Search

Chronic myeloid leukaemia (CML) is considered as the cancer of the blood or cancer of the bone marrow. Blood consists of three different cells, one that helps to fight diseases and some infections called white blood cells (WBCs), another that can carry oxygen to the tissues of the body called red blood cells (RBCs), and, last but not the least, those which help the formation of blood clots to stop bleeding termed as platelets. Cancer is observed as a disease ‘diversified in character’, which consists of many different subtypes. Blood cancer is the most common toxicant for the human body.

A significant subject in the field of computer vision and artificial intelligence is outward appearance acknowledgment. There are two mode of correspondence one is verbal, and another is non-verbal [Xiaoxi, M., Weisi, L.: Facial emotion recognition. In: IEEE 2nd International Conference on Signal and Image Processing (2017)]. Among verbal and non-verbal methods for correspondence, outward appearance is non-verbal methods for correspondence. Outward appearance assumes a crucial job which encourages human to communicate their feelings, express their emotions, psychological wellness, viewpoint, and so on [Kaur, M., Vashisht, R.: Comparative study of facial expression recognition techniques. Int. J. Comput. Appl. (2011)]. Understanding gets simpler when human and computer interact with each other if computer can react to non-verbal correspondence of human which is only feelings communicated. In this paper, a calculation is introduced for object discovery dependent on Viola–Jones algorithm. In this paper, there are introduced the consequences of acknowledgment of seven emotion states (neutral, happy, sad, fear, disgust, fear, surprised) in view of outward appearances. The grouping of the highlights was performed utilizing managed learning strategy, i.e., convolutional neural network (CNN).

The increasing burden of respiratory diseases caused by microbial infections poses an immense threat to global health. This review focuses on the various types of biofilms that affect the respiratory system and cause pulmonary infections, specifically bacterial biofilms. The article also sheds light on the current strategies employed for the treatment of such pulmonary infection-causing biofilms. The potential of nanocarriers as an effective treatment modality for pulmonary infections is discussed, along with the challenges faced during treatment and the measures that may be implemented to overcome these. Understanding the primary approaches of treatment against biofilm infection and applications of drug-delivery systems that employ nanoparticle-based approaches in the disruption of biofilms are of utmost interest which may guide scientists to explore the vistas of biofilm research while determining suitable treatment modalities for pulmonary respiratory infections.

Cloud computing, from a very long time has played an integral part in processing, analysing and managing large quantum of data related to heath care system. Healthcare IoT devices are responsible for generation, processing and integration of large volumes of data which is then stored in cloud servers. Nevertheless, this results in huge compromise by delay in response time, which is due to centralized location of cloud servers storing related data. This lag in response time could prove vital while dealing with critical patients like those presenting with cardiac arrest or myocardial infarction and other quality of service (QoS), thus proving the inefficacy of cloud computing in meeting such intense demand. In order to avoid such delay, it necessitates introduction of a novel technology such as Fog computing. In the present publication, we propose, fog computing architecture and the rationale in switching from cloud computing to fog computing for prompt response time.

The need for technology has always found space in Financial Transaction as the number of fraud in financial transactions increases day by day. In this research we have proposed a new methodology by using the isolation forest algorithm and local outlier detection algorithm to detect the financial fraud. A standard data set is used in experimentation to classify a transaction occurred is a fraudulent or not. We have used neural networks and machine learning for classification. We have focused on the deployment of anomaly detection algorithms that is Local Outlier Factor and Isolation Forest algorithm (IFA) on financial fraud transactions data.

