BITS Faculty Publications
Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867
Browse
16 results
Search Results
Item Least squares projection twin support vector clustering (LSPTSVC)(Elsevier, 2020-09) Richhariya, BharatClustering is a prominent unsupervised learning technique. In the literature, many plane based clustering algorithms are proposed, such as the twin support vector clustering (TWSVC) algorithm. In this work, we propose an alternative algorithm based on projection axes termed as least squares projection twin support vector clustering (LSPTSVC). The proposed LSPTSVC finds projection axis for every cluster in a manner that minimizes the within class scatter, and keeps the clusters of other classes far away. To solve the optimization problem, the concave-convex procedure (CCCP) is utilized in the proposed method. Moreover, the solution of proposed LSPTSVC involves a set of linear equations leading to very less training time. To verify the performance of the proposed algorithm, several experiments are performed on synthetic and real world benchmark datasets. Experimental results and statistical analysis show that the proposed LSPTSVC performs better than existing algorithms w.r.t. clustering accuracy as well as training time. Moreover, a comparison of the proposed method with existing algorithms is presented on biometric and biomedical applications. Better generalization performance is achieved by proposed LSPTSVC on clustering of facial images, and Alzheimer’s disease data.Item A fuzzy universum least squares twin support vector machine (FULSTSVM)(Springer, 2021-01) Richhariya, BharatUniversum based twin support vector machines give prior information about the distribution of data to the classifier. This leads to better generalization performance of the model, due to the universum. However, in many applications the data points are not equally useful for the classification task. This leads to the use of fuzzy membership functions for the datasets. Similarly, in universum based algorithms, all the universum data points are not equally important for the classifier. To solve these problems, a novel fuzzy universum least squares twin support vector machine (FULSTSVM) is proposed in this work. In FULSTSVM, the membership values are used to provide weights for the data samples of the classes, as well as to the universum data. Further, the optimization problem of proposed FULSTSVM is obtained by solving a system of linear equations. This leads to an efficient fuzzy based algorithm. Numerical experiments are performed on various benchmark datasets, with discussions on generalization performance, and computational cost of the algorithms. The proposed FULSTSVM outperformed the existing algorithms on most datasets. A comparison is presented for the performance of the proposed and other baseline algorithms using statistical significance tests. To show the applicability of FULSTSVM, applications are also presented, such as detection of Alzheimer’s disease, and breast cancer.Item Minimum variance-embedded deep kernel regularized least squares method for one-class classification and its applications to biomedical data(Elsevier, 2020-03) Richhariya, BharatDeep kernel learning has been well explored for multi-class classification tasks; however, relatively less work is done for one-class classification (OCC). OCC needs samples from only one class to train the model. Most recently, kernel regularized least squares (KRL) method-based deep architecture is developed for the OCC task. This paper introduces a novel extension of this method by embedding minimum variance information within this architecture. This embedding improves the generalization capability of the classifier by reducing the intra-class variance. In contrast to traditional deep learning methods, this method can effectively work with small-size datasets. We conduct a comprehensive set of experiments on 18 benchmark datasets (13 biomedical and 5 other datasets) to demonstrate the performance of the proposed classifier. We compare the results with 16 state-of-the-art one-class classifiers. Further, we also test our method for 2 real-world biomedical datasets viz.; detection of Alzheimer’s disease from structural magnetic resonance imaging data and detection of breast cancer from histopathological images. Proposed method exhibits more than 5% score compared to existing state-of-the-art methods for various biomedical benchmark datasets. This makes it viable for application in biomedical fields where relatively less amount of data is available.Item Machine Learning Techniques for the Diagnosis of Alzheimer’s Disease: A Review(ACM Digital Library, 2020-04) Richhariya, BharatAlzheimer’s disease is an incurable neurodegenerative disease primarily affecting the elderly population. Efficient automated techniques are needed for early diagnosis of Alzheimer’s. Many novel approaches are proposed by researchers for classification of Alzheimer’s disease. However, to develop more efficient learning techniques, better understanding of the work done on Alzheimer’s is needed. Here, we provide a review on 165 papers from 2005 to 2019, using various feature extraction and machine learning techniques. The