RESUMO
Leukemia is a type of blood cell cancer that is in the bone marrow's blood-forming cells. Two types of Leukemia are acute and chronic; acute enhances fast and chronic growth gradually which are further classified into lymphocytic and myeloid leukemias. This work evaluates a unique deep convolutional neural network (CNN) classifier that improves identification precision by carefully examining concatenated peptide patterns. The study uses leukemia protein expression for experiments supporting two different techniques including independence and applied cross-validation. In addition to CNN, multilayer perceptron (MLP), gated recurrent unit (GRU), and recurrent neural network (RNN) are applied. The experimental results show that the CNN model surpasses competitors with its outstanding predictability in independent and cross-validation testing applied on different features extracted from protein expressions such as amino acid composition (AAC) with a group of AAC (GAAC), tripeptide composition (TPC) with a group of TPC (GTPC), and dipeptide composition (DPC) for calculating its accuracies with their receiver operating characteristic (ROC) curve. In independence testing, a feature expression of AAC and a group of GAAC are applied using MLP and CNN modules, and ROC curves are achieved with overall 100% accuracy for the detection of protein patterns. In cross-validation testing, a feature expression on a group of AAC and GAAC patterns achieved 98.33% accuracy which is the highest for the CNN module. Furthermore, ROC curves show a 0.965% extraordinary result for the GRU module. The findings show that the CNN model is excellent at figuring out leukemia illnesses from protein expressions with higher accuracy.
Assuntos
Leucemia , Redes Neurais de Computação , Humanos , Leucemia/metabolismo , Leucemia/patologia , Curva ROC , Peptídeos/análiseRESUMO
The Internet of Things (IoT) is an innovative technology that presents effective and attractive solutions to revolutionize various domains. Numerous solutions based on the IoT have been designed to automate industries, manufacturing units, and production houses to mitigate human involvement in hazardous operations. Owing to the large number of publications in the IoT paradigm, in particular those focusing on industrial IoT (IIoT), a comprehensive survey is significantly important to provide insights into recent developments. This survey presents the workings of the IoT-based smart industry and its major components and proposes the state-of-the-art network infrastructure, including structured layers of IIoT architecture, IIoT network topologies, protocols, and devices. Furthermore, the relationship between IoT-based industries and key technologies is analyzed, including big data storage, cloud computing, and data analytics. A detailed discussion of IIoT-based application domains, smartphone application solutions, and sensor- and device-based IIoT applications developed for the management of the smart industry is also presented. Consequently, IIoT-based security attacks and their relevant countermeasures are highlighted. By analyzing the essential components, their security risks, and available solutions, future research directions regarding the implementation of IIoT are outlined. Finally, a comprehensive discussion of open research challenges and issues related to the smart industry is also presented.
RESUMO
The major challenge faced by autonomous vehicles today is driving through busy roads without getting into an accident, especially with a pedestrian. To avoid collision with pedestrians, the vehicle requires the ability to communicate with a pedestrian to understand their actions. The most challenging task in research on computer vision is to detect pedestrian activities, especially at nighttime. The Advanced Driver-Assistance Systems (ADAS) has been developed for driving and parking support for vehicles to visualize sense, send and receive information from the environment but it lacks to detect nighttime pedestrian actions. This article proposes a framework based on Deep Reinforcement Learning (DRL) using Scale Invariant Faster Region-based Convolutional Neural Networks (SIFRCNN) technologies to efficiently detect pedestrian operations through which the vehicle, as agents train themselves from the environment and are forced to maximize the reward. The SIFRCNN has reduced the running time of detecting pedestrian operations from road images by incorporating Region Proposal Network (RPN) computation. Furthermore, we have used Reinforcement Learning (RL) for optimizing the Q-values and training itself to maximize the reward after getting the state from the SIFRCNN. In addition, the latest incarnation of SIFRCNN achieves near-real-time object detection from road images. The proposed SIFRCNN has been tested on KAIST, City Person, and Caltech datasets. The experimental results show an average improvement of 2.3% miss rate of pedestrian detection at nighttime compared to the other CNN-based pedestrian detectors.
