Mirza Adnan Baig

Dr. Mirza Adnan Baig

UTM, Kuala Lumpur, Malaysia
orcid
Assistant Professor at IQRA University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
8 February 2024 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
HRHumaira Rana
Humaira Rana
MFMuhammad Umer Farooq
Muhammad Umer Farooq
AKAbdul Karim Kazi
Abdul Karim Kazi
Mirza Adnan BaigMirza Adnan Baig
Mirza Adnan Baig
MAMuhammad Ali Akhtar
Muhammad Ali Akhtar
The agriculture sector plays a crucial role in the economy of Pakistan, contributing significantly to the Gross Domestic Product (GDP) and the employment rate. However, this sector faces challenges such as climate change, water scarcity, and low productivity, which have a direct impact on agricultural commodity prices. Accurate forecasting of commodity prices is essential for farmers, traders, and policymakers to make informed decisions and improve economic outcomes. This paper explores the use of a big data framework for agricultural commodity price forecasting in Pakistan, using a historical dataset on commodity prices in various Pakistani cities from 2007 to 2022 and Apache Spark to preprocess and clean the data. Based on historical spinach prices in Vehari City, the machine learning models Auto-Regressive Moving Average (ARIMA), Random Forest, and Long-Short-Term Memory (LSTM) were applied to price trends, and their performance was compared using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and squared correlation coefficient (R2). LSTM outperformed ARIMA and Random Forest with a higher R2 value of 0.8 and the lowest MAE of 125.29. Such predictions can help farmers to effectively plan crop cultivation and traders to make well-informed decisions.

5 December 2023 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
ARAsif Raza
Asif Raza
MLMustafa Latif
Mustafa Latif
MFMuhammad Umer Farooq
Muhammad Umer Farooq
Mirza Adnan BaigMirza Adnan Baig
Mirza Adnan Baig
MAMuhammad A. Akhtar
Muhammad A. Akhtar
WAWaseemullah
Waseemullah
Adaptable chatbots have revolutionized user interactions by dynamically tailoring responses to users' knowledge and explainability preferences in interdisciplinary domains, such as AI in education and medicine. While strides have been made in model explainability, little attention has been paid to making models contextually aware and responsive to users' background knowledge. This study investigated interdisciplinary knowledge learning principles in a different domain, where the chatbot's contextual understanding is enhanced through dynamic knowledge graphs that capture users' past interactions to deliver up-to-date and relevant responses. By incorporating explainability features, chatbot responses become enriched, enabling users to understand the reasoning behind answers. This study proposed a model that showed superior chatbot performance and accurately addressed most queries, outperforming competitor chatbots DBpedia, ODC, and ODA. A 0.7 F-measure showcased its excellence, attributed to dynamic knowledge graphs and explainability checks. This study envisions a new era of conversational AI that not only meets user needs but also fosters a deeper understanding of AI decision-making, making it indispensable in delivering personalized, informed, and contextually aware interactions.

1 June 2024 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
TSTaskeena Siddiqui
Taskeena Siddiqui
MLMustafa Latif
Mustafa Latif
MFMuhammad Umer Farooq
Muhammad Umer Farooq
Mirza Adnan BaigMirza Adnan Baig
Mirza Adnan Baig
YHYusuf Sharif Hassan
Yusuf Sharif Hassan
Chronic Obstructive Pulmonary Disease (COPD) is a persistent respiratory disease that poses a significant threat to global human health with elevated incidence and mortality rates. Timely recognition and diagnosis of COPD play a pivotal role in efficiently managing and treating the condition. The incorporation of deep learning technologies into healthcare has significant potential to enhance diagnostics and treatment outcomes. This study proposes an innovative deep-learning approach along with an ensemble technique to address the imperative need for an effective predictive model in COPD disease classification, particularly in situations with limited available data. This was achieved by leveraging the ensemble bagging technique and incorporating ANN as a classifier within this framework. Training and evaluation of the proposed ensemble ANN model were performed on a dataset comprising a variety of attributes, including demographic information, medical history, diagnostic measurements, and pollution exposures. Data were collected from people aged 18 to 60 originating from Pakistan, encompassing patients, attendants, hospital staff, faculty, and students. The effectiveness of the model in classifying COPD was measured using F1 score, recall, precision, and accuracy. The evaluation of the model produced notable results, as it achieved a 90% F1 score, 96% recall, 84% precision, and 89% accuracy in identifying the presence of COPD in individuals. Furthermore, this study carried out a comparative analysis between a standalone ANN model and the proposed ensemble ANN model which revealed that the proposed Ensemble ANN model outperforms existing methods, particularly in scenarios with limited sample size. This research provides substantial contributions to healthcare technology, as it presents an efficient tool for COPD prediction, facilitates early intervention, and significantly increases the overall standard of patient care.

