after 6weeks compared with the NTD chickens. This study also examined tibial quality parameters from TD (n = 12) and NTD broilers (n = 12) and found that bone mineral content, bone mineral density, bone ash content, calcium content, and phosphorus content were significantly reduced in TD broilers. Transcriptome analysis revealed 849 differentially expressed genes (DEGs) in the growth plate between TD (n = 6) and NTD groups (n = 6). These genes were enriched in ECM-receptor interaction, cytokine-cytokine receptor interaction, calcium signaling pathway, and TGF-β signaling. Genes encoding the alpha chain of type XII collagen, that is, COL1A1, COL5A1, and COL8A1) were identified as critical in the regulatory network of TD. Gene set enrichment analysis (GSEA) revealed that the pathways of cartilage development, circulatory system development, and nervous system development were changed in the growth plates of TD birds. In the blood transcriptome, 12 DEGs were found in TD (n = 4) and NTD chickens (n = 4), and GSEA revealed that the pathways from TD broilers' blood related to the phagosome, linoleic acid metabolism, monoatomic ion homeostasis, and calcium ion transport were downregulated. This study provides a comprehensive understanding of TD, including its effects on tibial quality, tibial changes, and the circulatory system, along with identifying important genes that may lead to the development of TD.

Inclusive Production Capacity Building for MSMEs: Designing Open Source Machine Tools and the OLSK approach

By creating opportunities for formal employment and absorbing significant portions of the global workforce, micro, small and medium enterprises (MSMEs) can be potent catalysts for sustainable and inclusive economic growth while making supply chains more resilient. However, acquiring the digital fabrication machine tools necessary for manufacturing, primarily produced in a few industrialized nations, presents a significant financial challenge for many MSMEs in developing countries. Open source machine tools, where designers freely share machine designs online, challenge traditional intellectual property models, but they suffer from scattered and poorly documented designs. This paper introduces the Open Lab Starter Kit (OLSK) approach, aiming to design, develop, and document crucial open source machine tools (OSMT) commonly needed to establish fab labs. The OLSK follows open source principles, reducing costs and barriers by enabling local replication using local resources. This strategy aims to democratize access to OSMT, foster innovation in resource-constrained regions and contribute to the broader landscape of open source hardware and its transformative potential. The benefits of the OLSK for MSMEs are discussed, challenges are highlighted. Based on this, some solutions for the application of the OLSK approach to digital fabrication in MSMEs are derived which aim to increase its accessibility and sustainability.

Ethical Reflections on the Application of Artificial Intelligence in the Construction of Smart Cities

With the increasing reliance and demand for artificial intelligence in the construction of smart cities, AI has been embedded in various applications and infrastructures. However, uncertainties, concerns, and even fears about AI are constantly emerging. This study based on actor‐network theory (ANT) showcases the application practices of artificial intelligence in smart city, including smart transportation, smart water management, smart healthcare, smart grids, and smart city evaluation standards, and analyzes the process of constructing an actor‐network involving governments, technology development companies, and urban residents. It demonstrates the interactive network processes such as problem statement, interest alignment, recruitment, and mobilization. It explores the relationships among humans, humans and technology, and the self‐challenges faced by technology, such as digital ethics, machine ethics, and relational alienation. In the future, it is necessary to establish explainable, transparent, safe, and responsible AI in the development of smart cities, grant certain rights, and respect to nonhuman actors such as data, AI, and machines, and formulate a series of laws and ethical guidelines to ensure the sustainable development of smart city.

Development of an Intelligent Oil Field Management System based on Digital Twin and Machine Learning

This article introduces an innovative approach to oil field management using digital twin technology and machine learning. A detailed experimental setup was designed using oil displacement techniques, equipped with sensors, actuators, flow meters, and solenoid valves. The experiments focused on displacing oil using water, polymer, and oil, from which valuable data was gathered. This data was pivotal in crafting a digital twin model of the oil field. Utilizing the digital twin, ML algorithms were trained to predict oil production rates, detect potential equipment malfunctions, and prevent operational issues. Our findings highlight a notable 10-15% improvement in oil production efficiency, underscoring the transformative potential of merging DT and ML in the petroleum industry.

