Computer-based Processing Research Articles

Development and Initial Validation of the Computer-Based Orthographic Processing Assessment Short Form: An Application of Cognitive Diagnostic Modeling

Development and Initial Validation of the Computer-Based Orthographic Processing Assessment Short Form: An Application of Cognitive Diagnostic Modeling

Rancangan Sistem Pendukung Keputusan Pemilihan Calon Pegawai Honorer Pemerintah Kabupaten Lamandau Menggunakan Metode Profile Matching

This study aims to design a Decision Support System (DSS) that implements the Profile Matchingmethod for the selection of honorary employees in the Lamandau District Government. The oftennon-systematic selection process results in less objective decisions, necessitating a system that canenhance effectiveness and transparency in decision-making. The Profile Matching method is usedto compare the profiles of candidates with predetermined criteria, leading to a fairer and moreaccurate selection process. Data were collected through interviews with relevant stakeholders inthe Lamandau District Government, which were then analyzed to identify appropriate selectioncriteria. The findings indicate that the application of DSS can reduce subjectivity and improveclarity in the evaluation process. Additionally, the designed computer-based system facilitatesfaster data processing and presents information in a more comprehensible manner. Thus, thisresearch is expected to make a significant contribution to the development of employee selectionsystems in local government and enhance the quality of human resources in public service. Theimplementation of information technology in DSS is anticipated to serve as a reference for futureresearch in decision-making and human resource management.

Utility of deficit-specific computer-based training on children with temporal processing deficit.

Children with temporal processing deficits struggle to detect and discriminate syllables, phonemes, and stress patterns in speech. To overcome these deficits, computer-based auditory training programs have been widely used as one of the rehabilitation alternatives in recent years. The present study aimed to examine the usefulness of one such computer-based temporal processing training (CBTPT) module on children with temporal processing deficits. Sixteen children (8-15years) with temporal processing deficits were enrolled in the study, further divided into active (CBTPT) and placebo (placebo training) groups. Further, 8 typically developing children (no training) were enrolled as a comparison group. The auditory outcome measures included Duration Pattern Test (DPT), Gap Detection Test (GDT), Dichotic CV (DCV), and Speech-in-Noise-Indian English (SPIN-IE) assessed before and after training for all three groups. Wilcoxon-sign rank test showed a statically significant difference between pre and post-test scores of DPT, GDT, and SPIN (p < 0.001) except DCV among the active group. However, no significant differences were noted in the pre and post-test scores among the placebo and TD groups. Mann Whitney U test showed a significant difference in DPT and SPIN post-training scores between active and placebo groups; active and TD group; placebo and TD group. From the above finding, it is inferred that the CBTPT module is useful among children having temporal processing deficits.

A convenient archaeological ruins identification method through elevation information extraction from CORONA stereo pairs

Three-dimensional (3-D) stereo images can be generated via computer-based image processing of CORONA stereo pairs. To a certain extent, important terrain and surface feature data extracted from these stereo images can improve the survey of archaeological sites and the identification and mapping of major landscapes. In this study, we focused on the identification of the archaeological ruins of Liangzhu City. An optical stereo model (red/blue stereo image) of the Liangzhu site was created through computer-based mosaicking and processing of CORONA remote-sensing stereo pairs taken in the 1960s and 1970s. By importing the optical stereo model into mobile phones, tablet computers, and other mobile devices, the research team undertook real-time locating of ruins via human observation, on-site investigation, and image overlay during a field survey and identified several Liangzhu-period dams, some of which have been confirmed via archaeological field investigations. The research team later applied the same method to the identification of tombs at the site of the mausoleums of the six emperors of the Southern Song dynasty. The results further prove that this method is feasible and reliable and can be widely promoted and used for the identification of archaeological ruins.

