Volume-12 , Issue-9 , Sep - 2024 Go Back

Over the past decade, forest fires have caused devastation in many areas of India, severely harming forest ecosystems, reducing biodiversity, and affecting the lives of populations that depend on the forests for their subsistence. Convolutional Neural Networks (CNNs), or ConvNets, represent a specialized deep learning architecture that extracts and learns patterns directly from data. CNNs are excellent at recognizing patterns in images, allowing them to identify objects, group similar items, and classify different categories with high precision. They can also be highly effective at classifying audio, time-series, and signal data. This work suggests creating a model that can be used to classify whether or not there is forest fire based on the images. In order to get better outcomes, the deep neural network component of the final model was developed from the VGG16 basic architecture. 5062 photos from open source sources, including both fire and no-fire conditions, were used to train the model. This paper presents a model developed using Keras with TensorFlow and Theano as the backend and the efficiency of the model was compared. The TensorFlow based model provided an accuracy of 97.6% and the Theano based model provided an accuracy of 97.54%. Even with limited resolution, the model with Keras and TensorFlow backend was able to categorise the majority of the random pictures given to it as Fire(1) and No Fire(0) class with better evaluation scores and less time.

CNN, Deep Learning, VGG16, Forest Fires, Keras, TensorFlow, Theano, Image classification

[1] M. Aamir et al., “Natural Disasters Intensity Analysis and Classification Based on Multispectral Images Using Multi-Layered Deep Convolutional Neural Network,” Sensors, Vol.21, No.8, pp.2648, 2021.
[2] F. Guede-Fernández, L. Martins, R. V. de Almeida, H. Gamboa, and P. Vieira, “A Deep Learning Based Object Identification System for Forest Fire Detection,” Fire, Vol.4, No.4, pp.75, 2021.
[3] R. Xu, H. Lin, K. Lu, L. Cao, and Y. Liu, “A Forest Fire Detection System Based on Ensemble Learning,” Forests, Vol.12, No.2, pp.217, 2021.
[4] D. Kinaneva, G. Hristov, J. Raychev, and P. Zahariev, "Early Forest Fire Detection Using Drones and Artificial Intelligence," 2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp.1060-1065, 2019.
[5] Abdelmalek Bouguettaya, Hafed Zarzour, Amine Mohammed Taberkit, Ahmed Kechida, “A review on early wildfire detection from unmanned aerial vehicles using deep learning-based computer vision algorithms,” Signal Processing, Vol.190, pp.108309, 2022.
[6] Zhang, G., Wang, M., & Liu, K., “Forest Fire Susceptibility Modeling Using a Convolutional Neural Network for Yunnan Province of China,” Int J Disaster Risk Sci, Vol.10, pp.386–403, 2019.
[7] Abid, F., “A Survey of Machine Learning Algorithms Based Forest Fires Prediction and Detection Systems,” Fire Technol, Vol. 57, pp.559–590, 2021.
[8] M. Zainab, A. R. Usmani, S. Mehrban, and M. Hussain, "FPGA based implementations of RNN and CNN: a brief analysis," In 2019 International Conference on Innovative Computing (ICIC), pp.1-8, 2019.
[9] Alzubaidi, L., Zhang, J., Humaidi, A. J., et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J Big Data, Vol.8, pp.53, 2021.
[10] Bogacz, M., and A. Qouneh, "Convolution Neural Network on BeagleBone Black Wireless for Machine Learning Applications," 2022 IEEE MIT Undergraduate Research Technology Conference (URTC), Cambridge, MA, USA, pp.1-4, 2022.
[11] Shorten, C., and T. M. Khoshgoftaar, "A survey on image data augmentation for deep learning," Journal of Big Data, Vol.6, No.1, pp.1-48, 2019.
[12] N. T. Toan, P. Thanh Cong, N. Q. Viet Hung, and J. Jo, "A deep learning approach for early wildfire detection from hyperspectral satellite images," 2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA), pp.38-45, 2019.
[13] D. Rashkovetsky, F. Mauracher, M. Langer, and M. Schmitt, "Wildfire Detection From Multisensor Satellite Imagery Using Deep Semantic Segmentation," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.14, pp.7001-7016, 2021.
[14] M. Park, D. Q. Tran, D. Jung, and S. Park, “Wildfire-Detection Method Using DenseNet and CycleGAN Data Augmentation-Based Remote Camera Imagery,” Remote Sensing, Vol.12, No.22, pp.3715, 2020.
[15] K. Govil, M. L. Welch, J. T. Ball, and C. R. Pennypacker, “Preliminary Results from a Wildfire Detection System Using Deep Learning on Remote Camera Images,” Remote Sensing, Vol.12, No.1, pp.166, 2020.
[16] Shruthi G, Disha Bhat, Gagana H, Dimple M K, Kavitha, "Forest Fire Detection Using Convolutional Neural Networks", International Journal of Computer Sciences and Engineering, Vol.7, Special Issue.14, pp.323-325, 2019.