Effects of diclofenac sodium gel phonophoresis in sports activities induced grade-l ankle sprain

Purpose: the purpose of this study was to evaluate the effect of diclofenac sodium gel phonophoresis in grade -l ankle sprain. Materials & Methods: 54 patients were randomly included in this study and allocated equally into two groups. Group-1 was managed with therapeutic ultrasound (digital ultrasound machine, a product of HMS marketed in India with frequency of 1 MHz and 3MHz) with diclofenac sodium gel and group-2 was managed with therapeutic ultrasound with aquasonic gel. Therapeutic ultrasound with diclofenac sodium gel, marketed under the name of Voltaren, was administered at a frequency of 1MHz, an intensity of 0.8 W/cm2 with continuous mode (1:1) for five times a week for 2 weeks. The patients were examined by using Numeric Pain Rating Scale (NPRS) and Foot and Ankle Disability Index (FADI). They were assessed on the baseline, after 1st week, and after 2nd week of treatment. Results: one way ANOVA test was used to determine the significant difference at the 0.05 level of significance. There was reduction in NPRS and FADI p-value 0.000 after 2nd week of treatment in group-1 and group-2. But on the basis of mean difference score of NPRS and FADI, group-1 was better effective in terms of reduction of pain and improvement of function periodical manner (Table 3). Conclusion: significant dose-dependently relief was observed in NPRS and FADI for pain in disability for each group treated with diclofenac sodium gel compared with aquasonic gel using ultrasound. Acoustic streaming increased these benefits significantly when used after topical application of diclofenac sodium gel, and the dose-dependent effects of diclofenac sodium gel using therapeutic ultrasound.

Should We Wait for Major Frauds to Unveil to Plan an AI Use License?

Should We Wait for Major Frauds to Unveil to Plan an AI Use License?

(Invited) Self-Powered Image Sensors Based on Vertical Van Der Waals 2H/1T' -MoTe2 Homojunctions

Image sensors can convert optical images into electrical images, which play important roles in industrial application fields and emerging applications, including digital cameras, biomedical imaging, and machine visions. [1, 2] Compared to traditional three-dimensional rigid materials, two-dimensional (2D) materials with excellent electrical, optoelectrical, and mechanical properties exhibit great potentials in novel image sensors. This work aims to synthesize large scale van der Waals 1T’/2H MoTe2 homojunctions and fabricate image sensors for self-powered imaging functions. Firstly, a two-step chemical vapor deposition (CVD) method is adopted to synthesize the 1T’/2H MoTe2 homojunctions via tellurization process of molybdenum film. Secondly, the structural design of the self-powered photodetector based on 2H MoTe2 with asymmetric electrodes and the corresponding optoelectrical properties are investigated. [3] Thirdly, an image sensor consisting of a self-powered MoTe2 photodetectors array is constructed and exhibits excellent imaging functions with zero power electrical consumption. This work will open a new route to build image systems based on 2D materials, showing great opportunities in digital image systems with ultralow power consumption and excellent imaging functions. Acknowledgement This work was fully supported by a grant from the National Natural Science Foundation of China (Project No. 52022003).

The use of memristive devices in machine vision systems

The comparison results of processing units with memristive devices versus modern hardware accelerators of artificial neural networks (ANNs) based on traditional electronic components, as presented in the review [1], demonstrate numerous advantages across all major indicators such as throughput, energy efficiency, accuracy, and others. This report analyzes the current state of memristive devices in addressing machine vision issues. Special attention is paid to the concept of [2] neuromorphic machine vision systems (MVS) based on memristive devices. This concept’s distinct feature lies in its fully analog system, commencing from information input to its output. It encompasses sensory and neural components. The sensory part is responsible for gathering visual information and transferring it to the neural segment for processing through the ANN model algorithm. A specific instance for implementing the input channel of the sensor component involves connecting a photodiode (PD) and a memristor in a single circuit. When the circuit is flipped in reverse bias and light falls on the PD, a photocurrent flows through it from the cathode to the anode. Depending on the light intensity and exposure time, this photocurrent alters the resistance of the memristor, thereby converting illumination into resistance. If visual information doesn’t require encoding with memristor resistances, they can be replaced with a load resistance of the same nominal value for all channels. Irrespective of the input channel variant, the signal encoding visual information is fed into the neural part without digitization. Memristors act as synapses as part of the neural part. They can be used to implement synapses in both traditional formal ANN architectures, where input information is multiplied by a pre-programmed weight, and synapses for spiking neural networks, where a memristor exhibits synaptic plasticity mechanisms similar to those in biological neural networks [3]. If the output from the suggested MVS input channel variants is connected to a device that operates on the “integrate and fire” principle, the device can be deemed as not only an input for a structured ANN, but also a presynaptic neuron for a spiking ANN. The neuron’s frequency of spikes will depend on the light intensity; the brighter the light, the higher the frequency of spikes and vice versa. Faster charge accumulation occurs in channels with low resistance. The complete analog machine vision system will function as a spike neural network, without incorporating any analog-to-digital or digital-to-analog converters. Compared to digital machine vision systems, this approach will significantly decrease energy consumption while producing wearable and on-board electronics with distinct tactical and technical features. This design can be tailored to the size of modern matrices of photo and video fixation devices and employed as a hardware accelerator for the ANN models currently used to process images, and it can serve as a foundation for advancing this area.

