Sowing the Seeds of Precision: Innovations in Wireless Sensor Networks for Agricultural Environmental Monitoring

International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 DOI:10.5121/ijans.2024.14301 1 SOWING THE SEEDS OF PRECISION: INNOVATIONS IN WIRELESS SENSOR NETWORKS FOR AGRICULTURAL ENVIRONMENTAL MONITORING Sreedeep Dey and Sreejita Das Department of Microbiology, Vijaygarh Jyotish Ray College, affiliated to the University of Calcutta, Kolkata, India ABSTRACT Wireless Sensor Networks (WSNs) are used in precision agriculture to provide real-time environmental parameter monitoring that is essential to crop productivity. This study looks at the most current advancements in WSN technology and its application in monitoring vital factors including temperature, humidity, soil moisture, and light intensity in agricultural contexts, with an emphasis on the agricultural region of Bardhaman District, West Bengal, India. For sustainable and long-term sensor network functioning in this area, the study looks into several sensor placement procedures, creative data aggregation strategies, and energy-efficient protocols. To improve data accuracy and decision-making abilities, contemporary analytics techniques like machine learning and data fusion are also used. The results highlight how well WSNs work in Bardhaman District to maximise agricultural sustainability and productivity. The study discusses issues with WSN deployment, like network connectivity and power management, and suggests solutions specific to the region's agricultural environment. The goal of future study is to improve the precision agricultural utility of WSNs even more, with an emphasis on boosting resilience and productivity in farming operations in Bardhaman District. KEYWORDS Precision agriculture, Wireless Sensor Networks (WSNs), Environmental monitoring, Agricultural sustainability, Sensor deployment, Data aggregation, Energy-efficient protocols, Machine learning, Data fusion 1. INTRODUCTION West Bengal, India's Purba Bardhaman district is well known for its strengths in both agriculture and industry. Approximately 58% of the population works in agriculture, which makes up a significant portion of the region's economy. With an emphasis on producing rice, jute, sugarcane, and other commercial commodities on its enormous agricultural fields, the region is known for its varied agricultural practices. Since 1953, the Damodar Valley Corporation has played a key role in introducing irrigation projects, which have revolutionised agriculture by shifting from a rainfed system to one that is more sustainable [1]. Purba Bardhaman was chosen as our research site for our study of Wireless Sensor Networks (WSNs) in precision agriculture because of its important importance in West Bengal's industrial and agricultural sectors. The district benefits from sophisticated irrigation systems that lessen the effects of climate uncertainty on crop production, but it also faces the opportunities and problems that come with agricultural modernity. Our work focuses on using WSNs to optimise and monitor important environmental parameters like temperature, light intensity, and soil moisture [2]. In particular, we use machine learning techniques for data analytics and modern sensor technologies International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 2 like IoT-enabled soil moisture sensors and wireless data transmission modules like LoRaWAN. The objective of these technological interventions is to augment agricultural output, foster sustainability, and bolster rural economies by supporting well-informed policy decisions [3]. This study examines the cutting-edge uses of WSN technology in Purba Bardhaman precision agriculture, emphasising the particular tools and techniques used to transform farming methods. Our research intends to use these cutting-edge technologies to produce practical insights that strengthen farmers and other stakeholders, resulting in a more robust and effective agricultural sector in West Bengal [4]. 2. LITERATURE REVIEW An extensive examination of recent advancements and research in the use of Wireless Sensor Networks (WSNs) for agricultural environmental monitoring is given in the literature review section. It draws attention to significant developments, chronicles problems, and suggests areas that need more research. The four primary themes of the review include energy-efficient protocols, analytical techniques, data gathering and processing, and sensor placement options. 