Nesiga A, Sahani S Shetty, Mythili Mahesh Velapakam, Kiran Bailey, Geetishree Mishra, "A Comparative Study of CNN Models Built with TensorFlow and Theano for Forest Fire Detection," International Journal of Computer Sciences and Engineering, Vol.12, Issue.9, pp.1-8, 2024.

The field of Educational Data Mining (EDM) is still young and is focused on improving existing data mining (DM) techniques as well as creating new ones for locating data originating from educational systems. It seeks to employ these techniques to arrive at a logical understanding of students and the kind of learning environment they ought to experience. Knowledge Tracing (KT) and the prediction of student performance are closely intertwined. The academic community has made an effort to address it and has produced findings that are competitive. Several strategies have been implemented over the past 20 years that have improved on already-existing techniques by attacking the issue from different model architectures and experimenting with various datasets and formats. The efficiency of various machine learning models for predicting student performance is examined in this research. The outcomes were contrasted with earlier research that forecasted student achievement.

Educational Data Mining, Machine Learning, Student Performance Prediction, Knowledge Tracing, and Classification.

[1] Kaunang, F. J., & Rotikan, R, “Students` academic performance prediction using data mining”. In the proceedings of the 2018 Third International Conference on Informatics and Computing (ICIC) IEEE, pp.1-5, 2018.
[2] Hasan, R., Palaniappan, S., Raziff, A. R. A., Mahmood, S., Sarker, K. U, “Student academic performance prediction by using decision tree algorithm”. In the proceedings of the 2018 4th international conference on computer and information sciences (ICCOINS) IEEE, pp.1-5, 2018.
[3] Ahmad, F., Ismail, N. H., Aziz, A. A, “The prediction of students’ academic performance using classification data mining techniques”, Applied mathematical sciences, Vol.9, Issue.129, 2018.
[4] Balaji, P., Alelyani, S., Qahmash, A., Mohana, M, “Contributions of machine learning models towards student academic performance prediction: a systematic review”, Applied Sciences, Vol.11, Issue.21, 2015.
[5] Rodríguez-Hernández, C. F., Musso, M., Kyndt, E., Cascallar, E, “Artificial neural networks in academic performance prediction: Systematic implementation and predictor evaluation”, Computers and Education: Artificial Intelligence, Issue.2, pp.100018, 2021.
[6] Wang, X., Zhao, Y., Li, C., Ren, P, “ProbSAP: A comprehensive and high-performance system for student academic performance prediction”, Pattern Recognition, Vol.1, Issue.7, 2023.
[7] Aslam, N., Khan, I., Alamri, L., Almuslim, R, “An improved early student’s academic performance prediction using deep learning”, International Journal of Emerging Technologies in Learning (iJET), Vol.16, Issue.12, pp.108-122, 2021.
[8] Ajibade, S. S. M., Dayupay, J., Ngo-Hoang, D. L., Oyebode, O. J., Sasan, J. M. “Utilization of Ensemble Techniques for Prediction of the Academic Performance of Students”, Journal of Optoelectronics Laser, Vol.41, Issue.6, pp.48-54, 2022.
[9] Imran, M., Latif, S., Mehmood, D., Shah, M. S, “Student academic performance prediction using supervised learning techniques”. International Journal of Emerging Technologies in Learning, Vol.14, Issue.14, 2019.
[10] Ha, D. T., Loan, P. T. T., Giap, C. N., Huong, N. T. L, “An empirical study for student academic performance prediction using machine learning techniques”, International Journal of Computer Science and Information Security (IJCSIS), Vol.18, Issue.3, pp.75-82, 2020.
[11] Lu, O. H., Huang, A. Y., Huang, J. C., Lin, A. J., Ogata, H., Yang, S. J, “Applying learning analytics for the early prediction of Students` academic performance in blended learning”, Journal of Educational Technology & Society, Vol.21, Issue.2, pp.220-232. 2018.
[12] Asiah, M., Zulkarnaen, K. N., Safaai, D., Hafzan, M. Y. N. N., Saberi, M. M., Syuhaida, S. S, “A review on predictive modeling technique for student academic performance monitoring”, In the proceeding of the MATEC Web of Conferences, EDP Sciences, Vol.255, pp.03004, 2023.
[13] Balaji D. Raj, Marimuthu A, “Classification of ECG Signals Using Self Advising Support Vector Machine and Fuzzy C Means Clustering”, International Journal of Research in Advent Technology, Vol.6, No.11, pp.3252-3259, 2018.
[14] Walia, N., Kumar, M., Nayar, N., Mehta, G, “Student’s academic performance prediction in academic using data mining techniques”, In Proceedings of the International Conference on Innovative Computing & Communications (ICICC), 2020.
[15] Rai, S., Shastry, K. A., Pratap, S., Kishore, S., Mishra, P., Sanjay, H. A, “Machine learning approach for student academic performance prediction”, In the proceedings of the Evolution in Computational Intelligence: Frontiers in Intelligent Computing: Theory and Applications (FICTA 2020), Vol.1, pp.611-618, 2020.

