Support vector regression model for flight demand forecasting

Flight demand forecasting is a particularly critical component for airline revenue management because of the direct influence on the booking limits that determine airline profits. The traditional flight demand forecasting models generally only take day of the week (DOW) and the current data collection point (DCP) adds up bookings as the model input and uses linear regression, exponential smoothing, pick-up as well as other models to predict the final bookings of flights. These models can be regarded as time series flight demand forecasting models based on the interval between the current date and departure date. They fail to consider the early bookings change features in the specific flight pre-sale period, and have weak generalization ability, at last, they will lead to poor adaptability to the random changes of flight bookings. The support vector regression (SVR) model, which is derived from machine learning, has strong adaptability to nonlinear random changes of data and can adaptively learn the random disturbances of flight bookings. In this paper, flight bookings are automatically divided into peak, medium, and off (PMO) according to the season attribute. The SVR model is trained by using the vector composed of historical flight bookings and adding up bookings of DCP in the early stage of the flight pre-sale period. Compared with the traditional models, the priori information of flight is increased. We collect 2 years of domestic route bookings data of an airline in China before COVID-19 as the training and testing datasets, and divide these data into three categories: tourism, business, and general, the numerical results show that the SVR model significantly improves the forecasting accuracy and reduces RMSE compared with the traditional models. Therefore, this study provides a better choice for flight demand forecasting.

Potential Mechanism of Colchicine against COVID-19 and Non-Small Cell Lung Cancer based on Network Pharmacology and Bioinformatics Analysis

Colchicine is an alkaloid with antitumor effect isolated from Colchicum autumnale plants, it has been reported in multiple studies as a potential treatment for coronavirus disease-19 and this study applied network pharmacology and bioinformatics analysis to explore the potential mechanism of colchicine against non-small cell lung cancer and coronavirus disease-19. The R software was used to determine the differentially expressed genes of non-small cell lung cancer/coronavirus disease-19, and carry out prognostic analysis and clinical analysis of the differentially expressed genes, the targets of colchicine were obtained from various databases, the protein-protein interaction network of intersection targets of colchicine and non-small cell lung cancer/coronavirus disease-19 was constructed, enrichment analysis of gene ontology and kyoto encyclopedia of genes and genomes pathways was performed by Metascape database and the molecular docking and molecular dynamics simulation were completed. We obtained a total of 716 differentially expressed genes and identified 13 potential prognostic genes associated with the clinical characterization of non-small cell lung cancer/coronavirus disease-19 patients. C-C motif chemokine ligand 2, toll like receptor 4, intercellular adhesion molecule 1, peroxisome proliferator activated receptor gamma, interleukin 17A, interferon gamma, angiotensin I converting enzyme, fos proto-oncogene, nuclear factor kappa B inhibitor alpha, TIMP metallopeptidase inhibitor 1 and secreted phosphoprotein 1 were core targets. The intersection targets of colchicine and non-small cell lung cancer/coronavirus disease-19 were mainly enriched in biological processes such as inflammatory response, response to cytokine and response to lipopolysaccharide, as well as signal pathways such as interleukin 17 signaling pathway, hypoxia inducible factor 1 signaling pathway and nucleotide binding oligomerization domain-like receptor signaling pathway. The results of molecular docking showed that the colchicine is better combined with the core targets. Analysis of molecular dynamics simulation showed that the protein and ligand form a stabilizing effect. Based on bioinformatics analysis and network pharmacology, we obtained biomarkers that may be used for the prognosis of non-small cell lung cancer/coronavirus disease-19 patients and revealed that colchicine may play a potential role in the treatment of non-small cell lung cancer/coronavirus disease-19 by regulating multiple targets and multiple signaling pathways and participating in multiple biological processes.

Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning

Optimising HVAC operations towards human wellness and energy efficiency is a major challenge for smart facilities management, especially amid COVID situations. Although IoT sensors and deep learning were applied to support HVAC operations, the loss of forecasting accuracy in recursive prediction largely hinders their applications. This study presents a data-driven predictive control method with time-series forecasting (TSF) and reinforcement learning (RL), to examine various sensor metadata for HVAC system optimisation. This involves the development and validation of 16 Long Short-Term Memory (LSTM) based architectures with bi-directional processing, convolution, and attention mechanisms. The TSF models are comprehensively evaluated under independent, short-term recursive, and long-term recursive prediction scenarios. The optimal TSF models are integrated with a Soft Actor-Critic RL agent to analyse sensor metadata and optimise HVAC operations, achieving 17.4% energy savings and 16.9% thermal comfort improvement in the surrogate environment. The results show that recursive prediction leads to a significant reduction in model accuracy, and the effect is more pronounced in the temperature-humidity prediction model. The attention mechanism significantly improves prediction performance in both recursive and independent prediction scenarios. This study contributes new data-driven methods for smart HVAC operations in IoT-enabled intelligent buildings towards a human-centric built environment. © 2023 The Authors

