b) 2023-Scopus Open Access (Pdf)

Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/5193

Browse

Search Results

Now showing 1 - 10 of 22
  • Thumbnail Image
    Item
    AN OPTIMIZED UNCERTAINTY AWARE FINE-TUNED TRANSFER LEARNING FOR COVID-19 DIAGNOSIS FROM MEDICAL IMAGES (Article)
    (Intelligent Network and Systems Society, 2023-07) Selvam, Deepika; Murugesan, Rajeswari
    : In worldwide, COVID-19 has had a significant influence on patients and healthcare systems. Earlier stage of COVID-19 diagnosis and identification are the primary problems in the current pandemic condition. The identification of COVID-19 in CT and chest-X-ray (CXR) imaging is essential for diagnosis, treatment, and evaluation. However, radiologists face a foreseeable issue when it comes to coping with analytical ambiguity in medical imaging. In that situation, a paradigm based on convolutional neural network (CNN) with transfer learning (TL) and taking uncertainty into account was suggested to identify COVID-19 from CT and CXR scan images. However, this method was less capable to extract more useful and distinct image attributes. By fine-tuning the TL network design, this issue can be resolved. The fine tuning model can only fine tune specific layers associated with various goal objectives. However, one of the primary issues with such a method is the selection of layers. To solve this issue, this research uses an enhanced spider monkey optimization (ESMO) technique to select layers of ResNet architecture. Every population of an initialized spider monkey (SM) selects layer and parameter for fine tuning architecture. The fitness value of each SM is used to find best optimal solutions. Categorical cross-entropy loss (CCEL) is considered as fitness of SM. The fitness value of each SM is employed to determine the highest optimal solutions. Subsequent processes such as the stance update process, the learning and decision phase for the local and global leaders of ESMO algorithms, iteratively search for near optimal solutions until convergence. The proposed method can automatically estimate the various CNN layers, which can then be fine-tuned to extract more significant and discriminative features for efficient COVID-19 identification. Finally, the results reveal that the proposed ESMO-ResNet model on SARS-CoV-2 CT database achieves 91.23% accuracy, which is 21.46%, 20.2%, 12.4%, and 6% higher than the AlexNet, multi-source deep transfer learning (MSDTL), stacked convolutional neural network (S-CNN) and dynamic mutual training (DMT) models, respectively. Similarly, the ESMO-ResNet model on Covi-19 Radiography dataset achieves 90.06% accuracy, which is 21.34%, 20%, 9.7%, and 3.5% higher than AlexNet, MSDTL, S-CNN, and DMT models, respectively.
  • Thumbnail Image
    Item
    A STUDY ON NEW CLASSES OF BINARY SOFT SETS IN TOPOLOGICAL ROUGH APPROXIMATION SPACE (Article)
    (E.A. Buketov Karaganda University Publish house, 2023-12) Parvathy, C R; Sofia, A
    Soft binary relation is used to define new classes of soft sets, namely BR-soft simply open set and BR-soft simply* alpha open set, in topological rough approximation space over two different universes. The defined set provides information on the missing elements of a BR-soft set and can help in simplifying decision making. Approximation operators are defined and the characteristics of the proposed sets are studied with examples. The relationship between the defined sets and other soft sets is brought out. An accuracy check was done to compare the proposed method with other methods. It is identified that the proposed method is more accurate.
  • Thumbnail Image
    Item
    BIOSYNTHESIS AND BIODEGRADATION OF POLY(3-HYDROXYBUTYRATE) FROM PRIESTIA FLEXA; A PROMISING MANGROVE HALOPHYTE TOWARDS THE DEVELOPMENT OF SUSTAINABLE ECO-FRIENDLY BIOPLASTICS (Article)
    (Elsevier GmbH, 2023-02) Chathalingath, Nayana; Kingsly, Joshua Stephen; Gunasekar, Anbarasi
    The protracted persistence of petrochemical plastics in the environment and their non-biodegradability impede the survival of living creatures. Recently, biopolymers are being thoroughly researched as a potential replacement for conventional plastics. This present study sought to locate Poly(3-hydroxybutyrate) synthesizing bacterial species prevalent in the mangrove ecosystem. Six halophilic bacterial isolates were obtained from the mangrove habitat, four isolates displayed superior cell dry weight as well as PHB accumulation. Isolate PMPHB5 showed the highest cell dry weight (4.92 ± 0.02 g/L), while the maximum PHA yield (80%) was found with PMPHB7. Hence, PMPHB7 was chosen for further optimization of carbon source wherein glucose demonstrated improved cell growth as well as PHB production. The characterization of the PHB granules was performed by FT-IR spectroscopy and FE-SEM EDX. The presence of characteristic elements in the sample was confirmed using EDX. Isolate PMPHB7 was further identified as Priestia flexa through 16S rRNA gene sequencing (GenBank accession number: ON362236) and a phylogenetic tree was constructed to reveal the molecular relationships of this organism with others. The solvent-cast biopolymer film was made to check the biodegradability of the extracted PHB. When buried in soil, it was found that the biopolymer film exhibited approximately 73% biodegradation after 21 days. Thus, the present study sheds light on the potential of mangrove-associated halophytes to efficiently produce PHB that is readily biodegradable in soil.
