ICDMAI2023: 7TH INTERNATIONAL CONFERENCE ON DATA MANAGEMENT, ANALYTICS & INNOVATION
PROGRAM FOR SUNDAY, JANUARY 22ND
Days:
previous day
all days

View: session overviewtalk overview

09:00-09:30Registration
09:30-10:00 Session K5: Keynote-5
09:30
ESG, IoT, AI, 5G applied in Smart City: a practical case in Brazil

ABSTRACT. 5G Smart Campus Facens is a living lab program related to concept of Smart and Sustainable Cities created by University FACENS to support companies, startups, academics, and public sector to innovate. The program is support by 9 axes: ICT; Urbanization, Education and Culture; Energy; Mobility and Security; Health and Quality of Life; Industry and Business; Environment and Governance Area. Using the university campus as a place to prototype, test, analyse and replicate solutions for Smart and Sustainable Cities to convert real problems into applicable solutions in an urban context, providing an innovative multidisciplinary learning experience, supported by innovative thinking with commitment with the environment, social responsibility and governance. Since 2016 more than 350 projects have been done, and many of them are related to environment: all integrated to a Central Dashboard, using AI, 5G, and IoT technology.

 

10:00-10:30 Session K6: Keynote-6
10:00
Rajesh Kumble Nayak (IISER Kolkata, India)
Data Analysis in Gravitational Wave Astronomy

ABSTRACT. I talk about the importance of data analysis in gravitational wave astronomy. Einstein first predicted the existence of gravitational waves in the year 1916. Since the effects are so small, it took nearly 100 years to show the presence of these waves directly. The LIGO detectors first directly detected gravitational wave signals from astrophysical sources such as binary blackholes. Data analysis and modelling are one of the main ingredients of gravitational astronomy. In this talk, I discuss several standard analysis tools, such as match filtering and how newer schemes can improve speed and efficiency.

10:30-11:00 Session K7: Keynote-7
10:30
Dr. Mayukha Pal (ABB Ability Innovation Centre, India)
Attention is all that you need

ABSTRACT. Attention is ability to direct our consciousness and awareness to the object or topic under study or play. Attention to nature with science and engineering brings breakthrough innovation and technological advancement for the betterment of mankind. Attention to engineering problems with data science and physical parameters brings product or solution having features not practiced or unique creating differentiating value. Attention in deep learning and computer vision extracts information from the whole sequence, a weighted sum of all the past encoder states allowing the decoder to assign greater weight to certain elements of the input for each element of the output. The attention mechanism draws global dependencies between input and output bringing higher prediction accuracy. We will discuss various aspects of the attention-based mechanism from physics aware analytics to transformer models with supremacy of its performance, unique results.

11:00-12:15 Session Sp.Session2: Bio Signal Processing using Deep Learning
Location: Arjun/B-252
11:00
Megala G (Vellore Institute of Technology, India)
Swarnalatha P (Vellore Institute of Technology, India)
Venkatesan R (Vellore Institute of Technology, India)
Detecting Bone Tumor on Applying Edge Computational Deep Learning Approach
PRESENTER: Megala G

ABSTRACT. Bone cancer affects the majority of the elderly in today's world. It directly affects the neurotransmitters and leads to dementia. MRI images can spot bone irregularities related to mild cognitive damage. It can be useful for predicting bone cancer, though it is a big challenge. In this research, a novel technique is proposed to detect Bone cancer using Adaboost classifier with a hybrid ACO algorithm. Initially, MRI image features are extracted and the best features are identified by the Adaboost curvelet transform classifier. The proposed methods yield greater accuracy than the existing systems for analyzing MRI images and give excellent classification accuracy. Three metrics namely accuracy, specificity, and sensitivity are used to evaluate the proposed method. Based on the results the proposed methods yield greater accuracy than the existing systems.

11:15
G.N Balaji (Vellore Institute of Technology, Vellore, India)
S V Suryanarayana (CVR College of Engineering, India)
Vigneswaran T (SRM TRP Engineering College, India)
Convolution Neural Network for Weed Detection

ABSTRACT. To achieve precision agriculture, it is most important to identify the types of vegetation present in an image. In this paper, a deep leaning method is applied to estimate the percentage of weed, crop, grass, and soil in an image. The similarity between weed, crop, and grass is more therefore it’s a strenuous task to detect weed, crop, and grass from a visual. In the pre-processing step, the data augmentation techniques are applied to generalize the model and it enables the model to provide accurate results. In the proposed method one of the most predominant methods of deep learning called convolution neural network is utilized to build a weed detection system. The convolutional neural network is trained to classify and detect soybean crops, broadleaf weed, grass, and soil in an image. The features to classify elements are automatically extracted by CNN based on pixel intensity in the convolution layer. RMSprop optimizer is used to compile the model as the magnitude of recent gradients is utilized to generalize the model. The loss function is set to be categorical cross-entropy as the model is a multi-class classifier and the model achieved 96% accuracy.

11:00-12:15 Session Track1-D: Machine Learning
Location: Prithvi
11:00
Reetun Maiti (IIT Kharagpur, India)
Balagopal G Menon (IIT Kharagpur, India)
Predicting Injury Severity in Construction using Logistic Regression
PRESENTER: Reetun Maiti

ABSTRACT. Prediction of injury severity is an important task for articulating proper mitigation measures to reduce the loss of an accident resulting into injuries. In this study, using OSHA construction injury data, we developed a fatality prediction model using logistic regression and frequency weighted data transformation. The approach adopted here is useful for handling categorical predictors. The model is fairly fit to the data. The model could be used for prediction with the involvement of experienced domain experts. Interestingly, some of the predictors actuate an injury being fatal while other predictors inhibit it. Management should take appropriate mitigation measures to reduce the influence of the predictors contributing positively.

11:15
Manika Garg (University of Delhi, India)
Anita Goel (Dyal Singh College, University of Delhi, India)
Detection of Internet Cheating in Online Assessments using Cluster Analysis
PRESENTER: Manika Garg

ABSTRACT. Internet cheating is one of the biggest challenges in maintaining the integrity of online assessments. Students commonly exploit the Internet for unethically searching answers during the online assessment. In this paper, we aim to detect students involved in Internet cheating using a data-driven approach. We first use the K-means clustering algorithm to identify student clusters based on three kinds of attributes, namely, assessment data, process data and personality data. The results show the presence of two distinct clusters, where characteristics of one cluster strongly relate to Internet cheating, and the second cluster represents honest student behavior. The results of the clustering analysis are supported by the personality data. The proposed approach can potentially help to automatically flag probable cheaters in the online assessment. The findings also reveal that the improvisation of our quiz tool with the tab-switch functionality has facilitated the outcome in the cluster analysis. We suggest for the tools used in online assessment, new tools may include and the existing ones may be improvised, to include the tab-switch functionality for online assessment.

11:30
Vivek Saxena (DRDO, India)
Dr. Upasna Singh (DIAT, India)
Dr. L K Sinha (DRDO, India)
LANDSLIDE SUSCEPTIBILITY MAPPING USING J48 DECISION TREE AND ITS ENSEMBLE METHODS FOR RISHIKESH TO GANGOTRI AXIS
PRESENTER: Vivek Saxena

ABSTRACT. mplementing the various machine learning algorithms for landslide susceptibility mapping has been researched by many authors and is worth considering the issue. In the present study, the effectiveness of Decision Tree and its bagging and boosting based ensemble model techniques (like Random Forest, Rotation Forest, Extra Tree, Adaboost, and XGBoost) has been evaluated via generating the Landslide Susceptibility Map (LSM). Both threshold based i.e. overall accuracy and rank based i.e. Area Under Receiver Operating Characteristics(AUROC) measures have been used as the criteria for evaluating the various model’s performance. The result concluded that the XGBoost model has outperformed the other implemented algorithms after performing hyper-parameters tuning for each algorithm. The study area considered for the present study is Rishikesh to Gangotri axis with a buffer area of 3 km on each side. It is the first time that these algorithms have been implemented and compared for this study area.

11:45
Ieesha Deshmukh (MKSSS's Cummins College of Engineering for Women , Pune, India)
Pradnya Agrawal (MKSSS's Cummins College of Engineering for Women , Pune, India)
Aboli Khursale (MKSSS's Cummins College of Engineering for Women , Pune, India)
Neha Lahane (MKSSS's Cummins College of Engineering for Women , Pune, India)
Harsha Sonune (MKSSS's Cummins College of Engineering for Women , Pune, India)
Graphology based behavior prediction : Case study analysis
PRESENTER: Ieesha Deshmukh

ABSTRACT. The handwriting of a human being carries the richest information which helps gain insights into one's physical, emotional, and mental state. Graphology helps in interpreting a person’s characteristics by analyzing their handwriting. It is the investigation of a sensible state of mind at the time of writing. This gives an insight into the morality, enthusiasm and hidden talent of the writer. The state of the cerebrum is reflected in handwriting as the signals move from the cerebrum to the fingers. This has been studied for almost 400 years. Graphology has wide applications in the fields of medicine, education, criminology, etc. Integrative graphology primarily focuses on different strokes of the written word and the relation to an individual’s personality. Holistic graphology considers the form, use of space, and movement during writing. Features of handwriting such as con-cavity of letters, margin, spacing, pen pressure, baseline, size of letters, loops of alphabets, etc. are considered for the above-mentioned applications. These factors lead to the analysis and study of cases based on criminology and depression which focuses on examining the handwriting of the individual and keep a track of their behavior.

12:00
Santosh Kumar Vishwakarma (MANIPAL UNIVERSITY JAIPUR, India)
Chour Singh Rajpoot (MANIPAL UNIVERSITY JAIPUR, India)
Comparative Analysis of Recommendation System using Similarity Techniques

ABSTRACT. : Recommendation System (RS) is an important software for information filtering system. upper approximation algorithm apply for forming cluster from MSNBC dataset , in this paper find out more relevant similar web page using different similarity measure technique like sequence similarity length of longest common subsequence (LLCS) and set similarity Jaccard similarity, dice similarity and cosine similarity for calculating of recommendation system. In this work we compare existing work technique similarity result with proposed work technique result on MSNBC dataset using hybrid similarity technique (sequence set similarity measure) according to our comparative results, the suggested system offers new users recommendations with good reliability and accuracy values.

11:00-12:15 Session Track1-E: Machine Learning
Location: Kaveri/B-266
11:00
Deep Pancholi (Amrita Vishwa Vidyapeetham, Coimbatore, India)
Selvi C. (Indian Institute of Information Technology, Kottayam, Kerala, India)
Study of Cold-start Product Recommendations and its Solutions
PRESENTER: Deep Pancholi

ABSTRACT. In today's digital era, consumers rely more and more on the systems that provide them with a personalised experience. In interacting with the system, these consumers create more and more data of different types (click-through rates, items viewed, time spent, number of purchases, and other metrics.). This extensive collection of data from various users is used only to improve the personalising experience of the users. These systems that utilise consumers' data to create a more personalised and customised user experience are called Recommender Systems. Recommender Systems play a huge role in helping companies create a more engaging user experience. E-Commerce giants like Amazon and Flipkart employ such Recommender Systems. These can learn from the user-system interaction the likes and dislikes of users and can promote the visibility of items that interest the user. They are also helpful in luring the customer to buy those things he would have to search for manually in the absence of such a system, which can recommend the item to a user based on his previous interactions. Streaming services like YouTube, Amazon Prime Video and Netflix also use Recommender Systems to suggest movies/shows that the user might like based on the watch history. This study proposes a hybrid model with item-item collaborative filtering using a graph, user-user collaborative filtering based on textual reviews and ratings, and demographic data to generate accurate product recommendations that address the cold-start issue.

