Investigating a Machine Learning Approach to Predicting White Pixel Defects in Wafers-A Case Study of Wafer Fabrication Plant F.

CMOS image sensor (CIS) semiconductor products are integral to mobile phones and photographic devices, necessitating ongoing enhancements in efficiency and quality for superior photographic outcomes. The presence of white pixels serves as a crucial metric for assessing CIS product performance, primarily arising from metal impurity contamination during the wafer production process or from defects introduced by the grinding blade process. While immediately addressing metal impurity contamination during production presents challenges, refining the handling of defects attributed to grinding blade processing can notably mitigate white pixel issues in CIS products. This study zeroes in on silicon wafer manufacturers in Taiwan, analyzing white pixel defects reported by customers and leveraging machine learning to pinpoint and predict key factors leading to white pixel defects from grinding blade operations. Such pioneering practical studies are rare. The findings reveal that the classification and regression tree (CART) and random forest (RF) models deliver the most accurate predictions (95.18%) of white pixel defects caused by grinding blade operations in a default parameter setting. The analysis further elucidates critical factors like grinding load and torque, vital for the genesis of white pixel defects. The insights garnered from this study aim to arm operators with proactive measures to diminish the potential for customer complaints.

Infodemiology of Influenza-like Illness: Utilizing Google Trends' Big Data for Epidemic Surveillance.

Background: Influenza-like illness (ILI) encompasses symptoms similar to influenza, affecting population health. Surveillance, including Google Trends (GT), offers insights into epidemic patterns. Methods: This study used multiple regression models to analyze the correlation between ILI incidents, GT keyword searches, and climate variables during influenza outbreaks. It compared the predictive capabilities of time-series and deep learning models against ILI emergency incidents. Results: The GT searches for "fever" and "cough" were significantly associated with ILI cases (p < 0.05). Temperature had a more substantial impact on ILI incidence than humidity. Among the tested models, ARIMA provided the best predictive power. Conclusions: GT and climate data can forecast ILI trends, aiding governmental decision making. Temperature is a crucial predictor, and ARIMA models excel in forecasting ILI incidences.

Analyzing Monthly Blood Test Data to Forecast 30-Day Hospital Readmissions among Maintenance Hemodialysis Patients.

Background: The increase in the global population of hemodialysis patients is linked to aging demographics and the prevalence of conditions such as arterial hypertension and diabetes mellitus. While previous research in hemodialysis has mainly focused on mortality predictions, there is a gap in studies targeting short-term hospitalization predictions using detailed, monthly blood test data. Methods: This study employs advanced data preprocessing and machine learning techniques to predict hospitalizations within a 30-day period among hemodialysis patients. Initial steps include employing K-Nearest Neighbor (KNN) imputation to address missing data and using the Synthesized Minority Oversampling Technique (SMOTE) to ensure data balance. The study then applies a Support Vector Machine (SVM) algorithm for the predictive analysis, with an additional enhancement through ensemble learning techniques, in order to improve prediction accuracy. Results: The application of SVM in predicting hospitalizations within a 30-day period among hemodialysis patients resulted in an impressive accuracy rate of 93%. This accuracy rate further improved to 96% upon incorporating ensemble learning methods, demonstrating the efficacy of the chosen machine learning approach in this context. Conclusions: This study highlights the potential of utilizing machine learning to predict hospital readmissions within a 30-day period among hemodialysis patients based on monthly blood test data. It represents a significant leap towards precision medicine and personalized healthcare for this patient group, suggesting a paradigm shift in patient care through the proactive identification of hospitalization risks.

Earthquake-enhanced dissolved carbon cycles in ultra-deep ocean sediments.

Hadal trenches are unique geological and ecological systems located along subduction zones. Earthquake-triggered turbidites act as efficient transport pathways of organic carbon (OC), yet remineralization and transformation of OC in these systems are not comprehensively understood. Here we measure concentrations and stable- and radiocarbon isotope signatures of dissolved organic and inorganic carbon (DOC, DIC) in the subsurface sediment interstitial water along the Japan Trench axis collected during the IODP Expedition 386. We find accumulation and aging of DOC and DIC in the subsurface sediments, which we interpret as enhanced production of labile dissolved carbon owing to earthquake-triggered turbidites, which supports intensive microbial methanogenesis in the trench sediments. The residual dissolved carbon accumulates in deep subsurface sediments and may continue to fuel the deep biosphere. Tectonic events can therefore enhance carbon accumulation and stimulate carbon transformation in plate convergent trench systems, which may accelerate carbon export into the subduction zones.