  • Thumbnail Image
    Item
    PLANT DERIVED EXOSOME- LIKE NANOVESICLES: AN UPDATED OVERVIEW (Review)
    (Elsevier B.V, 2023-02) Subha, D; Harshnii, K; Madhikiruba, K G; Nandhini, M; Tamilselvi, K S
    Exosomes are nanovesicles in the size range of 30–150 nm, produced by mammalian and plant cells. They have the lipid bilayer enclosing a unique mix of biologically active components including proteins, nucleic acids, metabolites and lipids, that depend on their source of origin. The plant derived nanovesicles are gaining considerable research attention due to their ability to be absorbed from the dietary sources. Their bioactive components impart many therapeutic properties to them such as anti-tumorigenic, anti-oxidative, anti-inflammatory, hepatoprotective effects and tissue regeneration. The possibilities of using plant derived exosomes for drug delivery is also promising. This review focusses on the biogenesis and biological nature of exosomes derived from plants and describes their various inherent therapeutic properties. It sheds light on the recently developed methods to study them. The existing challenges in the exosomal research as well as the future prospective are highlighted. Overall, it is an update on the advancements on the research in plant exosomes which can provide a replacement for toxic synthetic drugs and possibilities for disease therapy.
  • Thumbnail Image
    Item
    NBCL5 FUNCTIONALIZED PERLITE: A POTENT AND RECYCLABLE CATALYST FOR SYNTHESIS OF PYRANS (Article)
    (MDPI, 2023-02) Lakshminarayanan, Komalavalli; Sivanandhan, Monisha; Ramasundaram, Subramaniyan; Oh, Tae Hwan; Shah, Kinjal J; Saranraj, Kumaravel; Parasuraman, Amutha; Balu, Krishnakumar
    Niobium pentachloride functionalised perlite was prepared via a solid state dispersion technique, which was utilized as an efficient heterogeneous catalyst for the synthesis of pyrans. The immobilisation of NbCl5 over perlite was examined by Fourier-transform infrared (FT-IR) spectroscopy, X-ray diffraction (XRD), Thermogravimetric analysis (TGA), scanning electron microscope (SEM) with energy dispersive spectra (EDS), and Brunauer, Emmett and Teller (BET) surface area measurements. The wt% of NbCl5-loaded perlite was optimized based on the adequacy with respect to the yield of the pyrans in various solvents. The recyclability of the catalyst was validated in synthesizing pyrans and the results marked its efficiency up to five runs. The efficacy of the NbCl5/perlite catalyst was found to be comparable and better with respect to the other heterogeneous catalysts reported. The structures of pyrans were confirmed by FT-IR, 1H and 13C NMR spectral techniques. The proposed recyclable heterogeneous NbCl5/perlite catalyst simplifies the protocol, and has minimal chemical waste, a lower reaction time and a high-yield.
  • Thumbnail Image
    Item
    PESTICIDE RECOMMENDATION FOR DIFFERENT LEAF DISEASES AND RELATED PESTS USING MULTI-DIMENSIONAL FEATURE LEARNING DEEP CLASSIFIER (Article)
    (International Information and Engineering Technology Association, 2023-02) Saleem, Jaithoon Bibi Mohammed; Shanmugam, Karpagavalli
    In agricultural applications, the most essential task is to classify leaf diseases and their associated pests from various aspects. To achieve this, a Deep Convolutional Neural Network (DCNN) model was developed to classify the leaf diseases based on the soil and climatic features. But it needs a recommendation system to control the pesticide use for controlling the leaf diseases caused by specific pests. Hence, this paper hybridizes the Multi-dimensional Feature Learning-based DCNN (MFL-DCNN) with the Rough Set (RS) on an intuitionistic Fuzzy approximation space (RSF)-based decision support system to suggest the proper pesticides for a certain crop to be planted in a particular region. First, the leaf images are augmented by the Positional-aware Dual-Attention and Topology-Fusion with Evolutionary Generative Adversarial Network (PDATFEGAN) model. Then, the multi-dimensional data such as the created leaf images, pest, soil, weather, and pesticide data are fed to the DCNN with a softmax classifier for classifying leaf diseases and related pests. Then, the RSF-based decision model is applied, which determines the correlation between leaf disease and pests to recommend suitable pesticides. Finally, the experimental results reveal that the MFL-DCNN-RSF accomplishes a maximum efficiency than all other models for recommending pesticides to control leaf diseases and pests.