RESUMO
Fundamentals of Database Systems is a core course in computing disciplines as almost all small, medium, large, or enterprise systems essentially require data storage component. Database System Education (DSE) provides the foundation as well as advanced concepts in the area of data modeling and its implementation. The first course in DSE holds a pivotal role in developing students' interest in this area. Over the years, the researchers have devised several different tools and methods to teach this course effectively, and have also been revisiting the curricula for database systems education. In this study a Systematic Literature Review (SLR) is presented that distills the existing literature pertaining to the DSE to discuss these three perspectives for the first course in database systems. Whereby, this SLR also discusses how the developed teaching and learning assistant tools, teaching and assessment methods and database curricula have evolved over the years due to rapid change in database technology. To this end, more than 65 articles related to DSE published between 1995 and 2022 have been shortlisted through a structured mechanism and have been reviewed to find the answers of the aforementioned objectives. The article also provides useful guidelines to the instructors, and discusses ideas to extend this research from several perspectives. To the best of our knowledge, this is the first research work that presents a broader review about the research conducted in the area of DSE.
RESUMO
Several smart city ideas are introduced to manage various problems caused by overpopulation, but the futuristic smart city is a concept based on dense and artificial-intelligence-centric cities. Thus, massive device connectivity with huge data traffic is expected in the future where communication networks are expected to provide ubiquity, high quality of service, and on-demand content for a large number of interconnected devices. The sixth-generation (6G) network is considered the problem-solving network of futuristic cities, with huge bandwidth and low latency. The expected 6G of the radio access network is based on terahertz (THz) waves with the capability of carrying up to one terabit per second (Tbps). THz waves have the capability of carrying a large amount of data but these waves have several drawbacks, such as short-range and atmospheric attenuation. Hence, these problems can introduce complications and hamper the performance of the 6G network. This study envisions futuristic smart cities using 6G and proposes a conceptual terrestrial network (TN) architecture for 6G. The nested Bee Hive is a scalable multilayer architecture designed to meet the needs of futuristic smart cities. Moreover, we designed the multilayer network infrastructure while considering the expectations from a network of futuristic smart cities and the complications of THz waves. Extensive simulations are performed using different pathfinding algorithms in the 3D multilayer domain to evaluate the performance of the proposed architecture and set the dynamics of futuristic communication of 6G.
Assuntos
Algoritmos , Inteligência Artificial , Animais , Abelhas , Cidades , PrevisõesRESUMO
Diabetic Retinopathy (DR) is a predominant cause of visual impairment and loss. Approximately 285 million worldwide population is affected with diabetes, and one-third of these patients have symptoms of DR. Specifically, it tends to affect the patients with 20 years or more with diabetes, but it can be reduced by early detection and proper treatment. Diagnosis of DR by using manual methods is a time-consuming and expensive task which involves trained ophthalmologists to observe and evaluate DR using digital fundus images of the retina. This study aims to systematically find and analyze high-quality research work for the diagnosis of DR using deep learning approaches. This research comprehends the DR grading, staging protocols and also presents the DR taxonomy. Furthermore, identifies, compares, and investigates the deep learning-based algorithms, techniques, and, methods for classifying DR stages. Various publicly available dataset used for deep learning have also been analyzed and dispensed for descriptive and empirical understanding for real-time DR applications. Our in-depth study shows that in the last few years there has been an increasing inclination towards deep learning approaches. 35% of the studies have used Convolutional Neural Networks (CNNs), 26% implemented the Ensemble CNN (ECNN) and, 13% Deep Neural Networks (DNN) are amongst the most used algorithms for the DR classification. Thus using the deep learning algorithms for DR diagnostics have future research potential for DR early detection and prevention based solution.
Assuntos
Aprendizado Profundo , Diabetes Mellitus , Retinopatia Diabética , Computadores , Retinopatia Diabética/diagnóstico por imagem , Fundo de Olho , Humanos , Redes Neurais de ComputaçãoRESUMO
Asthma is a deadly disease that affects the lungs and air supply of the human body. Coronavirus and its variants also affect the airways of the lungs. Asthma patients approach hospitals mostly in a critical condition and require emergency treatment, which creates a burden on health institutions during pandemics. The similar symptoms of asthma and coronavirus create confusion for health workers during patient handling and treatment of disease. The unavailability of patient history to physicians causes complications in proper diagnostics and treatments. Many asthma patient deaths have been reported especially during pandemics, which necessitates an efficient framework for asthma patients. In this article, we have proposed a blockchain consortium healthcare framework for asthma patients. The proposed framework helps in managing asthma healthcare units, coronavirus patient records and vaccination centers, insurance companies, and government agencies, which are connected through the secure blockchain network. The proposed framework increases data security and scalability as it stores encrypted patient data on the Interplanetary File System (IPFS) and keeps data hash values on the blockchain. The patient data are traceable and accessible to physicians and stakeholders, which helps in accurate diagnostics, timely treatment, and the management of patients. The smart contract ensures the execution of all business rules. The patient profile generation mechanism is also discussed. The experiment results revealed that the proposed framework has better transaction throughput, query delay, and security than existing solutions.