Calculation of coal cleats spacing for methane degassing by image processing

Coal bed methane is one of the clean energy sources in the world. Methane molecules are confined inside the pores of coals and when the gas drainage wells are drilled into the coal seams, due to the resulted pressure difference. Coal cleats are spread all over the coal seam as face and butt cleats and play an essential role in the methane gas drainage operation from coal mines. Calculating the coal cleats spacing makes great help in modeling the amount of emitted gas followed by calculating the spacing of gas suction wells. Furthermore, the time required for gas drainage will be determined. Computer-based image processing technique has been utilized to identify the cleats spacing. In this study, three-dimensional computed tomography scan images were prepared for coal samples from Tabas Coal Mine in Iran. Computer-based image processing technology was conducted to determine the coal cleats. Their spacing was then calculated. Based on the results obtained using image processing with computer, the average distance between face cleats was 20 to 30 mm and the distance between butt cleats was 15 to 25 mm. The results of this study are used to modeling the amount of methane gas in the coal cleats. Based on this modeling, the amount of released gas and the distance between the wells can be designed.

Perkembangan Teknologi Informasi dalam Sistem Informasi Manajemen di Bidang IT

Nowadays, most people increasingly perceive information as one of their basic needs besides the need for clothing, food and shelter. Along with this, information changes form into a commodity that has value and can be traded. This situation is proven by the increasing development of the information service business through various media, such as television stations, newspapers, radio and the internet, which have entered many aspects of people's lives. Rapid, dynamic and extensive environmental changes are supported by advances in information technology in almost all fields. This has encouraged changes in the lifestyle of traditional society into an information society. The rapid development of information technology has had an impact on people's lives. Since the discovery of computers in 1955, until now it continues to experience very significant developments. Information technology with computers as one of the very important components has changed the acquisition of information which is now not only from surrounding sources but information that comes from various sources. Computer-based information processing People are starting to become known and up to now there is a lot of software that people can use as a data processing tool to produce the desired information.

Artificial intelligence in forensic medicine and related sciences – selected issues = Sztuczna inteligencja w medycynie sądowej i naukach pokrewnych – wybrane zagadnienia

Aim. The aim of the work is to provide an overview of the potential application of artificial intelligence in forensic medicine and related sciences, and to identify concerns related to providing medico-legal opinions and legal liability in cases in which possible harm in terms of diagnosis and/or treatment is likely to occur when using an advanced system of computer-based information processing and analysis. Materials and methods. The material for the study comprised scientific literature related to the issue of artificial intelligence in forensic medicine and related sciences. For this purpose, Google Scholar, PubMed and ScienceDirect databases were searched. To identify useful articles, such terms as „artificial intelligence,” „deep learning,” „machine learning,” „forensic medicine,” „legal medicine,” „forensic pathology” and „medicine” were used. In some cases, articles were identified based on the semantic proximity of the introduced terms. Conclusions. Dynamic development of the computing power and the ability of artificial intelligence to analyze vast data volumes made it possible to transfer artificial intelligence methods to forensic medicine and related sciences. Artificial intelligence has numerous applications in forensic medicine and related sciences and can be helpful in thanatology, forensic traumatology, post-mortem identification examinations, as well as post-mortem microscopic and toxicological diagnostics. Analyzing the legal and medico-legal aspects, artificial intelligence in medicine should be treated as an auxiliary tool, whereas the final diagnostic and therapeutic decisions and the extent to which they are implemented should be the responsibility of humans.

Artificial intelligence in forensic medicine and related sciences - selected issues.

The aim of the work is to provide an overview of the potential application of artificial intelligence in forensic medicine and related sciences, and to identify concerns related to providing medico-legal opinions and legal liability in cases in which possible harm in terms of diagnosis and/or treatment is likely to occur when using an advanced system of computer-based information processing and analysis. The material for the study comprised scientific literature related to the issue of artificial intelligence in forensic medicine and related sciences. For this purpose, Google Scholar, PubMed and ScienceDirect databases were searched. To identify useful articles, such terms as "artificial intelligence," "deep learning," "machine learning," "forensic medicine," "legal medicine," "forensic pathology" and "medicine" were used. In some cases, articles were identified based on the semantic proximity of the introduced terms. Dynamic development of the computing power and the ability of artificial intelligence to analyze vast data volumes made it possible to transfer artificial intelligence methods to forensic medicine and related sciences. Artificial intelligence has numerous applications in forensic medicine and related sciences and can be helpful in thanatology, forensic traumatology, post-mortem identification examinations, as well as post-mortem microscopic and toxicological diagnostics. Analyzing the legal and medico-legal aspects, artificial intelligence in medicine should be treated as an auxiliary tool, whereas the final diagnostic and therapeutic decisions and the extent to which they are implemented should be the responsibility of humans.