BACKGROUND AND AIM Anterior mediastinal masses which invade the great vessels and heart are rare. We report a case of a 76-year-old male presenting with a large invasive anterior mediastinal mass following recent cardiac surgery (coronary artery bypass grafting and aortic valve replacement via sternotomy). MATERIALS AND METHODS This is a case report study with clinical patient information retrieved from hospital electronic records. RESULTS Computed tomography scanning revealed a large heterogeneous 6.5 × 7.2 × 7.0 cm right anterior mediastinal mass. The mass directly propagated via the left innominate vein into the superior vena cava (SVC) and proximal right atrium. The patient underwent redo sternotomy with the aid of cardiopulmonary bypass and hypothermic circulatory arrest to remove the mass. The mass was sitting in the right pleural cavity and was adherent to the right lung and pericardium. Tumor material was removed from the right atrium, SVC and left innominate vein. The mass was excised en bloc along with a portion of the upper lobe of the right lung. DISCUSSION AND CONCLUSION Histology of the mass revealed the diagnosis of invasive type A thymoma with transvenous and transcardiac invasion. We advocate for surgeons to be aggressive in their operative resection of such tumours to ensure the best prognostic outlook for the patient.

Data is generated from various heterogeneous sources in healthcare. To manage and process large amount of healthcare data, cloud computing has been proposed as a solution. However, some challenges like high latency, bandwidth and energy consumption are associated with such solution that reduces the associated quality of service associated. As heath data sets become larger, the probability of occurring errors in processing and transmitting data increases as well. In order to overcome the challenges, fog computing technology has been introduced. Fog computing is considered as an extension of cloud computing. It’s primarily objective is to assist with cloud computing and lately reduces the processing burden of cloud computing. Fog computing helps to provide decentralization of resources, reduced latency and finally improves the overall quality of service in healthcare being the latency sensitive system. Fog computing supports the real-time interaction to update and process the patient data. In first part of the paper, characteristics of fog computing is being defined. And in the second part, an idea is proposed to process data at fog node.

Drowsiness during driving has been seen as one of the main reason for the accidents, which results in life and economical loss. Drowsiness is detected by three conventional methods i.e. Behavior based method, vehicular based method and physiological based method. A lot of work has been done to detect the drowsiness. Different researcher uses different machine learning algorithms to identify drowsiness. The objective of this research is to compare the machine learning algorithms used by different researchers to identify the drowsiness based on behavior centered techniques like eyes, movement of head, yawning etc. for drowsiness detection.

Feature Selection (FS) is the selection of certain features by using a criterion assessment application. In the age of technological advancements and innovations, there has been a significant rise in the use of different social networking applications such as Facebook, YouTube, Twitter, and e-commerce platforms such as Amazon, Alibaba, Flipkart, and others. It has increased the use of sentiment analysis in the different real-world applications so that there is a classification of text in different preset polarities such as optimistic, pessimistic, and impartial. The current research aims to find out the selection process involved in choosing the optimal features for classification using sentimental textual data. The study presents the scope of the sentimental analysis using textual data, fundamentals of the classification process, and the significance of the feature selection schemes so that there is an implementation of effective feature selection for text classification and analysis of sentiments.

Internet of things (IoT) has shown a different research direction in the domain of farming and agriculture. Smart agriculture has reduced the farmer’s effort and improved their capability in managing their crops, soil, water, field monitoring, pesticide control, etc. IoT-based solutions have increased the farmer’s attention toward humidity, temperature, pH value and environment conditions that are the most important concern in agriculture. The unique features of Internet of things like faster access to application and data, reduced human efforts, efficient communication and the global connectivity through different devices have made it a fast-growing technology in providing agriculture solutions. This paper explored various IoT smart agriculture systems and the challenges faced in deploying these systems.

“Handwritten Char. Recognition”, is also known as “HCR”. It is a dynamic and developing area which has seen substantial improvements due to the use of in various areas. One of the exciting fields of machine learning and artificial intelligence is text detection. Numerous methods and techniques are used to classify characters. However, the techniques for translating textual content from a paper document into a machine-readable form were defined as preliminary studies and paperwork. The character recognition system may be a critical factor in establishing a paperless world by digitizing existing paper documents in the coming days. Numerous researches have been conducted in this field, but as handwriting styles differ from each human, it remained an active area of research. The biggest challenge is to obtain the highest possible character recognition accuracy rate, which will inevitably lead to a reduction in manual paperwork. The aim's to enhance handwriting text recognition s/w with a better accuracy, which makes it perfect, reducing the complexity of its space-time. Several papers have implemented a new diagonal-based feature extraction method, which generates a high precision rate than traditional feature extraction methods. This project aims at designing an expert system for "HCR (English) using Neural Network." Using the Artificial Neural Network approach, this can effectively recognize a specific character of type format. This paper shows an overview of the field of recognition of Handwritten Text.

