Dataset Information

A Deep Learning System for Recognizing and Recovering Contaminated Slider Serial Numbers in Hard Disk Manufacturing Processes.

ABSTRACT: This paper outlines a system for detecting printing errors and misidentifications on hard disk drive sliders, which may contribute to shipping tracking problems and incorrect product delivery to end users. A deep-learning-based technique is proposed for determining the printed identity of a slider serial number from images captured by a digital camera. Our approach starts with image preprocessing methods that deal with differences in lighting and printing positions and then progresses to deep learning character detection based on the You-Only-Look-Once (YOLO) v4 algorithm and finally character classification. For character classification, four convolutional neural networks (CNN) were compared for accuracy and effectiveness: DarkNet-19, EfficientNet-B0, ResNet-50, and DenseNet-201. Experimenting on almost 15,000 photographs yielded accuracy greater than 99% on four CNN networks, proving the feasibility of the proposed technique. The EfficientNet-B0 network outperformed highly qualified human readers with the best recovery rate (98.4%) and fastest inference time (256.91 ms).

SUBMITTER: Chousangsuntorn C

PROVIDER: S-EPMC8472306 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Deep Learning System for Recognizing and Recovering Contaminated Slider Serial Numbers in Hard Disk Manufacturing Processes.

Chousangsuntorn Chousak C Tongloy Teerawat T Chuwongin Santhad S Boonsang Siridech S

Sensors (Basel, Switzerland) 20210918 18

This paper outlines a system for detecting printing errors and misidentifications on hard disk drive sliders, which may contribute to shipping tracking problems and incorrect product delivery to end users. A deep-learning-based technique is proposed for determining the printed identity of a slider serial number from images captured by a digital camera. Our approach starts with image preprocessing methods that deal with differences in lighting and printing positions and then progresses to deep le ...[more]

PMID: 34577468

Similar Datasets

Project description:The chemical footprint (ChF), which combines life cycle assessment (LCA) and quantitative risk assessment principles, shows promise for exploring localized toxicity impacts of manufacturing processes, which is not achievable with LCA alone. An updated ChF method was applied to the global annual production of a hard disk drive (HDD) rare-earth element (REE) magnet assembly, assuming a supply chain in East and Southeast Asia. Existing REE magnet assembly LCA inventories were combined with supplier manufacturing locations to create a cradle-to-gate spatial unit process inventory. Emissions from the electricity grid for each manufacturing site were downscaled to hydrobasins of interest using the Global Power Plant Database. The predicted no effect concentration (PNEC) was chosen as the ecotoxicity pollution boundary to determine the threshold for dilution of each chemical of concern (CoC) and to calculate the ChF. Finally, a high-resolution hydrological database provided volumes of the freshwater river reach draining each hydrobasin and was used to calculate the dilution capacity (DC), that is, the volume required to remain at or below the PNEC for each CoC. The total ChF of annual REE magnet assembly production was 6.91E12 m3 , with hotspots in watersheds in China and Thailand where REEs are processed and steel metalworking takes place. Metals were the primary CoCs, with cadmium and chromium(VI) comprising 77% of total ChF. Dilution factors ranged from 5E-09 to 9E + 03 of the DC of the waterbody, reflecting the spatial variability in both emissions and DC. An advanced ChF method was demonstrated for HDD REE magnets. Scoping is a key step required to reduce model complexity. The use of regionalized fate factors and standardized hydrological data sets improves the comparability of ChFs across hydrobasins. Additional work to combine data sets into readily available tools is needed to increase usability and standardization of the ChF method and promote wider adoption. Integr Environ Assess Manag 2023;19:272-283. © 2022 The Authors. Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC).

