Syam Kishor K S
Research Subjects
Research Interests
Syam Kishor K S has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Manju G
Assistant Professor of Computer Science, Govt. College, Ambalapuzha, Kerala
2 shared publications Binson V A
1 shared publication- Binson V A
Saintgits College
1 shared publication - Sania Thomas
Department of Computer Science and Engineering, Saintgits College of Engineering, Kottayam 686532, India
1 shared publication - V. A. Binson
Department of Electronics Engineering, Saintgits College of Engineering, Kottayam 686532, India
1 shared publication
Latest Publications
- Open Access
An IoT-Enabled Real-Time Crop Prediction System Using Soil Fertility Analysis
Changes in soil fertility have led to a decline in crop production, making it challenging for farmers to select the best crops based on soil conditions. Accurate crop prediction can significantly enhance crop productivity, and machine learning plays a crucial role in this process. Crop forecasting is influenced by soil, geographic, and environmental characteristics, with feature selection being essential for identifying suitable crops. In this study, we developed a real-time soil fertility analyzer to obtain the real-time values of soil parameters such as potassium, phosphorus, nitrogen content, temperature, pH, moisture content, and electrical conductivity. The crops examined were coconut, ginger, plantain, and tapioca. The data collected from this analysis served as the dataset for different training and testing classification algorithms for crop prediction using 100 soil samples. Among the algorithms tested, the k-nearest neighbors (KNN) algorithm demonstrated the highest performance, with an accuracy of 84%, precision of 85%, recall of 88.8%, and specificity of 92.4%. These results indicate that machine learning, combined with real-time soil analysis, can effectively predict suitable crops, enhancing crop productivity and aiding farmers in making informed decisions. This approach can revolutionize traditional farming practices by providing precise, data-driven insights into crop selection, ultimately improving agricultural efficiency and sustainability.
Open AccessAn IoT-Enabled Real-Time Crop Prediction System Using Soil Fertility Analysis
Changes in soil fertility have led to a decline in crop production, making it challenging for farmers to select the best crops based on soil conditions. Accurate crop prediction can significantly enhance crop productivity, and machine learning plays a crucial role in this process. Crop forecasting is influenced by soil, geographic, and environmental characteristics, with feature selection being essential for identifying suitable crops. In this study, we developed a real-time soil fertility analyzer to obtain the real-time values of soil parameters such as potassium, phosphorus, nitrogen content, temperature, pH, moisture content, and electrical conductivity. The crops examined were coconut, ginger, plantain, and tapioca. The data collected from this analysis served as the dataset for different training and testing classification algorithms for crop prediction using 100 soil samples. Among the algorithms tested, the k-nearest neighbors (KNN) algorithm demonstrated the highest performance, with an accuracy of 84%, precision of 85%, recall of 88.8%, and specificity of 92.4%. These results indicate that machine learning, combined with real-time soil analysis, can effectively predict suitable crops, enhancing crop productivity and aiding farmers in making informed decisions. This approach can revolutionize traditional farming practices by providing precise, data-driven insights into crop selection, ultimately improving agricultural efficiency and sustainability.
- Open Access
- 20 July 2024
- Published by Dewspublication
- Vol. 20 (S8)
Advances in Early Lung Cancer Detection Through Sensor Array-Based VOC Analysis of Exhaled Breath
This review focuses on the emerging role of sensor array-based VOC analysis of exhaled breath, particularly using electronic nose (e-nose) technology, for the early detection of lung cancer. Given the critical importance of early diagnosis in improving lung cancer outcomes, this review emphasizes studies that target Stage I and Stage II lung cancer. Traditional diagnostic methods often fall short in identifying lung cancer at its earliest, most treatable stages, leading to high mortality rates. E-nose technology, inspired by the human olfactory system, offers a non-invasive, rapid, and potentially cost-effective approach to detecting volatile organic compounds (VOCs) in exhaled breath, which serve as biomarkers for lung cancer. Through a systematic review of the literature, we initially identified 193 studies related to e-nose-based breath analysis for lung cancer detection. After applying rigorous selection criteria, focusing specifically on studies involving early-stage lung cancer and excluding those using alternative VOC analysis methods, 12 studies were deemed eligible for inclusion. These studies demonstrate the significant potential of e-nose technology in detecting subtle changes in VOC profiles associated with early-stage lung cancer. This review synthesizes the current state of knowledge, highlights recent advancements, and discusses the challenges and future directions of integrating e-nose technology into clinical practice for early lung cancer detection. The findings underscore the promise of e-nose technology as a valuable tool in the ongoing effort to reduce lung cancer mortality through earlier diagnosis.