Agile digital machine development

In mechatronic machine design and development, it is no longer enough to think about machine functionality and integration as machines are increasingly digitalized. Virtual upgrades are being made to manufacturing systems to keep up with the need for faster product cycles, higher quality, and the introduction of Industry 4.0 technologies. The design and development of new mechatronic discrete manufacturing machines (MDMM) should thus include these characteristics in their design. However, most machine builders do not have the capabilities and resources to do virtual engineering (VE) at the required level, which means these machines are made with limitations or sometimes without their virtual counterparts. Reusable VE MDMM modularization allows machine builders to obtain these competencies quickly and with fewer resources. This research proposes developing adaptable digital twins (DT) by modularizing all virtual and physical mechatronic machine aspects. DTs are well-explored in literature, but re-engineering them requires massive resources and is often unviable. We introduce a new DT-based approach that allows machine builders to quickly re-engineer, adapt, and test machines, given its modular confined approach. Although VE on different abstraction levels still must be developed, confined modularization allows hiding the complexity into modules rather than addressing the entire machine simultaneously. Building machines through modularization is thus an investment, as machine builders and other stakeholders will be able to use and reuse them later for other machines, reducing the overall resources that go into the development. The paper shows how to develop adaptable DT machines using Siemens tools related to virtual engineering.

Menakar Digital Customer Service Machine Menggunakan Human Organization Technology Model

This study aims to analyze the factors that influence BNI customers in using digital service machines, namely Digi CS or Digital Customer Service Machine Using the Human Organization Technology (HOT-FIT) Model. This research is a descriptive-quantitative research with 134 respondents as who are customers of BNI Renon Branch using accidental sampling. Data was obtained through an open questionnaire points to measure or obtain opinions or responses from customers regarding the eight variables in this research, namely System Quality, Information Quality, Service Quality, System Use, User Satisfaction, Organization Structure, Environment and Net Benefits. The research results show that technological factors, namely the variables Information Quality, Service Quality, System Quality, have an influence on human factors, namely System Use, User Satisfaction, where these human factors also influence Net Benefits. Apart from that, organizational factors, namely Structure, influence the net Benefit but not the Environment which does not influence the Net Benefit.

Digital image processing applications in agriculture with a machine learning approach

Abstract. Digital image processing involves the manipulation of images by digital means, and its use has been increasing exponentially in recent decades. It is applied in a diverse range of fields including medicine, remote sensing, robotic vision, and audiovisual processing. Image processing technologies are widely used as a proficient tool in the agriculture sector. The combination of digital image processing and machine learning not only provides new insights into crop health and environmental circumstances, but also helps farmers reach timely and precise decisions. Using machine learning methods, this study examines digital image processing applications in agriculture, focusing on plant disease identification, fruit quality evaluation, weed detection, yield mapping, and robotic harvesting, to other issues. In essence, this study integrates existing knowledge at the interface of digital image processing, machine learning, and agriculture, providing insights into a promising and growing topic with significant implications for sustainable and resilient food production.

Ataxia severity classification using enhanced feature selection and ranking optimization through machine learning model

<span>The examination of neurological disorders and the monitoring of ataxic gait are major scientific topics that benefit from digital signal processing techniques and machine learning (ML) technologies. In this research, an ML approach is optimized with the use of Spatio-temporal data obtained from a kinect-sensor to differentiate between normal gait and ataxic. The current ML-based approaches perform very poorly because they cannot build feature-correlation among many gait characteristics. Furthermore, current ML-based techniques generate more false-positive whenever data is imbalanced in nature; especially for performing multi-label classification. This work presents a feature selection and ranking (FSR) based on extreme gradient boost (XGB) for ataxia severity classification. The FSR-XGB introduce an enhanced misclassification minimization error optimization and presents a novel feature selection and ranking to introduce feature importance using new cross-validation mechanism, both of which are aimed at solving the multi-label classification research problems. Results from experiments demonstrate that the presented FSR-XGB approach outperforms other ML-based and deep learning-based approaches.</span>

