NOTICE: SUMMER INTERNSHIP FOR STUDENTS AFTER 6TH SEMESTER

In continuation with the notice dated 16^th June 2023 regarding summer internship 2023 (4 to 6 weeks duration), Students are hereby informed that they can undergo internship under the following Faculty members:

1. Dr Guru Prasad

2. Dr Jay Bhatnagar

3. Dr Sumit Pundir

4. Dr Manish Shrama

5. Dr Ashwini Kumar Singh

6. Dr Akansha Gupta

7. Dr Neha Tripathi

8. Dr Parul Madan

9. Mr Prabhdeep Singh

10. Mr Akshay Rajput

11. Mr Yuvraj Joshi

12. Mr Yogesh Lohumi

Faculty/Internship
1. Dr Guru Prasad	Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy. When it comes to finding work in this field, the most important requisite is hands-on experience. A machine learning internship offers a practical understanding of the techniques and tools used by practitioners. Interns learn how to understand data, analyze data, and developing models Responsibilities at a machine learning internship may include: 1.         Detail Literature survey on Existing models 2.         Data Collection 3.         Date Preprocessing 4.         Developing models 5.         Experimental Analysis 6.         Writing Research Paper
2. Dr Jay Bhatnagar	U.G and P.G. (MCA/M. Tech) Students are invited to apply for any (one or multiple) Research Affiliate positions as given below. Applications may be submitted in the following form: 1) brief on prior projects undertaken stating problem and your coding / solution contributions, 2) SCGPA or semester/ education details, 3) few lines of future interest/ plans post B. Tech, 4) Two references from faculty/ any supervisor. The particulars stated may be sent in soft copy to: jaybhatnagar.cse@geu.ac.in Each position amounts to support of up to Rs. 1,500 p.m. for the duration of summer internship to deserving based on merit - interview. Addl. it may also carry LoR/Certificate of experience for work done as Research Affiliate. You will be given ample inputs on the problem, background areas and solution/ algorithm, while your role will be of implementation and importantly, documenting/ Report writing. Position 1: Ideal candidate is expected to know good documenting skills in the form of using MS word or LaTeX. This project entails in preparing draft (few figures, tables, text) for study material on some unpublished work. The candidate will also be duly cited in credits of this work, based on their contribution. Position 2: Ideal candidate is expected to help in implementing basic GUI using any of the following: C + + / C / Java / Python and operationally execute the developed algorithm for novel Human – Computer Interface Evaluation. First 15 - 20 days is implementation of the already developed process and set up execution with observations, next 15 - 20 days onwards is consolidation into report. Also, the developed results have to be reported/ closed in the form of standard report. Position 3: Ideal candidate is expected to implement basic theme for Android UI as Offline mobile App. Position 4: Ideal candidate is expected to help implement using any of the following: C + +/ C / Java/ Python. Also, the developed results have to reported/ closed in the form of standard report. Timelines: First 15 - 20 days is first-level implementation of the solution/ process and execution with observations, next-level aims to consolidate findings into report, All developed results have to be reported/ closed in standard form, and mentoring/ guidance will be provided for it.
3. Dr. Ashwini Kumar Singh	It will be a great opportunity to explore the field of Social Networks Analysis as an Internship candidate this summer in the department of CSE at GEU. We will learn and use the techniques of Web Scraping, Natural Language Processing, Text Analysis, Data Visualization, Machine Learning, and Deep Learning for exploring various important and interesting issues on social networks such as: Political polarization in online platforms. Detecting Biases in social media. Impact of social media on health. Misinformation/Fake news in social media spaces. Communication dynamics during the disaster. Influence maximization in social networks. Link prediction in social networks. Community detection in social networks. Online harm detection. Recommender systems. Interested candidates may apply by sending an email to  ashwini.cse@geu.ac.in within the due date.The application will  include a brief resume and topic of interest/problem statement.
4. Dr. Akansha Gupta	Epilepsy/2Seizure detection with deep learning Machine learning in advanced wireless communication
5. Dr. Neha Tripathi	Blockchain Driven Secure Automated Banking query response system. Secure IoT Driven Smart Healthcare Mechanism Smart and Secure Home Real-time Response System Secure and Smart Agriculture using Agri-sensors
6. Dr. Parul Madan	Proposal for Research Work on Medical Healthcare using Deep Learning I am writing to propose a research project focused on leveraging deep learning techniques to advance medical healthcare. This project aims to explore and develop novel algorithms and methodologies to improve disease diagnosis, patient monitoring, and treatment outcomes through the analysis of medical data. Objective: The objective of this research work is to investigate the potential of deep learning in medical healthcare and develop innovative solutions to address critical challenges. Specifically, we aim to explore the following research areas: 1. Medical Image Analysis: Develop deep learning models for accurate and efficient analysis of medical images, such as X-rays, CT scans, MRI scans, and histopathological images. This research will focus on tasks such as image classification, object detection, segmentation, and anomaly detection, to enhance diagnostic accuracy and reduce interpretation time. 2. Disease Risk Prediction: Investigate the use of deep learning methods to predict the risk of developing specific diseases based on patient data, including electronic health records (EHRs), genetic information, lifestyle factors, and environmental variables. This research will involve developing predictive models that can assist in early intervention and personalized healthcare planning. 3. Clinical Decision Support Systems: Explore the development of intelligent clinical decision support systems that integrate deep learning algorithms with patient data to aid healthcare providers in making accurate diagnoses, treatment recommendations, and prognostic predictions. This research will involve developing models that can analyze complex patient data and provide evidence-based recommendations. Methodology: To achieve the aforementioned objectives, the research project will follow the following methodology: 1. Literature Review: Conduct an extensive review of existing research papers, clinical studies, and relevant literature on medical applications of deep learning. This will provide a comprehensive understanding of the current state-of-the-art, identify research gaps, and lay the foundation for the proposed work. 2. Data Collection and Preparation: Gather diverse and representative medical datasets, including medical images, patient records, and clinical databases. Ensure the datasets adhere to privacy and ethical guidelines. Perform data pre-processing and augmentation techniques to enhance the quality and diversity of the data. 3. Model Development: Design and implement deep learning architectures tailored to each medical healthcare task. Experiment with different network architectures, loss functions, and optimization techniques to optimize performance. Transfer learning and domain adaptation approaches may be explored to leverage pre-trained models and address data scarcity challenges. 4. Experimental Evaluation: Conduct extensive experiments to evaluate the performance and effectiveness of the developed models. Compare the results with existing methods and state-of-the-art techniques. Utilize evaluation metrics such as accuracy, sensitivity, specificity, and area under the curve (AUC) to assess the performance of the models. 5. Clinical Validation: Collaborate with healthcare professionals and experts to validate the developed models in clinical settings. Assess the models' performance in real-world scenarios, evaluate their impact on clinical decision-making, and gather feedback from healthcare providers to refine and enhance the proposed algorithms. 6. Publication and Dissemination: Document the research findings in high-quality research papers and prepare them for submission to reputable conferences and journals. Additionally, organize workshops or seminars to share the knowledge and outcomes of the research with the medical community and stakeholders.
7. Mr. Prabhdeep Singh	Predictive Customer Analytics Platform. The Predictive Customer Analytics Platform will leverage advanced predictive analytics models to analyse the cleaned and pre-processed data. These models will be tailored to specific customer behaviour predictions, such as churn, lifetime value, and purchasing patterns. Techniques such as machine learning algorithms, regression analysis, and clustering will be employed to uncover patterns, trends, and correlation ns within the data. By applying these models, the platform will generate accurate predictions and insights about customer behaviour, enabling businesses to address customer needs and enhance their overall experience proactively. To ensure the accessibility and usability of the insights and predictions, the platform will feature a user-friendly interface. The interface will provide stakeholders with interactive dashboards, charts, and reports that visualize the generated insights clearly and concisely. Stakeholders can customize their views, explore different data dimensions, and drill down into specific segments or customer profiles. This interactive visualization capability will enable stakeholders to quickly identify trends, anomalies, and opportunities, facilitating data-driven decision-making. Bluetooth-Controlled Movable Robot with Greeting System and Motorized Hand.  A descriptive overview of a movable robot that incorporates four Johnson motors, a motor driver, an Arduino Uno, an XCO5 Bluetooth module, a smartphone application, an ultrasonic sensor, and a speaker. The robot is designed to be controlled via a mobile application using Bluetooth technology and has the additional functionality of greeting people using a speaker and a motorized hand. The combined functionality of the robot involves two primary aspects. Firstly, it can be controlled remotely via a mobile application using Bluetooth technology. This allows users to send commands wirelessly to the robot for movement and navigation. Secondly, the robot incorporates a greeting system that detects individuals using an ultrasonic sensor, generates audible greetings through a speaker, and performs hand gestures using a motorized hand. Disease Outbreak Prediction and Surveillance System.  The Disease Outbreak Prediction and Surveillance System is an advanced platform designed to collect, analyse, and predict disease outbreaks by leveraging data from various sources. The platform integrates data from public health records, social media platforms, and environmental sensors to provide early warning signs and actionable insights for healthcare organizations and public health authorities. The platform starts by collecting data from public health records, which include information about diagnosed cases, symptoms, and demographic details. This data is essential for understanding the disease landscape and identifying potential outbreaks. Additionally, the platform monitors social media platforms for real-time information and user generated content related to disease symptoms and outbreaks. By analysing social media data, the platform can detect early signals of disease activity and rapidly respond to emerging outbreaks. To enhance the accuracy of predictions, the platform incorporates data from environmental sensors such as air quality monitors and weather stations. These sensors provide valuable information about environmental factors contributing to disease spread, such as pollution levels, temperature, and humidity. By considering these factors alongside disease data, the platform can identify areas more susceptible to outbreaks and prioritize preventive measures. Healthcare Resource Optimization and Demand Forecasting.  The Healthcare Resource Optimization and Demand Forecasting platform is designed to address the challenges of resource allocation in the healthcare industry. By collecting and analysing data on healthcare resources such as hospital bed availability, staffing levels, and equipment utilization, the platform provides valuable insights for forecasting resource demands. Leveraging predictive analytics models, the platform generates accurate forecasts of future resource needs, enabling healthcare organizations to optimize resource allocation. The platform's user interface offers intuitive visualizations of resource utilization, demand forecasts, and recommendations for efficient resource allocation. Stakeholders can easily access and interpret the data, making informed decisions regarding resource allocation to ensure optimal operational efficiency and patient care. The platform's recommendations help healthcare organizations proactively address resource constraints and prevent shortages, leading to improved patient outcomes, reduced wait times, and enhanced resource utilization. By leveraging predictive analytics and data visualization, the Healthcare Resource Optimization and Demand Forecasting platform empowers healthcare organizations to optimize resource allocation and enhance overall operational performance. Pest and Disease Detection System.  The Pest and Disease Detection System is a ground-breaking project designed to assist farmers in identifying and managing pests and diseases in their crops. By harnessing data from various sources such as sensors, satellite imagery, and historical disease records, the system employs machine learning algorithms to analyse and detect signs of infestation or disease presence. The platform's user interface provides real-time visualizations highlighting disease outbreaks and infestation hotspots, allowing farmers to respond to emerging threats swiftly. Farmers can gain insights into the severity and spread of pests or diseases through these visualizations, enabling them to make informed decisions regarding pest control measures and disease management strategies. Also, the system offers recommended mitigation strategies based on the analysis of the collected data. By incorporating historical disease records and leveraging machine learning algorithms, the platform can provide tailored pest and disease control recommendations specific to the detected issues. This empowers farmers to take proactive measures, such as targeted pesticide application, crop rotation, or the introduction of beneficial insects, to mitigate the impact of pests and diseases on their crops.
8. Mr. Akshay Rajput	Inviting candidates for summer internship on ML, web Dev (industrial project).
9. Dr. Manish Sharma	Recommendation system Development of Web and Mobile Application Platforms Visualization, Data Analysis and Scraping on Social Media Platforms.
10. Mr. Yuvraj Joshi	Internship Overview:  The goal of this internship project is to create a user-friendly website and mobile application that will serve as a centralized platform for accessing information about vegetable market logs in different cities of India. This will involve the following key components:  1. User Interface and Experience:     - Designing an intuitive and visually appealing user interface for the website and application using HTML, CSS, and JavaScript.     - Ensuring a seamless user experience with easy navigation and accessibility.  2. Frontend Development:     - Implementing the frontend components of the website and application using popular frameworks such as React.js or Angular.     - Creating interactive features and responsive design to enhance user engagement.  3. Backend Development:     - Developing the backend infrastructure using Node.js and Express.js, which will handle data retrieval, storage, and manipulation.     - Integrating a database management system such as MongoDB or MySQL for efficient data storage and retrieval.  4. Data Collection and Storage:     - Gathering historical data on vegetable rates from various sources such as government reports, market surveys, and agricultural databases.     - Organizing and storing the data in a structured database, ensuring proper data normalization and indexing.  5. Machine Learning Algorithms:     - Developing and training machine learning models using Python and libraries such as scikit-learn or TensorFlow.     - Analysing historical data to identify patterns and trends in vegetable rates.     - Implementing regression or time series algorithms to predict future vegetable rates based on the available data.  6. Cloud Deployment:     - Deploying the website and application on a cloud platform such as AWS or Google Cloud for scalability and accessibility.     - Ensuring robust security measures to protect user data and maintaining high performance.  7. Additional Features:     - Incorporating interactive visualizations and charts using libraries like D3.js or Chart.js to present the market data effectively.     - Allowing users to compare rates across various cities and time periods through dynamic filtering and sorting options.     - Providing a feedback mechanism for users to contribute their market observations and ratings.  Internship Duration and Plan:  The proposed internship will span six weeks starting from July 8, 2023. The following is a suggested plan for the internship period:  Week 1: Internship-Project familiarization, requirement analysis, and designing the user interface wireframes.  Week 2: Setting up the development environment and implementing the frontend components using React.js/Angular.  Week 3: Developing the backend infrastructure and integrating the database management system.  Week 4: Gathering and cleaning historical data on vegetable rates, and preparing it for machine learning analysis.  Week 5: Training machine learning models using Python and implementing rate prediction algorithms.  Week 6: Finalizing the website and application, conducting testing and bug fixing, and deploying on the cloud platform.  During the internship, I will be responsible for delivering regular progress reports and seeking guidance from the assigned mentor. I am open to suggestions and adjustments to the proposed plan to align with the requirements and objectives of our department.  This internship project will provide valuable insights into web development, machine learning, and data analysis.
11. Dr Sumit Pundir	1. Engineering applications of Artificially neural network 2. WSN 3. SDN 4. Network Security

Contact the above faculties for more details.