Assuntos
Asma , Blockchain , Humanos , Pandemias , Segurança Computacional , Atenção à Saúde/métodos , Asma/diagnóstico , Asma/terapiaRESUMO
Implementation of cleaner production practices (CPP), service quality (SQ) and corporate social responsibility (CSR) is often studied at organizational level. A number of studies on trio have reported it's significant impact on overall organizational performance and profitability across the globe. However, not much is studied about the individual level micro influence of these constructs on employee engagement (EE), organizational pride (OP), organizational identification (OI) and "desire to have a significant impact through work" (DSIW). Therefore, this study presents a comprehensive framework for assessing the impact of the implementation of CPP, SQ and CSR on EE, OP, OI and DSIW. Data collected from 320 non-managerial staff members employed at a garments manufacturing company in Pakistan was analyzed using partial least square (PLS) approach. Findings revealed that the implementation of CPP, SQ and CSR plays an important role in shaping EE, OP, OI and DSIW in the garments manufacturing industry. Further, it is found that the implementation of CPP has a non-significant impact on SQ. Additionally, results of the importance-performance map analysis (IPMA) have also confirmed that the implementation of CPP at company level has shown a highest importance and performance amongst all the latent constructs proposed as predictors of DSIW in the garments manufacturing industry. These findings are a step forward and unique contribution of this study in the domain of CPP, SQ, CSR, EE, OP, OI and DSIW.
RESUMO
Software Development based on Scrum Agile in a distributed development environment plays a pivotal role in the contemporary software industry by facilitating software development across geographic boundaries. However, in the past different frameworks utilized to address the challenges like communication and collaboration in scrum agile distributed software development (SADSD) were notably inadequate in transparency, security, traceability, geographically dispersed location work agreements, geographically dispersed teamwork effectiveness, and trust. These deficiencies frequently resulted in delays in software development and deployment, customer dissatisfaction, canceled agreements, project failures, and disputes over payments between customers and development teams. To address these challenges of SADSD, this paper proposes a new framework called ChainAgile, which leverages blockchain technology. ChainAgile employs a private Ethereum blockchain to facilitate the execution of smart contracts. These smart contracts cover a range of functions, including acceptance testing, secure payments, requirement verification, task prioritization, sprint backlog, user story design and development and payments with the automated distribution of payments via digital wallets to development teams. Moreover, in the ChainAgile framework, smart contracts also play a pivotal role in automatically imposing penalties on customers for making late payments or for no payments and penalties on developers for completing the tasks that exceed their deadlines. Furthermore, ChainAgile effectively addresses the scalability limitations intrinsic in blockchain technology by incorporating the Interplanetary File System (IPFS) is used for storage solutions as an off-chain mechanism. The experimental results conclusively show that this innovative approach substantially improves transparency, traceability, coordination, communication, security, and trust for both customers and developers engaged in scrum agile distributed software development (SADSD).