The aim of the paper is to develop a system that can recognize various targeted objects in real-time by incorporating some computer vision techniques and advanced boosted Machine Learning algorithms to solve the problem of object recognition with high accuracy. The task of object detection is a combination of both, image classification and image localization. Image classification identifies the class of target object whereas localization identifies its position inside the input image. Viola-Jones is an algorithm that can work effectively for recognizing a large number of categories such as airplanes, cars, faces, etc. It works on feature extraction and uses Haar-Like features to achieve the objective. So, Viola-J ones is the algorithm that will be used for the development purpose of this paper. Also, instead of using a normal image, the image segmentation technique will be used to create segments in the image that will make it easy to analyze and process the image for further computations.

Presence of Simple Sequence Repeats (SSRs), both in genic and intergenic regions, have been widely studied in eukaryotes, prokaryotes, and viruses. In the current study, we undertook a survey to analyze the frequency and distribution of microsatellites or SSRs in multiple genomes of Coronaviridae members. We successfully identified 919 SSRs with length ≥12 bp across 55 reference genomes majority of which (838 SSRs) were found abundant in genic regions. The in-silico analysis further identified the preferential abundance of hexameric SSRs than any other size-based motif class. Our analysis shows that the genome size and GC content of the genome had a weak influence on SSR frequency and density. However, we find a positive correlation of SSRs GC content with genomic GC content. We also report relatively low abundances of all theoretically possible 501 repeat motif classes in all the genomes of Coronaviridae. The majority of SSRs were AT-rich. Overall, we see an underrepresentation of SSRs across the genomes of Coronaviridae. Besides, our integrative study highlights the presence of SSRs in ORF1ab (nsp3, nsp4, nsp5A_3CLpro and nsp5B_3CLpro, nsp6, nsp10, nsp12, nsp13, & nsp15 domains), S, ORF3a, ORF7a, N & 3′ UTR regions of SARS-CoV-2 and harbours multiple mutations (3′UTR and ORF1ab SSRs serving as major mutational hotspots). This indicates the genic SSRs are under selection pressure against mutations that might alter the reading frame and at the same time responsible for rapid protein evolution. Our preliminary results indicate the significance of the limited repertoire of SSRs in the genomes of Coronaviridae., Highlights • 919 SSRs were found across 55 members of the Coronaviridae family. • Genomes exhibit under-representation of SSRs. • Commonly 12–13 nt long hexanucleotide repeats occupying the genic region. • Identified genic SSRs in SARS-CoV-2 are under selection pressure against mutations. • 29% of the total bases covered by SSRs in SARS-CoV-2 were found to be variants.

Background Drug delivery system is a common practice in cancer treatment. RNA interference-mediated post-transcriptional gene silencing holds promise as an approach to knockdown in the expression of target genes responsible for cancer cell growth and metastasis. RNA interference (RNAi) can be achieved by delivering small interfering RNA (siRNA) and short hairpin RNA (shRNA) to target cells. Since neither interfering RNAs can be delivered in naked form due to poor stability, an efficient delivery system is required that protects, guides, and delivers the siRNA and shRNA to target cells as part of cancer therapy (chemotherapy). Recent findings In this review, a discussion is presented about the different types of drug delivery system used to deliver siRNA and shRNA, together with an overview of the potential benefits associated with this sophisticated biomolecular therapy. Improved understanding of the different approaches used in nanoparticle (NP) fabrication, along with an enhanced appreciation of the biochemical properties of siRNA/shRNA, will assist in developing improved drug delivery strategies in basic and clinical research. Conclusion These novel delivery techniques are able to solve the problems that form an inevitable part of delivering genes in more efficient manner and as part of more effective treatment protocols. The present review concludes that the nanoparticulate RNA delivery system has great possibility for cancer treatment along with several other proposed methods. Several NPs or nanocarriers are already in use, but the methods proposed here could fulfill the missing gap in cancer research. It is the future technology, which unravels the mystery of resolving genomic diseases that is, especially genomic instability and its signaling cascades.