- 20 July 2024
- Published by Dewspublication
- Vol. 20 (S8)
Open AccessAdvances in Early Lung Cancer Detection Through Sensor Array-Based VOC Analysis of Exhaled Breath
This review focuses on the emerging role of sensor array-based VOC analysis of exhaled breath, particularly using electronic nose (e-nose) technology, for the early detection of lung cancer. Given the critical importance of early diagnosis in improving lung cancer outcomes, this review emphasizes studies that target Stage I and Stage II lung cancer. Traditional diagnostic methods often fall short in identifying lung cancer at its earliest, most treatable stages, leading to high mortality rates. E-nose technology, inspired by the human olfactory system, offers a non-invasive, rapid, and potentially cost-effective approach to detecting volatile organic compounds (VOCs) in exhaled breath, which serve as biomarkers for lung cancer. Through a systematic review of the literature, we initially identified 193 studies related to e-nose-based breath analysis for lung cancer detection. After applying rigorous selection criteria, focusing specifically on studies involving early-stage lung cancer and excluding those using alternative VOC analysis methods, 12 studies were deemed eligible for inclusion. These studies demonstrate the significant potential of e-nose technology in detecting subtle changes in VOC profiles associated with early-stage lung cancer. This review synthesizes the current state of knowledge, highlights recent advancements, and discusses the challenges and future directions of integrating e-nose technology into clinical practice for early lung cancer detection. The findings underscore the promise of e-nose technology as a valuable tool in the ongoing effort to reduce lung cancer mortality through earlier diagnosis.
- Open Access
- 1 January 2024
- Published by GN1 Sistemas e Publicacoes Ltd. in ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)
- Vol. 10 (49) , 65-70
Precision crop prediction using IoT-enabled soil sensors and machine learning
This paper introduces a cutting-edge approach for crop prediction that harnesses IoT-enabled soil sensors and machine learning models, specifically targeting cardamom, black pepper, and coffee in Idukki District, Kerala, India. The study aims to bridge the gap between soil nutrient analysis and precision agriculture by integrating a JXCT 7-in-1 soil sensor with Arduino UNO. This sensor provides accurate real-time measurements of soil moisture, temperature, pH, electrical conductivity, nitrogen, phosphorus, and potassium levels, which are critical for assessing soil health and suitability. The dataset used comprises 300 soil samples for cardamom, 320 for black pepper, and 300 for coffee, providing a robust foundation for analysis. Data from these sensors were processed using XGBoost and AdaBoost algorithms. Among the models, XGBoost achieved the highest accuracy of 91.2% and an AUC of 0.93, while AdaBoost also demonstrated strong performance with an AUC of 0.91. The results confirm the effectiveness of the system in providing precise crop suitability predictions and supporting farmers in making informed decisions based on comprehensive soil data. This approach not only improves crop yields and promotes sustainable farming practices but also shows potential for broader application in different regions and crops. Future research could expand the dataset and incorporate additional IoT devices to enhance the system’s accuracy and agricultural impact.
- 1 January 2024
- Published by GN1 Sistemas e Publicacoes Ltd. in ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)
- Vol. 10 (49) , 65-70
Open AccessPrecision crop prediction using IoT-enabled soil sensors and machine learning
This paper introduces a cutting-edge approach for crop prediction that harnesses IoT-enabled soil sensors and machine learning models, specifically targeting cardamom, black pepper, and coffee in Idukki District, Kerala, India. The study aims to bridge the gap between soil nutrient analysis and precision agriculture by integrating a JXCT 7-in-1 soil sensor with Arduino UNO. This sensor provides accurate real-time measurements of soil moisture, temperature, pH, electrical conductivity, nitrogen, phosphorus, and potassium levels, which are critical for assessing soil health and suitability. The dataset used comprises 300 soil samples for cardamom, 320 for black pepper, and 300 for coffee, providing a robust foundation for analysis. Data from these sensors were processed using XGBoost and AdaBoost algorithms. Among the models, XGBoost achieved the highest accuracy of 91.2% and an AUC of 0.93, while AdaBoost also demonstrated strong performance with an AUC of 0.91. The results confirm the effectiveness of the system in providing precise crop suitability predictions and supporting farmers in making informed decisions based on comprehensive soil data. This approach not only improves crop yields and promotes sustainable farming practices but also shows potential for broader application in different regions and crops. Future research could expand the dataset and incorporate additional IoT devices to enhance the system’s accuracy and agricultural impact.