Assuntos
Blockchain , Comunicação , Dissidências e Disputas , Emoções , SoftwareRESUMO
Plagiarism detection (PD) is a process of identifying instances where someone has presented another person's work or ideas as their own. Plagiarism detection is categorized into two types (i) Intrinsic plagiarism detection primarily concerns the assessment of authorship consistency within a single document, aiming to identify instances where portions of the text may have been copied or paraphrased from elsewhere within the same document. Author clustering, closely related to intrinsic plagiarism detection, involves grouping documents based on their stylistic and linguistic characteristics to identify common authors or sources within a given dataset. On the other hand, (ii) extrinsic plagiarism detection delves into the comparative analysis of a suspicious document against a set of external source documents, seeking instances of shared phrases, sentences, or paragraphs between them, which is often referred to as text reuse or verbatim copying. Detection of plagiarism from documents is a long-established task in the area of NLP with remarkable contributions in multiple applications. A lot of research has already been conducted in the English and other foreign languages but Urdu language needs a lot of attention especially in intrinsic plagiarism detection domain. The major reason is that Urdu is a low resource language and unfortunately there is no high-quality benchmark corpus available for intrinsic plagiarism detection in Urdu language. This study presents a high-quality benchmark Corpus comprising 10,872 documents. The corpus is structured into two granularity levels: sentence level and paragraph level. This dataset serves multifaceted purposes, facilitating intrinsic plagiarism detection, verbatim text reuse identification, and author clustering in the Urdu language. Also, it holds significance for natural language processing researchers and practitioners as it facilitates the development of specialized plagiarism detection models tailored to the Urdu language. These models can play a vital role in education and publishing by improving the accuracy of plagiarism detection, effectively addressing a gap and enhancing the overall ability to identify copied content in Urdu writing.
RESUMO
The wheat crop that fulfills 35% of human food demand is facing several problems due to a lack of transparency, security, reliability, and traceability in the existing agriculture supply chain. Many systems have been developed for the agriculture supply chain to overcome such issues, however, monopolistic centralized control is the biggest hurdle to realizing the use of such systems. It has eventually gained consumers' trust in branded products and rejected other products due to the lack of traceable supply chain information. This study proposes a blockchain-based framework for supply chain traceability which provides trustable, transparent, secure, and reliable services for the wheat crop. A crypto token called wheat coin (WC) has been introduced to keep track of transactions among the stakeholders of the wheat supply chain. Moreover, an initial coin offering (ICO) of WC, crypto wallets, and an economic model are proposed. Furthermore, a smart contract-based transaction system has been devised for the transparency of wheat crop transactions and conversion of WC to fiat and vice versa. We have developed the interplanetary file system (IPFS) to improve data availability, security, and transparency which stores encrypted private data of farmers, businesses, and merchants. Lastly, the results of the experiments show that the proposed framework shows better performance as compared to previous crop supply chain solutions in terms of latency to add-blocks, per-minute transactions, average gas charge for the transaction, and transaction verification time. Performance analysis with Bitcoin and Ethereum shows the superior performance of the proposed system.
Assuntos
Blockchain , Cryptococcus neoformans , Criptosporidiose , Humanos , Triticum , Reprodutibilidade dos Testes , Agricultura , ComércioRESUMO
Autism spectrum disorder (ASD) presents a neurological and developmental disorder that has an impact on the social and cognitive skills of children causing repetitive behaviours, restricted interests, communication problems and difficulty in social interaction. Early diagnosis of ASD can prevent from its severity and prolonged effects. Federated learning (FL) is one of the most recent techniques that can be applied for accurate ASD diagnoses in early stages or prevention of its long-term effects. In this article, FL technique has been uniquely applied for autism detection by training two different ML classifiers including logistic regression and support vector machine locally for classification of ASD factors and detection of ASD in children and adults. Due to FL, results obtained from these classifiers have been transmitted to central server where meta classifier is trained to determine which approach is most accurate in the detection of ASD in children and adults. Four different ASD patient datasets, each containing more than 600 records of effected children and adults have been obtained from different repository for features extraction. The proposed model predicted ASD with 98% accuracy (in children) and 81% accuracy (in adults).
Assuntos
Transtorno do Espectro Autista , Transtorno Autístico , Humanos , Adulto , Criança , Transtorno do Espectro Autista/diagnóstico , Aprendizado de Máquina , Interação Social , Máquina de Vetores de SuporteRESUMO
With the rise of social media, the dissemination of forged content and news has been on the rise. Consequently, fake news detection has emerged as an important research problem. Several approaches have been presented to discriminate fake news from real news, however, such approaches lack robustness for multi-domain datasets, especially within the context of Urdu news. In addition, some studies use machine-translated datasets using English to Urdu Google translator and manual verification is not carried out. This limits the wide use of such approaches for real-world applications. This study investigates these issues and proposes fake news classier for Urdu news. The dataset has been collected covering nine different domains and constitutes 4097 news. Experiments are performed using the term frequency-inverse document frequency (TF-IDF) and a bag of words (BoW) with the combination of n-grams. The major contribution of this study is the use of feature stacking, where feature vectors of preprocessed text and verbs extracted from the preprocessed text are combined. Support vector machine, k-nearest neighbor, and ensemble models like random forest (RF) and extra tree (ET) were used for bagging while stacking was applied with ET and RF as base learners with logistic regression as the meta learner. To check the robustness of models, fivefold and independent set testing were employed. Experimental results indicate that stacking achieves 93.39%, 88.96%, 96.33%, 86.2%, and 93.17% scores for accuracy, specificity, sensitivity, MCC, ROC, and F1 score, respectively.
