Authors: Rajesh Chaurasiya, Vishal Sharma

Abstract: With the rapid growth of artificial intelligence (AI), deep learning models are becoming more complex and require significant computing power, memory, and energy. This makes it difficult to deploy them on devices with limited resources, such as smartphones, embedded systems, and edge devices. To address this challenge, model compression techniques have emerged as a key solution. These methods reduce the size and computational cost of AI models while keeping their performance close to that of the original models. This paper explores four widely used model compression techniques: pruning, quantization, knowledge distillation, and low-rank factorization. Each technique is explained in terms of how it works, its advantages, and the trade-offs it brings. A special focus is placed on pure compression strategies, which avoid external indexing or lookup tables and are better suited for simple and energy-efficient systems. A case study using a convolutional neural network (CNN) shows that combining pruning and quantization can reduce model size by more than 80% and speed up inference time by 30% with only a small loss in accuracy. The study also highlights key metrics for evaluating compressed models, including memory usage, speed, and accuracy. Finally, the paper discusses real-world applications in mobile devices, healthcare, and autonomous systems, along with future directions such as automated compression tools and energy-aware training. Overall, this research supports the development of more accessible, scalable, and eco-friendly AI by making models lighter and more efficient.

DOI: http://doi.org/10.5281/zenodo.15718659

 

Published by: vikaspatanker

Authors: Mohammed Muzaffar, Mohammed Saif, Abdul Baser

Abstract: Nowadays, people pay more attention in artificial intelligence (AI) research, and they try to make Al smarter. The machine learning became a popular subject, especially in object recognition area. Aiming at providing a faster and more accurate plant species recognition program, the author introduced the deep learning and convolution neural network (CNN), and decided to build a CNN project with pycharm, anaconda, kera to find the best way to improve recognition program accuracy and recognition speed. The author tried to change the learning epoch time and learning data set capacity to found the best solution. After tests were finished, the result of output plots analyze is that both adding learning epochs time and extend training image set are all helpful to improve recognition accuracy and speed. As for the effect of increase learning time, it is more obvious in improving accuracy while extend training set size, which is a better method to reduce recognition time. The end of the thesis contained the experiment result, the deficiency of this essay and the future prospect forecast of the machine learning applied in plant area.

Published by: vikaspatanker

Authors: Shashanth. N, Naveen Kumar, Dr Sanjay Dutta

Abstract: Graph isomorphism the problem of finding out whether two graphs are structurally identical or same is one of the most fundamental in various fields such as computer science, chemistry, and biology specifically mathematics and so on .This breakdown deals into several algorithms which are designed to address or evaluate graph isomorphism, some of the algorithms are been studied in this paper those are, is_isomorphic, could_be_isomorphic, fast_could_be_isomorphic, and faster_could_be_isomorphic .Each algorithm preforms using different strategies to evaluate graph similarity, from strict structural comparison to quick preliminary checks based on graph properties. While is_isomorphic uses the VF2 algorithm for precise matching, could_be_isomorphic functions offer faster assessments by evaluating global and local graph properties. However these algorithms possess limitations such as potential false positives and scalability issues for large datasets. The provided flowcharts illustrate the step by step processes involved in each algorithm, which helps in understanding their functionalities. By developing graph isomorphism algorithms researchers can find out new opportunities for applications in network analysis, pattern recognition, and beyond.

Published by: vikaspatanker

Authors: Mr. K. Amarander, Y Anusha, K Shivani, G Kumaraswamy, T Tharun Kumar

 

 

Abstract: This project presents a cost-effective and real-time system for flood alert and rain detection utilizing the ESP32 microcontroller, an ultrasonic sensor, an OLED display, a rain sensor, and a buzzer. The ultrasonic sensor continuously measures the water level, while the rain sensor detects the presence and intensity of rainfall. Data from these sensors are processed by the ESP32, which triggers visual alerts on the OLED display and audible warnings via the buzzer when predefined water level thresholds are breached or significant rainfall is detected. The system, powered by a suitable power supply, offers a proactive approach to mitigate flood risks by providing timely warnings to potentially affected areas. Its compact design and low power consumption make it suitable for deployment in various environments susceptible to flooding. The low-power nature of the ESP32 and the selected sensors contributes to the system's energy efficiency, allowing for extended operation with appropriate power management. Field testing and calibration would be crucial to optimize the system's reliability and accuracy under diverse environmental conditions. Ultimately, this project demonstrates a tangible application of readily available microelectronics in creating resilient and responsive solutions for natural hazard monitoring and early warning.

DOI: http://doi.org/

 

 

Published by: vikaspatanker

Authors: Associate Professor K Chiranjeevi, R Sai Deepika, G Praveen, S Nikhitha, K Sachin

Abstract: The control system of an industrial robotic arm is a coordinated assembly of electromechanical components designed to execute complex movements and tasks with precision. At the heart of the robotic arm are DC motors, which serve as actuators that convert electrical energy into mechanical motion. These motors are responsible for driving the arm's joints and enabling rotational and linear movements. Gears are integrated with the motors to modify torque and speed, allowing the arm to handle heavy loads or perform fine manipulations with accuracy. To power the system, batteries are used as a portable and stable source of DC electrical energy. These batteries provide sufficient voltage and current to drive the motors and auxiliary electronics. DC connectors are employed to ensure secure and efficient connections between the power source and the motors, allowing easy interfacing and maintenance.