Optimizing the Quality of Machine Learning for Identifying the Share of Biogenic and Fossil Carbon in Solid Waste.

Insights into carbon sources (biogenic and fossil carbon) and contents in solid waste are vital for estimating the carbon emissions from incineration plants. However, the traditional methods are time-, labor-, and cost-intensive. Herein, high-quality data sets were established after analyzing the carbon contents and infrared spectra of substantial samples using elemental analysis and attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR), respectively. Then, five classification and eight regression machine learning (ML) models were evaluated to recognize the proportion of biogenic and fossil carbon in solid waste. Using the optimized data preprocessing approach, the random forest (RF) classifier with hyperparameter tuning ranked first in classifying the carbon group with a test accuracy of 0.969, and the carbon contents were successfully predicted by the RF regressor with R2 = 0.926 considering performance-interpretability-computation time competition. The above proposed algorithms were further validated with real environmental samples, which exhibited robust performance with an accuracy of 0.898 for carbon group classification and an R2 value of 0.851 for carbon content prediction. The reliable results indicate that ATR-FTIR coupled with ML algorithms is feasible for rapidly identifying both carbon groups and content, facilitating the calculation and assessment of carbon emissions from solid waste incineration.

An International Federal Hyperledger Fabric Verification Framework for Digital COVID-19 Vaccine Passport.

The COVID-19 virus has been spreading worldwide on a large scale since 2019, and the most effective way to prevent COVID-19 is to vaccinate. In order to prove that vaccination has been administered to allow access to different areas, paper vaccine passports are produced. However, paper vaccine passport records are vulnerable to counterfeiting or abuse. Previous research has suggested that issuing certificates digitally is an easier way to verify them. This study used the consortium blockchain based on Hyperledger Fabric to upload the digital vaccine passport (DVP) to the blockchain network. In order to enable collaboration across multiple systems, networks, and organizations in different trust realms. Federated Identity Management is considered a promising approach to facilitate secure resource sharing between collaborating partners. Therefore, the international federal identity management architecture proposed in this study enables inspectors in any country to verify the authenticity of the DVP of incoming passengers using the consortium blockchain. Through practical construction, the international federal Hyperledger verification framework for the DVP proposed in this study has shown the feasibility of issuing a global DVP in safety analysis and efficacy testing.

Dysarthria Speech Detection Using Convolutional Neural Networks with Gated Recurrent Unit.

In recent years, due to the rise in the population and aging, the prevalence of neurological diseases is also increasing year by year. Among these patients with Parkinson's disease, stroke, cerebral palsy, and other neurological symptoms, dysarthria often appears. If these dysarthria patients are not quickly detected and treated, it is easy to cause difficulties in disease course management. When the symptoms worsen, they can also affect the patient's psychology and physiology. Most of the past studies on dysarthria detection used machine learning or deep learning models as classification models. This study proposes an integrated CNN-GRU model with convolutional neural networks and gated recurrent units to detect dysarthria. The experimental results show that the CNN-GRU model proposed in this study has the highest accuracy of 98.38%, which is superior to other research models.

Cluster Analysis of US COVID-19 Infected States for Vaccine Distribution.

Since December 2019, COVID-19 has been raging worldwide. To prevent the spread of COVID-19 infection, many countries have proposed epidemic prevention policies and quickly administered vaccines, However, under facing a shortage of vaccines, the United States did not put forward effective epidemic prevention policies in time to prevent the infection from expanding, resulting in the epidemic in the United States becoming more and more serious. Through "The COVID Tracking Project", this study collects medical indicators for each state in the United States from 2020 to 2021, and through feature selection, each state is clustered according to the epidemic's severity. Furthermore, through the confusion matrix of the classifier to verify the accuracy of the cluster analysis, the study results show that the Cascade K-means cluster analysis has the highest accuracy. This study also labeled the three clusters of the cluster analysis results as high, medium, and low infection levels. Policymakers could more objectively decide which states should prioritize vaccine allocation in a vaccine shortage to prevent the epidemic from continuing to expand. It is hoped that if there is a similar epidemic in the future, relevant policymakers can use the analysis procedure of this study to determine the allocation of relevant medical resources for epidemic prevention according to the severity of infection in each state to prevent the spread of infection.

