Conventional Manual Process Research Articles

Sistem Informasi Pengelolaan Program Bantuan Dana Hibah Berbasis Website di Biro Kesejahteraan Rakyat Pemerintah Provinsi Lampung

The study addresses the inefficiencies of managing the Grant Fund Assistance Program in the People's Welfare Bureau of Lampung Province, where conventional manual processes have led to errors, inefficiencies, and data duplication. By developing a web-based Grant Fund Assistance Management Information System using the waterfall methodology, the research provides a structured and modern solution to these issues. The system incorporates a robust database design, leveraging the Model View Controller (MVC) framework to enhance functionality, scalability, and user access management. It adopts a user-friendly interface built with PHP, JavaScript, HTML, and CSS to ensure accessibility for different stakeholders, including administrators and applicants. Comprehensive testing was performed to ensure system reliability and compliance with functional and non-functional requirements, such as security and usability. This innovation is expected to improve administrative efficiency, enhance transparency in fund allocation, and streamline the application process for community and organizational beneficiaries, supporting the goals of good governance and clean governance.

Extendable machine tool wear monitoring process using image segmentation based deep learning model and automatic detection of depth of cut line

Automating the monitoring of machine tools poses a significant challenge, with previous studies relying on machine vision to address this issue, primarily focusing on measuring specific tool wear using custom algorithms. In this study, we introduce an automated tool wear monitoring process capable of assessing wear across various tools. Utilizing deep neural network models for image classification and segmentation, our proposed process effectively masks areas where tool wear occurs. The image classification model selects the best-performing backbone model based on the highest F1 score. To account for varying depths-of-cut lines among different tools in the masked area, we introduce an algorithm that utilizes the Hough transform to determine the horizontal angle with the cut line. By systematically measuring the maximum flank wear of diverse tools, including indexable, ball, and solid endmills, using this method, we can replace conventional manual processes. This approach can be extended and automated for various machine tools, offering substantial potential for enhancing manufacturing tool monitoring processes.

Blood flow characterization in nailfold capillary using optical flow-assisted two-stream network and spatial-temporal image

The blood flow velocity in the nailfold capillary is an important indicator of the status of microcirculation. The conventional manual processing method is both laborious and prone to human artifacts. A feasible way to solve this problem is to use machine learning to assist in image processing and diagnosis. Inspired by the Two-Stream Convolutional Networks, this study proposes an optical flow-assisted two-stream network to segment nailfold blood vessels. Firstly, we use U-Net as the spatial flow network and the dense optical flow as the temporal stream. The results show that the optical flow information can effectively improve the integrity of the segmentation of blood vessels. The overall accuracy is 94.01 %, the Dice score is 0.8099, the IoU score is 0.6806, and the VOE score is 0.3194. Secondly, The flow velocity of the segmented blood vessel is determined by constructing the spatial-temporal (ST) image. The blood flow velocity evaluated is consistent with the typical blood flow speed reported. This study proposes a novel two-stream network for blood vessel segmentation of nailfold capillary images. Combined with ST image and line detection method, it provides an effective workflow for measuring the blood flow velocity of nailfold capillaries.

Evaluation of a Mobile Wound Care Device for Assessment of Wounds: A Time Motion Study

Background: Comprehensive wound assessments are critical in identifying potential complications that affect wound healing and determining appropriate interventions for the patient. A wound care device (WCD) comprising a mobile device integrated with multi-spectral sensors that can capture stereoscopic and thermal images was recently introduced. A trial was conducted to assess potential productivity gains of the device.Methods: A total of 30 inpatients who required wound care were recruited and assessed via a time motion study. For every patient recruited in this study, wound measurements and documentation steps were repeated twice for a total of 55 wounds, once using the WCD and the other using a conventional manual process, with the order of assessment determined using a random group assignment generator. A t-test was used for statistical analysis.Results: The use of the WCD had a mean process time 4.86 minutes shorter than the conventional manual process (P<0.001). This constituted an increase in productivity by 44% for wound measurement, photography, and documentation. With estimated time savings of 5 minutes per patient, this amounts to 6,631 hours per year or a total of 3.42 nursing full-time equivalent savings per year based on an estimated load of 218 patients per day requiring wound care at an acute care institution in Singapore.Conclusion: The adoption of a mobile WCD has potential to improve work productivity and result in full-time equivalent savings for wound care nurses. Most importantly, the WCD could provide clinically beneficial outcomes for the patient by enhancing the management and documentation of wound care.