machine learning techniques are surveyed under three main categories: support vector machine (SVM), artificial neural network (ANN), and deep learning (DL) and ensemble methods. We present a detailed review on these three approaches for Alzheimer’s with possible future directions.Item NEXT Neuroprotective Efficacy of Co-Encapsulated Rosiglitazone and Vorinostat Nanoparticle on Streptozotocin Induced Mice Model of Alzheimer Disease(ACS, 2021-04) Chitkara, Deepak; Taliyan, RajeevAnomalies in brain insulin signaling have been demonstrated to be involved in the pathology of Alzheimer disease (AD). In this context, the neuroprotective efficacy of an insulin sensitizer, rosiglitazone, has been confirmed in our previous study. In the present study, we hypothesize that a combination of an epigenetic modulator, vorinostat, along with rosiglitazone can impart improved gene expression of neurotrophic factors and attenuate biochemical and cellular alteration associated with AD mainly by loading these drugs in a surface modified nanocarrier system for enhanced bioavailability and enhanced therapeutic efficacy. Hence, in this study, rosiglitazone and vorinostat were loaded onto a poloxamer stabilized polymeric nanocarrier system and administered to mice in the intracerebroventricular streptozotocin (3 mg/kg) induced model of AD. Treatment with the free drug combination (rosiglitazone 5 mg/kg, vorinostat 25 mg/kg) for 3 weeks attenuated the behavioral, biochemical, and cellular alterations as compared to either treatment alone (rosiglitazone 10 mg/kg, vorinostat 50 mg/kg). Further, the coencapsulated nanoformulation (rosiglitazone 5 mg/kg, vorinostat 25 mg/kg) exerted better neuroprotective efficacy than the free drug combination as evidenced by improved behavioral outcome, reduced oxidative stress, and elevated levels of neurotrophic factors. In conclusion, the synergistic neuroprotective efficacy of rosiglitazone and vorinostat has been increased through the poloxamer stabilized polymeric nanocarrier system.Item Development and Validation of PEG-PCL Based Nanoformulation of Rosiglitazone and Evaluation of its Brain Selectivity in Mice Model of Alzheimer’s disease(Alzheimer's Association, 2021-12) Taliyan, RajeevType-2 Diabetes Mellitus and insulin resistance increases the risk of Alzheimer’s disease (AD). Recent studies highlighted the role of peroxisome proliferator-activated receptor-gamma (PPAR-γ) in modulation of AD. This study was designed to investigate the effect of rosiglitazone alone or in its nanoformulated form for an effective drug delivery in mice model of AD.Item Design and biological evaluation of Repaglinide loaded polymeric nanocarriers for diabetes linked neurodegenerative disorder: QbD-driven optimization, in situ, in vitro and in vivo investigation(Elsevier, 2023-04) Taliyan, RajeevDiabetes mellitus is a metabolic disorder characterized by inadequate insulin secretion and signaling dysfunction, leading to a vast spectrum of systemic complications. These complications trigger cascades of events that result in amyloid-beta plaque formation and lead to neurodegenerative disorders such as Alzheimer’s. Repaglinide (REP) an insulinotropic agent, suppresses the down regulatory element antagonist modulator (DREAM) and enhances the ATF6 expression to provide neuroprotection following the DREAM/ATF6/apoptotic pathway. However, oral administration of REP for brain delivery becomes more complicated due to its physicochemical characteristics (high protein binding (>98%), low permeability, short half-life (∼1 h), low bioavailability). Therefore, to circumvent these problems, we develop a polymeric nanocarrier system (PNPs) by in-house synthesized di-block copolymer (PEG-PCL). PNPs were optimized using quality by design approach response surface methodology and characterized by particle size (112.53 ± 5.91 nm), PDI (0.157 ± 0.08), and zeta potential (−6.20 ± 0.82 mV). In vitro release study revealed that PNPs (∼70% in 48 h) followed the Korsmeyer-Peppas model with a Fickian diffusion release pattern, and in intestinal absorption assay PNPs showed increment of ∼1.3 folds compared of REP. Moreover, cellular studies confirmed that REP-loaded PNPs significantly enhance the cellular viability, uptake and reduce the peroxide-induced stress in neuroblastoma SHSY-5Y cells. Further, pharmacokinetic parameters of PNPs showed an increment in tmax (2.46-fold), and Cmax (1.25-fold) associated with REP. In the brain biodistribution study, REP loaded PNPs was sustained for 24 h whereas free REP sustained only for12 h. In DM induced neurodegenerative murine model, a significantly (p < 0.01) enhanced pharmacodynamic was observed in PNP treated group by estimating biochemical and behavioral parameters. Hence, oral administration of REP-loaded PNPs promotes efficient brain uptake and improved efficacy of REP in the diseased modelItem Neuroprotective Effect of Lentivirus-Mediated FGF21 Gene Delivery in Experimental Alzheimer’s Disease is Augmented when Concerted with Rapamycin(Springer, 2022-02) Taliyan, RajeevAlzheimer type of dementia is accompanied with progressive loss of cognitive function that directly correlates with accumulation of amyloid beta plaques. It is known