Buying into healthcare: Why the industry must learn to appeal to consumers to survive and thrive

This paper explores the transformative changes required to address patient needs in innovative and personalised ways. The discussion delves into innovative and personalised solutions, including digital applications, virtual visits, artificial intelligence and machine learning capabilities. The authors emphasise the importance of meeting patients where they are through state-of-the-art digital solutions and propose transforming from a traditional health system to an integrated health platform. The paper includes topics such as the recent surge in digital applications and virtual visits during the COVID-19 pandemic, as well as the potential of artificial intelligence and machine learning in helping consumers better understand and manage their own health.

Additive manufacture of ultrasoft bioinspired metamaterials

The dynamic loading behavior of materials plays a vital role in various engineering applications, such as aerospace protective components, armor, marine infrastructures, and automotive crash safety. The advent of additive manufacturing technologies has enabled the design of metamaterials that exhibit exceptional mechanical performance and artificially engineered properties not found in nature. However, fabricating ideal materials that resist dynamic loading is challenging because of the complexity of dynamic mechanical processes and varying requirements across different applications. In this study, a novel hierarchical design is proposed that combines natural fiber-inspired frameworks with graphene-inspired parent structures. This design aims to produce metamaterials, with characteristics such as reduced dynamic compressive strength, high energy absorption, and programmable dynamic loading, via advanced manufacturing technologies. An additive-manufacturing-oriented digital design approach and machine learning techniques were employed to engineer the dynamic loading performance of graphene-inspired metamaterials using the bonding principles inspired by natural fibers, to facilitate the design of next-generation metamaterial for advanced manufacturing. Experimental results illustrate the significant improvements achieved with our metamaterials compared to their existing counterparts. These improvements include a decrease in dynamic compressive strength of up to 86 %, while maintaining a remarkable 682 % enhancement in energy absorption during dynamic compressions, with a 42 % reduction in the energy decay rate. A compositional design strategy and programmable dynamic compression curve methodology is proposed that enable the tailored optimization of dynamic loading behaviors without modifying the base topology of metamaterials. This research offers a promising pathway for the development of next-generation materials, engineered to withstand dynamic loadings with intelligent and programmable performances suitable for aerospace, defense, and other high-value applications. By leveraging the advantages of natural fiber-inspired structures and graphene-inspired metamaterials, this work contributes to the advancement of materials with tailored resistance to dynamic loading and opens new possibilities for intelligent dynamic loading performance.

Towards investigation of transfer learning framework for Globotruncanita genus and Globotruncana genus microfossils in Genus-Level and Species-Level prediction

The applicability of digital imaging techniques and machine learning models to paleontological datasets is exploring the possibility of predicting microfossils extracted from the rock samples instead of the traditional identifying methodologies under the microscope in a one-by-one way via a domain expert. However, these processes, including labeling, are carried out manually and take a high time-consuming, especially for many quantities and diversity of complex morphological microfossil specimens. In this work, we propose a transfer learning framework based on a custom model CNN (Convolutional Neural Network) and diverse pre-trained deep models (ResNet50, Xception, InceptionV3, VGG6, MobileNet) trained with the millions of images for Globotruncanita genus and Globotruncana genus in genus-level and species-level prediction. The second primary advantage of our framework is able to provide better and more robust decisions for a limited number of microfossil images captured by the low-cost light microscope imaging technology. The comparison of the diverse methods was evaluated with different performance metrics, and the observation of the framework was made to perform high prediction scores reaching up to the outcomes (>99 % accuracy and > 0.99 AUC score for genus-level/>81 % accuracy and > 0.89 AUC score for species-level). As far as we know, this research study is the first attempt to investigate a transfer learning framework to predict the Globotruncanita genus and Globotruncana genus families at the genus-level and species-level microfossils. Overall, it may extend the existing literature on paleontological science and automated/quick classification manner.