In a pilot study, automated real-time systematic review updates were feasible, accurate, and work-saving

ObjectivesThe aim of this study is to describe and pilot a novel method for continuously identifying newly published trials relevant to a systematic review, enabled by combining artificial intelligence (AI) with human expertise. Study Design and SettingWe used RobotReviewer LIVE to keep a review of COVID-19 vaccination trials updated from February to August 2021. We compared the papers identified by the system with those found by the conventional manual process by the review team. ResultsThe manual update searches (last search date July 2021) retrieved 135 abstracts, of which 31 were included after screening (23% precision, 100% recall). By the same date, the automated system retrieved 56 abstracts, of which 31 were included after manual screening (55% precision, 100% recall). Key limitations of the system include that it is limited to searches of PubMed/MEDLINE, and considers only randomized controlled trial reports. We aim to address these limitations in future. The system is available as open-source software for further piloting and evaluation. ConclusionOur system identified all relevant studies, reduced manual screening work, and enabled rolling updates on publication of new primary research.

Construction of Protocol-Based Pharmacotherapy Management (PBPM) Using an Electronic Medical Record Interlocking Support System to Prevent Hepatitis B Virus Reactivation Induced by Cancer Chemotherapy

Patients with overt or resolved hepatitis B virus (HBV) infection undergoing immunosuppressive therapy or chemotherapy for malignant diseases should be screened and monitored for their viral status under the Japan Society of Hepatology Guidelines for the Management of Hepatitis B Virus Infection to prevent the reactivation of HBV. To complete these recommendations, we have adopted a protocol-based pharmacotherapy management for HBV (PBPM-HBV) that allows pharmacists to order additional complementary blood tests on behalf of doctors in our hospital. We also constructed a support system that automatically detects and reports the cases with insufficient examinations by scanning the information of all the chemotherapy patients. By introducing PBPM-HBV, the screening implementation rate was improved significantly from 29.0％ to 81.8％ (P < 0.001). Also, by utilizing this support system, we were able to achieve remarkable labor and time savings compared to the conventional manual process of checking examination results by opening each electronic medical record. The average time taken to complete the checking process for each patient before and after the introduction of the support system was 1.93 minutes (n = 100) and 0.55 minutes (n = 300), respectively. By utilizing this support system, operating efficiency has been remarkably improved and appropriate HBV screening and monitoring for all cancer chemotherapy patients has become possible regardless of injection or oral administration of the drugs. PBPM-HBV using this support system is considered to be a good example of minimizing the increase in the workload of pharmacists as a result of task shifting from doctors.

Research on automatic preprocessing equipment of salivary analyte for PCR inspection of coronavirus.

Polymerase chain reaction (PCR) inspection of salivary analyte is performed by pretreatment, RNA extraction setup, RNA extraction, PCR setup, and the PCR process. However, the pretreatment process is conducted manually, and it is a bottleneck to the overall process. The author created automatic preprocessing logistics and prototypes using robotic technology for the pretreatment process. A dissolving agent of saliva is poured into the salivary container, the transfer syringe is automated, and a transfer robot injects an inactivating solubilizer using a robotic hand. Ninety-six inactivated vessel units are processed for the next RNA extraction process. The automatic preprocessing equipment is successfully developed and used in the inspection at a hospital. Pretreatment efficiency is up to eight times greater compared to that with the conventional manual process. The 96 units/h inspection is made possible by a single of equipment. The developed automatic preprocessing method assures high efficiency, standardization, and safety for coronavirus inspection.

Machining technology of shaft parts based on CAD technology

With the continuous development of manufacturing industry, the requirements of process design with system intelligence and informatization are higher and higher. Traditional manual technology can not meet the modern requirements, modern intelligent computer-aided process design is more and more widely used. The purpose of this study is to use CAD technology with process shaft technology. In this study, different radii of shaft components were selected and horizontal tensions of 600 kN and 1200 kN were applied to test their effects and efficiency. We compared the processing efficiency and accuracy of conventional manual processing technology and computer-assisted design. In this study, a parametric process planning template with constraint knowledge is established for each part group and stored in the process planning template library. A parametric process plan was derived using the 3d model and the feature parameters extracted from the specific manufacturing environment knowledge base. The results show that the amplitude frequency characteristic of the whole workpiece increases first and then decreases from the chuck to the tip, and the amplitude frequency characteristic amplitude is the largest at the distance of 3/4 from the chuck. The maximum value appears at 174.47Hz and the amplitude is 0.000427N/mm. Compared with manual machining, the machining time of CAD machining mode is reduced by 22.94%, the metal removal rate is increased by 34%, and the cutting efficiency is significantly improved. It is concluded that the computer-aided design technology in this study plays a more accurate and time-saving role in the processing of shaft parts and contributes to the intelligent part processing.