Project description:Epithelial tissues have sparse stroma, in contrast to their corresponding tumours. The effect of cancer cells on stromal cells is well recognized. Increasingly, stromal components, such as endothelial and immune cells, are considered indispensable for cancer progression. The role of desmoplastic stroma, in contrast, is poorly understood. Targeting such cellular components within the tumour is attractive. Recent evidence strongly points towards a dynamic stromal cell participation in cancer progression that impacts patient prognosis. The role of specific desmoplastic stromal cells, such as stellate cells and myofibroblasts in pancreatic, oesophageal and skin cancers, was studied in bio-engineered, physiomimetic organotypic cultures and by regression analysis. For pancreatic cancer, the maximal effect on increasing cancer cell proliferation and invasion, as well as decreasing cancer cell apoptosis, occurs when stromal (pancreatic stellate cells) cells constitute the majority of the cellular population (maximal effect at a stromal cell proportion of 0.66-0.83), accompanied by change in expression of key molecules such as E-cadherin and ?-catenin. Gene-expression microarrays, across three tumour types, indicate that stromal cells consistently and significantly alter global cancer cell functions such as cell cycle, cell-cell signalling, cell movement, cell death and inflammatory response. However, these changes are mediated through cancer type-specific alteration of expression, with very few common targets across tumour types. As highlighted by these in vitro data, the reciprocal relationship of E-cadherin and polymeric immunoglobulin receptor (PIGR) expression in cancer cells could be shown, in vivo, to be dependent on the stromal content of human pancreatic cancer. These studies demonstrate that context-specific cancer-stroma crosstalk requires to be precisely defined for effective therapeutic targeting. These data may be relevant to non-malignant processes where epithelial cells interact with stromal cells, such as chronic inflammatory and fibrotic conditions.

Project description:BackgroundEnvironmental monitoring of bacterial pathogens is critical for disease control in coastal marine ecosystems to maintain animal welfare and ecosystem function and to prevent significant economic losses. This requires accurate taxonomic identification of environmental bacterial pathogens, which often cannot be achieved by commonly used genetic markers (e.g., 16S rRNA gene), and an understanding of their pathogenic potential based on the information encoded in their genomes. The decreasing costs of whole genome sequencing (WGS), combined with newly developed bioinformatics tools, now make it possible to unravel the full potential of environmental pathogens, beyond traditional microbiological approaches. However, obtaining a high-quality bacterial genome, requires initial cultivation in an axenic culture, which is a bottleneck in environmental microbiology due to cross-contamination in the laboratory or isolation of non-axenic strains.ResultsWe applied WGS to determine the pathogenic potential of two Vibrio isolates from coastal seawater. During the analysis, we identified cross-contamination of one of the isolates and decided to use this dataset to evaluate the possibility of bioinformatic contaminant removal and recovery of bacterial genomes from a contaminated culture. Despite the contamination, using an appropriate bioinformatics workflow, we were able to obtain high quality and highly identical genomes (Average Nucleotide Identity value 99.98%) of one of the Vibrio isolates from both the axenic and the contaminated culture. Using the assembled genome, we were able to determine that this isolate belongs to a sub-lineage of Vibrio campbellii associated with several diseases in marine organisms. We also found that the genome of the isolate contains a novel Vibrio plasmid associated with bacterial defense mechanisms and horizontal gene transfer, which may offer a competitive advantage to this putative pathogen.ConclusionsOur study shows that, using state-of-the-art bioinformatics tools and a sufficient sequencing effort, it is possible to obtain high quality genomes of the bacteria of interest and perform in-depth genomic analyses even in the case of a contaminated culture. With the new isolate and its complete genome, we are providing new insights into the genomic characteristics and functional potential of this sub-lineage of V. campbellii. The approach described here also highlights the possibility of recovering complete bacterial genomes in the case of non-axenic cultures or obligatory co-cultures.

Dataset Information

A Deep Learning System for Recognizing and Recovering Contaminated Slider Serial Numbers in Hard Disk Manufacturing Processes.

Publications

A Deep Learning System for Recognizing and Recovering Contaminated Slider Serial Numbers in Hard Disk Manufacturing Processes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets