Catalogue Search | MBRL
Search Results Heading
Explore the vast range of titles available.
MBRLSearchResults
-
DisciplineDiscipline
-
Is Peer ReviewedIs Peer Reviewed
-
Item TypeItem Type
-
SubjectSubject
-
YearFrom:-To:
-
More FiltersMore FiltersSourceLanguage
Done
Filters
Reset
8
result(s) for
"Arulprakash, P"
Sort by:
Multi-modal active learning with deep reinforcement learning for target feature extraction in multi-media image processing applications
by
Kumar, A. Vignesh
,
Sujitha, S.
,
Raja, R. Arshath
in
1178: Pattern Recognition for Adaptive User Interfaces
,
Accuracy
,
Active learning
2023
The advancement in on demand Multimedia Streaming Applications (MAS) enables faster video transmission as per the user request in various fields. This system suffers from poor speed, flexibility and efficiency in accessing and presenting the multimedia contents from the archive. It mostly undergoes delay, packet loss and congestion during data delivery. Hence, the requirement of manual annotation is required for access and retrieval but it suffers from poor retrieval accuracy over large databases. The need of automatic annotation in MAS takes the lead for increased retrieval accuracy on most similar image retrieval systems based on various low-level features. Thus, it eliminates the gap between the high-level semantics and low-level feature representation. The approach on automated annotation of images is considered dependent on the accuracy of a model while detecting edges, color, texture, shape and spatial information. In this paper, we develop an automated annotation model that retrieves visually similar images from online multimedia streams with optimal feature extraction. The automated annotation model is designed with a Multi-modal Active Learning (MAL) that uses Convolutional Recurrent Neural Network (CRNN) for automatic annotation of labels based on visually similar contents or features like edges, color, texture, shape and spatial information. Further, a Deep Reinforcement Learning (DRL) algorithm is used that increases the performance of the retrieval engine based on validating the visually extracted features. The simulation of MAL-CNN is conducted over large online streaming databases and it is then validated by DRL on an online real-time streaming. The performance is validated in terms of its retrieval accuracy, sensitivity, specificity, f-measure, geometric mean and mean absolute percentage error (MAPE). The results confirm the accuracy of the proposed MAL-DRL model against conventional machine learning, reinforcement learning and deep learning automatic annotation models.
Journal Article
Optimal route and cluster head selection using energy efficient-modified African vulture and modified mayfly in manet
by
Prakash, S. Poorna
,
Arulprakash, P
,
Kumar, A. Suresh
in
Algorithms
,
Brownian motion
,
Clusters
2023
The dynamic nature of the Mobile Adhoc network (MANET) is regarded as the primary issue when routing. In MANET, Routing protocol and optimal route selection from various paths are identified for efficient routing. The major goal of this research is the shortest path determination for data transfer in a MANET. This research presents an Energy Efficient-Modified African Vulture and Modified Mayfly (E-MAVMMF) method that contains two sections namely cluster head selection and optimal route selection. In the first stage, the cluster head is selected by using the Modified African Vulture optimization algorithm (AVOA) in which Brownian motion is used so that the effectiveness of AVOA is improved and in the second stage, the optimal route is chosen using a Modified Mayfly algorithm (MMF), which is enhanced by using a modified mutation phase of Symbiotic Organism Search (SOS), which aids in obtaining the global best solution. The suggested approach is built on the NS2 platform. Various performance metrics, such as the delivery ratio of the packet, loss rate of the packet, energy, throughput, etc. are evaluated. The observed outcome shows that the suggested method E-MAV: MMF is more efficient when compared with the existing approach ANFIS-based Group teaching optimization algorithm (O-AeGTA-MANET).
Journal Article
Spot- Zombie Filtering System
by
Rajagopal, Arathy
,
Arulprakash, P
,
Geethanjali, B
in
Computer information security
,
Filtering
,
Filtration
2014
A major security challenge on the Internet is the existence of the large number of compromised machines. Such machines have been increasingly used to launch various security attacks including spamming and spreading malware, DDoS, and identity theft. These compromised machines are called \"Zombies\". In general E-mail applications and providers uses spam filters to filter the spam messages. Spam filtering is a technique for discriminating the genuine message from the spam messages. The attackers send the spam messages to the targeted machine by exalting the filters, which causes the increase in false positives and false negatives. The authors develop an effective spam zombie detection system named SPOT by monitoring outgoing messages of a network. SPOT focuses on the number of outgoing messages that are originated or forwarded by each computer on a network to identify the presence of Zombies. SPOT is designed based on a powerful statistical tool called Sequential Probability Ratio Test, which has bounded false positive and false negative error rates.