AI CHATBOT FOR MENTAL HEALTH

Modern artificial intelligence (AI), and machine learning in particular, is being utilized to develop prediction, detection, and treatment solutions for mental health care with the emergence of digital approaches to mental health. AI is being used in therapy to improve user experience and maximize individualized mental health care through digital interventions, including web and smartphone apps. Modern sources of copious amounts of data allow for the development of prediction/detection models for mental health disorders through the use of data-driven AI techniques. Specifically, behavioral or mental health insights can be extracted from an individual's "digital exhaust," which is the data obtained from their multiple personal digital devices and social media activities. Language has traditionally been seen as a window into the human mind, but with the help of potent computer-based natural language processing, it can now be statistically used as data to infer mental health. Furthermore, conversational agents for therapeutic intervention can be created using natural language processing

Chat GPT의 원리, 활용, 한계와 업무효율화

This paper introduces the principles and applications of Chat GPT, which utilizes the large-scale language model GPT. It first discusses the detailed workings of natural language processing, where embedding serves as the initial step in computer-based language processing. The relationship between transformers and GPT is explained for sentence-level embedding. Then this paper explores the development of Chat GPT based on GPT-3.5, which has been improved via reinforcement learning from human feedback or RLHF, and released by OpenAI. Chat GPT can be utilized in various domains such as question answering, translation, correction, summarization, tabular data processing, and coding. It can guide users to obtain desired responses through role-setting and data delivery. However, its broad application is having significant societal impacts. Issues related to corporate or national security have led to usage restrictions, while debates over authorship recognition in the scientific community and discussions about artistic value in the cultural and arts sector have sparked strikes due to job concerns. The emergence of fake problems produced by generative AI, along with its misuse for cybercrime, is also highlighted. Such limitations of Chat GPT, including hallucination phenomena, are discussed in this work. Lastly, suggestions are made for utilizing Chat GPT in business that include emphasizing the need for content verification with hallucination in mind, cautioning against relying solely on search engines, utilizing generative AI with retrieval-augmented generation(RAG) functionality, and employing small large language models (sLLMs) developed for professional domains.

Multiuser Based Savings And Loans Information System

The increasingly rapid development of computer technology provides convenience for humans in carrying out life activities, this has resulted in the use of computers being an alternative taken by various agencies because it is considered to provide more advantages than disadvantages. Computers are tools to improve performance in various fields. In solving data processing problems at the KSU " DANA MANDIRI " Cooperative, based on the survey carried out, the author tried to change the manual or conventional data processing program into a computer-based data processing program, namely by using the Visual Foxpro 9.0 program. This change aims to provide comfort for operators in carrying out their work. With old programs, conventionally inputting data still takes a long time and when searching for data you still have to look for codes one by one because it cannot be done automatically. With these problems the author tries to formulate the problem, namely "How to make a data processing program to save borrow at KSU " DANA MANDIRI " using the Visual Foxpro 9.0 programming language. The savings and loan data processing process can be accessed quickly and precisely and provides a more attractive appearance. In solving this problem the author tried to collect data related to savings and loan data. In designing a new system, several stages are carried out including data design. Table creation, ERD creation, DFD and normalization. In processing the savings and loan data, it is hoped that it can help with problems that arise at the KSU " DANA MANDIRI " Cooperative and the program created of course still has several weaknesses and shortcomings, this is possible because the author still has little knowledge and experience in programming issues. Suggestions and criticism really help the author to further develop knowledge in this field.

