9th International Conference on ICT for Sustainable Development

Authors - Rushin Bhatt, Kaushal Shah
Abstract - In an era dominated by digital technologies, because of the integration of computer systems and online platforms used by academic institutions likes schools, it is vitally important that sensitive data has to be safeguarded in a dynamic environment. This review article focuses on the complex landscape of network security in the education sector, offering a practical solution to prevent cyberattacks. As part of our study, we have created an Entity-Relationship (ER) diagram that shows how stakeholders in the education sector are related, and how they interact with each another. We will be exploring the use of advanced cryptography algorithms as well, for enhancing security measures. Our aim is to provide educational institutes with a comprehensive understanding of security considerations, enabling them to implement strong security measures for the safety of all stakeholders- students, teachers, and administrators. Through this exploration, we contribute to establishing a robust digital foundation for the education sector.

Authors - Shantala Giraddi, Prema Akkasaligar, Bushra Mthaigar, Pritam Shetty, Sneha Biradar, Sridhar Shetti
Abstract - This study presents a new method for brain tumour detection employing the Extreme Learning Machine (ELM) algorithm, focusing on medical imaging. The approach emphasizes image pre processing to enhance significant features and minimize noise before inputting them into the ELM-based classifier which is known for its fast learning and efficient data handling because of its single hidden layer, the ELM algorithm outperforms previous methods, as evidenced by multiple trials on publicly available data. The system demonstrates high accuracy, sensitivity, and specificity, making it suitable for real-time applications in medical imaging. This advancement has the potential to improve computer-aided diagnosis systems by enabling early and reliable identification of brain tumors, thereby enhancing patient care.

Authors - Priyanka Gulhane, Himangi Pande
Abstract - The Eyes are highly developed sensory organ of human body. In fact, major part of brain is dedicated to the functions of eyesight than those of other sensory organs. According to WHO almost 285 million people are visually impaired [1]. Approximately 8.7% of visual impairment is caused by ARMD [1]. Retinal images have achieved a vital role in detection and diagnosis of various eye diseases like DR, Macular hole, Age-Related Macular Degeneration, Cataract, Glaucoma etc. These diseases are primary cause of blindness and vision impairment in India. These diseases can cause severe conditions like blurred vision, vision loss or photophobia. Ocular diseases symptoms are not shown in early stage and they are not diagnosed till advanced stage. Age-related macular degeneration is the popular eye disease that mostly affects the elderly population having age above 50 years. ARMD is responsible for blurring the central vision of an individual. Many eye abnormalities are prominently visible in retina than any other part of the human eye. Growing number of retinal disease patient, hospital expenses and shortage in no. of ophthalmologists are barriers to attain recommended screening in the patients who are at the risk of retinal diseases.

Authors - Devesh Bedmutha, Purva Bapecha, Digambar Chaure, Piyush Bora, Rachna Karnavat
Abstract - This paper presents the implementation of an online proctoring system designed to operate entirely on the client side, addressing the inherent challenges associated with server-side processing in existing exam portals. By shifting the processing tasks to the client side, our system aims to alleviate the burden on servers and reduce network dependency, while ensuring robust face detection and suspicious activity detection capabilities. We have used siamese technique for face verification and MobileNet Model for object detection. Additionally, We have developed a custom browser extension that will detect and disable flagged extensions during the exam. Our system also has the support of a variety of question types including coding, subjective and multiple-choice (MCQ) questions. Through our implementation, we aim to enhance the efficiency, cost-effectiveness, and security of online exam proctoring, offering a solution that minimizes server load and maximizes performance by leveraging client-side resources

Authors - Gayatri Joshi, Soham Joshi, Vatsal Mehta, Kumkum Saxena
Abstract - Emails have become a centre for a large user base, leading it to be a platform for reaching large crowds with minimum effort and enabling an effortless spread of information to larger audiences. But on the downside, it has also led to an increase of user traffic in email, which also consists of some unwanted marketing and promotion-related emails. Several users' private data is being extracted, and such superfluous emails are sent which are largely known as spam. The paper aims to combat the problems by making use of different machine learning approaches. Despite the multitude of available classifiers to build classification models for an imbalanced dataset, the main task was to reduce the bias of the majority class. This paper aims to restructure the imbalanced nature of the dataset and apply different machine learning algorithms, like Support Vector Machine, Random Forest, Multinomial Naive Bayes and XGBoost. In addition to this, the paper also compares between different ensemble techniques used. Not only does this avoid erroneous categorisation of legitimate emails as spam, but also provides insightful knowledge to rectify imbalanced dataset problems. It underscores the potential of using different methods to enhance the accuracy and combating the problem.

Authors - D.S. Jadhav, Avinash Andhale, Avinash Padale, Anjana Auti, Neha Bokfode, Supriya Mane, Avinash Golande
Abstract - This research introduces an extensive health monitoring solution designed for parents or elderly family members, addressing the challenges of separation due to work. The proposed system is structured into three key stages: hardware, cloud, and a React Native-based mobile application. In the hardware phase, various sensors (MAX30102 for pulse rate and SpO2, DS18B20 for temperature) are intricately connected to the ESP8266 microchip. Utilizing the Arduino IDE, the microchip enables seamless communication, efficiently collecting health data. The ESP8266 WiFi module in the second phase establishes robust communication with Thingspeak cloud, enhancing data comprehensibility through graph visualization on the Thingspeak website. The system ensures data security with a unique API key. In the final phase, meticulously processed data is transmitted to a React Native mobile app, supporting Android platforms. The app features a user-friendly interface with login, signup, and a main home screen displaying health data through a circular progress bar. Abnormal readings trigger push notifications, prompting timely investigation of potential health issues, such as elevated heart rate indicating a possible heart attack. The integrated system provides a secure and user-friendly platform for remote health monitoring, ensuring caregivers receive timely alerts regarding their loved ones' health concerns. The system's combination of hardware, cloud, and mobile application promotes peace of mind and facilitates swift intervention, contributing to an elevated level of care and well-being. The system architecture includes three layers: device layer (ESP8266, MAX30102), cloud layer (data processing and storage), and web app layer (real-time data visualization and alerts). The methodology involves data collection by ESP8266, transmission to Thingspeak cloud via API, and real-time monitoring through the web application.