RESUMO
Epilepsy is a life-threatening neurological brain disorder that gives rise to recurrent unprovoked seizures. It occurs due to abnormal chemical changes in our brains. For many years, studies have been conducted to support the automatic diagnosis of epileptic seizures for clinicians' ease. For that, several studies entail machine learning methods for early predicting epileptic seizures. Mainly, feature extraction methods have been used to extract the right features from the EEG data generated by the EEG machine. Then various machine learning classifiers are used for the classification process. This study provides a systematic literature review of the feature selection process and classification performance. This review was limited to finding the most used feature extraction methods and the classifiers used for accurate classification of normal to epileptic seizures. The existing literature was examined from well-known repositories such as MDPI, IEEE Xplore, Wiley, Elsevier, ACM, Springer link, and others. Furthermore, a taxonomy was created that recapitulates the state-of-the-art used solutions for this problem. We also studied the nature of different benchmark and unbiased datasets and gave a rigorous analysis of the working of classifiers. Finally, we concluded the research by presenting the gaps, challenges, and opportunities that can further help researchers predict epileptic seizures.
RESUMO
The Internet of things (IoT) is an emerging technology that enables ubiquitous devices to connect with the Internet. IoT technology has revolutionized the medical and healthcare industry by interconnecting smart devices and sensors. IoT-based devices and biosensors are ideal to detect diabetes disease by collecting the accurate value of glucose continuously. Diabetes is one of the well-known and major chronic diseases that has a worldwide social impact on community life. Blood glucose monitoring is a challenging task, and there is a need to propose a proper architecture of the noninvasive glucose sensing and monitoring mechanism, which could make diabetic people aware of self-management techniques. This survey presents a rigorous discussion of diabetes types and presents detection techniques based on IoT technology. In this research, an IoT-based healthcare network infrastructure has been proposed for monitoring diabetes disease based on big data analytics, cloud computing, and machine learning. The proposed infrastructure could handle the symptoms of diabetes, collect data, analyze it, and then transmit the results to the server for the next action. Besides, presented an inclusive survey on IoT-based diabetes monitoring applications, services, and proposed solutions. Furthermore, based on IoT technology the diabetes disease management taxonomy has also been presented. Finally, presented the attacks taxonomy as well as discussed challenges, and proposed a lightweight security model in order to secure the patient's health data.
RESUMO
Brassica napus L. (canola, oil seed rape) is one of the world's most important oil seed crops. In the last four decades, the discovery of cytoplasmic male-sterility (CMS) systems and the restoration of fertility (Rf) genes in B. napus has improved the crop traits by heterosis. The homologs of Rf genes, known as the restoration of fertility-like (RFL) genes, have also gained importance because of their similarities with Rf genes. Such as a high non-synonymous/synonymous codon replacement ratio (dN/dS), autonomous gene duplications, and a possible engrossment in fertility restoration. B. napus contains 53 RFL genes on chromosomes A9 and C8. Our research aims to study the function of BnaRFL11 in fertility restoration using the CRISPR/Cas9 genome editing technique. A total of 88/108 (81.48%) T0 lines, and for T1, 110/145 (75%) lines carried T-DNA insertions. Stable mutations were detected in the T0 and T1 generations, with an average allelic mutation transmission rate of 81%. We used CRISPR-P software to detect off-target 50 plants sequenced from the T0 generation that showed no off-target mutation, signifying that if the designed sgRNA is specific for the target, the off-target effects are negligible. We also concluded that the mutagenic competence of the designed sgRNAs mediated by U6-26 and U6-29 ranged widely from 31% to 96%. The phenotypic analysis of bnarfl11 revealed defects in the floral structure, leaf size, branch number, and seed production. We discovered a significant difference between the sterile line and fertile line flower development after using a stereomicroscope and scanning electron microscope. The pollen visibility test showed that the pollen grain had utterly degenerated. The cytological observations of homozygous mutant plants showed an anther abortion stage similar to nap-CMS, with a Orf222, Orf139, Ap3, and nad5c gene upregulation. The bnarfl11 shows vegetative defects, including fewer branches and a reduced leaf size, suggesting that PPR-encoding genes are essential for the plants' vegetative and reproductive growth. Our results demonstrated that BnaRFL11 has a possible role in fertility restoration. The current study's findings suggest that CRISPR/Cas9 mutations may divulge the functions of genes in polyploid species and provide agronomically desirable traits through a targeted mutation.