Sistem Informasi Data Pemantauan Wilayah Setempat Kesehatan Ibu Dan Anak ( KIA)

Computer-based data processing has developed greatly. In health institutions such as community health centers, the role of information technology can no longer be separated. Almost all community health centers currently implement computer-based systems to manage health-related data, such as maternal and child health (KIA). With a computerized system, we can provide good and fast service and present information effectively and efficiently. This requires the ability of human resources to master and follow developments in science and technology; the development of science is always followed by technological advances which are needed in data processing, namely by using computer tools and programs, data processing will be carried out well and the results Perfect.

Optimized Deep Learning Model Using Modified Whale’s Optimization Algorithm for EEG Signal Classification

Brain-Computer Interface (BCI) is a technology in which Electroencephalogram (EEG) signals are utilized to create a link between a person’s mental state and a computer-based signal processing system that decodes the signals without needing muscle movement. The mental process of picturing the movement of a body component without actually moving that body part is known as Motor Imagery (MI). MI BCI is a Motor Imagery-based Brain-Computer Interface that allows patients with motor impairments to interact with their environment by operating robotic prostheses, wheelchairs, and other equipment. Feature extraction and classification are essential parts of the EEG signal processing for MI BCI. In this work, Whales Optimization Algorithm with an Improved Mutualism Phase is proposed to find the optimal Convolutional Neural Network architecture for the classification of motor imagery tasks with high accuracy and less computational complexity. The Neurosky and BCI IV 2a datasets were used to evaluate the proposed methodology. Experiments demonstrate that the suggested technique outperforms other competing methods regarding classification accuracy values at 94.1% and 87.7% for the Neurosky and BCI datasets, respectively.

Extracting Masks from Herbarium Specimen Images Based on Object Detection and Image Segmentation Techniques

Extracting Masks from Herbarium Specimen Images Based on Object Detection and Image Segmentation Techniques

Как се прави показалец?

A brief summary is made of prof. Yanakiev's views on the creation of indexes for different types of scientific publications, changes are noted in these views due to the development of electronics and computer-based text processing, and a comparison is provided with Prof. Yanakiev's practice in the book “Stylistics and language learning”.

Ship Detection in Navy Using Satellite Images by Deep Learning Approach

Ship identification in satellite images poses significant challenges within the domain of remote sensing. Its importance extends to critical areas such as security, encompassing concerns such as military attacks, accidents, illegal transportation of goods, illegal fishing, territorial violations, and ship hijackings. Additionally, effective traffic management and smuggling prevention heavily rely on accurate ship identification. While synthetic aperture radar (SAR) has historically dominated maritime monitoring, researchers are increasingly exploring optical satellite images as a potential alternative. Previous ship detection techniques have utilized Computer-based image processing vision methods. However, this study proposes a novel approach employing a Convolutional Neural Network (CNN) based method to accurately identify ships in satellite data. The suggested approach entails the utilization and assessment of a custom-designed deep learning model based on CNN architecture. to recognize ships in satellite photos. Keywords - ship detection, optical images, Convolutional Neural Networks.

Recent Applications of Deconvolution Microscopy in Medicine.

Deconvolution microscopy is a computational image-processing technique used in conjunction with fluorescence microscopy to increase the resolution and contrast of three-dimensional images. Fluorescence microscopy is a widely used technique in biology and medicine that involves labeling specific molecules or structures within a sample with fluorescent dyes and then electronically photographing the sample through a microscope. However, the resolution of conventional fluorescence microscopy is limited by diffraction within the microscope's optical path, which causes blurring of the image and reduces the ability to resolve structures in close proximity with one another. Deconvolution microscopy overcomes this limitation by means of computer-based image processing whereby mathematical algorithms are used to eliminate the blurring caused by the microscope's optics and thus obtain a higher-resolution image that reveals the fine details of the sample with greater accuracy. Deconvolution microscopy, which can be applied to a range of image acquisition modalities, including widefield, confocal, and super-resolution microscopy, has become an essential tool for studying the structure and function of biological systems at the cellular and molecular levels. In this perspective, the latest deconvolution techniques have been introduced and image-processing methods for medical purposes have been presented.