Journal Article
Immunogenicity and safety of hepatitis B vaccine (Shanvac-B) using a novel pre-filled single use injection device uniject in Indian subjects
by
Joshi N, Kumar A, Raghu MB, Bhave S, Arulprakash R, Bhusari P, Rao Raman
in
Adolescent
,
Adult
,
Care and treatment
2004
BACKGROUND: Hepatitis B is a major public health problem, which has
now been controlled to some extent by vaccination especially with the
recombinant hepatitis B vaccine, which has been proven to be safe and
efficacious since its introduction in the 1990s. But problems of unsafe
injection practices still persist. Now newer delivery devices like
uniject are available for making vaccination very safe. OBJECTIVE: To
evaluate the immunogenicity and safety of the Hepatitis-B (Shanvac-B)
vaccine in Uniject pre-filled device administered to healthy adults and
infants at 0, 1, 2 months schedule. METHODS: A total of 122 healthy
subjects (62 adults and 60 infants) were administered three doses of
the recombinant Hepatitis-B vaccine using Uniject pre-filled device.
Blood samples for antibody titer estimation were taken before
vaccination and 4-6 weeks after third dose. Subjects, parents or
guardians were given diary cards to record any adverse reactions.
RESULTS: Protective immune responses to the vaccine were seen in 96.4%
of adults and 100% of infants who completed the study. The Geometric
Mean Titers (GMT) in adults and infants were 518.5 and 385.41 mIU/ml
respectively. Mild fever, itching, and swelling at injection site were
the most common side effects observed. CONCLUSION: The safety and
immunogenicity of the Hepatitis B Vaccine in the novel pre-filled
device Uniject was effectively demonstrated in the present study.
Journal Article
Expression of Cry2Aa, a Bacillus thuringiensis insecticidal protein in transgenic pigeon pea confers resistance to gram pod borer, Helicoverpa armigera
by
Sreevathsa, Rohini
,
Kumar, Nikhil Ram
,
Dash, Prasanta K.
in
38/77
,
631/449/447/2311
,
631/61/447/2311
2018
Pigeon pea is an important legume infested by a plethora of insect pests amongst which gram pod borer
Helicoverpa armigera
is very prominent. Imparting resistance to this insect herbivore is of global importance in attaining food security. Expression of insecticidal crystal proteins (ICP) in diverse crops has led to increased resistance to several pests. We report in this paper, expression of Cry2Aa in transgenic pigeon pea and its effectiveness towards
H
.
armigera
by employing
Agrobacterium
-mediated
in planta
transformation approach. Approximately 0.8% of T
1
generation plants were identified as putative transformants based on screening in the presence of 70 ppm kanamycin as the selection agent. Promising events were further recognized in advanced generations based on integration, expression and bioefficacy of the transgenes. Seven T
3
lines (11.8% of the selected T1 events) were categorized as superior as these events demonstrated 80–100% mortality of the challenged larvae and improved ability to prevent damage caused by the larvae. The selected transgenic plants accumulated Cry2Aa in the range of 25–80 µg/g FW. The transgenic events developed in the study can be used in pigeon pea improvement programmes for pod borer resistance.
Journal Article
A Study of Respiratory Hygiene Among Patients With Respiratory Manifestations in a Selected Primary Healthcare Setting in India
by
Maria, Lovling
,
S, Arulprakash
,
Sharon P, Minthami
in
Chronic illnesses
,
Consent
,
Data collection
2024
Tuberculosis is the second leading infectious killer disease, mainly transmitted through undiagnosed presumptive and inadequately treated pulmonary tuberculosis (PTB) cases in the community.
This study was conducted to assess the knowledge, attitude, and practices (KAP) related to respiratory hygiene and sputum disposal methods and to estimate the proportion of presumptive PTB cases among patients with clinical features of respiratory manifestations.
A hospital-based cross-sectional study was conducted among 80 adult patients with respiratory manifestations at an urban health centre in Goa using a validated, pre-tested, semi-structured questionnaire by interview method.