RESUMO
Earthquakes are a natural phenomenon which may cause significant loss of life and infrastructure. Researchers have applied multiple artificial intelligence based techniques to predict earthquakes, but high accuracies could not be achieved due to the huge size of multidimensional data, communication delays, transmission latency, limited processing capacity and data privacy issues. Federated learning (FL) is a machine learning (ML) technique that provides an opportunity to collect and process data onsite without compromising on data privacy and preventing data transmission to the central server. The federated concept of obtaining a global data model by aggregation of local data models inherently ensures data security, data privacy, and data heterogeneity. In this article, a novel earthquake prediction framework using FL has been proposed. The proposed FL framework has given better performance over already developed ML based earthquake predicting models in terms of efficiency, reliability, and precision. We have analyzed three different local datasets to generate multiple ML based local data models. These local data models have been aggregated to generate global data model on the central FL server using FedQuake algorithm. Meta classifier has been trained at the FL server on global data model to generate more accurate earthquake predictions. We have tested the proposed framework by analyzing multidimensional seismic data within 100 km radial area from 34.708° N, 72.5478° E in Western Himalayas. The results of the proposed framework have been validated against instrumentally recorded regional seismic data of last thirty-five years, and 88.87% prediction accuracy has been recorded. These results obtained by the proposed framework can serve as a useful component in the development of earthquake early warning systems.
RESUMO
The introductory programming course (IPC) holds a special significance in computing disciplines as this course serves as a prerequisite for studying the higher level courses. Students generally face difficulties during their initial stages of learning how to program. Continuous efforts are being made to examine this course for identifying potential improvements. This article presents the review of the state-of-the-art research exploring various components of IPC by examining sixty-six articles published between 2014 and 2020 in well-reputed research venues. The results reveal that several useful methods have been proposed to support teaching and learning in IPC. Moreover, the research in IPC presented useful ways to conduct assessments, and also demonstrated different techniques to examine improvements in the IPC contents. In addition, a variety of tools are evaluated to support the related course processes. Apart from the aforementioned facets, this research explores other interesting dimensions of IPC, such as collaborative learning, cognitive assessments, and performance predictions. In addition to reviewing the recent advancements in IPC, this study proposes a new taxonomy of IPC research dimensions. Furthermore, based on the successful practices that are listed in the literature, some useful guidelines and advices for instructors have also been reported in this article. Lastly, this review presents some pertinent open research issues to highlight the future dimensions for IPC researchers.
RESUMO
The purpose of this research was to provide a "systematic literature review" of knee bone reports that are obtained by MRI, CT scans, and X-rays by using deep learning and machine learning techniques by comparing different approaches-to perform a comprehensive study on the deep learning and machine learning methodologies to diagnose knee bone diseases by detecting symptoms from X-ray, CT scan, and MRI images. This study will help those researchers who want to conduct research in the knee bone field. A comparative systematic literature review was conducted for the accomplishment of our work. A total of 32 papers were reviewed in this research. Six papers consist of X-rays of knee bone with deep learning methodologies, five papers cover the MRI of knee bone using deep learning approaches, and another five papers cover CT scans of knee bone with deep learning techniques. Another 16 papers cover the machine learning techniques for evaluating CT scans, X-rays, and MRIs of knee bone. This research compares the deep learning methodologies for CT scan, MRI, and X-ray reports on knee bone, comparing the accuracy of each technique, which can be used for future development. In the future, this research will be enhanced by comparing X-ray, CT-scan, and MRI reports of knee bone with information retrieval and big data techniques. The results show that deep learning techniques are best for X-ray, MRI, and CT scan images of the knee bone to diagnose diseases.