2.1. Sensor Deployment Strategies The effectiveness of WSNs in precision agriculture depends on the deployment of sensors with efficiency. In order to minimize costs and redundancy and maximize coverage and data accuracy, the best location for sensors has been investigated in a number of studies [5]. 2.1.1. Optimal Placement Techniques After researching several sensor placement algorithms, R Akhter et al. (2022) came to the conclusion that, depending on the particular agricultural application and topography, grid-based and random deployment approaches each have certain advantages and disadvantages. They underlined the necessity of using flexible deployment tactics that may be tailored to various crop kinds and field circumstances [6]. 2.1.2. Cost-Effectiveness and Scalability In their 2008 study, Blaszczyszyn and Radunovic focused on finding a balance between cost and coverage while examining the financial elements of sensor deployment. To improve scalability and lower total costs, they suggested a hybrid strategy that combines stationary and mobile sensors. Obstacles and Restrictions: Although these investigations offer insightful information, issues including uneven terrain, long-term sensor performance, and upkeep still need to be addressed. To create reliable, affordable deployment strategies that can be widely used in a variety of agricultural contexts, more study is required [7]. 2.2. Data Aggregation and Processing In order to handle the massive volumes of data produced by WSNs, data aggregation is essential for maintaining data accuracy during processing and transmission. 2.2.1. Aggregation techniques In 2024, Zhenpeng Liu, Jialiang Zhang, Yi Liu, Fan Feng, and Yifan Liu studied a range of centralised, distributed, and hybrid data aggregation techniques. They found that distributed International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 3 algorithms have significant benefits in terms of scalability and energy efficiency, despite the fact that they may suffer from increased complexity and potential data inconsistency. [8]. 2.2.2. Reduction of Communication Overhead Recent developments in data compression approaches by Lucia K. Ketshabetswe et al. (2023) have demonstrated promise in lowering communication overhead. Their research unveiled a cutting-edge compression method that significantly reduces energy consumption while maintaining data integrity [9]. 2.2.3. Correctness vs. Efficiency Maintaining a balance between computing efficiency and data correctness is still a major difficulty. Research conducted by Shams Forruque Ahmed et al. (2023) highlights the necessity of creating adaptable algorithms that may change their behaviour dynamically in response to network conditions and application requirements [10]. 2.3. Protocols for Energy Efficiency In order to guarantee long-term operation and lower maintenance costs, particularly in remote agricultural areas, energy efficiency is crucial for WSNs. 2.3.1. Energy-Saving Strategies Liyazhou Hu et al. (2024) investigated a number of strategies to save energy, such as duty cycling, which involves sensors switching between active and sleep modes on an ongoing basis. According to their findings, sensor lifespan can be greatly increased by using duty cycles that have been appropriately tuned [11]. 2.3.2. Energy Harvesting Dhanaraju, Muthumanickam, Poongodi Chenniappan, Kumaraperumal Ramalingam, Sellaperumal Pazhanivelan, and Ragunath Kaliaperumal (2022) have studied solar-powered sensors and shown that combining solar panels with WSNs can significantly improve sustainability. But there's a problem with solar energy supply fluctuating, which calls for effective energy storage options [12]. 2.3.3. Protocol Innovations B Han et al. (2022) investigated cutting-edge methods including LEACH (Low Energy Adaptive Clustering Hierarchy) and PEGASIS (Power-Efficient GAthering in Sensor Information Systems), which lower energy consumption through hierarchical clustering and chain-based data transfer. [13]. 