11:15
Harikumar Radhakrishnan (Indian Navy, India)
Saikat Bank (DIAT, India)
Bharath R (Defence Institute of Advanced Technology, India)
C P Ramanarayanan (DEFENCE INSTITUTE OF ADVANCED TECHNOLOGY, India)
Statistics Driven Suspicious Event Detection of Fishing Vessels based on AIS Data
PRESENTER: Saikat Bank

ABSTRACT. Fishing vessels have been widely used in contraband activities, and are also highly vulnerable to accidents, malfunction of the engines, etc. Fishing vessels are also reported in incidents by roaming in restricted border areas raising tensions across the nations. Timely monitoring and tracking of the fishing vessels will be needed such that it can improve the vigilance on the fishing vessel in contraband activities, provide rescue in case of accidents, malfunction of the vessel, or alarm in the case of sailing in restricted areas. In this paper, we propose an automated algorithm to detect any suspicious activity of the fishing vessel in real time, which can alarm the concerned authorities to take the necessary action. The algorithm is based on how frequent the fishing vessels transmit the automatic identification system (AIS) data. Monitoring the fishing vessels all the time is not necessary and is also likely infeasible. Knowing the limitation, we propose a statistics-driven threshold, based on which, we can reduce the instances for which we have to give attention to the fishing vessels.

11:30
Harikumar Radhakrishnan (Indian Navy, India)
Shyam Sundar (DIAT, India)
Bharath R (Defence Institute of Advanced Technology, India)
C P Ramanarayanan (DEFENCE INSTITUTE OF ADVANCED TECHNOLOGY, India)
Suspicious Event Detection of Cargo Vessels based on AIS Data
PRESENTER: Shyam Sundar

ABSTRACT. Cargo ship vessels have been widely used in the global trade market. Pirate attacks or failure of the cargo ship vessels can have a considerable impact on the supply chain in global trade. Continuous monitoring and tracking of the cargo vessels and timely intervention of the cargo vessels on their voyage can reduce the loss incurred in case of attack, accident or malfunction of engine, etc. Since most of the global trade happens across bodies, there are will be many cargo ships sailing simultaneously, hence continuous tracking of all the cargo ships manually is a highly tedious job. In this paper, we propose an automated algorithm to detect suspicious events in cargo ships based on AIS data. The features like Speed over the Ground (SoG), and how frequent the cargo vessel transmits the AIS data will be analyzed to detect suspicious event detection. Based on the statistical distribution of the data, we propose a threshold value for SoG and an allowed time interval for receiving AIS data, on which if the cargo vessel is not transmitting, will be labelled as suspicious event detection, otherwise, it is considered normal. With the proposed algorithm, the number of instances where the concerned authority needs to pay attention to the vessel will be significantly reduced

11:00-12:15 Session Track2-D: AI & Deep Learning
Location: Pinaka
11:00
Sita Yadav (Army Institute of Technology, India)
Dr. Sandeep Chaware (RSCOE, JSPM, India)
Video object detection with an improved classification approach
PRESENTER: Sita Yadav

ABSTRACT. The deep learning models enhanced object detection in videos to a very large scale. Object detection is a prime task in self-driven cars, satellite images, robotics, etc. The researchers are working to improve the efficiency of deep learning models for better object detection. The object detection models broad categories into one-stage and two-stage detectors. The current work focused on improvement in accuracy and speed of one stage detector with the help of hyper-parameter tuning. The earlier researcher has shown that YOLO and R-CNN are the appropriate models for real-time object detection. In this paper, a custom CNN model is given with hyper-parameter tuning and the results are compared with regions with convolutional neural networks, Fast regions with convolutional neural networks, Faster Region with CNN, and YOLO. The impact of hyper-parameter tuning on the result of CNN models for object detection is shown in this paper. The results are verified on live video dataset.