that Fibroblast growth factor 21 (FGF21), a metabolic hormone, with strong neuroprotective potential, is induced during oxidative stress in Alzheimer’s disease. Interestingly, FGF21 cross-talks with autophagy, a mechanism involved in the clearance of abnormal protein aggregate. Moreover, autophagy activation by Rapamycin delivers neuroprotective role in Alzheimer’s disease. However, the synergistic neuroprotective efficacy of overexpressed FGF21 along with Rapamycin is not yet investigated. Therefore, the present study examined whether overexpressed FGF21 along with autophagy activation ameliorated neurodegenerative pathology in Alzheimer’s disease. We found that cognitive deficits in rats with intracerebroventricular injection of Amyloid beta1-42 oligomers were restored when injected with FGF21-expressing lentiviral vector combined with Rapamycin. Furthermore, overexpression of FGF21 along with Rapamycin downregulated protein levels of Amyloid beta1-42 and phosphorylated tau and expression of major autophagy proteins along with stabilization of oxidative stress. Moreover, FGF21 overexpressed rats treated with Rapamycin revamped the neuronal density as confirmed by histochemical, cresyl violet and immunofluorescence analysis. These results generate compelling evidence that Alzheimer’s disease pathology exacerbated by oligomeric amyloid beta may be restored by FGF21 supplementation combined with Rapamycin and thus present an appropriate treatment paradigm for people affected with Alzheimer’s disease.Item Nanocarrier mediated drug delivery as an impeccable therapeutic approach against Alzheimer’s disease(Elsevier, 2022-03) Taliyan, Rajeev; Singhvi, GautamFor the past several years, dementia, is one of the predominantly observed groups of symptoms in a geriatric population. Alzheimer’s disease (AD) is a progressive memory related neurodegenerative disease, for which the current Food and drug administration approved therapeutics are only meant for a symptomatic management rather than targeting the root cause of AD. These therapeutics belong to two classes, Acetylcholine Esterase inhibitors and N-methyl D-aspartate antagonist. Furthermore, to facilitate neuroprotective action in AD, the drugs are majorly expected to reach the specific target area in the brain for the desired efficacy. Thus, there is a huge requirement for drug discovery and development for facilitating the entry of drugs more in brain to exert a specific action. The very first line of defense and the major limitation for the entry of drugs into the brain is the Blood Brain Barrier, followed by Blood-Cerebrospinal Fluid Barrier. More than a barrier, these mainly act as selectively permeable membranes, which allows entry of specific molecules into the brain. Furthermore, specific enzymes result in the degradation of xenobiotics. All these mechanisms pose as hurdles in the way of effective drug delivery in the brain. Thus, novel techniques need to be harbored for the facilitation of the delivery of such drugs into the brain. Nanocarriers are advantageous for facilitating the specific targeted drug treatment in AD. As nanomedicines are one of the novels and most useful approaches for AD, thus the present review mainly focuses on understanding the advanced use of nanocarriers for targeted drug delivery in the management of AD.Item Epigenetic modifications by inhibiting histone deacetylases reverse memory impairment in insulin resistance induced cognitive deficit in mice(Elsevier, 2016-06) Taliyan, RajeevInsulin resistance has been reported as a strong risk factor for Alzheimer's disease. However, the molecular mechanisms of association between these still remain elusive. Various studies have highlighted the involvement of histone deacetylases (HDACs) in insulin resistance and cognitive deficits. Thus, the present study was designed to investigate the possible neuroprotective role of HDAC inhibitor, suberoylanilide hydroxamic acid (SAHA) in insulin resistance induced cognitive impairment in mice. Mice were subjected to either normal pellet diet (NPD) or high fat diet (HFD) for 8 weeks. HFD fed mice were treated with SAHA at 25 and 50 mg/kg i.p. once daily for 2 weeks. Serum insulin, glucose, triglycerides, total cholesterol and HDL-cholesterol levels were measured. A battery of behavioral parameters was performed to assess cognitive functions. Level of tumour necrosis factor (TNF-α) was measured in hippocampus to assess neuroinflammation. To further explore the molecular mechanisms we measured the histone H3 acetylation and brain derived neurotrophic factor (BDNF) level. HFD fed mice exhibit characteristic features of insulin resistance. These mice also showed a severe deficit in learning and memory along with reduced histone H3 acetylation and BDNF levels. In contrast, the mice treated with SAHA showed significant and dose dependent improvement in insulin resistant condition. These mice also showed improved learning and memory performance. SAHA treatment ameliorates the HFD induced reduction in histone H3 acetylation and BDNF levels. Based upon these results, it could be suggested that HDAC inhibitors exert neuroprotective effects by increasing H3 acetylation and subsequently BDNF level.