Assessing the Impact of the Covid-19 on the US Airline Market Using an Instrumental Variable and a DID Empirical Strategy

In this paper, we examine the affects of COVID-19 and related policies on the aviation industry. Using archival data from the John Hopkins Coronavirus Resource Center, Department of Transportation Statistics, and the COVID-19 U.S. State Policy database, and an instrumental variable and a difference-in-differences empirical strategy, we find that COVID-19 severity is negatively correlated with both the mean ticket price and the number of passengers for the four major airlines in the US, and that the implementation of COVID-19 control policies is positively correlated with the mean ticket price, while negatively correlated with the number of passengers. © 2022 ACM.

Discussion and Practice of Online and Offline Mixed Teaching of Track and Field Course Based on OBE Concept

The emergence of the "Internet plus education” program has provided an opportunity. In recent years, the government has issued relevant documents in succession, so as to create a new mode of training talents that is suitable for the times and share high-quality educational resources. Especially during the epidemic period of New Coronavirus pneumonia, the online and offline teaching mode plays a vital role in the teaching process of colleges and universities. However, the development of online and offline hybrid teaching is not perfect, which needs further research and continuous improvement by scholars. In response to the implementation of the national "Internet plus education” program, reforming the traditional physical education teaching mode, improving the learning efficiency of students and promoting the development of students' personality, this paper, based on the OBE concept, takes the construction of online and offline blended teaching mode in track and field as the research object. Through the investigation and analysis of the current situation of traditional physical education teaching and the feasibility of online and offline mixed teaching mode of track and field course, this paper provides a basis for the construction and application strategy of online and offline mixed teaching mode of track and field course. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

RNAi Degrades the SARS-CoV-2 Spike Protein RNA for Developing Drugs to Treat COVID-19

COVID-19 is caused by severe acute respiratory SARS-CoV-2. Regardless of the availability of treatment strategies for COVID-19, effective therapy will remain essential. A promising approach to tackle the SARS-CoV-2 could be small interfering (si) RNAs. Here we designed the small hairpin RNA (named as shRNA688) for targeting the prepared 813 bp Est of the S protein genes (Delta). The conserved and mutated regions of the S protein genes from the genomes of the SARS-CoV-2 variants in the public database were analyzed. A 813 bp fragment encoding the most part of the RBD and partial downstream RBD of the S protein was cloned into the upstream red florescent protein gene (RFP) as a fusing gene in the pCMV-S-Protein RBD-Est-RFP plasmid for expressing a potential target for RNAi. The double stranded of the DNA encoding for shRNA688 was constructed in the downstream human H1 promoter of the plasmid in which CMV promoter drives enhanced green fluorescent protein (EGFP) marker gene expression. These two kinds of the constructed plasmids were co-transfected into HEK293T via Lipofectamine 2000. The degradation of the transcripts of the SARS-CoV-2 S protein fusing gene expressed in the transfected HEK293T treated by RNAi was analyzed by RT-qPCR with a specific probe of the targeted SARS-CoV-2 S protein gene transcripts. Our results showed that shRNA688 targeting the conserved region of the S protein genes could effectively reduce the transcripts of the S protein genes. This study provides a cell model and technical support for the research and development of the broad-spectrum small nucleic acid RNAi drugs against SARS-CoV-2 or the RNAi drugs for the other hazard viruses which cause human diseases. Copyright © Weiwei Zhang, Linjia Huang, Jumei Huang, Xin Jiang, Xiaohong Ren, Xiaojie Shi, Ling Ye, Shuhui Bian, Jianhe Sun, Yufeng Gao, Zehua Hu, Lintin Guo, Suyan Chen, Jiahao Xu, Jie Wu, Jiwen Zhang, Daxiang Cui, and Fangping Dai.