Published by: vikaspatanker

Authors: Md Mirja Galib, Soumyadip Roy, Shilpi Pal, Payel Mondal, Sarbani Ganguly

Abstract: The rapid increase in global CO2 emissions since 1950 has led to a surge in weather- and climate-related disasters worldwide. To address this, the United Nations Framework Convention on Climate Change (UNFCCC) was established in 1992, aiming to stabilize greenhouse gas (GHG) emissions. The Kyoto Protocol introduced the Clean Development Mechanism (CDM), incentivizing both developed and developing nations to reduce emissions. Through the trading of carbon credits, CDM projects aim to mitigate climate change while fostering sustainable development. However, despite its goals, Asia and the Pacific regions dominate CDM projects, with limited participation from Africa. India's success in CDM projects fluctuated over time, with challenges persisting due to the CDM system's crisis. Despite uncertainties surrounding its future, the CDM's legacy in promoting emissions reductions and sustainable development remains significant. Transitioning to the Sustainable Development Mechanism (SDM) under the Paris Agreement poses challenges and opportunities for international climate cooperation and sustainable development efforts, particularly for countries like India

 

 

Published by: vikaspatanker

Authors: Vriddhi Shah

Abstract: Genetic research has revolutionized our understanding of diseases, revealing strong hereditary components in conditions such as cancer, diabetes, and autoimmune diseases. While environmental factors also contribute, genetic mutations play a crucial role in disease susceptibility. This paper explores the genetic basis of these diseases, highlighting specific genes, inheritance patterns, and statistical insights. Recent advancements in genome-wide association studies (GWAS) and precision medicine are also discussed.

DOI: http://doi.org/10.5281/zenodo.15689196

Published by: vikaspatanker

Authors: Md Mirja Galib, Soumya Kanti Roy, Sarbani Ganguly, Payel Mondal, Rupa Bhattacharyya

 

Abstract: The Electric vehicles (EVs) represent a promising solution to lighten environmental challenges associated with traditional internal combustion engine vehicles (ICEVs). This abstract examines the environmental impact of EVs, focusing on key factors such as greenhouse gas emissions, resource extraction and production, battery recycling and disposal, energy efficiency, infrastructure development, and lifecycle analysis. While EVs produce zero tailpipe emissions and can significantly reduce greenhouse gas emissions, their environmental benefits depend on factors such as the energy source for electricity generation. Additionally, the extraction of materials for EV batteries and the challenges of battery recycling and disposal poses environmental concerns that require attention. The location of a charging station can also affect its carbon footprint. If a charging station is located in an area with high traffic obstruction, the carbon footprint of charging an EV may be higher due to increase idling and emissions from other vehicles. EV production will have external costs of emissions extra, around Rp. 2.23 trillion, or an increasing about 0.6%. Based upon these findings, it is concluded that electric vehicle production increases productivity, gross value-added, and job creation with a corresponding to the small impact on the environment. Despite these challenges, EVs illustrate higher energy efficiency and offer potential prolong benefits in reducing dependence on fossil fuels. Comprehensive lifecycle evaluation is necessary for understanding the overall environmental impact of EVs compared to ICEVs. Continued development in technology, policy support, and infrastructure improvement are crucial for maximizing the environmental benefits of EVs and promoting sustainable transportation.

DOI: https://doi.org/10.5281/zenodo.15689367

 

Published by: vikaspatanker

Authors: Subhranil Sarkar, Sayna Datta, Assistant Professor Aparajita Paul, Assistant Professor Pallav Dutta, Rupa Bhattacharyya

Abstract: Environmental tipping points represent critical thresholds within ecological and climate systems, beyond which significant and often irreversible changes occur. Driven largely by human activities such as deforestation, fossil fuel combustion, pollution, and overexploitation of natural resources, these tipping points threaten the stability of the Earth's life-support systems. Key examples include the collapse of coral reef ecosystems, the thawing of permafrost, and disruptions to major oceanic and atmospheric circulation patterns. These shifts are often accelerated by positive feedback loops, making them difficult to reverse once triggered. This paper explores the mechanisms behind environmental tipping points, identifies major systems at risk, and examines the profound ecological, social, and economic consequences of crossing these thresholds. It also highlights the urgent need for integrated, science-based sustainability strategies aimed at mitigating human impacts and building resilience within natural systems. Preventing the crossing of critical tipping points is not only an ecological imperative but also a central challenge for the future of humanity.

DOI: https://doi.org/10.5281/zenodo.15688670

Published by: vikaspatanker

Authors: Priyanka A Giramkar, Dr. Quazi khabeer

Abstract: The rise of fake insights (AI) presents transformative openings within the space of career services, especially in continue building, a basic component for job searchers pointing to distinguish themselves in an progressively competitive scene.This inquire about investigates the development of an AIbased resume builder planned to help clients in making highly customized, proficient resumes that adjust precisely with industry measures and job-specific requirements By coordination normal dialect processing(NLP), machine learning, the framework analyzes work depictions to distinguish significant catchphrases, skillsets, and role specific necessities. It at that point appliesthis investigation to prescribe important substance, improve phrasing, and organize the continue in a way that maximizes both significance and lucidness for human recruiters and candidate following frameworks (ATS). Furthermore,the framework powerfully adjusts resumes to reflect users' advancing career encounters, optimizing sections such as accomplishments, abilities, and proficient summaries for focused on parts. Moreover, the framework powerfully adjusts resumes to reflect users' advancing career encounters, optimizing sections such as accomplishments, abilities, and proficient summaries for focused on parts. Through broad testing and data-driven refinement, this AI-powered resume builder illustrates the potential to streamline the work application prepare, upgrade candidate perceivability, and altogether increment the likelihood of securing interviews. This investigate contributes to the field by displaying how AI can reshape cont

Published by: vikaspatanker