Automatic Reading Research Articles

AI-based mobile application to fight antibiotic resistance

Antimicrobial resistance is a major global health threat and its development is promoted by antibiotic misuse. While disk diffusion antibiotic susceptibility testing (AST, also called antibiogram) is broadly used to test for antibiotic resistance in bacterial infections, it faces strong criticism because of inter-operator variability and the complexity of interpretative reading. Automatic reading systems address these issues, but are not always adapted or available to resource-limited settings. We present an artificial intelligence (AI)-based, offline smartphone application for antibiogram analysis. The application captures images with the phone’s camera, and the user is guided throughout the analysis on the same device by a user-friendly graphical interface. An embedded expert system validates the coherence of the antibiogram data and provides interpreted results. The fully automatic measurement procedure of our application’s reading system achieves an overall agreement of 90% on susceptibility categorization against a hospital-standard automatic system and 98% against manual measurement (gold standard), with reduced inter-operator variability. The application’s performance showed that the automatic reading of antibiotic resistance testing is entirely feasible on a smartphone. Moreover our application is suited for resource-limited settings, and therefore has the potential to significantly increase patients’ access to AST worldwide.

IoT Based Sensor for Humidity and Temperature Measurement in Smart HVAC Systems

The initials HVAC stand for Heating, Ventilation and Air Conditioning. They describe the functions of an HVAC system. This mechanical system’s design is primarily an attempt to take control of the environmental conditions inside the space of work by controlling and monitoring the temperature of a room through heating and cooling. It also controls the humidity level in that environment by controlling the movement and distribution of air inside the room. For determining the temperature and humidity, costly sensors are required. These sensors are the traditional mechanical sensors which can’t offer any additional services like cloud support, data storage, etc. Hence here I am proposing an IoT based sensor with cloud data storage using Arduino-Uno development board, ESP8266 and Thingspeak cloud. This sensor is economical and supports automatic reading and controlling of the humidity and temperature and sends this data to a secured server and thus monitors and controls the temperature and humidity of the system.

Action Video Games Enhance Attentional Control and Phonological Decoding in Children with Developmental Dyslexia.

Reading acquisition is extremely difficult for about 5% of children because they are affected by a heritable neurobiological disorder called developmental dyslexia (DD). Intervention studies can be used to investigate the causal role of neurocognitive deficits in DD. Recently, it has been proposed that action video games (AVGs)—enhancing attentional control—could improve perception and working memory as well as reading skills. In a partial crossover intervention study, we investigated the effect of AVG and non-AVG training on attentional control using a conjunction visual search task in children with DD. We also measured the non-alphanumeric rapid automatized naming (RAN), phonological decoding and word reading before and after AVG and non-AVG training. After both video game training sessions no effect was found in non-alphanumeric RAN and in word reading performance. However, after only 12 h of AVG training the attentional control was improved (i.e., the set-size slopes were flatter in visual search) and phonological decoding speed was accelerated. Crucially, attentional control and phonological decoding speed were increased only in DD children whose video game score was highly efficient after the AVG training. We demonstrated that only an efficient AVG training induces a plasticity of the fronto-parietal attentional control linked to a selective phonological decoding improvement in children with DD.

Text Recognition of Cardboard Pharmaceutical Packages by Utilizing Machine Vision

In this paper, text recognition of variably curved cardboard pharmaceutical packages is studied from the photometric stereo imaging point-of-view with focus on developing a method for binarizing the expiration date and batch code texts. Adaptive filtering, more specifically Wiener filter, is used together with haze removal algorithm with fusion of LoG-edge detected sub-images resulting an Otsu thresholded binary image of expiration date and batch code texts for future analysis. Some results are presented, and they appear to be promising for text binarization. Successful binarization is crucial in text character segmentation and further automatic reading. Furthermore, some new ideas will be presented that will be used in our future research work.

Image-Based Automatic Watermeter Reading under Challenging Environments.