Durvalumab (D) +/- tremelimumab (T) + chemotherapy (CT) in 1L metastatic (m) NSCLC: Overall survival (OS) update from POSEIDON after median follow-up (mFU) of approximately 4 years (y)

Background: In the Phase 3 POSEIDON study, 1L T+D+CT demonstrated statistically significant improvements in PFS and OS (OS HR 0.77;95% CI 0.65-0.92;p=0.0030;mFU 34.9 mo in censored pts) vs CT alone in pts with mNSCLC. D+CT showed a statistically significant improvement in PFS and a positive trend for OS improvement vs CT that did not reach significance (OS HR 0.86;95% CI 0.72-1.02;p=0.0758). Here we report an updated exploratory analysis of OS, and histology and mutational status subgroups, after a mFU of ~4 y. Method(s): Pts with EGFR/ALK wild-type mNSCLC were randomised 1:1:1 to 1L D (until progression) +/- limited-course T (up to 5 doses) + platinum-based CT (up to 4 cycles);or CT (up to 6 cycles). Alpha-controlled endpoints were PFS and OS for D+CT vs CT and T+D+CT vs CT. Pt tumours were molecularly characterised via sequencing of tissue and/or ctDNA samples. Result(s): At an updated data cutoff (DCO) of 11 Mar 2022 (mFU 46.5 mo in censored pts), T+D+CT continued to show OS benefit vs CT (HR 0.75;95% CI 0.63-0.88) with an estimated 25.0% of pts alive at 3 y vs 13.6% (Table). D+CT continued to numerically improve OS vs CT (HR 0.84;95% CI 0.71-0.99;3 y OS 20.7%). Consistent with results at the earlier DCO, OS benefit appeared more pronounced with T+D+CT vs CT in pts with non-squamous (than squamous;data will be presented) histology. A trend for OS benefit with T+D+CT vs CT continued to be observed in non-squamous subgroups with mutations (m) in STK11 (Table), KEAP1 or KRAS (data will be presented). No new safety signals were identified based on collection of serious AEs during long-term FU. [Formula presented] Conclusion(s): The results of this exploratory analysis from POSEIDON, after mFU of ~4 y, demonstrate the durable long-term OS benefit of adding a limited course of T to D and 4 cycles of CT. These data support the use of this regimen as a 1L treatment option for pts with mNSCLC, including harder-to-treat mutational subgroups such as STK11m, KEAP1m or KRASm. Clinical trial identification: NCT03164616 (release date: 23 May 2017). Editorial acknowledgement: Medical writing support for the development of this , under the direction of the authors, was provided by James Holland, PhD, of Ashfield MedComms (Macclesfield, UK), an Inizio company, and was funded by AstraZeneca. Legal entity responsible for the study: AstraZeneca PLC. Funding(s): AstraZeneca. Disclosure: B.C. Cho: Financial Interests, Personal, Advisory Board: KANAPH Therapeutic Inc, Brigebio therapeutics, Cyrus therapeutics, Guardant Health, Oscotec Inc;Financial Interests, Personal, Member of the Board of Directors: Interpark Bio Convergence Corp., J INTS BIO;Financial Interests, Personal, Stocks/Shares: TheraCanVac Inc, Gencurix Inc, Bridgebio therapeutics, KANAPH Therapeutic Inc, Cyrus therapeutics, Interpark Bio Convergence Corp, J INTS BIO;Financial Interests, Personal, Royalties: Champions Oncology;Financial Interests, Personal, Research Grant: Novartis, Bayer, AstraZeneca, MOGAM Institute, Dong-A ST, Champions Oncology, Janssen, Yuhan, Ono, Dizal Pharma, MSD, AbbVie, Medpacto, GIInnovation, Eli Lilly, Blueprint medicines, Interpark Bio Convergence Corp;Financial Interests, Personal, Advisory Role, Consulting: Novartis, AstraZeneca, Boehringer Ingelheim, Roche, BMS, Ono, Yuhan, Pfizer, Eli Lilly, Janssen, Takeda, MSD, Janssen, Medpacto, Blueprint medicines;Financial