Processing speed test and 30-day readmission in elderly non-cardiac surgery patients- A retrospective study.

Preoperative cognitive function screening can help identify high-risk patients, but resource-intensive testing limits its widespread use. A novel self-administered tablet computer-based Processing Speed Test (PST) was used to assess cognitive "executive" function in non-cardiac surgery patients, but the relationship between preoperative test scores and postoperative outcomes is unclear. The primary outcome was a composite of 30-day readmission/death. The secondary outcome was a collapsed composite of discharge to a long-term care facility/death. Exploratory outcomes were 1) time to discharge alive, 2) 1-year mortality and 3) a collapsed composite of postoperative complications. This retrospective study, after approval, was conducted in elective non-cardiac surgery patients ≥65 years old. We assessed the relationship between processing speed test scores and primary/secondary outcomes using multivariable logistic regression, adjusting for potential confounding variables. Overall 1568 patients completed the PST, and the mean ± standard deviation test score was 33 ± 10. The higher PST score is associated with better executive function. A 10-unit increase in the test score was associated with an estimated 19% lower 30-day readmission/death odds, with an odds ratio (OR) and 95% confidence interval (CI) of 0.81 (0.68, 0.96) (P = 0.015). Similarly, 10-unit increase in test score was associated with an estimated 26% lower odds of long-term care need/death, with OR (95% CI) of 0.74 (0.61, 0.91) (P = 0.004). We also found statistically significant associations between the test scores and time to discharge alive and to 1-year mortality, however, not with a composite of postoperative complications. Elderly non-cardiac surgery patients with better PST scores were less likely to be readmitted, need long-term care after discharge or die within 30 days. Preoperative assessment of cognitive function using a simple self-administered test is feasible and may guide perioperative care.

Review of Advances in Speech Processing with Focus on Artificial Neural Networks

Speech is the primary way via which most humans communicate. Computers facilitate this transfer of information, especially when people interact with databases. While some methods to manipulate and interpret speech date back many decades (e.g., Fourier analysis), other processing techniques were developed late last century (e.g., linear predictive coding and hidden Markov models). Nonetheless, the last 25 years have seen major advances leading to the wide acceptance of computer-based speech processing, e.g., cellular telephones and real-time online conversations. This paper reviews older techniques and recent methods that focus largely on artificial neural networks. The major highlights in speech research are examined, without delving into mathematical detail, while giving insight into the research choices that have been made. The focus of this work is to understand how and why the discussed methods function well.

Weld defect identification and characterization in radiographic images using deep learning: Review

Defects in the welds degrade the quality of the weld. Weld defect identification is a challenging task in the industry because of the wide range of weld imperfections. Weld defect detection using radiographic images is an effective technique for achieving good weld quality in shipbuilding and aerospace applications. Foreign inclusions, cracks and pores are examples of welding joint imperfections. Several appropriate computer-based image processing techniques have made the detection of weld defects possible. It is challenging because weld imperfection can show various sizes, shapes, contrasts and locations in radiography images. The accuracy of this inspection process is more dependent on various external factors and is also time-consuming. Automatic weld defect detection is needed by analyzing the images obtained directly from digital radiographic systems. This paper uses a unique image-based approach to a small batch of x-ray imaging datasets to investigate a potential solution for weld defect identification. This article compares a deep learning network’s performance for various parameter and hyper-parameter combinations. Also it compares the traditional approaches of defect detection using manual inspection method, feature-based defect identification, and finally deep - learning based approach on several types of weld defects in various industrial applications. This comparative analysis concludes that deep learning-based approaches have achieved more accuracy as compared to conventional techniques. This research paper also highlights a few challenges and future directions in welding area.