Porous Supramolecular Assembly of Pentiptycene-Containing Gold(I) Complexes: Persistent Excited-State Aurophilicity and Inclusion-Induced Emission Enhancement.

We report herein a porous supramolecular framework formed by a linear mononuclear Au(I) complex (1) via the tongue-and-groove-like joinery between the pentiptycene U-cavities (grooves) and the rod-shaped π-conjugated backbone and alkyl chains (tongues) with the assistance of C-H···π and aurophilic interactions. The framework contains distorted tetrahedral Au4 units, which undergo stepwise and persistent photoinduced Au(I)-Au(I) bond shortening (excited-state aurophilicity), leading to multicolored luminescence photochromism. The one-dimensional pore channels could accommodate different solvates and guests, and the guest inclusion-induced luminescence enhancement (up to 300%) and/or vapochromism are characterized. A correlation between the aurophilic bonding and the luminescence activity is uncovered by TDDFT calculations. Isostructural derivatives 2 and 3 corroborate both the robustness of the porous supramolecular assembly and the mechanisms of the stimulation-induced luminescence properties of 1. This work demonstrates the cooperation of aurophilicity and structural porosity and adaptability in achieving novel supramolecular photochemical properties.

Repercussions of clinical waste co-incineration in municipal solid waste incinerator during COVID-19 pandemic.

During coronavirus disease 2019 pandemic, the exponential increase in clinical waste (CW) generation has caused immense burden to CW treatment facilities. Co-incineration of CW in municipal solid waste incinerator (MSWI) is an emergency treatment method. A material flow model was developed to estimate the change in feedstock characteristics and resulting acid gas emission under different CW co-incineration ratios. The ash contents and lower heating values of the feedstocks, as well as HCl concentrations in flue gas showed an upward trend. Subsequently, 72 incineration residue samples were collected from a MSWI performing co-incineration (CW ratio <10 wt%) in Wuhan city, China, followed by 20 incineration residues samples from waste that were not co-incineration. The results showed that the contents of major elements and non-volatile heavy metals in the air pollution control residues increased during co-incineration but were within the reported ranges, whereas those in the bottom ashes revealed no significant changes. The impact of CW co-incineration at a ratio <10 wt% on the distribution of elements in the incineration residues was not significant. However, increase in alkali metals and HCl in flue gas may cause potential boiler corrosion. These results provide valuable insights into pollution control in MSWI during pandemic.

Ultra-Wideband Positioning Sensor with Application to an Autonomous Ultraviolet-C Disinfection Vehicle.

Due to the COVID-19 virus being highly transmittable, frequently cleaning and disinfecting facilities is common guidance in public places. However, the more often the environment is cleaned, the higher the risk of cleaning staff getting infected. Therefore, strong demand for sanitizing areas in automatic modes is undoubtedly expected. In this paper, an autonomous disinfection vehicle with an Ultraviolet-C (UVC) lamp is designed and implemented using an ultra-wideband (UWB) positioning sensor. The UVC dose for 90% inactivation of the reproductive ability of COVID-19 is 41.7 J/m2, which a 40 W UVC lamp can achieve within a 1.6 m distance for an exposure time of 30 s. With this UVC lamp, the disinfection vehicle can effectively sterilize in various scenarios. In addition, the high-accuracy UWB positioning system, with the time difference of arrival (TDOA) algorithm, is also studied for autonomous vehicle navigation in indoor environments. The number of UWB tags that use a synchronization protocol between UWB anchors can be unlimited. Moreover, this proposed Gradient Descent (GD), which uses Taylor method, is a high-efficient algorithm for finding the optimal position for real-time computation due to its low error and short calculating time. The generalized traversal path planning procedure, with the edge searching method, is presented to improve the efficiency of autonomous navigation. The average error of the practical navigation demonstrated in the meeting room is 0.10 m. The scalability of the designed system to different application scenarios is also discussed and experimentally demonstrated. Hence, the usefulness of the proposed UWB sensor applied to UVC disinfection vehicles to prevent COVID-19 infection is verified by employing it to sterilize indoor environments without human operation.

Design of a Spark Big Data Framework for PM2.5 Air Pollution Forecasting.