11:15
Ketki Deshmukh (MPSTME,NMIMS University, Mumbai, India)
Dr. Avinash More (MPSTME,NMIMS University, Mumbai, India)
Modified Long Short-Term Memory Algorithm for faulty node detection using node’s raw data pattern
PRESENTER: Ketki Deshmukh

ABSTRACT. Detection of faults in an automated manner is a very powerful computing technique. In recent years because of technological development, it is now possible to detect the fault based on raw sensor data patterns. Passive Infrared sensor (PIR) is very useful in motion detection (hu-man, animal etc.) in the deployed field. We have proposed a modified scheme based on the Long Short-Term Memory (LSTM) algorithm for detecting faults in the PIR sensor module. Our mechanism is specifically tuned for the PIR sensor, which achieved 87% accuracy for detecting faults using the raw data pattern of the PIR sensor module. Further, we have computed loss concerning mini-batch size and sample size to determine the modified mechanism's accuracy. We expect that future re-searchers may work on complex sensors and try to detect their faults using a modified LSTM algorithm.

11:30
Aditya Srinivas Menon (Indian Institute of Information Technology Kottayam, India)
Anand Konjengbam (Indian Institute of Information Technology Kottayam, India)
X-ABI: Towards Parameter Efficient Multilingual Adapter Based Inference for Cross-Lingual Transfer

ABSTRACT. Natural Language Inference for low-resource languages is challenging due to the unavailability of sufficient training samples for downstream tasks. This work proposes to leverage the large corpus availability of high-resource languages and transfer learning to assist low-resource languages. We pro-pose a method X-ABI (Multilingual Adapter Based Inference) to interpolate through the language spaces in multilingual language models using adapters in transformers. This results in comparable accuracies on downstream tasks by efficiently training the model on available training samples from mainstream languages. We show that training only ~0.1% of the parameters on the English dataset performs 20.9% better than baseline and is compara-ble to the state-of-the-art of other languages present on the XNLI dataset with 4 hours of training on free Google Colab GPU.

11:45
Archana Patil (College of Engineering Pune, India)
Dr. Shashikant Ghumbre (GCOE&R, Avasari, India)
Dr. Vahida Attar (COEP, India)
Named Entity Recognition over Dialogue Dataset using Pre-trained Transformers
PRESENTER: Archana Patil

ABSTRACT. Need of Natural Language Processing (NLP) applications and advancement in Deep Learning (DL) techniques have increased the need of large amount of human readable data leading to interesting research area Named Entity Recognition (NER), which is the sub task of Natural Language Processing which identifies and tags different real-life entities in their predefined categories. Pre-defined categories include person, locations, times, organization, events etc. depending upon the dataset in hand. For different natural language applications such as question answering system, dialogue system, summarization of text, machine translation etc. NER forms a base work. Performance of earlier NER techniques is good but requires human intervention for forming domain specific features or rules. Performance of NER system is further improved by application of emerging Deep Learning models. In this paper we mention different techniques which can be applied to do NER task and fine tune the pretrained transformers to work on In-car dataset for NER task and evaluate the performance of system.

12:00
Arvind Kumar (CSIR-Central Scientific Instruments Organisation, India)
Bhargab Das (CSIR-Central Scientific Instruments Organisation, India)
Raj Kumar (CSIR-Central Scientific Instruments Organisation, India)
Virendra Kumar (CSIR-Central Scientific Instruments Organisation, India)
Comparative Study of Depth Estimation from 2-D Scene Using Deep Learning Model
PRESENTER: Arvind Kumar

ABSTRACT. Estimating depth is critical for 3D scene reconstruction and visualization. Usually, Depth is measured using depth cameras, LIDAR, and stereo cameras. However, these devices have limitations in terms of range and calibration. Depth estimation using a monocular RGB image is the subject of extensive research as it eliminates the need for physical depth measuring instruments. For this objective, many deep learning models are employed. Deep Learning models have achieved significant advances in accuracy in recent years, addition to the fact that this increases the computing cost. We examine and compare two deep learning models DenseDepth and U-Net, and their properties such as training parameters, loss function, accuracy, and so on in this study. Furthermore, we explore challenges in estimating monocular depth.