Design of Eye Health Monitoring System Under Color Fundus Image Visual Cup Segmentation Algorithm

In order to study the application of color fundus image (CFI) visual cup segmentation (VCS) algorithm in the design of eye health monitoring system and solve the problem that traditional image processing technology requires artificial design features, which is time-consuming, laborious, and inaccurate, deep learning (DL) algorithm is combined with residual neural network (RNN) to propose a new eye health monitoring system based on CFI VCS algorithm. Firstly, the forward propagation (FP) algorithm and back propagation (BP) algorithm of DL are theoretically derived and improved. Then, the eye health monitoring and image processing system is designed and optimized with RNN. Finally, the effect analysis VCS of the system is carried out on the real data center platform; the accuracy, sensitivity, and specificity of image processing are compared with the traditional manual processing technology and the general residual network technology. The results show that the results of RIM-ONE data set and Glaucoma Repo data set are consistent with the expert standard; in the RIM-ONE data set, the accuracy rate, sensitivity, and specificity of traditional manual processing technology are 69.68%, 71.38%, and 74.71% respectively; the accuracy, sensitivity, and specificity of common residual network technology are 81.89%, 80.56%, and 86.82% respectively; the accuracy of the system is 93.57%, the sensitivity is 87.31%, and the specificity is 90.16%. In the Glaucoma Repo data set, the accuracy, sensitivity, and specificity of conventional manual processing technology are 75.28%, 73.35%, and 82.63% respectively; the accuracy, sensitivity, and specificity of common residual network technology are 82.74%, 81.49%, and 88.82% respectively; the accuracy, sensitivity, and specificity of the system are 94.66%, 91.33%, and 94.22% respectively, which show that the system has a good effect on the segmentation of CFI, can adapt to various features of the image, has a high degree of accuracy and robustness, and provides a new way of thinking for the monitoring and management of eye health in daily life.

Design of King Grass Crusher Based on SCM Control

King grass is rich in nutriments and palatable, and has soft and succulent leaves, with high digestibility. It is one of the best green fodders for herbivore livestock and poultry. In the process of breading flocks and herds, the feed cost can be reduced largely by utilizing king grass rationally. King grass needs to be cut and ground for being used as feedingstuff. Conventional manual process consumes a large quantity of manpower and material resources, leads to the reduction of production efficiency, and brings about high labor intensity. In view of this, an automatic control king grass crusher high efficiency and practicability is designed, which integrates cutting and crushing. This machine is based on SCM, which realizes whole-process automatic control and rational coordination of pressure sensor with stepping motor for various movements, and can handle king grass crushing well.

A Reliable Auto-Robust Analysis of Blood Smear Images for Classification of Microcytic Hypochromic Anemia Using Gray Level Matrices and Gabor Feature Bank

Accurate blood smear quantification with various blood cell samples is of great clinical importance. The conventional manual process of blood smear quantification is quite time consuming and is prone to errors. Therefore, this paper presents automatic detection of the most frequently occurring condition in human blood—microcytic hyperchromic anemia—which is the cause of various life-threatening diseases. This task has been done with segmentation of blood contents, i.e., Red Blood Cells (RBCs), White Blood Cells (WBCs), and platelets, in the first step. Then, the most influential features like geometric shape descriptors, Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), and Gabor features (mean squared energy and mean amplitude) are extracted from each of the RBCs. To discriminate the cells as hypochromic microcytes among other RBC classes, scanning is done at angles (0, 45, 90, and 135). To achieve high-level accuracy, Adaptive Synthetic (AdaSyn) sampling for imbalance learning is used to balance the datasets and locality sensitive discriminant analysis (LSDA) technique is used for feature reduction. Finally, upon using these features, classification of blood cells is done using the multilayer perceptual model and random forest learning algorithms. Performance in terms of accuracy was 96%, which is better than the performance of existing techniques. The final outcome of this work may be useful in the efforts to produce a cost-effective screening scheme that could make inexpensive screening for blood smear analysis available globally, thus providing early detection of these diseases.

Automatic Remasking of Digital Subtraction Angiography Images in Pulmonary Angiography.

