Manickam Ramasamy

Mr. Manickam Ramasamy

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2025 in Machines
Verified
Journal Article
Open access
PDF file
ELANGO NATARAJANELANGO NATARAJAN
ELANGO NATARAJAN
MRManickam Ramasamy
Manickam Ramasamy
SESangeetha Elango
Sangeetha Elango
KMKarthikeyan Mohanraj
Karthikeyan Mohanraj
CAChun Kit Ang
Chun Kit Ang
Ali KhalfallahAli Khalfallah
Ali Khalfallah
This paper proposes and demonstrates a domain-adapted ensemble machine learning approach for enhanced prediction of surface roughness (Ra) during the machining of polymeric materials. The proposed model methodology employs a two-stage pipelined architecture, where classified data are fed into the model for regressive analysis. First, a classifier (Logistic Regression or XGBoost, selected based on performance) categorizes machining data into distinct regimes based on cutting Speed (Vc), feed rate (f), and depth of cut (ap) as inputs. This classification leverages output discretization to mitigate data imbalance and capture regime-specific patterns. Second, a regressor (Support Vector Regressor or XGBoost, selected based on performance) predicts Ra within each regime, utilizing the classifier’s output as an additional feature. This structured hybrid approach enables more robust prediction in small, noisy datasets characteristic of machining studies. To validate the methodology, experiments were conducted on Polyoxymethylene (POM), Polytetrafluoroethylene (PTFE), Polyether ether ketone (PEEK), and PEEK/MWCNT composite, using a L27 Design of Experiments (DoEs) matrix. Model performance was optimized using k-fold cross-validation and hyperparameter tuning via grid search, with R-squared and RMSE as evaluation metrics. The resulting meta-model demonstrated high accuracy (R2 > 90% for XGBoost regressor across all materials), significantly improving Ra prediction compared to single-model approaches. This enhanced predictive capability offers potential for optimizing machining processes and reducing material waste in polymer manufacturing.

6 December 2022
Verified
Book Chapter
Open access
PDF file
CLChekHong Lee
ChekHong Lee
MRManickam Ramasamy
Manickam Ramasamy
SDS. Deivasigamani
S. Deivasigamani
MKM.K.A. Ahamed Khan
M.K.A. Ahamed Khan
The proposed IoT based farming system was built with the Arduino board, Node MCU and various sensors. The IoT platform used to support this project was Blynk. The prototype consists of two nodes that are transmitter node and receiver node. The transmitter node sends the sensing data including temperature, humidity, motion, and soil moisture to the receiver node. Meanwhile, the water pump was activated when the soil moisture was lower than 25% and off if the soil moisture was higher or equal to 25%. In receiver node, the various data was displayed in the OLED display and sent to the Blynk cloud simultaneously. The users of this system can monitor their crops using mobile application and websites. The DHT22 was able to measure high accurate data by comparing the results with infrared thermometer sensor and the PIR motion sensor detects the far motion up to 8 meters. The maximum RSSI value of LoRa WAN data transmission in this project was up to -86.9dBm when the distance between transmitter and receiver was 10 meters but the wireless connection was still function because the result is still not lower than the noise floor which is -120dBm and there will be no loss of data in LoRaWAN, this proved LoRa was the suitable network architecture in the field of agriculture.

25 April 2025
Verified
Book Chapter
Closed access
LMLatha Manickam
Latha Manickam
MRManickam Ramasamy
Manickam Ramasamy
SJSofia Jonathan
Sofia Jonathan
JSJonathan Samuel
Jonathan Samuel
The modern logistics sector, crucial to worldwide trade, is also a major source of carbon emissions. The environmental impact is significant, from transporting goods over long distances to the energy-intensive activities in warehouses. With the pressing necessity to cut down greenhouse gas emissions and address climate change, the logistics industry is at a crucial point. Introducing artificial intelligence (AI), an impressive technology that has the ability to transform logistics and greatly reduce its environmental impact.

7 November 2025
Verified
Book Chapter
Closed access
SGSofia Jonathan G.
Sofia Jonathan G.
LMLatha Manickam
Latha Manickam
MRManickam Ramasamy
Manickam Ramasamy
In today's digital landscape, cyber threats are becoming increasingly sophisticated, persistent, and difficult to counter with traditional perimeter-based defenses. This has necessitated a fundamental shift in cybersecurity, emphasizing proactive threat detection over reactive response. By integrating the proactive threat detection strategies such as defensive monitoring, machine learning, behavioral analytics, and threat intelligence, organizations can identify anomalies and potential attacks before they escalate into full-scale breaches. Proactive strategies not only improve detection accuracy and response times but also reduce the risk of data loss, regulatory non-compliance, and reputational damage. Despite challenges proactive threat detection remains a cornerstone of resilient cybersecurity, equipping organizations to anticipate, adapt to and mitigate emerging threats in an evolving threat landscape.

27 June 2025
Verified
Book Chapter
Closed access
GJG. Sofia Jonathan
G. Sofia Jonathan
LMLatha Manickam
Latha Manickam
JSJonathan Samuel
Jonathan Samuel
MRManickam Ramasamy
Manickam Ramasamy
The agriculture and food supply chain are the most dynamic and complex sectors globally, especially when dealing with highly perishable goods like fruits. Demand for fruits is inherently seasonal and varies significantly by region, influenced by a multitude of factors. Accurately forecasting demand is critical for optimizing supply chain operations, minimizing waste, and maximizing profitability. In recent years, Generative Artificial Intelligence (AI), through their ability to simulate and predict complex patterns, can significantly enhance decision-making in the fruits business through demand forecasting. This chapter will explore how generative AI can be applied to forecast seasonal and regional demand in the fruit industry. The types of data required, the most relevant AI techniques, and the practical applications and benefits of generative AI in the fruit supply chain are discussed here. In addition to that, the challenges associated with deploying these models and potential future directions for research and implementation are examined.