Authors - Tarang Boharupi, S. Poonkuntran
Abstract - Preserving the cultural heritage of iconic landmarks is paramount in maintaining their historical significance. This research focuses on the restoration of damaged images of the Mysore Palace, a heritage site of immense cultural importance. A dataset comprising 171 real and damaged images of the palace, captured with a OnePlus mobile device, forms the basis of this study. The proposed methodology leverages an inpainting technique to generate mask images, which are subsequently utilized in the training of a Generative Adversarial Network (GAN). The GAN architecture is employed to learn the intricate patterns and details necessary for reconstructing the damaged portions of the images. The training process resulted in a model with a PSNR (Peak Signal-to-Noise Ratio) value of 16.5 and SSIM (Structural Similarity Index) of 0.023. The outcomes of this research showcase the efficacy of the developed GAN model in restoring damaged images of heritage structures. The achieved PSNR value indicates a notable improvement in image quality, while the SSIM metric reflects the preservation of structural details. The study contributes to the field of image restoration, especially concerning heritage conservation, offering a novel approach that can be extended to safeguard other cultural landmarks.

Authors - Ramesh Guntha, Aiswarya A, Soham Adla, Maya Presannakumar, Mario Alberto Ponce Pacheco, Saket Pande
Abstract - The agricultural sector, particularly in rural areas, faces numerous challenges including labor shortages, fluctuating costs, and unpredictable weather patterns. The Makara app emerges as a pioneering digital solution, specifically designed to address the multifaceted needs of small-scale farmers. This paper presents a case study on the Makara app, highlighting its role in transforming agricultural practices through digital innovation. The app provides a comprehensive platform for farmers to manage their land, crops, and financials effectively. It offers detailed land and crop management, budgeting, and activity management. Additionally, Makara's day-to-day advisory service and risk prediction module assist farmers in optimizing resource use and enhancing productivity. The app's multilingual interface and offline mode ensure accessibility and usability in remote areas. This study analyzes the software development, farmer engagement, feedback collection, software refinement, and deployment process of the Makara app among the select farmers of the Nagpur region in Maharashtra, India. The Makara app exemplifies the potential of digital tools in promoting sustainable and profitable farming practices in rural communities.

Authors - Samuel Nghidengwa Nakale, Fungai Bhunu Shava, Gloria Iyawa
Abstract - Employee fatigue is one of the major risk factors across different industries. Consequences of fatigue include injuries and fatalities which in turn affect employee productivity and results in various economic and social costs. Artificial Intelligence (AI) especially Machine Learning (ML) techniques have been used to develop data driven solutions for fatigue monitoring and detection in various industries. However, the fatigue detection systems proposed in literature were predominantly evaluated on simulated data which may not capture some of the real-world driving conditions like in the mining environment. This study deploys three ML classifiers (Support Vector Classifier, Random Forest Classifier and the K-Nearest Neighbor Classifier) to investigate the performance of ML based fatigue detection systems for drivers in the mining industry. The proposed system is implemented in Python and evaluated on a simulated dataset, the Yawning Detection Dataset (YawDD), and a real-world mining operation dataset. All three models achieved a fatigue prediction accuracy above 90% for both datasets. The major challenge to developing behavioral based fatigue detection systems for real world setting like the mining environment is face detection accuracy which is affected by factors such as low image resolution due to poor and variable lighting conditions, face orientation to camera and proximity of face to the camera. The significant contribution of this study is the use of real-world dataset to evaluate the performance of ML based fatigue detection models.

Authors - MARTIN H MOLLAY, Deepak Sharma
Abstract - With an emphasis on sustainability's environmental, economic, and social aspects, this literature review critically investigates the complex relationship between technology and sustainability. It summarizes the body of research to offer a thorough grasp of the application of sustainable technology practices, their influence on various industries, and their wider consequences for preserving the environment and reducing the effects of climate change. This component examines how initial investment costs, ongoing operating costs, and possible returns on investment can be used to analyze how sustainable technologies can reduce costs over time. The necessity for a comprehensive strategy that balances economic growth, ecological preservation, and social well-being is underscored by key results that stress the significance of incorporating sustainability principles into technology breakthroughs. The review emphasizes the importance of using renewable energy sources, energy-efficient improvements, afforestation and reforestation programs, sustainable land management practices, and sustainable manufacturing practices to reduce climate change and promote environmental preservation. This study, which synthesizes the body of literature already in existence, highlights research gaps and essential areas of interest, providing guidance for future studies and valuable takeaways for stakeholders such as corporations and governments. The results demonstrate how vital technology is to achieving sustainability goals and stress the importance of teamwork in tackling global issues like climate change and environmental degradation. The present literature review adds to the recent knowledge and its offers a vivid synopsis of the relationship between technology and sustainability. It also illuminates prospective directions for further investigation and real-world implementations across multiple industries.