2.4. Analytical Approaches The utilisation of sophisticated analytical methods, such as data fusion and machine learning, has demonstrated promise in augmenting the usefulness of information gathered by wireless sensor networks. International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 4 2.4.1. Applications of Machine Learning Research conducted by D. Tamayo-Vera (2024) has shown that machine learning algorithms are effective in forecasting crop health and environmental variables. They demonstrated how machine learning algorithms, trained on historical data, may offer precise predictions and early illness and pest warning systems [14]. 2.4.2. Data Fusion Techniques To increase overall data quality and dependability, data fusion, as covered by J Dong et al. (2009), entails merging data from different sensors. Their study demonstrated the advantages of combining data from multiple sensors to have a more thorough understanding of the surrounding environment [15]. 2.4.3. Obstacles and Prospects In spite of these developments, there is still a dearth of real-world agricultural scenarios in which these analytical tools have been applied in practice. To create user-friendly tools and platforms that farmers with different degrees of technological competence can readily use, more research is required. 3. RESEARCH GAP AND CONTRIBUTION 3.1. Research Gap Wireless Sensor Networks (WSNs) for precision agriculture have made progress, however there are still a number of important gaps: 3.1.1. Deployment Optimisation Current sensor deployment techniques are frequently unscalable and expensive, especially when dealing with a variety of crop varieties and agricultural terrains. 3.1.2. Data Accuracy and Integration Large, diversified datasets are difficult for current data aggregation approaches to handle well, which results in errors and less-than-ideal decision-making [16]. 3.1.3. Long-Term Sustainability Stronger integration is required for renewable energy solutions like solar power, as many energyefficient procedures are ill-suited for extended deployments in distant locations. 3.1.4. Application of Modern Analytics Although data fusion and machine learning techniques show potential, farmers with various levels of technological skill may not find them generally accessible or useful [17]. 3.2. Contribution This study fills in these gaps by: International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 5 3.2.1. Innovative Deployment Strategies Creating cost-effective, scalable sensor deployment techniques that can be adjusted to different crops and terrains by combining fixed and mobile sensors in a hybrid approach. 3.2.2. Improved Data Aggregation and Processing Using sophisticated, adaptive data aggregation algorithms lowers transmission overhead while increasing data accuracy and efficiency. 3.2.3. Sustainable Energy Solutions Investigating protocols that use less energy and combining solar-powered sensors with effective long-term storage options [18]. 3.2.4. Application of Machine Learning and Data Fusion Developing user-friendly tools for farmers to use in the real world and leveraging machine learning and data fusion to improve environmental predictions and insights. 3.2.5. Thorough Field Study To test and evaluate suggested approaches in actual agricultural contexts, field research will be carried out in West Bengal's Bardhaman District. By advancing WSN technology in precision agriculture, these contributions hope to increase output, sustainability, and decision-making. 4. METHODOLOGY The technique describes the strategy used to fill in the knowledge gaps found in the investigation of Wireless Sensor Networks (WSNs) for precision agriculture. This section comprises six key components: an overview of the study site; the deployment of sensors; data collecting and processing; energy-efficient protocols; machine learning and data fusion methodologies; application; and field testing and validation. 4.1. Study Site Description The study was carried out in the Bardhaman District of West Bengal, India, a significant region for the cultivation of potatoes, rabi rice, and kharif rice. Five blocks with different crop sequences are present on the site: 1) Mangalkote: Early Kharif Vegetables, Rice, Potato, and Fallow. International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 6 Figure 1 Location of Mangalkote in West Bengal, India. In the Indian state of West Bengal, Mangalkote is an assembly located in the Katwa subdivision of the Purba-Bardhaman district. It is part of the Mongalkote CD block. The location is 23°31′30.6°N 87°54′12.3°E. Reproduced with permission. Licensed under “CCBY-SA-3.0-DE” in Wikipedia. 