D. Boominath, S. Dhinakaran, "Analysis of Students Performance Prediction Models Using Machine Learning Approaches," International Journal of Computer Sciences and Engineering, Vol.12, Issue.9, pp.9-13, 2024.

As the AdTech industry evolves, it increasingly relies on Key Performance Indicators (KPIs) to measure success. Traditional KPIs such as ad-impressions, ad click-through rates and survey responses have long served as benchmarks for campaign performance. However, with the rise of machine learning (ML) and automation, the need for more sophisticated and predictive KPIs is apparent. This paper introduces a novel approach, proposing machine learning-driven KPIs designed to optimize revenue streams and address challenges like ad fatigue, cross-device behavior, and accessibility. By automating KPI validation and implementing advanced metrics—such as Ad Accessibility Optimization, Ad Fatigue Prevention Index, and Cross-Device Path Efficiency—this paper offers an innovative framework for enhancing data-driven decision-making in real time. These new KPIs aim to predict optimal ad strategies and improve campaign performance, ultimately maximizing ROI.

Key Performance Indicators (KPI), automation, machine learning, AdTech, revenue optimization, accessibility, ad fatigue, cross-device efficiency.

[1] A. Abran, Software Metrics and Software Metrology. John Wiley, 2010.
[2] Z. Bo and B. Zhang, "Precise Marketing of Precision Marketing Value Chain Based on Big Data,” Journal of Intelligent and Fuzzy Systems, 2018.
[3] A. Goldfarb and C. E. Tucker, "Standardization and the Effectiveness of Online Advertising," Operations Research, 2017.
[4] S. Muthukrishnan, "Ad exchanges: Research issues," in Proc. Int. Workshop Internet Netw. Econ., pp.1-12, 2009.
[5] C. Perlich, B. Dalessandro, R. Hook, O. Stitelman, T. Raeder, and F. Provost, "Bid optimizing and inventory scoring in targeted online advertising," in Proc. 18th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, pp.804-812, 2012.
[6] H. B. McMahan et al., "Ad click prediction: A view from the trenches," in Proc. Int. Conf. Knowl. Discov. Data Mining, pp.1222-1230, 2013.
[7] M. A. Badri, D. Davis, and D. Davis, "A study of measuring the critical factors of quality management," Int. J. Qual. Reliab. Manag., Vol.12, No.2, pp.36–53, 1994.
[8] J. Shu, X. Shen, H. Liu, B. Yi, and Z. Zhang, "A content-based recommendation algorithm for learning resources," Multimedia Systems, Mar., Vol.24, No.2, pp.163-173, 2018.
[9] M. Bernard, S. Gianni, and A. Neely, "Intellectual capital-defining key performance indicators for organizational knowledge assets," J. Bus. Process Manag., Vol.10, No.5, pp.551–569, 2004.
[10] H. Meier, H. Lagemann, F. Morlock, and C. Rathmann, "Key performance indicators for assessing the planning and delivery of industrial services," Procedia Cirp, Vol.11, pp.99-104, 2013.
[11] Yash Patil, Samidha Ashtikar, Sakshi Shirodkar, Krishna Dudhate, Shraddha V. Pandit, “Recommendation Systems in Online Retail: A Comprehensive Survey of AI Techniques,” Feb., Vol.12, Issue.2, pp.30-36, 2024.
[12] Shashank Saroop, Radha, “Blockchain Based Data Privacy through Artificial Intelligence: Review” Dec., Vol.11, Issue.12, pp.32-37, 2023.