With the rapid development of artificial intelligence and fifth-generation mobile network technologies, automatic instrument reading has become an increasingly important topic for intelligent sensors in smart cities. We propose a full pipeline to automatically read watermeters based on a single image, using deep learning methods to provide new technical support for an intelligent water meter reading. To handle the various challenging environments where watermeters reside, our pipeline disentangled the task into individual subtasks based on the structures of typical watermeters. These subtasks include component localization, orientation alignment, spatial layout guidance reading, and regression-based pointer reading. The devised algorithms for orientation alignment and spatial layout guidance are tailored to improve the robustness of our neural network. We also collect images of watermeters in real scenes and build a dataset for training and evaluation. Experimental results demonstrate the effectiveness of the proposed method even under challenging environments with varying lighting, occlusions, and different orientations. Thanks to the lightweight algorithms adopted in our pipeline, the system can be easily deployed and fully automated.

An Adaptive Method for Recognition of Dual-pointer Mechanical Instrument Based on Hough Transform

For automatic and efficient reading of dual-pointer mechanical instruments in petroleum engineering applications, an adaptive recognition method based on Hough transform is proposed. Firstly, the instrument dial is detected by Hough transform. Then the center of circle is located, as well as the pointer is recognized. Finally, the linear relationship between the dial scale and the pointer is adopted to calculate the pointer reading. The experimental results show that the algorithm achieves high application value for the dual-pointer mechanical instrument with uniform scales.

Discovery Engine for Finding Hidden Connections in Prose Comprehension from References

Reading is one of the essential practices of modern human learning. Comprehending prose text simply from the available text is particularly challenging as in general the comprehension of prose requires the use of external knowledge or references. Although the processes of reading comprehension have been widely studied in the field of psychology, no algorithm level models for comprehension have yet to be developed. This paper has proposed a comprehension engine consisting of knowledge induction which connects the knowledge space by augmenting associations within it. The connections are achieved through the automatic incremental reading of external references and the capturing of high familiarity knowledge associations between prose concepts. The Ontology Engine is used to find lexical knowledge associations amongst concept pairs, with the objective being to obtain a knowledge space graph with a single giant component to establish a base model for prose comprehension. The comprehension engine is evaluated through experiments with various selected prose texts. Akin to human readers, it could mine reference texts from modern knowledge corpuses such as Wikipedia and WordNet. The results demonstrate the potential efficiency of using the comprehension engine that enhances the quality of reading comprehension in addition to reducing reading time. This comprehension engine is considered the first algorithm level model for comprehension compared with existing works.

INSPECTION OF DEFECTIVE PRODUCTS IN THE INDUSTRY WITH IMAGE PROCESSING BASED ON DEEP LEARNING METHODS

Aim: This paper studies to detect the undetectable defects in casting such as air holes, pinholes, burrs, tensile defects, mold material defects, metal casting defects, metallurgical defects, and etc. Through images via deep learning methods. Method: In the study, an automatic reading review for submersible pump impeller is proposed and a deep learning model is developed. The data set of the images include defective and smooth submersible pump impeller has been utilized to prove the performance of the designed network architecture. Results: According to the obtained results, maximum accuracy of 89% for the classifier has been achieved in the training stage and it reached a maximum accuracy of 93% in the testing stage. Conclusion: Along with the developing systems, quality control systems have been evolved through image processing. Thanks to the image processing-based control systems, the capacity and efficiency of the production facilities can be increased and perfect products can be delivered to the end-user by making precise measurements. In this study, since casting is an important and frequently used process in the industry, its defects are evaluated and a deep learning model to automate the review process and detect the defective products of submersible pump impellers is presented. The success rate of 89% obtained show that the defective product inspection in the industry can be performed over the images by using a convolutional neural network (CNN) architecture.

Double Image Segmentation Algorithm for Tick-Mark Recognition of Analog Instrument

Tick-mark recognition is a key step for automatic reading of analog instrument with computer vision techniques which is called for in many automatic processes among industries. As many factors result in the tick-mark distortion in the sampled image such as the generally stained surface of instrument, or/and reflection and refraction of light, the accuracy and robustness of tick-mark reading are directly or indirectly weakened. Double image segmentation algorithm (DISA) is employed to solve this problem which makes coarse segmentation with structural parameters of instruments, and makes accurate segmentation with gray difference between tick-marks and their background. Tests have been conducted with 640 * 480 pixel industry camera and 4 kinds of pointer pressure meter, and the results show that read-out rate of tick-mark in pointer meter reached 100% at sufficient illumination and 76% at insufficient illumination for air packed instrument. In addition with oil packed instrument, DISA still experienced 64% recognition in comparison with 0 success record by Hough Transformation.