2) Kalna I: Jute, Standard Kharif Rice, and Vegetables. Figure 2 Location of Kalna I in West Bengal, India. In the Indian state of West Bengal, the Kalna subdivision of PurbaBardhaman district comprises a community development block that serves as an administrative division. Location: 23°13′00 N, 88°22′00 E. Reproduced with permission. Licensed under the “Creative Commons Attribution-Share Alike 4.0 International” license. 3) Bhatar: Normal for vegetables and fodder Early Rabi rice, vegetables, and fodder during Kharif. Figure 3 Location of Bhatar in West Bengal, India. Bhatar is a village in the PurbaBardhaman district of West Bengal, India. It is located in the Bhatar CD block of the Bardhaman Sadar North subdivision. Coordinates: 23°25′11.0′′N 87°55′00.0′′E. Reproduced with permission. Licensed under the “CC-BY-SA3.0-DE” in Wikipedia. International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 7 4) Kalna II: Late Rabi Rice, Jute, Karif Rice, and Fallow. Figure 4 Location of Kalna II in West Bengal, India. In the Purba Bardhaman district of the West Bengal state of India, the Kalna subdivision is home to Kalna II, a community development block that functions as an administrative division. Coordinates: 23°13′00′′N 88°22′00′′E. Reproduced with permission. Licensed under “CC BY-SA 4.0.” 5) Raina I: Rabi rice, potatoes, and kharif rice. Figure 5 Location of Raina I in West Bengal, India. A community development block that acts as an administrative division in the Purba Bardhaman district of the Indian state of West Bengal's Bardhaman Sadar South subdivision is sometimes referred to as Rainagar and occasionally Rayna. Location: 23°04′07′′N 87°54′22′′E. Reproduced with permission. Licensed under “CC BY-SA 4.0.” 4.2. Sensor Deployment To give the highest coverage and data accuracy possible, a hybrid deployment strategy was used: 4.2.1. Fixed Sensors Sold equipment was used, including the Decagon Devices 5TE for temperature, electrical conductivity, and soil moisture and the Hobo U30 weather station for humidity and light intensity. The study blocks were equipped with strategically positioned sensors [19]. International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 8 4.2.2. Mobile sensors These are used on moveable platforms and drones (like the DJI Agras MG-1S) to cover regions that fixed sensors are unable to reach. They are especially helpful in fields with different crop layouts and topographies. To test effectiveness, sensor nodes were placed using a grid and random placement techniques. Sensor data was sent to a central node for additional processing [20]. [Temperature range: 15–35°C; humidity range: 40–90%; soil moisture range: 10–60% , Intensity of Light: 200–1000 µmol m-2 s-1] 4.3. Data Aggregation and Processing To manage the massive amount of data gathered, sophisticated data aggregation techniques were created: 4.3.1. Distributed Aggregation Before data is sent to the central node, local nodes preprocess it to increase efficiency and scalability. Among the tools utilised are TelosB motes [21]. 4.3.2. Compression Techniques To ensure effective data transfer without sacrificing accuracy, algorithms like S-LZW (Streaming Lempel-Ziv-Welch) were employed to lower communication overhead [22]. 4.3.3. Adaptive Algorithms Used to balance computational efficiency and data accuracy by constantly adjusting processing based on network conditions.  Ratio of data compression: 60–80%  100–500 ms is the data transmission delay. 4.4. Energy-Efficient Protocols Several energy-efficient practices were put in place to guarantee sustainability over the long term: 4.4.1. Duty Cycling To save energy, sensors switched between the active and sleep modes. Using MicaZ motes, a 20– 30% lifespan extension was shown. 4.4.2. Integration of Solar Power To capture renewable energy, sensors were connected to solar panels (such the Voltaic Systems Arc 20W), which were backed by 10,000 mAh Li-ion batteries, an effective form of energy storage. International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 9 4.4.3. Protocols for Energy-Efficient Communication Protocols like PEGASIS (Power-Efficient GAthering in Sensor Information Systems) and LEACH (Low Energy Adaptive Clustering Hierarchy) were able to lower energy consumption through the use of hierarchical clustering and chain-based data transport. [23].  