In pulmonary angiography, the heartbeat creates artifacts that hinder extraction of blood vessel images in digital subtraction angiography. Remasking according to the cardiac phase of the angiogram may be effective but has yet to be automated. Here, automatic remasking was developed and assessed according to the cardiac phase from electrocardiographic information collected simultaneously with imaging. Manual remasking, fixed remasking, and our proposed automatic remasking were applied to 14 pulmonary angiography series from five participants with either chronic thromboembolic pulmonary hypertension or pulmonary arteriovenous malformation. The processing time and extent of artifacts from the heartbeat were compared. In addition, the peak signal-to-noise ratio (PSNR) was measured from differential images between mask image groups before the injection of the contrast medium to investigate optimal mask images. The mean time required for automatic remasking was 4.7s/series, a significant reduction in processing time compared with the mean of 266s/series for conventional manual processing. A visual comparison of the different approaches showed virtually no misregistration artifacts from the heartbeat in manual or automatic remasking according to cardiac phase. The results from measuring the PSNR for differential images between mask image groups also showed that smaller cardiac phase difference and time difference between two images ensure higher PSNR (p < 0.01). Automatic remasking according to the cardiac phase was fast and easy to implement and reduced misregistration artifacts from heartbeat.

Heating lines Arrangement Method of Hull Complex Surface Based on Interpolation Principle11This work was supported by the Science & Technology research project of the Chongqing Municipal Education Committee (CQKJ) grant funded by the Chongqing government (No. KJ1605403).

The technology of hull complex surface is an important part in the ship-building industry. It has been widely concerned by the researchers about how to make the complex surface forming better and faster. In this study, an interpolation principle is proposed and utilized to substitute for the conventional manual process. In the proposed process, the new heating line arrangement methods are adopted to conFigure an equivalent forming arc plate, S plate, sail plate and saddle plate according to the interpolation principle. And they are transferred to a numerical simulation model using COMSOL Multiphysics, and finite element analysis is conducted to check the formability of the process. Further, experimental investigations are carried out to verify the feasibility of the process using the new heating lines. The results obtained from the finite element analysis are in good agreement with results of experiments. Consequently, it is confirmed that four kinds curved thick plate could be obtained by interpolation principle heating lines arrangement methods.

Deep Learning for Epileptic Spike Detection

In the clinical diagnosis of epilepsy using electroencephalogram (EEG) data, an accurate automatic epileptic spikes detection system is highly useful and meaningful in that the conventional manual process is not only very tedious and time-consuming, but also subjective since it depends on the knowledge and experience of the doctors. In this paper, motivated by significant advantages and lots of achieved successes of deep learning in data mining, we apply Deep Belief Network (DBN), which is one of the breakthrough models laid the foundation for deep learning, to detect epileptic spikes in EEG data. It is really useful in practice because the promising quality evaluation of the spike detection system is higher than $90$\%. In particular, to construct accurate detection model for non-spikes and spikes, a new set of detailed features of epileptic spikes is proposed. These features were then fed to the DBN which is modified from a generative model into a discriminative model to aim at classification accuracy. The experiment results indicate that it is possible to use deep learning models for epileptic spike detection with very high performance in item of sensitivity, selectivity, specificity and accuracy 92.82%, 97.83% , 96.41%, and 96.87%, respectively.

Improved standardization and potential for shortened time to results with BD Kiestra™ total laboratory automation of early urine cultures: A prospective comparison with manual processing

We compared the results of 505 urine specimens prospectively processed by both conventional manual processing (MP) with 16–24h incubation to BD Kiestra™ Total Laboratory Automation (TLA) system with a shortened incubation of 14h: 97% of culture results were clinically concordant. TLA processing was associated with improved standardization of time of first culture reading and total incubation time.

Two dimensional barcode-inspired automatic analysis for arrayed microfluidic immunoassays

The usability of many high-throughput lab-on-a-chip devices in point-of-care applications is currently limited by the manual data acquisition and analysis process, which are labor intensive and time consuming. Based on our original design in the biochemical reactions, we proposed here a universal approach to perform automatic, fast, and robust analysis for high-throughput array-based microfluidic immunoassays. Inspired by two-dimensional (2D) barcodes, we incorporated asymmetric function patterns into a microfluidic array. These function patterns provide quantitative information on the characteristic dimensions of the microfluidic array, as well as mark its orientation and origin of coordinates. We used a computer program to perform automatic analysis for a high-throughput antigen/antibody interaction experiment in 10 s, which was more than 500 times faster than conventional manual processing. Our method is broadly applicable to many other microchannel-based immunoassays.