  • Thumbnail Image
    Item
    MANNOSE: A POTENTIAL SACCHARIDE CANDIDATE IN DISEASE MANAGEMENT (Review)
    (Springer, 2023-03) Dhanalakshmi, M; Sruthi, D; Jinuraj, K R; Das, Kajari; Dave, Sushma; Andal N, Muthulakshmi; Das, Jayashankar
    There are a plethora of antibiotic resistance cases and humans are marching towards another big survival test of evolution along with drastic climate change and infectious diseases. Ever since the first antibiotic [penicillin], and the myriad of vaccines, we were privileged to escape many infectious disease threats. The survival technique of pathogens seems rapidly changing and sometimes mimicking our own systems in such a perfect manner that we are left unarmed against them. Apart from searching for natural alternatives, repurposing existing drugs more effectively is becoming a familiar approach to new therapeutic opportunities. The ingenious use of revolutionary artificial intelligence-enabled drug discovery techniques is coping with the speed of such alterations. D-Mannose is a great hope as a nutraceutical in drug discovery, against CDG, diabetes, obesity, lung disease, and autoimmune diseases and recent findings of anti-tumor activity make it interesting along with its role in drug delivery enhancing techniques. A very unique work done in the present investigation is the collection of data from the ChEMBL database and presenting the targetable proteins on pathogens as well as on humans. It shows Mannose has 50 targets and the majority of them are on human beings. The structure and conformation of certain monosaccharides have a decisive role in receptor pathogen interactions and here we attempt to review the multifaceted roles of Mannose sugar, its targets associated with different diseases, as a natural molecule having many success stories as a drug and future hope for disease management.
  • Thumbnail Image
    Item
    AN AMINO ACID GRAFTED GRAPHENE OXIDE AS PROMISING MATERIAL IN POLY(UREA-FORMALDEHYDE)-EPOXY MICROCAPSULES FOR ENHANCING THE INTERFACIAL ADHESION OF EPOXY COATINGS (Article)
    (Asian Publication Corporation, 2023-03) Priyanka, D; Nalini, D
    Novel microencapsulated materials with superior anti-corrosion properties and improved adhesive strength on the metal substrate were produced by emulsion polymerization and characterized successfully. Initially, serine grafted graphene oxide was prepared and characterized through various sophisticated techniques. Then, MC-GO/epoxy and MC-GO-Ser were individually impregnated into th epoxy system and applied on the mild steel substrates. Corrosion tests were performed to evaluate the non-corrosive nature of MC-GO/epoxy and MC-GO-Ser/epoxy samples. After 7 days of exposure in saline media, MC-GO-Ser microcapsules demonstrated 80.6 % protective efficiency. Furthermore, the peel strength of 2.90 N revealed that the coating loaded with MC-GO-Ser microcapsules had improved adherence to the mild steel surface. Results of urea-formaldehyde GO-Ser microcapsules showed better corrosion protection and greater adhesive strength, which is probably because of the exceptional barrier action of microcapsules against the incursion of corrosion solution onto the mild steel surface.
  • Thumbnail Image
    Item
    GENERATING NOVEL FOCAL PATTERNS FOR RADIAL VARIANT VECTOR BEAM FOCUSING THROUGH A DIELECTRIC INTERFACE
    (Photonics Society of Poland, 2023-04-02) Maruthasalam, Lavanya; Thiruarul, Duraisamy; Rajesh, Karuppaiya Balasundaram
    Electric and magnetic energy densities as well as energy flux (Poynting vector) for radial variant vector beam focusing through a dielectric interface is analyzed numerically based on vector diffraction theory. The electric and magnetic energy densities are tailored by properly manipulating the radial as well as initial phases to generates novel focal patterns in the focal area. These peculiar properties may find applications in fields such as optical trapping, optical recording, magnetic recording, and magnetic resonance microscopy and semiconductor inspection.
  • Thumbnail Image
    Item
    GREEN NANOBIOPOLYMERS FOR ECOLOGICAL APPLICATIONS: A STEP TOWARDS A SUSTAINABLE ENVIRONMENT (Review)
    (Royal Society of Chemistry, 2023-04-20) Chincholikar, Preeti; Singh, Kshitij RB; Natarajan, Arunadevi; Kerry, Rout George; Singh, Jay; Malviya, Jitendra; Singh, Ravindra Pratap
    To minimize the usage of non-renewable resources and to maintain a sustainable environment, the exploitation of green nanobiopolymers should be enhanced. Biopolymers are generally developed from various microorganisms and plants in the specified condition. This review article discusses the current advances and trends of biopolymers, particularly in the arena of nanotechnology. In addition, discussion on various synthesis steps and structural characterization of green polymer materials like cellulose, chitin, and lignin is also encompassed. This article aims to coordinate the most recent outputs and possible future utilization of nanobiopolymers to the ecosystem with negligible effects by promoting the utilities of polymeric materials like polycaprolactones, starch, and nanocellulose. Additionally, strategic modification of cellulose into nanocellulose via rearrangement of the polymeric compound to serve various industrial and medical purposes has also been highlighted in the review. Specifically, the process of nanoencapsulation and its advancements in terms of nutritional aspects was also presented. The potential utility of green nanobiopolymers is one of the best cost-effective alternatives concerning circular economy and thereby helps to maintain sustainability.