Interests, Personal, Other: DAAN Biotherapeutics. J.A. Alatorre Alexander: Financial Interests, Personal, Speaker's Bureau: BMS, Roche, AstraZeneca, MSD, Boehringer Ingelheim, Takeda, Eli Lilly, Janssen;Financial Interests, Personal, Advisory Board: BMS, Roche, AstraZeneca, MSD, Boehringer Ingelheim, Takeda, Eli Lilly, Janssen. S. Lucien Geater: Financial Interests, Personal, Advisory Board: Pfizer;Financial Interests, Institutional, Principal Investigator: AstraZeneca, Roche, Novartis, Boehringer Ingelheim;Financial Interests, Personal, Advisory Role: Pfizer. K. Sang-We: Non-Financial Interests, Personal, Invited Speaker: Boehringer Ingelheim;Financial I terests, Personal, Research Grant: Yuhan;Non-Financial Interests, Personal, Advisory Role: AstraZeneca, BMS, Boehringer Ingelheim, Norvatis, Lilly, Takeda, Therapex, and Yuhan. M. Hussein: Financial Interests, Personal, Advisory Board: AbbVie, Aptitude Health, AstraZeneca, Biopahrama, BMS, Exelixis, Mirati Therapeutics, Cardinal Health, Coherus Biosciences, Athenex, Karyopharm Therapeutics, IntegraConnect, Oncocyte. C.T. Yang: Financial Interests, Personal, Principal Investigator: AstraZeneca, Boehringer Ingelheim, Lilly, MSD, Merck, Amgen, Johnson & Johnson, AbbVie, Hanso Pharma, Roche, Ono, BMS, Chugai. L.H. Araujo: Financial Interests, Personal, Invited Speaker: MSD, Roche, Pfizer, AstraZeneca, Takeda, Lillly, Janssen, Amgen, Novartis, BMS, Sanofi;Financial Interests, Personal, Advisory Board: Roche, MSD, Takeda, AstraZeneca, Sanofi. H. Saito: Financial Interests, Personal, Speaker's Bureau: AstraZeneca, ONO Pharmaceutical;Financial Interests, Personal, Principal Investigator: AstraZeneca, Chugai Pharmaceutical ONO Pharmaceutical, Bristol Myers Squibb. N. Reinmuth: Financial Interests, Personal, Invited Speaker: Amgen, AstraZeneca, Bristol Myers Squibb, Boehringer Ingelheim, Daiichi Sankyo, Hoffmann-La Roche, Janssen, Lilly, MSD, Merck, Pfizer, and Takeda;Financial Interests, Personal, Speaker's Bureau: Amgen, AstraZeneca, Bristol Myers Squibb, Boehringer-Ingelheim, Daiichi Sankyo, Hoffmann-La Roche, Janssen, Lilly, MSD, Merck, Pfizer, and Takeda;Financial Interests, Personal, Advisory Board: Amgen, AstraZeneca, Bristol Myers Squibb, Hoffmann-La Roche, Janssen, MSD, Merck, Pfizer, and Takeda;Financial Interests, Personal, Other: Symphogen: Data Safety Monitoring Board. Z. Lai, H. Mann, X. Shi: Financial Interests, Personal, Full or part-time Employment: AstraZeneca;Financial Interests, Personal, Stocks/Shares: AstraZeneca. S. Peters: Financial Interests, Institutional, Advisory Board: Vaccibody, Takeda, Seattle Genetics, Sanofi, Roche/Genentech, Regeneron, Phosplatin Therapeutics, PharmaMar, Pfizer, Novartis, Mirati, Merck Serono, MSD, Janssen, Incyte, Illumina, IQVIA, GlaxoSmithKline, Gilhead, Genzyme, Foundation Medicine, F-Star, Eli Lilly, Debiopharm, Daiichi Sankyo, Boehringer Ingelheim, Blueprint Medicines, Biocartis, Bio Invent, BeiGene, Bayer, BMS, AstraZeneca, Arcus, Amgen, AbbVie, iTheos, Novocure;Financial Interests, Institutional, In ited Speaker: Takeda, Sanofi, Roche/Genentech, RTP, Pfizer, PRIME, PER, Novartis, Medscape, MSD, Imedex, Illumina, Fishawack, Eli Lilly, Ecancer, Boehringer Ingelheim, AstraZeneca, BMS, OncologyEducation, RMEI, Mirati;Financial Interests, Personal, Other, Associate Editor Annals of Oncology: Elsevier;Financial Interests, Institutional, Invited Speaker, MERMAID-1: AstraZeneca;Financial Interests, Institutional, Invited Speaker, MERMAID-2, POSEIDON, MYSTIC: AstraZeneca;Financial Interests, Institutional, Invited Speaker, Clinical Trial