In recent years, with rapid economic development, air pollution has become extremely serious, causing many negative effects on health, environment and medical costs. PM2.5 is one of the main components of air pollution. Therefore, it is necessary to know the PM2.5 air quality in advance for health. Many studies on air quality are based on the government's official air quality monitoring stations, which cannot be widely deployed due to high cost constraints. Furthermore, the update frequency of government monitoring stations is once an hour, and it is hard to capture short-term PM2.5 concentration peaks with little warning. Nevertheless, dealing with short-term data with many stations, the volume of data is huge and is calculated, analyzed and predicted in a complex way. This alleviates the high computational requirements of the original predictor, thus making Spark suitable for the considered problem. This study proposes a PM2.5 instant prediction architecture based on the Spark big data framework to handle the huge data from the LASS community. The Spark big data framework proposed in this study is divided into three modules. It collects real time PM2.5 data and performs ensemble learning through three machine learning algorithms (Linear Regression, Random Forest, Gradient Boosting Decision Tree) to predict the PM2.5 concentration value in the next 30 to 180 min with accompanying visualization graph. The experimental results show that our proposed Spark big data ensemble prediction model in next 30-min prediction has the best performance (R2 up to 0.96), and the ensemble model has better performance than any single machine learning model. Taiwan has been suffering from a situation of relatively poor air pollution quality for a long time. Air pollutant monitoring data from LASS community can provide a wide broader monitoring, however the data is large and difficult to integrate or analyze. The proposed Spark big data framework system can provide short-term PM2.5 forecasts and help the decision-maker to take proper action immediately.

An Azure ACES Early Warning System for Air Quality Index Deteriorating.

With the development of industrialization and urbanization, air pollution in many countries has become more serious and has affected people's health. The air quality has been continuously concerned by environmental managers and the public. Therefore, accurate air quality deterioration warning system can avoid health hazards. In this study, an air quality index (AQI) warning system based on Azure cloud computing platform is proposed. The prediction model is based on DFR (Decision Forest Regression), NNR (Neural Network Regression), and LR (Linear Regression) machine learning algorithms. The best algorithm was selected to calculate the 6 pollutants required for the AQI calculation of the air quality monitoring in real time. The experimental results show that the LR algorithm has the best performance, and the method of this study has a good prediction on the AQI index warning for the next one to three hours. Based on the ACES system proposed, it is hoped that it can prevent personal health hazards and help to reduce medical costs in public.

Vigilance-related attention systems subserve the discrimination of relative intensity differences between painful stimuli.

Humans require the ability to discriminate intensities of noxious stimuli to avoid future harm. This discrimination process seems to be biased by an individual's attention to pain and involves modulation of the relative intensity differences between stimuli (ie, Weber fraction). Here, we ask whether attention networks in the brain modulate the discrimination process and investigate the neural correlates reflecting the Weber fraction for pain intensity. In a delayed discrimination task, participants differentiated the intensity of 2 sequentially applied stimuli after a delay interval. Compared with nonpain discrimination, pain discrimination performance was modulated by participants' vigilance to pain, which was reflected by the functional connectivity between the left inferior parietal lobule and the right thalamus. Of note, this vigilance-related functional coupling specifically predicted participants' behavioral ability to differentiate pain intensities. Moreover, unique to pain discrimination tasks, the response in the right superior frontal gyrus linearly represented the Weber fraction for pain intensity, which significantly biased participants' pain discriminability. These findings suggest that pain intensity discrimination in humans relies on vigilance-related enhancement in the parieto-thalamic attention network, thereby allowing the prefrontal cortex to estimate the relative intensity differences between noxious stimuli.

Fluorescent Probe Encapsulated in SNAP-Tag Protein Cavity To Eliminate Nonspecific Fluorescence and Increase Detection Sensitivity.

Despite the promising improvements made recently on fluorescence probes for the detection of enzymes and reactive small molecules, two fundamental problems remain: weaker fluorescence of many dyes in aqueous buffers and strong nonspecific signals in samples containing high protein levels. In this paper, we introduce a novel fluorescent probe encapsulated in protein cavity (FPEPC) concept as demonstrated by SNAP-tag protein and three environment-sensitive fluorescence probes to overcome these two problems. The probes were constructed by following the current probe design for enzymes and reactive small molecules but with an additional benzylguanine moiety for selective SNAP-tag conjugation. The SNAP-tag conjugated probes achieved quantitative nitroreductase and hydrogen sulfide detection in blood plasma, whereas analyte concentrations were overestimated up to 700-fold when bare fluorescent probes were employed for detection. Furthermore, detection sensitivity was increased dramatically, as our probes displayed 390-fold fluorescence enhancement upon SNAP-tag conjugation, in stark contrast to the weak fluorescence of the free probes in aqueous solutions. Compared with the conventional approaches where fluorescent probes are encapsulated into polymers and nanoparticles, our simple and general approach successfully overcame many key issues such as dye leakage, long preparation steps, inconsistent dye-host ratios, difficulty in constructing in situ in a complex medium, and limited application to detect only small metabolites.