11:00-12:15 Session Track2-E: AI & Deep Learning
Location: Sagarika
11:00
Jyoti Kanjalkar (VIT, Pune, India)
Abu Ansari (VIT, Pune, India)
Kaivalya Aole (VIT, Pune, India)
Arya Tiwari (VIT, Pune, India)
Harshal Abak (VIT, Pune, India)
Pramod Kanjalkar (VIT, Pune, India)
Analysis of Machine Learning Algorithms for COVID Detection Using Deep Learning
PRESENTER: Abu Ansari

ABSTRACT. The global pandemic of COVID-19 has caused havoc in our lives in every way. COVID-19 (coronavirus) is an ongoing pandemic caused by coronavirus 2 (severe acute respiratory illness) (SARS-CoV-2). More precisely, healthcare systems were pushed to their breaking points. Artificial intelligence advancements have made it possible to develop complex apps that meet clinical accuracy criteria. Because medical facilities have a limited quantity of COVID-19 test kits, it is critical to design and deploys an automatic detection system as an alternate diagnosis option for COVID-19 detection that can be employed on a commercial scale. The first imaging tool to be used in the diagnosis of COVID-19 disease is a chest X-ray. To detect pneumonia induced by COVID-19 respiratory problems, researchers used customized and pre-trained deep-learning models based on convolutional neural networks. We used data from a publicly available dataset. Convolutional neural networks for image analysis and classification have seen a lot of success thanks to the abundance of large-scale annotated image datasets. In this paper, we propose a deep convolutional neural network trained on open-access datasets: Normal and Covid. With the merged dataset, the findings reveal a high detection accuracy of 95%, and most models handled additional data with a minor loss in accuracy.

11:15
Md Shahzeb (Defence Institute of Advanced Technology,Pune, India)
Sunita Dhavale (Defence Institute of Advanced Technology(DIAT),Pune, India)
D Srikanth (Defence Institute of Advanced Technology(DIAT),Pune, India)
Suresh Kumar (Defence Institute of Psychological Research(DIPR),Delhi, India)
DCNN-based Transfer Learning approaches for Gender Recognition
PRESENTER: Md Shahzeb

ABSTRACT. Gender recognition becomes a very critical task for security agencies while assessing protest activities. At present, with the advent of GPUs, high computing machines, and Deep Convolution Neural Networks (DCCN), automated gender recognition is possible. In this research work, we explore the performance of various DCNN architectures using transfer learning approaches for gender recognition. We performed a detailed ablation study on different input sizes and on different architectures to see the trade-off between latency and the accuracy of the classification. The performance of models tested against standard dataset WIKI, UTKFace, and Adience. We explored VGG-16 and MobileNetV3 architectures for comparison against accuracy and latency parameters in order to select a model suitable for the embedded device considering their low processing and less storage capacity. Experiments conducted using standard architecture against the standard dataset by changing the resolution and fine-tuning it.

11:30
Mahima Arya (Unikul Solutions Pvt. Limited, India)
S V S S N V G Krishna Murthy (Defence Institute of Advanced Technology, India)
Priyesh Kumar Roy (Defence Institute of Advanced Technology, India)
CycleGAN implementation on cross-modality transfer between Magnetic resonance image (MRI) and Computed tomography (CT) images

ABSTRACT. The present work offers an analysis of how to perform cross-modality transfer between two medical modalities, Computed tomography (CT) scans and Magnetic Resonance Imaging (MRI) data using CycleGAN neural processing method. We performed this analysis on two different datasets of sizes 40 and 367, respectively. The effect of dataset size, and the information it contains has been examined. It is found that the CycleGAN can learn robust features even for a smaller size dataset, however, the quality of the model improves with the dataset size for a given number of epochs. average values of PSNR/SSIM are found to be 41.2/0.67 and 75.3/0.23 for the models developed on small and big data sets, respectively. Irrespective of the low quality of image translation, the present work is useful for medical image data augmentation, which is further helpful in improving the efficiency of other neural network-based medical tasks such as segmentation.