Steering committee CheckMate 743, CheckMate 73L, CheckMate 331 and 451: BMS;Financial Interests, Institutional, Invited Speaker, RELATIVITY 095: BMS;Financial Interests, Institutional, Invited Speaker, BGB-A317-A1217-301/AdvanTIG-301: BeiGene;Financial Interests, Institutional, Invited Speaker, Clinical Trial Chair ZEAL-1: GSK;Financial Interests, Institutional, Invited Speaker, Clinical Trial steering Committee PEARLS, MK-7684A: MSD;Financial Interests, Institutional, Invited Speaker, Clinical Trial Steering Committee SAPPHIRE: Mirati;Financial Interests, Institutional, Invited Speaker, LAGOON: Pharma Mar;Financial Interests, Institutional, Invited Speaker, phase 1/2 trials: Phosplatin Therapeutics;Financial Interests, Institutional, Invited Speaker, Clinical Trial Chair Skyscraper-01;chair ALEX;steering committee BFAST;steering committee BEAT-Meso;steering committee ImPower-030, IMforte: Roche/Genentech;Financial Interests, Institutional, Invited Speaker, Phase 2 Inupadenant with chemo: iTeos;Non-Financial Interests, Personal, Officer, ESMO President 2020-2022: ESMO;Non-Financial Interests, Personal, Officer, Council Me ber & Scientific Committee Chair: ETOP/IBCSG Partners;Non-Financial Interests, Personal, Officer, Vice-President Lung Group: SAKK;Non-Financial Interests, Personal, Other, Involved in Swiss politics: Swiss Political Activities;Non-Financial Interests, Personal, Officer, President and Council Member: Ballet Bejart Lausanne Foundation;Non-Financial Interests, Personal, Principal Investigator, Involved in academic trials: ETOP / EORTC / SAKK;Non-Financial Interests, Personal, Member: Association of Swiss Physicians FMH (CH), IASLC, ASCO, AACR;Non-Financial Interests, Personal, Leadership Role, ESMO President: ESMO;Non-Financial Interests, Personal, Member, Vice-President Lung Group: SAKK;Non-Financial Interests, Personal, Leadership Role, Vice -President: SAMO;Non-Financial Interests, Personal, Member, Association of Swiss interns and residents: ASMAC/VSAO. E.B. Garon: Financial Interests, Personal, Advisory Board: ABL Bio, AstraZeneca, Boehringer Ingelheim, Bristol Myers Squibb, Dracen Pharmaceuticals, Eisai, Eli Lilly, EMD Serono, Gilead, GSK, Merck, Natera, Novartis, Personalis, Regeneron, Sanofi, Shionogi, Xilio Therapeutics;Financial Interests, Personal, Research Grant: ABL Bio, AstraZeneca, Bristol Myers Squibb, Dynavax Technologies, EMD Serono, Genentech, Iovance Biotherapeutics, Eli Lilly, Merck, Mirati Therapeutics, Neon Therapeutics, Novartis. T.S.K. Mok: Financial Interests, Personal, Invited Speaker: ACEA Pharma, Alpha Biopharma Co., Ltd., Amgen, Amoy Diagnostics Co., Ltd., AstraZeneca (before 1/1/19), BeiGene, BI, BMS, Daiichi Sankyo, Daz Group, Fishawack Facilitate Ltd., InMed Medical Communication, Janssen Pharmaceutica NV, Jiahui Holdings Co. Limi, Novartis, OrigiMed Co. Ltd., P. Permanyer SL, PeerVoice, Physicians' Education Resource, Pfizer, PrIME Oncology, Research to Practice, RochePharmaceuticals/Diagnostics/Foundation One, Sanofi-Aventis, Shanghai BeBirds Translation & Consulting Co., Ltd., T;Financial Interests, Personal, Advisory Board: AbbVie Inc., ACEA Pharma, Amgen, AstraZeneca, Berry Oncology, Blueprint Medicines Corporation, Boehringer Ingelheim Pharmaceuticals Inc., Bristol Myers Squibb Company, C4 Therapeutics, Inc, Covidien LP, CStone Pharmaceuticals, Curio Science, D3 Bio Ltd., Hengrui Therapeutics Inc., HutchMed, Ignyta, Inc., Incyte Corporation, Inivata, IQVIA, Janssen, Lily, Loxo-Oncology Inc., Lunit, Inc., Mer k Serono, Merck Sharp & Dohme, Mirati Therapeutics, Inc., MiRXES