Sankhadeep Chatterjee

ORCID: 0000-0002-3930-4699
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Imbalanced Data Classification Techniques
  • Digital Imaging for Blood Diseases
  • Retinal Imaging and Analysis
  • Hydrological Forecasting Using AI
  • Medical Image Segmentation Techniques
  • Brain Tumor Detection and Classification
  • AI in cancer detection
  • Image Retrieval and Classification Techniques
  • Sentiment Analysis and Opinion Mining
  • Text and Document Classification Technologies
  • Advanced Image and Video Retrieval Techniques
  • Water Quality Monitoring Technologies
  • Artificial Intelligence in Healthcare
  • Chaos-based Image/Signal Encryption
  • Anomaly Detection Techniques and Applications
  • Metaheuristic Optimization Algorithms Research
  • Energy Load and Power Forecasting
  • Smart Agriculture and AI
  • Spam and Phishing Detection
  • Image Processing Techniques and Applications
  • Radiomics and Machine Learning in Medical Imaging
  • Currency Recognition and Detection
  • Advanced Steganography and Watermarking Techniques
  • Cutaneous Melanoma Detection and Management
  • DNA and Biological Computing

University of Engineering & Management
2017-2024

Indian Institute of Engineering Science and Technology, Shibpur
1955-2024

University of Calcutta
1954-2021

Armed Forces Medical College
2019

Budge Budge Institute of Technology
2018

Techno India University
2018

Cleveland Clinic Lerner College of Medicine
2008

Case Western Reserve University
2008

Cleveland Clinic
2008

The Ohio State University
2003

Microscopic image analysis is one of the challenging tasks due to presence weak correlation and different segments interest that may lead ambiguity. It also valuable in foremost meadows technology medicine. Identification counting cells play a vital role features extraction diagnose particular diseases precisely. Different should be identified accurately order identify count microscope image. Consequently, current work, novel method for cell segmentation identification has been proposed...

10.1002/jemt.22900 article EN Microscopy Research and Technique 2017-05-30

<p>Image segmentation is a challenging process in numerous applications. Region growing one of the techniques as basis for Seeded Growing method. A novel real time integrated method was developed current work to locate segmented region interest an image based on along with thresholding supported segmentation. Through proposed work, homogeneity pixel intensity suggested well threshold value can be decided via variety schemes such manual selection, Iterative method, Otsu’s local obtain...

10.11591/ijece.v6i6.11801 article EN International Journal of Electrical and Computer Engineering (IJECE) 2016-12-01

<p>Image segmentation is a challenging process in numerous applications. Region growing one of the techniques as basis for Seeded Growing method. A novel real time integrated method was developed current work to locate segmented region interest an image based on along with thresholding supported segmentation. Through proposed work, homogeneity pixel intensity suggested well threshold value can be decided via variety schemes such manual selection, Iterative method, Otsu’s local obtain...

10.11591/ijece.v6i6.pp2773-2780 article EN cc-by-nc International Journal of Electrical and Computer Engineering (IJECE) 2016-12-01

Structural design has an imperative role in deciding the failure possibility of a Reinforced Concrete (RC) structure. Recent research works achieved goal predicting structural RC structure with assistance machine learning techniques. Previously, Artificial Neural Network (ANN) been trained supported by Particle Swarm Optimization (PSO) to classify structures reasonable accuracy. Though, keeping mind sensitivity failure, more accurate models are still absent context Machine Learning. Since...

10.12989/sem.2017.63.4.429 article EN STRUCTURAL ENGINEERING AND MECHANICS 2017-01-01

Various vague and unstructured problems encountered the civil engineering/designers that persuaded by their experiences. One of these is structural failure reinforced concrete (RC) building determination. Typically, using traditional Limit state method time consuming complex in designing structures are optimized terms one/many parameters. Recent research has revealed Artificial Neural Networks potentiality solving various real life problems. Thus, current work employed Multilayer Perceptron...

10.12989/sem.2016.58.3.459 article EN STRUCTURAL ENGINEERING AND MECHANICS 2016-05-10

The current work proposes a neural based detection method of two different skin diseases using imaging. Skin images namely Basel Cell Carcinoma and Angioma are utilized. SIFT feature extractor has been employed followed by clustering phase on space in order to reduce the number features suitable for models. extracted bag-of-features modified dataset is used train metaheuristic supported hybrid Artificial Neural Networks classify detect under study. A well-known multi objective optimization...