35% (LEACH) and 40% (PEGASIS) of the energy saved  Duration of Network: 1-2 Years 4.5. Utilizing Data Fusion and Machine Learning Data fusion and machine learning techniques were applied to increase data utility: 4.5.1. Machine Learning Models To forecast crop health and environmental conditions, algorithms like Random Forest and Support Vector Machines (SVM) were trained on historical and current data. 4.5.2. Data Fusion Techniques By combining data from several sensors, methods like Bayesian data fusion and Kalman filtering can increase the overall quality and dependability of the data [24].  85–90% prediction accuracy  Improvement in Data Quality: 20–30% To enable farmers to apply these advanced analytics practically, a user-friendly platform was created that visualises data and offers them actionable insights using programmes like MATLAB and QGIS. 4.6. Field Testing and Validation Field experiments were carried out in the Bardhaman District's five blocks in order to validate the suggested methodologies: 4.6.1. Data Collection To evaluate the effectiveness of the sensor network, environmental data were gathered throughout the course of several seasons. Temperature, humidity, soil moisture content, and light intensity were among the parameters [25]. 4.6.2. Performance Metrics Data accuracy, energy usage, network coverage, and forecast accuracy were among the metrics assessed. 4.6.3. Farmer Input The usefulness and efficacy of the offered tools and insights were solicited from nearby farmers. By using this thorough methodology, the study sought to fill in the current gaps in WSN International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 16 [9] Lucia K. Ketshabetswe, Adamu Murtala Zungeru, Caspar K. Lebekwe, Bokani Mtengi, Energyefficient algorithms for lossless data compression schemes in wireless sensor networks, Scientific African, Volume 23, 2024, e02008, ISSN 2468-2276, https://doi.org/10.1016/j.sciaf.2023.e02008. (https://www.sciencedirect.com/science/article/pii/S2468227623004623) [10] Ahmed, S.F., Alam, M.S.B., Hassan, M. et al. Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artif Intell Rev 56, 13521–13617 (2023). https://doi.org/10.1007/s10462-023-10466-8 [11] Hu L, Han C, Wang X, Zhu H, Ouyang J. Security Enhancement for Deep Reinforcement LearningBased Strategy in Energy-Efficient Wireless Sensor Networks. Sensors (Basel). 2024 Mar 21;24(6):1993. doi: 10.3390/s24061993. PMID: 38544256; PMCID: PMC10975816. [12] Dhanaraju M, Chenniappan P, Ramalingam K, Pazhanivelan S, Kaliaperumal R. Smart Farming: Internet of Things (IoT)-Based Sustainable Agriculture. Agriculture. 2022; 12(10):1745. https://doi.org/10.3390/agriculture12101745 [13] Han B, Ran F, Li J, Yan L, Shen H, Li A. A Novel Adaptive Cluster Based Routing Protocol for Energy-Harvesting Wireless Sensor Networks. Sensors (Basel). 2022 Feb 17;22(4):1564. doi: 10.3390/s22041564. PMID: 35214461; PMCID: PMC8877631. [14] Tamayo-Vera D, Wang X, Mesbah M. A Review of Machine Learning Techniques in Agroclimatic Studies. Agriculture. 2024; 14(3):481. https://doi.org/10.3390/agriculture14030481 [15] Dong J, Zhuang D, Huang Y, Fu J. Advances in Multi-Sensor Data Fusion: Algorithms and Applications. Sensors. 2009; 9(10):7771-7784. https://doi.org/10.3390/s91007771 [16] Musa P, Sugeru H, Wibowo EP. Wireless Sensor Networks for Precision Agriculture: A Review of NPK Sensor Implementations. Sensors (Basel). 2023 Dec 21;24(1):51. doi: 10.3390/s24010051. PMID: 38202913; PMCID: PMC10780601. [17] Meng, Yuquan, Yuhang Yang, Haseung Chung, Pil-Ho Lee, and Chenhui Shao. 2018. "Enhancing Sustainability and Energy Efficiency in Smart Factories: A Review" Sustainability 10, no. 12: 4779. https://doi.org/10.3390/su10124779 [18] Dananjayan, Sathian & Zhuang, Jiajun & Tang, Yu & He, Yong & Hou, Chaojun & Luo, Shaoming. (2022). Wireless sensor deployment scheme for cost-effective smart farming using the ABC-TEEM algorithm. Evolving Systems. 14. 10.1007/s12530-021-09412-2. [19] Matula, Svatopluk, Kamila Báťková, and Wossenu Lemma Legese. 