Segmentation of the quadratus lumborum muscle using statistical shape modeling

To compare automated segmentation of the quadratus lumborum (QL) based on statistical shape modeling (SSM) with conventional manual processing of magnetic resonance (MR) images for segmentation of this paraspinal muscle. The automated SSM scheme for QL segmentation was developed using an MR database of 7 mm axial images of the lumbar region from 20 subjects (cricket fast bowlers and athletic controls). Specifically, a hierarchical 3D-SSM scheme for segmentation of the QL, and surrounding psoas major (PS) and erector spinae+multifidus (ES+MT) musculature, was implemented after image preprocessing (bias field correction, partial volume interpolation) followed by image registration procedures to develop average and probabilistic MR atlases for initializing and constraining the SSM segmentation of the QL. The automated and manual QL segmentations were compared using spatial overlap and average surface distance metrics. The spatial overlap between the automated SSM and manual segmentations had a median Dice similarity metric of 0.87 (mean = 0.86, SD = 0.08) and mean average surface distance of 1.26 mm (SD = 0.61) and 1.32 mm (SD = 0.60) for the right and left QL muscles, respectively. The current SSM scheme represents a promising approach for future automated morphometric analyses of the QL and other paraspinal muscles from MR images.

Application of flexible forming process to hull structure forming

The conventional line heating method has been applied for the manufacture of various curved blocks used for hull structures in the ship-building industry. However, it has low economical efficiency and productivity because most of its processes are based entirely on the skillful experience of experts. In this study, a flexible forming process is proposed and utilized to substitute for the conventional manual process. In the proposed process, numbers of punches which have round shapes on the contact tip are adopted to configure an equivalent forming surface according to the arbitrarily curved objective surface. A simple punch height determination algorithm that considers the discrete surface and its spatial planar equations is applied to determine the discrete forming surface composed of the adjusted punches. Punch height data are transferred to a numerical simulation model using ANSYS parametric design language, and finite element analysis is conducted to check the formability of the process. Further, experimental investigations are carried out to verify the feasibility of the process using a flexible forming apparatus. Consequently, it is confirmed that a double-curved thick plate could be obtained by the flexible forming process.

Computer-aided design and fabrication of dental restorations: Current systems and future possibilities

For more than 20 years, researchers have been trying to automate conventional manual processes in dental technology with the hope of producing higher- and more uniform-quality materials, standardizing manufacturing processes and reducing production costs. The authors review existing computer-aided design (CAD)/computer-aided manufacturing (CAM) systems, describing the components of CAD/CAM technologies and addressing the limitations of current systems, and suggest possibilities for future systems. Existing dental CAD/CAM systems vary dramatically in their capabilities; each has distinct advantages and limitations. None can yet acquire data directly in the mouth and produce the full spectrum of restoration types (with the breadth of material choices) that can be created by traditional techniques. Emerging technologies may expand dramatically the capabilities of future systems, but they also may require a different type of training to use them to their full effectiveness. In the future, automatically fabricated, fully esthetic restorations might be produced more quickly and have longer lifetimes than restorations currently produced with CAD/CAM systems.

Integrated image analysis solutions for PET datasets in damaged brain.

To identify and discuss the problems inherent in the processing of multiparametric functional imaging datasets from patients with acute brain injury, using "triple oxygen" positron emission tomography (PET) as an example. To present an integrated imaging solution for analysis of such datasets and report on its use in practice. Structured analysis of the steps in image analysis for triple oxygen studies in patients with acute brain injury, subarachnoid haemorrhage and carotid artery disease was undertaken. Systematic identification of the drawbacks of conventional manual processing techniques, which make use of modules from different commercially available software packages was carried out. This analysis informed the construction of an image analysis gateway that addressed these issues. We describe an integrated image analysis gateway (PETAn) that provides for the automated integration of all processing steps, along with outputs that detail analysis stages, error logs and results. Implementation of PETAn allowed batch processing of clinical PET data sets, reduced the level of technical expertise required for analysis, improved the quality of results and achieved significant reductions in operator analysis time. While modules from several imaging software suites can be usefully combined to allow analysis of multiparametric PET data sets from patients with acute brain injury, sequential use of these modules for various steps in image analysis is fraught with difficulty. Careful automation and integration of these steps greatly facilitates the interrogation of information-rich data sets and increases research productivity.