Group, Novartis, OrigiMed, Pfizer, Puma Biotechnolo;Financial Interests, Personal, Member of the Board of Directors: AstraZeneca PLC, HutchMed;Financial Interests, Personal, Full or part-time Employment: The Chinese University of Hong Kong (Full-Time);Financial Interests, Personal, Stocks/Shares: Aurora Tele-Oncology Ltd., HutchMed, Act Genomics-Sanomics Group, Loxo-oncology, Virtus Medical Group and Lunit USA, Inc;Non-Financial Interests, Institutional, Research Grant: AstraZeneca, BMS, G1 Therapeutics, MSD, Merck Serono, Novartis, Pfizer, Roche, SFJ, Takeda, XCovery;Financial Interests, Personal, Leadership Role: Lunit USA, Inc., ACT Genomics-Sanomics Group, Aurora;Financial Interests, Personal, Other, Independent contractor: AbbVie Inc., ACEA Pharma, Alpha Biopharma Co., Ltd., Amgen, Amoy Diagnostics Co., Ltd., AstraZeneca (before 1/1/19), BeiGene, Berry Oncology, BI, Blueprint Medicines Corporation, BMS, C4 Therapeutics, Inc, CStone Pharmaceuticals, Curio Science, Daiichi Sa, Loxo-Oncology, Merck Serono, MSD, Mirati Therapeutics Inc., MoreHealth, Novartis, OrigiMed, Pfizer, Puma Biotechnology Inc., Qiming Development (HK) Ltd., Roche Pharmaceuticals, Sanofi-Aventis, SFJ Pharmaceutical Ltd., Takeda Pharmaceuticals HK Ltd., Vert, Guardant Health, Hengrui Therapeutics Inc., HutchMed, Ignyta, Inc., Incyte Corporation, Inivata, IQVIA, Janssen, Lilly, Lunit USA, Inc., Loxo-Oncology, Lucence Health Inc., Medscape LLC/ WebMD, Merck Serono, MSD, Mirati Therapeutics Inc., MiRXES, MoreHea. M.L. Johnson: Financial Interests, Institutional, Research Grant: AbbVie;Acerta;Adaptimmune;Amgen;Apexigen;Arcus B osciences;Array BioPharma;Artios Pharma;AstraZeneca;Atreca, BeiGene;BerGenBio;BioAtla;Boehringer Ingelheim, Calithera Biosciences;Checkpoint Therapeutics;Corvus Pharmaceuticals;Curis;CytomX, Daiichi Sanyo;Dracen Pharmaceuticals;Dynavax, Eli Lilly, Elicio Therapeutics, EMD Serono, Erasca, Exelixis, Fate Therapeutics, Genentech/Roche, Genmab, Genocea Biosciences, GlaxoSmithKline, Gritstone Oncology, Guardant Health, Harpoon, Helsinn Healthcare SA, Hengrui Therapeutics, Hutchison MediPharma, IDEAYA Biosciences, IGM Biosciences, Immunocore, Incyte, Janssen, Jounce Therapeutics, Kadmon Pharmaceuticals, Loxo Oncology, Lycera, Memorial Sloan Kettering, Merck, Merus, Mirati Therapeutics, NeoImmuneTech, Neovia Oncology, Novartis, Numab Therapeutics, Nuvalent, OncoMed Pharmaceuticals, Pfizer, PMV Pharmaceuticals, RasCal Therapeutics, Regeneron Pharmaceuticals, Relay Therapeutics, Revolution Medicines, Ribon Therapeutics, Rubius Therapeutics, Sanofi, Seven and Eight Biopharmaceuticals/Birdie Pharmaceuticals, Shattuck Labs, Silicon Therapeutics, Stem CentRx, Syndax Pharmaceuticals, Takeda Pharmaceuticals, Tarveda, TCR2 Therapeutics, Tempest Therapeutics, Tizona Therapeutics, Tmunity Therapeutics, Turning Point Therapeutics, University of Michigan, Vyriad, WindMIL, Y-mAbs Therapeutics;Financial Interests, Institutional, Advisory Role: AbbVie, Amgen, Astellas, AstraZeneca, Axelia Oncology, Black Diamond, Boehringer Ingelheim, Bristol Myers Squibb, Calithera Biosciences, Checkpoint Therapeutics, CytomX Therapeutics, Daiichi Sankyo, EcoR1, Editas Medicine, Eisai, Eli Lilly, EMD Serono, G1 Therapeutics, Genentech/Roche, Genmab, Genocea Biosciences, GlaxoSmithKline, Gritstone Oncology, IDEAYA Biosciences, iTeos, Janssen, Merck, Mirati Therapeutics, Novartis, Oncorus, Regeneron Pharmaceuticals, Revolution Medicines, Ribon Therapeutics, Sanofi, Turning Point Therapeutics, WindMIL. All other authors have declared no conflicts of interest. Copyright © 2022