Neural Network for Handwriting Recognition

Today, in the digital age, the problem of pattern recognition is very relevant. In particular, the task of text recognition is important in banking, for the automatic reading of documents and their control; in video control systems, for example, to identify the license plate of a car that violated traffic rules; in security systems, for example, to check banknotes at an ATM and in many other areas. A large number of methods are known for solving the problem of pattern recognition, but the main advantage of neural networks over other methods is their learning ability. It is this feature that makes neural networks attractive to study. The article proposes a basic neural network model. The main algorithms are considered and a programming model is implemented in the Python programming language. In the course of research, the following shortcomings of the basic model were revealed: low learning rate (the number of correctly recognized digits in the first epochs of learning); retraining - the network has not learned to generalize the knowledge gained; low probability of recognition - 95.13%.To solve the above disadvantages, various techniques were used that increase the accuracy and speed of work, as well as reduce the effect of network retraining.

Introduction of a digital near-vision reading test for normal and low vision adults: development and validation

BackgroundMNREAD is an advanced near-vision acuity chart that has already been translated and validated in Greek language. Considering that no validated Greek digital near-vision test exists, our primary objective was to develop and validate a digital near-vision reading test based on the fundamental properties of the Greek printed MNREAD (MNREAD-GR).MethodsThis is a prospective, comparative study. A digital near-vision chart was developed (Democritus Digital Acuity Reading Test – DDART) with text size calibration, audio recording for automatic reading timing, as well as automatic calculation of reading acuity (RA), maximum reading speed (MRS), critical print size (CPS) and reading accessibility index (ACC). Normal and low vision subjects participated in the validation process, responding to MNREAD-GR and DDART at the same day, at a 40 cm viewing distance. Differences in all parameters between the charts were compared with t-test and intraclass correlation coefficients (ICCs). Within 15 days, all participants responded again to DDART in a different set of sentences to assess its test-retest reliability.ResultsOne hundred patients (normal vision group - NVG: 70 patients; low vision group - LVG: 30 patients) responded to both reading tests. Non-significant differences were detected for all parameters between DDART and MNREAD-GR except for MRS and ACC that were significantly higher in MNREAD-GR in NVG (p < 0.01). NVG participants demonstrated sufficient ICCs that ranged from 0.854 to 0.963, while LVG demonstrated ICCs for RA, ACC, MRS and CPS equal to 0.986, 0.894, 0.794 and 0.723, respectively. All parameters calculated with DDART demonstrated excellent test-retest reliability (ICCs: 0.903 – 0.956).ConclusionsThe proposed reading test presented comparable validity and repeatability to MNREAD-GR suggesting that it can be used both in normal and low vision Greek patients.Trial registrationClinicalTrials.gov, NCT04242836. Registered 24 January 2020 – Retrospectively registered.

A High-Robust Automatic Reading Algorithm of Pointer Meters Based on Text Detection.

Automatic reading of pointer meters is of great significance for efficient measurement of industrial meters. However, existing algorithms are defective in the accuracy and robustness to illumination shooting angle when detecting various pointer meters. Hence, a novel algorithm for adaptive detection of different pointer meters was presented. Above all, deep learning was introduced to detect and recognize scale value text in the meter dial. Then, the image was rectified and meter center was determined based on text coordinate. Next, the circular arc scale region was transformed into a linear scale region by polar transform, and the horizontal positions of pointer and scale line were obtained based on secondary search in the expanded graph. Finally, the distance method was used to read the scale region where the pointer is located. Test results showed that the algorithm proposed in this paper has higher accuracy and robustness in detecting different types of meters.

Automatic analog meter reading for plant inspection using a deep neural network

The high demand for automatic plant inspections by robots has been because a plant has many dangerous locations to cover during daily inspections. In this study, we propose automatically reading an analog meter using a Deep Neural Network (DNN), because reading an analog meter is included in the daily inspections. In particular, we artificially generate training data including shooting noise and apply these data for training the DNN. The learned DNN is robust against readable angles, meter contamination, and meter light reflection, and achieves a reading absolute error within 0.05. Additionally, we verify the effectiveness of the proposed method using cross-validation and accuracy comparison with conventional methods.

Pointer instrument image recognition system for veterinary drug production based on RFID and deep learning

Based on RFID technology, the tag data can be read and identified dynamically, real-time, contactless, long-distance and batch, and the image information of pointer instrument can be collected. Using Faster-RCNN to detect and locate the dial area, and combining with Le Net-5 method to identify the dial number, the system has the advantages of fast reading, high accuracy, strong adaptability and intelligent management. It provides a solution for the automatic recognition and reading of pointer instrument in the complex environment of veterinary medicine production workshop.

Analog Gauge Reader based on Image Recognition

Analog dial are widely used in modern production and life. In the fields of meter detection and meter scale value recording, the demand for automatic reading of analog dial is increasing. This paper proposes an improved method of fast reading of images, which refines the scale circle and uses the branch point extraction algorithm to extract the intersection of the scale line and the scale circle to express the scale line indirectly. Finally, the pointer reading is calculated based on the ratio of the deflection angle of the pointer to the total angle of the range.

The Prevalence of Dyslexia in Primary School Children and Their Chinese Literacy Assessment in Shantou, China.

The epidemiological studies of Chinese developmental dyslexia (DD) in China are still limited. In addition, literacy assessment has seldom been performed for children with dyslexia, due to lack of uniform assessment tools. This study was aimed at investigating the prevalence rate of children with dyslexia, and to evaluate their Chinese reading ability. A total of 2955 students aged 7–12 years were enrolled by randomized cluster sampling. The study was divided into three stages. In stage I, all participating students were asked to finish the Combined Raven Test (CRT) and Chinese Vocabulary Test and Assessment Scale. In stage II, the Chinese teachers and parents of the children with suspected dyslexia were interviewed by psychiatrists, and finished the Dyslexia Checklist for Chinese Children (DCCC). In stage III, these children were evaluated by child psychiatrists for the diagnosis with or without dyslexia, according to the fifth edition of Diagnostic and Statistical Manual of Mental Disorders (DSM-5), and their Chinese literacy was further evaluated by using the Chinese Reading Ability Test (CRAT). The prevalence rate of children with dyslexia was 5.4% in Shantou city, 8.4% in boys and 2.3% in girls, with a gender ratio of 3.7:1.0. Children with dyslexia scored lower in all the five subscales of the CRAT tests. including phonological awareness, morphological awareness, rapid automatized naming, orthographic awareness, and reading ability than the control group (all p < 0.001). This study suggested that the prevalence rate of Chinese dyslexia in Shantou city is roughly equivalent to that previously reported in China. Children with dyslexia have a relatively lower Chinese reading ability in all assessments.

Bidirectional longitudinal relationship between Chinese children's compounding awareness and vocabulary knowledge from Grades 3 to 6

BackgroundThis study examined the developmental relationship between Chinese children's compounding awareness and vocabulary knowledge following a 4‐year longitudinal design.MethodsA test battery that included measures of vocabulary knowledge, compounding awareness, nonverbal IQ, phonological awareness, rapid automatized naming, orthographic awareness and word reading was administered to 142 Chinese‐speaking students in Grade 3 (T1). In addition, vocabulary knowledge and compounding awareness were followed in Grades 4 (T2) and 6 (T3).ResultsControlling for nonverbal IQ, phonological awareness, rapid automatized naming, orthographic awareness and word reading at the initial level, the structural equation modeling results showed that children's compounding awareness made a significant direct contribution to vocabulary knowledge from T1 to T2. Children's vocabulary knowledge at T1 predicted compounding awareness at T2. However, the paths from vocabulary knowledge at T2 to compounding awareness at T3, and compounding awareness at T2 to vocabulary knowledge at T3, respectively, were not significant. The results suggest a reciprocal relationship between children's compounding awareness and vocabulary knowledge from Grades 3 to 4 in Chinese.ConclusionsThese findings indicate the developmental bootstrapping relationship between Chinese students' compounding awareness and vocabulary acquisition in the middle stages of primary school.

Blood pressure control in patients with chronic kidney disease according to office and home blood pressures.

The aim of this study was to assess blood pressure (BP) control in patients with chronic kidney disease (CKD) according to office and home BP and to assess the prevalence of normal BP, white-coat uncontrolled hypertension (WUCH), masked uncontrolled hypertension (MUCH) and elevated BP. Patients with renal failure with or without proteinuria were included in this multicenter observational study. Office BP was first measured by the physician using a self-monitoring BP device (three automatic readings), then by the patient at home (morning and evening) over 3 consecutive days. WUCH was defined as a systolic BP (SBP)/diastolic BP (DBP) ≥140/90 mmHg in the clinic and SBP/DBP<135/85 mmHg at home. MUCH was defined as SBP/DBP <140/90 mmHg in the clinic and SBP/DBP ≥135/85 mmHg at home. Among the 243 included subjects, data of 225 patients were analyzed. Mean estimated glomerular filtration rate was 37.7 ± 15.7 mL/min/1.73 m and mean office SBP/DBP was 154 ± 19/83 ± 13 mmHg. Mean office SBP/DBP was significantly higher than home SBP/DBP (+9.0 ± 15.1/+7.0 ± 10.0 mmHg, P < 0.01). Normal BP (office and home BP), WUCH, MUCH and elevated BP (office and home BP) rates were 12.0, 14.2, 6.7 and 67.1%, respectively. The patients were taking, on average, 2.8 ± 1.5 antihypertensive drugs/day. BP control in patients with CKD was poor. Routine use of 'out-of-office' BP measurement, in addition to office BP by which we can identify patients with WUCH or MUCH, should be recommended based on the current findings.

Hemodynamic Activity and Connectivity of the Prefrontal Cortex by Using Functional Near-Infrared Spectroscopy during Color-Word Interference Test in Korean and English Language.

In daily living, people are challenged to focus on their goal while eliminating interferences. Specifically, this study investigated the pre-frontal cortex (PFC) activity while attention control was tested using the self-made color-word interference test (CWIT) with a functional near-infrared spectroscopy device (fNIRS). Among 11 healthy Korean university students, overall the highest scores were obtained in the congruent Korean condition 1 (CKC-1) and had the least vascular response (VR) as opposed to the incongruent Korean condition 2 (IKC-2). The individual’s automatic reading response caused less brain activation while IKC-2 involves color suppression. Across the three trials per each condition, no significant differences (SD) in scores and in VR since there was no intervention did. Meanwhile, SD was observed between CKC-1 and English Congruent Condition 3 (ECC-3) across trials. However, SD was only observed on the third trial of VR. In the connectivity analysis, right and left PFC are activated on ECC-3. In CKC-1 and IKC-2, encompassing dorsomedial and dorsolateral although CKC-1 has less connection and connectivity due to less brain activation as compared. Therefore, aside from VR, brain connectivity could be identified non-invasively using fNIRS without ionizing radiation and at low-cost.

The Screening of Hypertension in a Dental School: An insight into Dentist Role and Patients Drug Adherence. A Cross-Sectional Study

Objectives: We aim to screen the hypertension prevalence in a dental school in Egypt. Meanwhile, we aim to evaluate the role of dentist in early detection of hypertension and to investigate the patient’s adherence toward anti-hypertensive drugs. Methods: a cross-sectional study. The study was conducted at the Diagnostic Center, Faculty of Dentistry, Cairo University, Cairo, Egypt. This clinic carries out the overwhelming part of dental care in Egypt. All the patients aged 18 and older who admitted to the Diagnostic Center had their blood pressure measured before the dental examination. Blood pressure measurement was conducted by trained volunteer dental and medical students. Blood pressure diagnosis was based on the Seventh Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure (JNC 7) recommendations using an automatic blood pressure reading device (Omron M4®). Patients with elevated blood pressure were scheduled for a second confirmatory measurement. Hypertension prevalence in a dental educational hospital. Results: The overall hypertension prevalence was 17.1 % and the prevalence was 17.4 % in males and 16.9 % in females. 14.9 % of hypertensive patients were not known to be hypertensive and were newly discovered as hypertensive when blood pressure measurement was done. 40.2 % of hypertensive were noncompliant with their antihypertensive medications. Conclusions: Dental patient screening for hypertension has the potential to benefit public health outcomes, by identifying patients with hypertension, and allowing for earlier intervention.