1 January 2022 in Computers, Materials & Continua
Verified
Journal Article
Open access
PDF file
Mirza Adnan BaigMirza Adnan Baig
Mirza Adnan Baig
GMGhulam Ali Mallah
Ghulam Ali Mallah
NSNoor Ahmed Shaikh
Noor Ahmed Shaikh
Precipitation prediction (PP) have become one of the significant research areas of deep learning (DL) and machine vision (MV) techniques are frequently used to predict the weather variables (WV). Since the climate change has left significant impact upon weather variables (WV) and continuously changes are observed in temperature, humidity, cloud patterns and other factors. Although cloud images contain sufficient information to predict the precipitation pattern but due to changes in climate, the complex cloud patterns and rapid shape changing behavior of clouds are difficult to consider for rainfall prediction. Prediction of rainfall would provide more meticulous assistance to the farmers to know about the weather conditions and to care their cash crops. This research proposes a framework to classify the dark cloud patterns (DCP) for prediction of precipitation. The framework consists upon three steps to classify the cloud images, first step tackles noise reduction operations, feature selection and preparation of datasets. Second step construct the decision model by using convolutional neural network (CNN) and third step presents the performance visualization by using confusion matrix, precision, recall and accuracy measures. This research contributes (1) real-world clouds datasets (2) method to prepare datasets (3) highest classification accuracy to predict estimated as 96.90%.

31 October 2021 in IETE Journal of Research
Verified
Journal Article
Closed access
Mirza Adnan BaigMirza Adnan Baig
Mirza Adnan Baig
DKDr Najeed Ahmed Khan
Dr Najeed Ahmed Khan
MRMuhammad Masood Rafi
Muhammad Masood Rafi
Currently, fire detection systems based on computer vision techniques are highly appreciated for their intelligent detections at earliest. These systems use surveillance cameras to capture high-level information from a fire that enables a system to take preventive and corrective measures before the happening of a fire hazard. Handling false fire detection and reducing false alarm in such developed systems are still big challenges that need to be addressed. In this paper, a novel framework is proposed that uses angular and regional area information of the fire flame to predict the existence of a fire flame in sequence of a video frames. The proposed system especially handles false detection of fire object in video. The results achieved on different dataset of fire videos show that extracted features using the proposed framework efficiently distinguish fire and non-fire objects.r These features are also useful to estimate the size and direction of a fire flame. The regional area information can be fed into a machine-learning algorithm to learn a model for a fire flame that can be used to predict about the existence of fire flame.

11 April 2026 in Advances and Applications in Statistics
Verified
Journal Article
Open access
RQRohail Qamar
Rohail Qamar
WAWaseemullah
Waseemullah
MKMoona Kanwal
Moona Kanwal
Mirza Adnan BaigMirza Adnan Baig
Mirza Adnan Baig
RARaheela Asif
Raheela Asif
MAMarrium Asim
Marrium Asim
The cryptocurrency market has high volatility and a dynamic nature, which poses significant challenges for long-term predictions and investment decision-making. This study investigates approaches that enable investors to enhance cryptocurrency investment decision-making by integrating on-chain data, technical indicators, and sentiment analysis. The evaluation process includes testing of ARIMA, XGBoost, Facebook Prophet and Long Short-Term Memory (LSTM) models together with sentiment analysis methods that used VADER (Valence Aware Dictionary and sEntiment Reasoner), logistic regression, support vector machine, multinomial Naive Bayes and bi-directional LSTM. Logistic regression achieved an accuracy of 87% while VADER outperformed all other models with an accuracy of 93%. The XGBoost regressor achieved better Bitcoin price forecasting results when technical indicators and on-chain data were combined because the RMSE decreased to 1,952.39 from its initial value of 2,031.56. The model achieved better results after sentiment data integration because it produced an RMSE value of 1,926.24. This demonstrates that the integration of advanced analytical methods with sentiment analysis enhances investment strategies, enabling improved prediction of cryptocurrency market trends and more informed decision-making. Received: January 27, 2026Revised: February 11, 2026Accepted: March 28, 2026