AMAnum Mehmood

Anum Mehmood

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Anum Mehmood has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Gene Editing in Agriculture

    by Anum Mehmood, Uzair Aslam Bhatti, Mukhayya Ruzieva, Nargiza Abdusamiyeva, Yonis Gulzar, Yazeed Yasin Ghadi

    Sustainable agriculture is essential for meeting the growing global demand for food while minimizing environmental impacts and preserving natural resources. Gene editing technologies, particularly CRISPR-Cas systems, have emerged as transformative tools for improving crop productivity, resilience, and nutritional quality. Unlike conventional breeding methods, gene editing enables precise modifications of specific genetic sequences, accelerating the development of desirable traits in plants and livestock. This technology offers significant opportunities to enhance resistance to pests and diseases, improve tolerance to drought, salinity, and temperature extremes, and reduce reliance on chemical fertilizers and pesticides. Consequently, gene editing can contribute to increased agricultural efficiency, reduced environmental degradation, and strengthened food security under changing climatic conditions. In addition, gene-edited crops have the potential to improve nutritional content and post-harvest quality, supporting healthier and more sustainable food systems.

  • Autonomous Decision-Making and Domain-Specific Intelligence in Edge–Cloud IoT Applications

    by Anum Mehmood, Babayev Shavkat, Mamatkhujaev Otabek, Akbar Toyirov, Mukhammad Khabibullaev, Sardor Sabirov

    This paper explores the concept of autonomous decision-making and domain-specific intelligence in Edge–Cloud IoT applications. It examines how artificial intelligence and machine learning techniques can be deployed across edge and cloud layers to support context-aware, adaptive, and autonomous operations. The study highlights architectural frameworks, decision-making mechanisms, and application-specific intelligence models that enhance system responsiveness, reliability, and resource efficiency. Furthermore, it discusses key challenges, including interoperability, security, data management, and computational constraints, and presents potential strategies to address them. The findings demonstrate that combining edge and cloud intelligence enables scalable, resilient, and intelligent IoT ecosystems capable of meeting the requirements of modern smart applications such as healthcare, industrial automation, smart cities, and autonomous transportation systems.

  • Scalable Training, Optimization, and Deployment Strategies for Deep Learning Across Edge and Cloud Layers

    by Anum Mehmood, Yonis Gulzar, Yazeed Yasin Ghadi, Mamatkhujaev Otabek, Babayev Shavkat, Ulugbek Bobamuratov, Mukhammad Khabibullaev, Sardor Sabirov

    This chapter examines scalable strategies for developing and managing deep learning systems across edge and cloud layers. It explores distributed training frameworks, federated learning, model compression, pruning, quantization, knowledge distillation, and resource-aware optimization techniques that improve efficiency while maintaining model accuracy. The chapter further discusses cloud-edge collaboration architectures, real-time inference mechanisms, containerization, orchestration technologies, and AI lifecycle management for large-scale deployments. Emerging trends such as edge intelligence, TinyML, serverless AI, and autonomous model adaptation are also reviewed. By integrating scalable learning, optimization, and deployment methodologies, organizations can build robust, low-latency, and cost-effective AI systems capable of supporting next-generation intelligent applications across heterogeneous computing environments.

  • Impact of Microplastic Contaminants on Mangrove Root Function Using Remote Sensing

    by Anum Mehmood, Babamuratov Bekzod, Zaribova Nafisa Umirbay Qizi, Khudaybergen Kochkarov, Sardor Sabirov

    Microplastic pollution has emerged as a significant environmental threat, affecting marine and coastal ecosystems, including mangrove forests. Mangrove roots, essential for stabilizing coastlines and supporting biodiversity, are particularly vulnerable to microplastic contamination, which can interfere with nutrient uptake, root growth, and overall ecosystem health. Remote sensing technologies provide an effective means to monitor the extent and impact of microplastics on mangrove ecosystems, offering insights into root health and environmental conditions. By using satellite imagery and drone-based sensors, researchers can assess changes in vegetation health, canopy structure, and root systems that may result from microplastic exposure. These data can be integrated with ground-based observations to provide a comprehensive understanding of how microplastics affect mangrove root functions, such as gas exchange and nutrient cycling

  • Remote Sensing Data Assimilation Techniques for Blue Carbon Flux Modeling in Estuarine Ecosystems

    by Anum Mehmood, Odilbek Kosimov, Intizor Avazmetova, Jumaniyazova Shaxnoza Ishonkuliyevna, Odilbek Matsapayev

    Remote sensing data assimilation techniques are becoming increasingly crucial for accurately modeling blue carbon fluxes in estuarine ecosystems, which play a key role in carbon storage and climate regulation. Estuaries, with their dynamic and highly variable environments, are challenging to monitor using traditional methods due to their complexity and the difficulty of continuous data collection. Remote sensing, combined with data assimilation, allows for the integration of satellite and airborne imagery with environmental models to improve the accuracy of blue carbon flux predictions. By assimilating remotely sensed data into carbon models, researchers can better estimate carbon sequestration rates, monitor vegetation health, and evaluate the impacts of environmental changes on carbon fluxes. This approach helps overcome spatial and temporal limitations, offering real-time insights into estuarine dynamics and the effectiveness of conservation efforts.