Background: The recent treatment challenges posed by the widespread emergence of pathogenic multidrug-resistant (MDR) bacterial strains cause huge health problems worldwide. Infections caused by MDR organisms are associated with longer periods of hospitalization, increased mortality, and inflated healthcare costs. Staphylococcus aureus is one of these MDR organisms identified as an urgent threat to human health by the World Health Organization. Infections caused by S. aureus may range from simple cutaneous infestations to life-threatening bacteremia. S. aureus infections easily escalate in severely ill, hospitalized, and or immunocompromised patients with an incapacitated immune system. Also, in HIV-positive patients, S. aureus ranks amongst one of the most common comorbidities where it can further worsen a patient’s health condition. At present, anti-staphylococcal therapy is typically reliant on chemotherapeutics that are gaining resistance and pose unfavorable side-effects. Thus, newer drugs are required that can bridge these shortcomings and aid effective control against S. aureus. Objective: In this review, we summarize drug resistance exhibited by S. aureus, lacunae in current anti-staphylococcal therapy and nanoparticles as an alternative therapeutic modality. The focus lies on various green synthesized nanoparticles, their mode of action, and their application as potent antibacterial compounds against S. aureus. Conclusion: The use of nanoparticles as anti-bacterial drugs has gained momentum in the recent past, and green synthesized nanoparticles, which involve microorganisms and plants or their byproducts for the synthesis of nanoparticles, offer a potent, as well as environment friendly solution in warfare against MDR bacteria.

Aim Nontuberculous mycobacterial (NTM) infection such as endophthalmitis, dacryocystitis, and canaliculitis are pervasive across the globe and are currently managed by antibiotics. However, the recent cases of Mycobacteroides developing drug resistance reported along with the improper practice of medicine intrigued us to explore its genomic and proteomic canvas at a global scale and develop a chimeric vaccine against Mycobacteroides. Main methods We carried out a vivid genomic study on five recently sequenced strains of Mycobacteroides and explored their Pan-core genome/proteome in three different phases. The promiscuous antigenic proteins were identified via a subtractive proteomics approach that qualified for virulence causation, resistance and essentiality factors for this notorious bacterium. An integrated pipeline was developed for the identification of B-Cell, MHC (Major histocompatibility complex) class I and II epitopes. Key findings Phase I identified the shreds of evidence of reductive evolution and propensity of the Pan-genome of Mycobacteroides getting closed soon. Phase II and Phase III produced 8 vaccine constructs. Our final vaccine construct, V6 qualified for all tests such as absence for allergenicity, presence of antigenicity, etc. V6 contains β-defensin as an adjuvant, linkers, Lysosomal-associated membrane protein 1 (LAMP1) signal peptide, and PADRE (Pan HLA-DR epitopes) amino acid sequence. Besides, V6 also interacts with a maximum number of MHC molecules and the TLR4/MD2 (Toll-like receptor 4/Myeloid differentiation factor 2) complex confirmed by docking and molecular dynamics simulation studies. Significance The knowledge harnessed from the current study can help improve the current treatment regimens or in an event of an outbreak and propel further related studies.