10.1109/uemcon.2017.8249038 article EN 2017-10-01

Automated, efficient and accurate classification of skin diseases using digital images is very important for bio-medical image analysis. Various techniques have already been developed by many researchers. In this work, a technique based on meta-heuristic supported artificial neural network has proposed to classify images. Here 3 common considered namely angioma, basal cell carcinoma lentigo simplex. Images obtained from International Skin Imaging Collaboration (ISIC) dataset. A popular multi...

10.1109/iemecon.2017.8079594 article EN 2017-08-01

A global pandemic scenario is witnessed worldwide owing to the menace of rapid outbreak deadly COVID-19 virus. To save mankind from this apocalyptic onslaught, it essential curb fast spreading dreadful Moreover, absence specialized drugs has made even more badly and thus an early-stage adoption necessary precautionary measures would provide requisite supportive treatment for its prevention. The prime objective article use radiological images as a tool help in early diagnosis. interval type 2...

10.1109/tfuzz.2021.3097806 article EN IEEE Transactions on Fuzzy Systems 2021-07-30

In the present work a Cuckoo Search (CS) trained Neural Network (NN) or NN-CS based model has been proposed to detect Chronic Kidney Disease (CKD) which become one of newest threats developing and undeveloped countries. Studies surveys in different parts India have suggested that CKD is becoming major concern day by day. The financial burden treatment future consequences could be unaffordable many if not detected at an earlier stage. Motivated this, significantly overcomes problem using...

10.1109/iementech.2017.8077016 article EN 2017 1st International Conference on Electronics, Materials Engineering and Nano-Technology (IEMENTech) 2017-04-01

Domestic and industrial pollutions affected the water quality to a greater extent. Polluted became major reason behind several community diseases, mainly in undeveloped developing countries. The public health condition is deteriorating putting an extra burden of countermeasures prevent such borne diseases from spreading. Detecting drinking can scenarios prior critical stage. Recent research works have achieved reasonable success predicting quality. However, accuracy levels already proposed...

10.1109/indin.2017.8104902 article EN 2022 IEEE 20th International Conference on Industrial Informatics (INDIN) 2017-07-01

Chronic kidney failure (chronic disease 'CKD') is a serious that related to the gradual loss of function. It considered one health threats in developing and undeveloped countries At early stages, few symptoms can be detected, where CKD may not become obvious until significant function impaired occur. treatment focuses on reducing damage progression by controlling underlying cause, which requires detection at initial stages. In addition, financial burden future consequences detection. present...

10.1109/emes.2017.7980405 article EN 2017-06-01

A novel rainfall prediction method has been proposed. In the present work in Southern part of West Bengal (India) conducted. two-step employed. Greedy forward selection algorithm is used to reduce feature set and find most promising features for prediction. First, training phase data clustered by applying k-means algorithm, then each cluster a separate Neural Network (NN) trained. The proposed two step model (Hybrid or HNN) compared with MLP-FFN classifier terms several statistical...

10.1109/sigtelcom.2018.8325807 article EN 2018-01-01

Computer aided diagnostic is one of the most active research area and has huge impact on health care industry. With advent intelligent methods, biomedical data processing becomes easier less error prone. Moreover, remote also possible using IoT infrastructure. However, security over network always considered as a challenge. Biomedical are generally sensitive to external disturbances small manipulation in may cause difference ultimate result. Wrong diagnosis can be life threatening some...

10.1109/aicai.2019.8701382 article EN 2019-02-01

Micro-Blogging platforms have become one of the popular medium which reflects opinion/sentiment social events and entities. Machine learning based sentiment analyses been proven to be successful in finding people's opinion using redundantly available data. However, current study has pointed out that data being used train such machine models could highly imbalanced. In live tweets from Twitter systematically effect class imbalance problem analysis. Minority oversampling method is employed...

10.1109/icawst.2019.8923218 article EN 2019-10-01

Brain hemorrhages have become increasingly common and can be fatal if left untreated. Current methods for monitoring the progression of disorder that rely on MRI PET scans are inconvenient costly patients. This has spurred research toward portable cost-effective techniques predicting current stage malignancy hemorrhages. In this study, simulated S-parameter data obtained from a two-antenna system placed over head is used in conjunction with machine learning to detect dielectric changes brain...

10.1109/access.2024.3371886 article EN cc-by-nc-nd IEEE Access 2024-01-01

Domestic and industrial pollution affected the water quality to a greater extent. Recent research studies have achieved reasonable success in predicting using several machine learning based techniques. In current work, proposed cuckoo search (CS) has been applied improve support classification process during prediction. The model (NN-CS) gradually minimises an objective function; namely root mean square error (RMSE) order find optimal weight vector for artificial neural network (ANN). was...

10.1504/ijcistudies.2017.089054 article EN International Journal of Computational Intelligence Studies 2017-01-01
Coming Soon ...