Collaborative adoption of blockchain technology: A supply chain contract perspective

The outbreak of COVID-19 has significantly affected the development of enterprises. In the post-pandemic era, blockchain technology has become one of the important technologies to help enterprises quickly gain market competitiveness. The heavy investment required of supply chain stakeholders to employ blockchain technology has hindered its adoption and application. To tackle this issue, this study aims to facilitate the adoption of blockchain technology in a supply chain consisting of a core enterprise and a small/medium-sized enterprise through an effective supply chain contract. We analyze the performance of a cost-sharing (CS) contract and a revenue-sharing (RS) contract and propose a new hybrid CS-RS contract for better performance. We conduct comparative analyses of the three contracts and find that the hybrid CS-RS contract can more effectively incentivize both parties to reach the highest level of blockchain technology adoption and achieve supply chain coordination.

Fast and direct identification of SARS-CoV-2 variants via 2D InSe field-effect transistors

As the COVID-19 pandemic evolves and new variants emerge, the development of more efficient identification approaches of variants is urgent to prevent continuous outbreaks of SARS-CoV-2. Field-effect transistors (FETs) with two-dimensional (2D) materials are viable platforms for the detection of virus nucleic acids (NAs) but cannot yet provide accurate information on NA variations. Herein, 2D Indium selenide (InSe) FETs were used to identify SARS-CoV-2 variants. The device's mobility and stability were ensured by atomic layer deposition (ALD) of Al2O3. The resulting FETs exhibited sub-fM detection limits ranging from 10(-14) M to 10(-)(8) M. The recognition of single-nucleotide variations was achieved within 15 min to enable the fast and direct identification of two core mutations (L452R, R203M) in Delta genomes (p < .01). Such capability originated from the trap states in oxidized InSe (InSe1-xOx) after ALD, resulting in traps-involved carrier transport responsive to the negative charges of NAs. In sum, the proposed approach might highly provide epidemiological information for timely surveillance of the COVID pandemic.

Double Hydrogen-bonding Reinforced High-Performance Supramolecular Hydrogel Thermocell for Self-powered Sensing Remote-Controlled by Light

Non-contact human-machine interaction is the future trend for wearable technologies. This demand is recently highlighted by the pandemic of coronavirus disease (COVID-19). Herein, an anti-fatigue and highly conductive hydrogel thermocell with photo-thermal conversion ability for non-contact self-powering applications is designed. Double hydrogen-bonding enhanced supramolecular hydrogel is obtained with N-acryloyl glycinamide (NAGA) and diacrylate capped Pluronic F68 (F68-DA) via one-step photo-initiated polymerization. The supramolecular hydrogel can accommodate saturated electrolytes to fulfill the triple function of ionic crosslinking, heat-to-electricity conversion, and light response of thermocell. Eminently, the thermocell stands out by virtue of its high seebeck coefficient (-2.17 mV K−1) and extraordinary toughness (Fatigue threshold ≈ 3120 J m−2). The self-powering ability under the control of light heating is explored, and a model of a non-contact "light-remoted” sensor with self-powered and sensing integrated performance remote-controlled by light is constructed. It is believed that this study will pave the way for the non-contact energy supply of wearable devices. © 2023 Wiley-VCH GmbH.

Attribute Analysis and Diagnosis of LUNG CT Images of COVID-19

Computed Tomography (CT) is an authoritative verification standard for patients with Corona Virus Disease 2019 (COVID-19). Automatic detection of lung infection through CT is of great significance for epidemic prevention and control and prevention of cross-infection. The accuracy of existing lung CT image segmentation methods is not high, and due to the privacy protection measures of hospitals, the number of COVID-19 lung CT data sets is too small, which is prone to over-fitting during training. In this paper, we propose a qualitative mapping model for the diagnosis and localization of COVID-19 lesions. The binary image processed by U-net network is used as input, and lung CT is segmented as four attributes, and attribute diagnosis is carried out with the help of correlation matrix and transformation degree function. Experiments show that this method not only avoids the over-fitting risk of data sets, but also increases the robustness of data. Experiments also prove that this design has higher accuracy than the simple neural network learning. © 2022 IEEE.

GloVe-CNN-BiLSTM Model for Sentiment Analysis on Text Reviews

Nowadays, social media networks generate a tremendous amount of social information from their users. To understand people's views and sentimental tendencies on a commodity or an event timely, it is necessary to conduct text sentiment analysis on the views expressed by users. For the microblog comment data, it is always mixed with long and short texts, which is relatively complex. Especially for long text data, it contains a lot of content, and the correlation between words is more complex than that in short text. To study the sentiment classification of these mixed texts composed of long-text and short-text, this research proposes an optimized GloVe-CNN-BiLSTM-based sentiment analysis model. In this model, GloVe is used to vectorize words, and CNN is given to represent part space character. BiLSTM is used to build temporal relationship. Twitter's comment data on COVID-19 is used as an experimental dataset. The results of the experiments suggest that this method can effectually identify the sentimental tendency of users' online comments, and the accuracy of sentiment classification on complete-text, long-text, and short-text can achieve to 0.9565, 0.9509, and 0.9560, respectively, which is obviously higher than other deep learning models. At the same time, experiments show that this method has good field expansion.

A Dashboard for Mitigating the COVID-19 Misinfodemic

This paper describes the current milestones achieved in our ongoing project that aims to understand the surveillance of, impact of, and effective interventions against the COVID-19 misinfodemic on Twitter. Specifically, it introduces a public dashboard which, in addition to displaying case counts in an interactive map and a navigational panel, also provides some unique features not found in other places. Particularly, the dashboard uses a curated catalog of COVID-19 related facts and debunks of misinformation, and it displays the most prevalent information from the catalog among Twitter users in user-selected U.S. geographic regions. The paper explains how to use BERT-based models to match tweets with the facts and misinformation and to detect their stance towards such information. The paper also discusses the results of preliminary experiments on analyzing the spatiotemporal spread of misinformation.