Among 80 study participants, 10 (12.5%) presumptive PTB cases were found. The knowledge regarding the exact cause and transmission of tuberculosis was 55% (44) and 72.4% (58), respectively. Around 32.5% (26) of participants were not following cough etiquette and they studied only up to middle school. Regarding the attitude towards ideal sputum disposal methods, more than three-fourths (81.3%, 65) of the responses were towards unsafe sputum disposal methods.
There is a need for health education regarding proper respiratory hygiene and sputum disposal methods, especially among patients with low educational and socio-economic groups.
Journal Article
Clinical profile of 1208 newly diagnosed colorectal cancer patients in Tamil Nadu—A multi-centric survey
2024
Background
An increasing incidence of colorectal cancer (CRC) is being reported in developing countries, including India. Most Indian studies on CRC are retrospective and single-centered. The present study is an attempt to understand the current clinical profile and stage of newly diagnosed CRCs across multiple centers in Tamil Nadu, India.
Methods
A multi-centric observational survey was conducted between September 1, 2021, and August 31, 2022, under the aegis of the Indian Society of Gastroenterology - Tamil Nadu chapter. Patients 18 years of age and older with a recent diagnosis of CRC fulfilling the inclusion criteria were prospectively recruited at the participating centers. Their demographic, clinical, biochemical, endoscopic, histopathologic, radiologic and risk factor details were systematically collected and analyzed.
Results
Across 23 centers in Tamil Nadu, 1208 patients were recruited. The male:female ratio was 1.49:1, while mean (SD) age was 57.7 (13.5) years. A majority (81.9%) were Tamils and 78.5% belonged to lower socioeconomic classes. The predominant symptoms were hematochezia (30.2%) and a change in bowel habits (27.5%). The most common locations were the rectum (34.3%) and rectosigmoid (15.1%). Synchronous CRCs were seen in 3.3% and synchronous colorectal polyps in 12.8%. Predisposing factors for CRC were seen in 2%. A past history of any cancer among CRC patients was obtained in 3.1% and a family history of any cancer was found in 7.6%. Patients who were either overweight or obese constituted 46.4% of the study population. At presentation, the predominant stages were stage III (44.7%) and stage IV (20.8%).
Conclusions
A majority of patients with newly diagnosed CRC in Tamil Nadu belonged to the lower socioeconomic classes. About 60% had CRCs located within the reach of the flexible sigmoidoscope. Two-thirds of the patients exceeded stage II disease at presentation.
Trial registration
Not applicable
Graphical Abstract
Journal Article
Role of bedside pancreatic scores and C-reactive protein in predicting pancreatic fluid collections and necrosis
2017
BackgroundAcute pancreatitis is a disease with variable outcome; the course of the disease can be modified by early aggressive management in patients with severe pancreatitis. Easily calculable pancreatic scores and investigations can help to triage these patients. We aimed to determine the role of bedside index for severity in acute pancreatitis (BISAP), harmless acute pancreatitis score (HAPS), and systemic inflammatory response syndrome (SIRS) scores on day of admission and C-reactive protein (CRP) at 48 h for predicting the presence of pancreatic fluid collection (PFC) and necrosis on CT scans done at 72 h.MethodsOf a total of 114 consecutively seen patients of pancreatitis, 64 with acute pancreatitis were enrolled in the study. All individuals had the pancreatitis predicting scores calculated at the time of admission, CRP at 48 h, and contrast-enhanced computed tomography (CECT) abdomen at 72 h from admission.ResultsThe study population of 64 (55 male) had a mean (+SD) age of 37.7 ± 13 years. Alcohol was the most common (68.8%) etiology in these patients. Based on CECT, patients were divided into 2 groups; group 1 with 41 patients who had mild pancreatitis and group 2 with 23 patients who had pancreatic fluid collection with or without necrosis (PFCN). PFCN were seen in 19 (29.7%) of patients with 2 or more SIRS criteria, 17 (26.6%) of patients with BISAP score ≥3, and 16 patients (25.0%) with HAPS >0 respectively. All three scores were able to predict PFCN significantly. CRP >150 mg/L was noted in 23 patients and was able to predict the presence of fluid collections (p=0.0002) and pancreatic necrosis (p = 0.0004) on CT.ConclusionBISAP, HAPS, and SIRS scores and CRP of 150 mg/L all correlated significantly with the occurrence of fluid collections and pancreatic necrosis on CT at 72 h. None of the scores was superior to the other in this respect.
Journal Article