Transcranial Doppler Screening of Children with Sickle Cell Disease for a Large, Multinational Interventional Study: Experience from the Phase 3 HOPE-Kids 2 Trial Investigating the Effect of Voxelotor Treatment on Transcranial Doppler Flow Velocity

Introduction: Transcranial Doppler (TCD) ultrasound is an effective screening tool for identifying children with sickle cell disease (SCD) who are at high risk of stroke. Implementing TCD screening, along with appropriate therapies, for the purpose of primary stroke prevention in resource-constrained settings remains challenging. HOPE-KIDS 2 (NCT04218084) is an ongoing, phase 3, multicenter, double-blind, placebo-controlled trial of voxelotor in children with SCD and elevated arterial cerebral blood flow (measured by time-averaged maximum of the mean velocity [TAMMV]). Our aim is to describe the findings from successful implementation of a standardized TCD screening protocol that was conducted in a multinational setting. Methods: The purpose of HOPE-KIDS 2 is to evaluate the effect of voxelotor treatment on reducing the risk of stroke in participants aged 2 to <15 years with SCD who have conditional TAMMV (170 to <200 cm/s) at baseline. Children aged 2 to <15 years with SCD (HbSS/HbSβ 0) were screened after local sonographers were trained and certified on standardized TCD examination protocol, using the same model of Multi-Dop T digital machine (Compumedics DWL, Germany). TCD assessments were sent for central quality review and interpretation by 2 independent reviewers. STOP criteria were used to classify stroke risk: normal, <170 cm/s; conditional, 170 to <200 cm/s; or abnormal, ≥200 cm/s. Patient baseline characteristics, including clinical measurements of markers of anemia and hemolysis, were measured during study screening. The reasons for patient screen failure were summarized. Results: Between Nov 2020 and Feb 2023, 708 participants consented at 29 sites in Nigeria (n=250; 5 sites), Kenya (n=241; 4 sites), Egypt (n=145; 4 sites), Ghana (n=28; 2 sites), the US (n=17; 8 sites), Italy (n=9; 3 sites), Oman (n=9; 1 site), Saudi Arabia (n=8; 1 site), and the UK (n=1; 1 site). Of these patients, 92.1% (652/708) completed TCD screening examinations (mean [SD] age 7.6 [3.24] years; range 2.0-14.0 years; 50.8% male; 23.0% receiving hydroxyurea). Of the patients who completed TCD screening, the mean (SD) TAMMV was 163.0 (31.26) cm/s, and 47.1% (307/652) had conditional TCD at baseline (29.0% low conditional, 18.1% high conditional). The main reason for screen failure was index TAMMV outside of conditional range (abnormal, n=39 [6.0%]; normal, n=306 [46.9%]). Elevated TAMMV on screening TCD was more common in younger children (2 to ≤8 years vs >8 to <15 years); patients aged 2-8 years comprised 66.8% and 82.1% of the conditional and abnormal TCD categories, respectively. There were 39 assessments that required adjudication, but only 9 were deemed unreadable. Of all patients screened, 36.2% (236/652) fulfilled eligibility criteria for randomization; the characteristics at screening of these patients are summarized (Table). The mean (SD) Hb level and TAMMV at screening for randomly assigned patients was 7.7 (1.06) g/dL and 182.7 (7.53) cm/s, respectively. Conclusions: Clinical sites for the HOPE-KIDS 2 study successfully implemented a standardized, local TCD screening protocol supported by central quality review. For a large interventional trial aimed at reducing the risk of stroke in children with SCD, African and Middle Eastern sites presented relatively few limitations with respect to participant screening.

Food safety-based evaluation of 3D printed objects

The 3D printing technology involves a digital manufacturing machine that produces three-dimensional objects according to designs created by the user via 3D modelling or computer-aided design/manufacturing (CAD/CAM) software. This work analyzes the processing timeline of the filament (material for 3D printing) from unboxing to the extrusion trough the nozzle. It is an important task to analyze the growth of bacteria on 3D printed surface and in gaps between the layers. By default, 3D printed object is not food safe after longer usage and direct contact with food (even though the food safe filaments were used), but there are solutions for this problem. We tested several methods to prevent or reduce the emerging microbial contamination. These methods are coating with epoxy resin, using antimicrobial and high temperature-resistant filaments. The best results were obtained by epoxy resin coating, where the object was cleanable like any other injection molded plastic object with smooth surface. Very good results have also been obtained by boiling the objects, and it is good to see that nowadays more and more special filaments have food safe certificate and can withstand boiling temperatures too. Using antibacterial filaments reduced bacterial colonies by 80%, which is not a perfect solution.