Cancer is the leading cause of mortality among humans globally. Knowing about the etiology underlying the advancement of cancer is imperative for curtailing the monetary and social burden of cancer. In addition to genetic mutations, altered metabolism involved metabolic rewiring is needed in cancer cells to support their high nutritional demand needed for energy generation. Cancer metabolism also refers to the perturbations in biochemical pathways that are reported in tumor cells compared with most of the normal cells. Metabolic impairments in tumor cells are more frequent which include aerobic glycolysis, decreased oxidative phosphorylation, and the accelerated production of biosynthetic intermediates crucial to the proliferative cells for their growth and development. Interruptions in metabolic cascades responsible for fueling energy into the cancer cells for their growth has been observed in most of the cancer forms. These interruptions, in turn, facilitates growth in tumor cells by ceasing biochemical signals used to inhibit tumor initiation, hence eventually increase the metastatic character of the tumor cells. However, the precise mechanisms whereby metabolic pathways contribute to the cancer prognosis remain uncertain. This chapter thus consolidates recent findings regarding cross talk between metabolic alterations and cancer biology. Further, a concrete and deep understanding of this heterogeneity may enable the advancement and optimization of potential therapeutic approaches that target biochemical pathways associated with proliferation of malignant cells.

Nowadays, the field of biomarker discovery has become the topic of vivid research with the current emergence of novel technologies. Major progress in cancer control will be significantly aided by early detection for the diagnosis and treatment of cancer in its preinvasive state. Cancer being a diverse disease involves mutations in mostly three classes of genes such as oncogenes (proto-oncogenes), DNA repair genes, and tumor suppressor genes, presenting a wide range of opportunities for the development and formulation of various cancer biomarkers. Cancer biomarkers are used to follow up disease process before it becomes more severe and help in screening, thus greatly aid in cancer diagnosis and treatment. They also act as biochemical indicators to show the evidence of the presence of a tumor. There are various types of tumor biomarkers, which are classified on the basis of their functionalities. For instance, tumor diagnostic markers aid in predicting the occurrence of tumor during diagnosis, while tumor prognostic markers are clinical measures used to assist in bringing out an individual patients risk of a future consequence including disease reoccurrence after primary treatment. Similarly, various biomarkers are accountable for serving as a potential biochemical indicator to examine the processes of disease progression and help in disease diagnosis. However, the precise roles of cancer biomarkers in contributing to examine the cancer progression remain uncertain. This chapter therefore recapitulates about the recent findings of current and emerging biomarkers in cancer with fundamental insight into different markers used in cancer detection. Further, biomarkers based on these strategies may lead to remarkable improvement in cancer screening, prognosis, and management of therapeutic response in cancer patients.

In this paper, we propose an improved end-to-end learning algorithm to address the aggregation of multiclass classification and regression for age estimation by using deep Convolutional Neural Networks (CNNs). Inspired by Soft Stagewise Regression Network (SSR-Net), we take residual units embedded with channel and spatial feature response correlation values and dynamically adopted the kernel corresponding to these feature maps into our model. In addition, we used weight normalization at each layer by using input samples at the beginning of training and this weight normalization was beneficial both in terms of accuracy as well as training time. We validate the proposed model based on benchmark datasets and compare the MAE with seven other mainstream networks. The results reveal that our model achieves an improved performance. Our contribution is an updated algorithm for age estimation by adopting the latest attention and normalization mechanisms for balancing the efficiency and accuracy of the proposed model.

Mobile ad hoc Network is infrastructure less wireless network and decentralized way, and then for a large network number of nodes dynamically therefor the connection established between source node to destination node is really challenging. The challenge is interconnecting ad hoc network to the internet seems from the needs to inform ad hoc nodes about available gateways in an extremely challenging scenario while a making a minimum consumption of the source network resources. Then an efficient gateway discovery of an ad hoc network becomes one of the central factors to enable the economic consumption of hybrid ad hoc network in future mobile and wireless network. In mobile ad hoc network have multihop nature of MANET therefore several reachable gateways for mobile node at any period of time. If the mobile node receives gatways advertisement from more than one gateway. It has to determine which gateway to use for connecting to the net. Most existing protocol choose the gateway which is closer in terms of the number of physical hops. This paper has focused on design an efficient and adaptive subnetting hybrid gateway discovery mechanism on the basis of dynamic TTL value adjustment such that congestion and unnecessary overhead is reduced. Selecting the gateway on the basis of one and two parameters will increase the performance and throughput of the network. The main objective of adaptive gateway discovery to determine the optimal TTL value in terms of number of hops to determine the proactive area, nodes outside this area follow the reactive approach. Consequently, for achieving a good trade off between performanceand network operating expense.