Fluorescent Probe Encapsulated in Avidin Protein to Eliminate Nonspecific Fluorescence and Increase Detection Sensitivity in Blood Serum.

Quantitative detection of trace amounts of a biomarker in protein rich human blood plasma using fluorescent probes is a great challenge as the real signal is usually obscured by nonspecific fluorescence. This problem occurs because most of the fluorescent dyes bind very tightly with blood proteins to produce a large fluorescence increase, resulting in overestimation of the biomarker concentrations and false positive diagnosis. In this paper, we report that biotinylated fluorescent probes encapsulated in avidin protein can generate very specific fluorescence in blood serum by blocking out nonspecific dye-protein interactions. We applied our novel probe design to detect two different types of biomolecules, hydrogen sulfide and nitroreductase. Our Avidin conjugated probes achieved quantitative analyte detection in blood serum; whereas concentrations were overestimated up to 320-fold when bare fluorescent probes were employed. As compared to conventional approaches where fluorescent probes are encapsulated into polymers and nanoparticles, our simple approach successfully overcomes many key issues such as dye leakage, long preparation steps, inconsistent dye-host ratios, difficulty in constructing in situ in a complex medium, and limited application to detect only small metabolites.

Protein sensing in living cells by molecular rotor-based fluorescence-switchable chemical probes.

In this paper, we introduce a general design to construct fluorescence-switching probes by using conjugates of a fluorescent molecular rotor and protein specific ligands for the selective protein detection and real-time tracking of protein degradation in living cells. Upon the interaction of the ligand with the protein ligand-binding domain, the crowded surroundings restrict the bond rotation of the fluorescent molecular rotor to trigger the emission of a strong fluorescence signal, which is reduced upon the addition of a competitive ligand or after protein degradation. With this probe design, two fluorescent probes for MGMT and hCAII proteins were constructed and applied for detecting the endogenous proteins in living cells. In addition, real-time degradation kinetics of the alkylated-MGMT at the single living cell level were revealed for the first time. We believe that this fluorescence-switching probe design can possibly be extended for the analysis of other proteins, for which there are still no effective tools to visualize them in living cells.

Accumulation and elimination of polychlorinated dibenzo-p-dioxins and dibenzofurans in mule ducks.

In Taiwan, a food safety crisis involving a presence of high concentrations of dioxin residues in duck eggs occurred in 2004. The dioxin content in duck meat sampled from supermarkets was also reported to be substantially higher than in products from other farm animals. Despite increased awareness of the potential for contamination and exposure to dioxins, the accumulation and elimination of dioxins in ducks have not been well characterized. In the present study, mule ducks were fed capsules containing polychlorinated dibenzo-p-dioxins and dibenzofurans (PCDD/Fs) for 14 days and the trial was continued for another 28 days without PCDD/Fs supplementation. Ducks were sacrificed on the 14th, 28th, and 42nd days from the beginning of administration and samples of abdominal fat, breast, and liver tissue were obtained. The concentrations of PCDD/Fs were analyzed in the samples to investigate their distribution and elimination in various duck tissues. The bioaccumulation of PCDD/Fs in ducks was found to be tissue-dependent. In the abdominal fat, the bioconcentration factor was negatively correlated with the degree of chlorination. Conversely, more chlorinated PCDD/Fs (hexa- or hepta-congeners) were associated with higher bioconcentration in the liver and breast tissue. In terms of the efficiency of PCDD/Fs elimination, the liver was found to be the fastest, followed by the breast and the abdominal fat. The clearance rate positively correlated with the degree of chlorination, as determined by comparing the apparent elimination rate constant (k) of PCDD/Fs in various tissues. Overall, lower k values observed in this study imply that mule ducks have a reduced clearance of PCDD/Fs in comparison with layer and broiler chickens.