Naga Harini Kodey, "Machine Learning-Driven KPIs for Revenue Optimization in Adtech," International Journal of Computer Sciences and Engineering, Vol.12, Issue.9, pp.14-17, 2024.

This research investigates the integration of SAP ERP with Robotic Process Automation (RPA) and Power Apps to address specific challenges in field service operations, particularly in remote areas with unreliable internet connectivity. The solution leverages SAP`s ERP capabilities and RPA to enable seamless offline data capture, synchronization, and automated processing of service transactions. Field technicians visiting customer sites use mobile devices to capture data (e.g., repair parts orders) immediately in the system offline, thus reducing errors and improving accuracy. This paper details how data is captured both online and offline and how it synchronizes with SAP ERP upon reconnection, triggering RPA bots to create shipment orders and update inventory, thereby streamlining the workflow. The study explores concrete implementation strategies like offline-capable SAP interfaces, external database integration, and optimized automated workflow management. SAP ERP and RPA integration significantly enhances efficiency, minimizes manual intervention, and improves service delivery in low-connectivity environments. Evaluations show quantifiable improvements in transaction times, data integrity, and service quality, ultimately leading to increased customer satisfaction. The findings demonstrate the broad scalability of this approach across industries, optimizing ERP use in remote operations. The framework provides a practical model for organizations seeking to enhance SAP ERP, reduce costs, and overcome connectivity barriers in field service management. Keywords: SAP ERP, Robotic Process Automation (RPA), Offline Data Capture, Data Synchronization, Automated Transaction Processing, Service Delivery Improvement, Operational Efficiency, SAP Integration, Field Service Management.

SAP ERP, Robotic Process Automation (RPA), Field Service Management, Offline Data Capture, Power Apps, Mobile Devices, BOT, Process Automation