11:45
Nilanjan Sinhababu (Indian Institute of Technology Kharagpur, India)
Monalisa Sarma (Indian Institute of Technology Kharagpur, India)
Debasis Samanta (Indian Institute of Technology Kharagpur, India)
Improving Autoencoder based Recommendation Systems

ABSTRACT. Recommendation systems help in providing suggestions regarding the products/services that the users might be interested in by analysing ratings, reviews, and other feedback obtained from the users on their previous purchases. These systems are used in various domains like e-commerce, entertainment, news, etc. In the e-commerce domain, the ratings and reviews obtained from user feedback are far less in number when compared with the number of users and items. This leads to data sparsity issues where the recommendation systems may not be able to provide accurate recommendations. To counter this issue, in our study, we used both auto-encoder and sentiment analysis on the reviews using the BERT language model to generate a more accurate version of the rating matrix. The empirical studies done on the Amazon baby product reviews dataset have shown that the approach has significantly increased the accuracy of predicted ratings.

12:00-12:15Tea
12:15-12:45 Session K8: Keynote-8
12:15
N.R. Srinivasa Raghavan (Tarxya Limited, UK)
My experiments with Data Science

ABSTRACT. In this talk, we will present several industrial case studies where the author was personally involved in formulating, designing, developing and deploying solutions to challenging real world problems. The talk will highlight both the 'hard' and 'soft' aspects of implementing AI/Data Science/Data engineering driven solutions. Specifically, the applications of techniques from Statistics, Machine Learning, AI, Data Science and Data Engineering will be highlighted. Best practices in build cycles will be discussed. Cutting edge research directions will also be highlighted towards the end of the session.

12:45-13:30 Session K9: Keynote-9
12:45
Prof Chittaranjan Yajnik (KEM Hospital Pune, India)
'Transgenerational transmission of Diabesity: Mere Paas Data Hai'

ABSTRACT. Diabetes and other chronic non-communicable diseases are usually portrayed to have genetic susceptibility and precipitation by unhealthy lifestyle. Genetic susceptibility is not modifiable at present, so the prevention is focused on lifestyle modification. Recent research has revealed a modifiable susceptibility factor of intrauterine epigenetic programming which is largely driven by environmental factors like maternal nutrition, metabolism, hormones, stress and pollutants. This has led to the concept of intrauterine programming of health and disease (Developmental Origins of Health and Disease - DOHaD). India has the double burden of malnutrition (undernutrition in early life and a rapidly rising epidemic of diabetes, obesity and cardiovascular disease). India has been at the forefront of DOHaD research since its description by Prof David Barker in the UK and has contributed vital information from many birth cohorts and mechanistic and interventional studies. Role of maternal undernutrition and maternal diabetes have been extensively investigated. Pune Maternal Nutrition Study, Pune Children’s Study and Diabetes in Pregnancy studies at KEM Hospital, Pune are some of the flagship studies from India. In the Pune studies we have 3 generational longitudinal data on body size, nutrition, metabolism, cardiometabolic risk factors and imaging data. A 3-generation blood bank is available for further measurements of various biomarkers.

13:30-14:30Lunch
14:30-14:50 Session K10: Keynote-10
14:30
Aninda Bose (Springer Nature, India)
Publication Ethics

ABSTRACT. The importance of research publishing can be defined by a simple quote of Gerard Piel, which says “Without publication, science is dead.” The first scientific journal was published in 1665 and we have travelled 350 years since then. In the last 20 years, science and reporting of science have undergone revolutionary changes. Computerization and Internet have changed the traditional ways of reading and writing. Hence, it is very important for scientists and students of the sciences in all disciplines to understand the complete process of writing and publishing of scientific paper in good journals. There is also a downside of digital publishing. The principal challenge for publishers is to handle ethical issues and it is of utmost importance for the authors to understand the ethical practices involved in the process. The talk is designed to provide information on different ethical practices and also on how to make use of various author services for the publishing work.