In recent years, deep neural networks (DNNs) have achieved a remarkable progression in solving many complex problems. DNNs are suitable for dealing with the problems related to time series, such as speech recognition and natural language processing. Video dynamics detection, for instance, is time dependent. Apparently, video dynamics detection needs to utilize the present, previous, and next frames of a given video. If a frame change occurs, it triggers whether a video event happens or not. In this paper, video dynamics detection based on deep learning is implemented and our contributions are to effectively improve the accuracy of video dynamics detection. The contributions of this paper are as follows: 1) increasing the accuracy rate to 96% compared to an FSM-based video dynamics detection in real time; 2) By combining convolutional neural network and recurrent neural network (RNN) together, the training time is greatly reduced as we expected.

Today millions of ordinary citizens are using networks for banking, shopping and filing their tax return. Network security has become a massive problem. All this requires network to identify its legal users for providing services. An authentication protocol used is Kerberos which uses strong secret key for user authentication but it is vulnerable in case of weak passwords. Authentication & key distribution protocols requires sharing secret key(s) with a view that only the concerned users know to derive the information from it. These protocols are vulnerable to key guessing attacks. Another important consideration is perfect forward secrecy in which our proposed scheme cover cases with application servers, authentication servers or clients key are revealed & their combination. In this paper our proposed scheme deal with key guessing attacks, perfect forward secrecy and protocols for few combinations of keys. All these protocols are based on the fact that the keys are weak & can be exploited easily.

Rapid development in Internet and the increase in online information, the technology demanded for intelligently classifying the textual data has become significant role in Information Retrieval Process. Based on given query in the search box, the response from the internet has made open to the public. Thus, the scope of text mining is being explored by several researchers. Sentiment Analysis is one of the most popular process for analysing user opinions and feelings, and since, online communication has become the fast ever growing medium for expressing thoughts, therefore, there have been development in text classification to improve sentiment analysis. In this paper, some of the prior works on sentiment analysis and the advancements in text classification have been discussed.

Question Answering over Linked Data (QALD) refer to the use of Linked Data by question answering systems, and in recent times this has become increasingly popular as it opens up a massive Linked Data cloud which is a rich source of encoded knowledge. However, a major shortfall of current QALD systems is that they focus on presenting a single fact or factoid answer which is derived using SPARQL (SPARQL Protocol and RDF Query Language) queries. There is now an increased interest in development of human-like systems which would be able to answer questions and even hold conversations by constructing sentences akin to humans. In this paper, we introduce a new answer construction and presentation system, which utilizes the linguistic structure of the source question and the factoid answer to construct an answer sentence which closely emanates a human-generated answer. We employ both semantic Web technology and the linguistic structure to construct the answer sentences. The core of the research resides on extracting dependency subtree patterns from the questions and utilizing them in conjunction with the factoid answer to generate the answer sentence with a natural feel akin to an answer from a human when asked the question. We evaluated the system for both linguistic accuracy and naturalness using human evaluation. These evaluation processes showed that the proposed approach is able to generate answer sentences which have linguistic accuracy and natural readability quotients of more than 70%. In addition, we also carried out a feasibility analysis on using automatic metrics for answer sentence evaluation. The results from this phase showed that the there is not a strong correlation between the results from automatic metric evaluation and the human ratings of the machine-generated answers.

Natural Language Generation (NLG) is defined as the systematic approach for producing human understandable natural language text based on non-textual data or from meaning representations. This is a significant area which empowers human-computer interaction. It has also given rise to a variety of theoretical as well as empirical approaches. This paper intends to provide a detailed overview and a classification of the state-of-the-art approaches in Natural Language Generation. The paper explores NLG architectures and tasks classed under document planning, micro-planning and surface realization modules. Additionally, this paper also identifies the gaps existing in the NLG research which require further work in order to make NLG a widely usable technology.