Self-interest Attribution Behavior in Annual Reports under the COVID-19 Pandemic-Taking restaurant companies for example

The outbreak of the COVID-19 pandemic at the end of 2019 has caused a profound impact on economic development. The catering, logistics and tourism industries have suffered a huge blow. This paper selects the catering industry as the research object, selects the 2019 and 2020 annual reports of five representative listed catering companies, classifies and summarizes the stated criteria for determination of the occurrence of self-interest attribution, calculates the degree of self-interest attribution, and compares and analyzes whether the self-interest attribution behavior of the five case companies before and after the COVID-19 pandemic stands out or amplifies the self-interest attribution behavior of the companies. The case studies showed that the degree of self-interest attribution was higher in the poor-performing companies, and that the impact of the COVID-19 pandemic on the self-interest behavior of restaurant companies was prominent, and that the poor external environment was more likely to lead to a higher degree of self-interest attribution behavior. © 2022 IEEE.

COVIDNet: An Automatic Architecture for COVID-19 Detection With Deep Learning From Chest X-Ray Images

Up to now, the coronavirus disease 2019 (COVID-19) has been sweeping across all over the world, which has affected individual's lives in an overwhelming way. To fight efficiently against the COVID-19, radiography and radiology images are used by clinicians in hospitals. This article presents an integrated framework, named COVIDNet, for classifying COVID-19 patients and healthy controls. Specifically, ResNet (i.e., ResNet-18 and ResNet-50) is adopted as a backbone network to extract the discriminative features first. Second, the spatial pyramid pooling (SPP) layer is adopted to capture the middle-level features from the features of ResNet. To learn the high-level features, the NetVLAD layer is used to aggregate the features representation from middle-level features. The context gating (CG) mechanism is adopted to further learn the high-level features for predicting the COVID-19 patients or not. Finally, extensive experiments are conducted on the collected database, showing the excellent performance of the proposed integrated architecture, with the sensitivity up to 97% and specificity of 99.5% of the ResNet-18, and with the sensitivity up to 99% and specificity of 99.4% of the ResNet-50. © 2014 IEEE.

A POPULATION-BASED STUDY OF DO NOT RESUSCITATE ORDERS IN STROKE PATIENTS BEFORE AND DURING THE PANDEMIC

Background and aims: We studied use of do not resuscitate (DNR) orders in the Brain Attack Surveillance in Corpus Christi (BASIC) study before and during the COVID-19 pandemic. Methods: All hospitalized stroke cases were ascertained in Nueces County, Texas, USA during an equal time period before the pandemic (January, 2019-Feb, 2020) and during the pandemic (March, 2020-April, 2021). We compared use of DNR orders before and during the pandemic using logistic regression adjusted for demographic and clinical variables including initial stroke severity (NIHSS score). Nueces County is geographically isolated making complete case capture likely. Cases were validated by stroke physicians using source documentation. Results: There were more cases during the pandemic (N=716) than pre-pandemic (N=681). Median NIHSS score was 5 (IQR 9) during the pandemic and 4 (IQR 9) pre-pandemic (p=0.03). During the pandemic 18.0% of stroke patients had DNR orders compared with 13.3% prepandemic (p=0.016). Other demographic and risk factors were similar in the two time periods. In models adjusted for age, sex, race-ethnicity, NIHSS score, diabetes, hypertension, current smoking and stroke history, DNR orders were not more common in the pandemic compared with pre-pandemic (p=0.2), but stroke severity (NIHSS score) remained significantly higher during the pandemic (p<0.01). Conclusions: In this population-based study, greater use of DNR orders were seen during the pandemic than before the pandemic. The greater use of DNR orders may be due, in part, to the worse stroke severity presenting to hospitals during the pandemic.

A Feature Extraction Method for scRNA-seq Processing and Its Application on COVID-19 Data Analysis

Single-cell RNA-sequencing (scRNA-seq) is a rapidly increasing research area in biomedical signal processing. However, the high complexity of single-cell data makes efficient and accurate analysis difficult. To improve the performance of single-cell RNA data processing, two single-cell features calculation method and corresponding dual-input neural network structures are proposed. In this feature extraction and fusion scheme, the features at the cluster level are extracted by hierarchical clustering and differential gene analysis, and the features at the cell level are extracted by the calculation of gene frequency and cross cell frequency. Our experiments on COVID-19 data demonstrate that the combined use of these two feature achieves great results and high robustness for classification tasks. © 2021 Journal of Beijing Institute of Technology