[1] E. Puica, "How is it a benefit using robotic process automation in supply chain management?", Journal of Supply Chain Customer Relationship Management, 2022.
[2] L. Aho, "Mobile data collection and storing solution for Microsoft environments," Master`s thesis, Tampere Univ. of Technology, 2018.
[3] J. Saha, "Exploring process automation opportunities: Power Platform and Robot Framework," 2022.
[4] H. Moon, "Implementation of a mobile business application built in Microsoft Power Platform," Thesis, 2020.
[5] A. H. Zadeh, H. M. Zolbanin, A. Sengupta, et al., "Enhancing ERP learning outcomes through Microsoft Dynamics," Journal of Information Systems Education, Vol.31, No.2, 2020.
[6] B. Mohapatra and S. Mohapatra, "ERP as business process automation tool," 2023.
[7] F. Gürcan and G. Taentzer, "Using Microsoft PowerApps, Mendix and OutSystems in two development scenarios: An experience report," Proceedings of the ACM/IEEE International Symposium on Empirical Software Engineering and Measurement. 2021.
[8] M. Weston, Learn Microsoft Power Apps: Build customized business applications without writing any code. Apress, 2019.
[9] Y.-W. Kao, C.-F. Lin, K.-A. Yang, and S.-M. Yuan, "A Web-based, Offline-able, and Personalized Runtime Environment for executing applications on mobile devices," Computer Standards & Interfaces, Vol.34, No.4, pp.322-332, 2012.
[10] J. Ribeiro, R. Lima, T. Eckhardt, and S. Paiva, "Robotic process automation and artificial intelligence in Industry 4.0–A literature review," Procedia Computer Science, Vol.180, pp.354-363, 2021.
[11] Y. Devarajan, "A study of robotic process automation use cases today for tomorrow`s business," International Journal of Computer Techniques, Vol.5, No.6, pp.1-7, 2018.
[12] B. Axmann and H. Harmoko, "Robotic process automation: An overview and comparison to other technology in Industry 4.0," 10th International Conference on Human System Interactions (HSI), 2020.
[13] E. Puica, "How is it a benefit using robotic process automation in supply chain management?," Journal of Supply Chain Customer Relationship Management, 2022.
[14] J. Saha, "Exploring process automation opportunities: Power Platform and Robot Framework," 2022.
[15] H. Vartiainen, "Lean Management Empowerment: Elevating Employee Experience through RPA Implementation with Microsoft Power Automate," Thesis, 2024.
[16] T Oliveira, MF Martins. Literature review of information technology adoption models at firm level. Electronic Journal of Information Systems Evaluation, 2011.
[17] HO Awa, OU Ojiabo. A model of adoption determinants of ERP within TOE framework. Information Technology & People, 2016.
[18] C Sharma, SS Bharadwaj, N Gupta. Robotic process automation adoption: contextual factors from service sectors in an emerging economy. Journal of Enterprise Information Management, 2023.
[19] DA da Silva Costa, H São Mamede, et al. Robotic process automation (RPA) adoption: A systematic literature review. Engineering Management in Production and Services, 2022.
[20] A Leshob, A Bourgouin. Towards a process analysis approach to adopt robotic process automation. IEEE 15th International Conference on Services Computing, 2018.
[21] J Siderska. The adoption of robotic process automation technology to ensure business processes during the COVID-19 pandemic. Sustainability, 2021.
[22] H Moon. Implementation of a mobile business application built in Microsoft Power Platform. 2020.
[23] J Laaksonen. Best practices for Microsoft Power Apps implementation. 2024.
[24] PP Kumar, PS Rao. Oracle Apps Task Automation–OATA. 2020.
[25] D Pramod. Robotic process automation for industry: adoption status, benefits, challenges and research agenda. Benchmarking: an international journal, 2022.
[26] S Gomathi. Future Trends in ERP and Business Central. Springer.
[27] A Leshob, A Bourgouin. Towards a process analysis approach to adopt robotic process automation. IEEE 15th International Conference on Services Computing, 2018.
[28] H Moon. Implementation of a mobile business application built in Microsoft Power Platform. 2020.
[29] J Laaksonen. Best practices for Microsoft Power Apps implementation. 2024.
[30] Microsoft. Build offline-capable canvas apps. In Power Apps Documentation, 2023.
[31] Microsoft. Configure data sources for offline use. In Power Apps Documentation, 2023.
[32] Microsoft. Understand data storage in Power Apps. In Power Apps Documentation, 2023.
[33] Microsoft. Create a list in SharePoint. In SharePoint Documentation, 2023.
[34] Microsoft. Automate a workflow with Power Automate (formerly Microsoft Flow). In Power Apps Documentation, 2023.
[35] SAP. SAP API Business Hub. In SAP API Business Hub, 2023.
[36] Microsoft. Update a SharePoint list item. In Power Automate Documentation, 2023.
[37] Microsoft. Power Apps documentation. In Power Apps Documentation, 2023.
[38] Microsoft. SharePoint documentation. In SharePoint Documentation, 2023.
[39] Microsoft. Power Automate (formerly Microsoft Flow) documentation. In Power Automate Documentation, 2023.

Jeyaganesh Viswanathan, "Transforming ERP Transactions Using SAP And Robotic Process Automation (RPA)," International Journal of Computer Sciences and Engineering, Vol.12, Issue.9, pp.18-24, 2024.