2016. "Laboratory Performance of Five Selected Soil Moisture Sensors Applying Factory and Own Calibration Equations for Two Soil Media of Different Bulk Density and Salinity Levels" Sensors 16, no. 11: 1912. https://doi.org/10.3390/s16111912 [20] Abbas, Aqleem, Zhenhao Zhang, Hongxia Zheng, Mohammad Murtaza Alami, Abdulmajeed F. Alrefaei, Qamar Abbas, Syed Atif Hasan Naqvi, Muhammad Junaid Rao, Walid F. A. Mosa, Qamar Abbas, and et al. 2023. "Drones in Plant Disease Assessment, Efficient Monitoring, and Detection: A Way Forward to Smart Agriculture" Agronomy 13, no. 6: 1524. https://doi.org/10.3390/agronomy13061524 [21] Moshawrab, Mohammad, Mehdi Adda, Abdenour Bouzouane, Hussein Ibrahim, and Ali Raad. 2023. "Reviewing Federated Learning Aggregation Algorithms; Strategies, Contributions, Limitations and Future Perspectives" Electronics 12, no. 10: 2287. https://doi.org/10.3390/electronics12102287 [22] Prokop, Kamil, Andrzej Bień, and Szymon Barczentewicz. 2023. "Compression Techniques for RealTime Control and Non-Time-Critical Big Data in Smart Grids: A Review" Energies 16, no. 24: 8077. https://doi.org/10.3390/en16248077 [23] Baniata, M., Reda, H. T., Chilamkurti, N., & Abuadbba, A. (2021). Energy-Efficient Hybrid Routing Protocol for IoT Communication Systems in 5G and Beyond. Sensors (Basel, Switzerland), 21(2), 537. https://doi.org/10.3390/s21020537 [24] Araújo SO, Peres RS, Ramalho JC, Lidon F, Barata J. Machine Learning Applications in Agriculture: Current Trends, Challenges, and Future Perspectives. Agronomy. 2023; 13(12):2976. https://doi.org/10.3390/agronomy13122976 [25] Zhu, Jin & Salim, Md. (2013). Implementation and Field Testing of a Wireless Sensor Network for Infrastructure Monitoring. Journal of Engineering Technology. 30. 18. [26] Jin X-B, Yang N-X, Wang X-Y, Bai Y-T, Su T-L, Kong J-L. Hybrid Deep Learning Predictor for Smart Agriculture Sensing Based on Empirical Mode Decomposition and Gated Recurrent Unit Group Model. Sensors. 2020; 20(5):1334. https://doi.org/10.3390/s20051334 International Journal on AdHoc Networking Systems (IJANS) Vol. 14, No.2/3, July 2024 17 [27] Beneyaz Ara Begum, Satyanarayana V. Nandury, Data aggregation protocols for WSN and IoT applications – A comprehensive survey, Journal of King Saud University - Computer and Information Sciences, Volume 35, Issue 2, 2023, Pages 651-681, ISSN 1319-1578, https://doi.org/10.1016/j.jksuci.2023.01.008. (https://www.sciencedirect.com/science/article/pii/S1319157823000083) [28] Ibraheem MKI, Al-Abadi AAJ, Mohamed MB, Fakhfakh A. A Security-Enhanced Energy Conservation with Enhanced Random Forest Classifier for Low Execution Time Framework (S-2ECERF) for Wireless Sensor Networks. Applied Sciences. 2024; 14(6):2244. https://doi.org/10.3390/app14062244 [29] Nguyen, L. P., Tung, D. D., Nguyen, D. T., Le, H. N., Tran, T. Q., Binh, T. V., & Pham, D. T. N. (2023). The Utilization of Machine Learning Algorithms for Assisting Physicians in the Diagnosis of Diabetes. Diagnostics (Basel, Switzerland), 13(12), 2087. https://doi.org/10.3390/diagnostics13122087 [30] Soussi, A., Zero, E., Sacile, R., Trinchero, D., & Fossa, M. (2024). Smart Sensors and Smart Data for Precision Agriculture: A Review. Sensors (Basel, Switzerland), 24(8), 2647. https://doi.org/10.3390/s24082647 [31] Shafi, U., Mumtaz, R., García-Nieto, J., Hassan, S. A., Zaidi, S. A. R., & Iqbal, N. (2019). Precision Agriculture Techniques and Practices: From Considerations to Applications. Sensors (Basel, Switzerland), 19(17), 3796. https://doi.org/10.3390/s19173796 [32] Sishodia, R.P.; Ray, R.L.; Singh, S.K. Applications of Remote Sensing in Precision Agriculture: A Review. Remote Sens. 2020, 12, 3136. https://doi.org/10.3390/rs12193136 AUTHORS Mr. Sreedeep Dey holds B.Sc. (Hons.) and M.Sc. degrees in Microbiology from the University of Calcutta. He has made substantial contributions to numerous clinical trials at the Department of Hematology, Nil Ratan Sarkar Medical College and Hospital in Kolkata, West Bengal. Presently, his research endeavors are concentrated on advancing Agricultural Biotechnology through the integration of Nanotechnology, Ad Hoc Networking Systems, Artificial Intelligence, and Machine Learning in India. Miss Sreejita Das holds B.Sc. (Hons.) and M.Sc. degree in Microbiology from the University of Calcutta. In the course of her postgraduate studies, Miss Sreejita Das worked extensively in the Calcutta School of Tropical Medicine's Department of Biochemistry and Medical Biotechnology. Her current research focuses on improving agronomy techniques using Ad Hoc networking and genetic investigations, as well as advances in the field.