Muhammad Abu Bakr

Reliable differentiation of crops and weeds is essential for precision agriculture, where real-time detection can minimize chemical inputs and support site-specific interventions. This study presents the large-scale and systematic benchmark of 19 YOLO-family variants, spanning YOLOv3 through YOLOv11, for cotton–weed detection using the Cotton–8 dataset. The dataset comprises 4440 annotated field images with five categories: broadleaf weeds, grass weeds, and three growth stages of cotton. All models were trained under a standardized protocol with COCO-pretrained weights, fixed seeds, and Ultralytics implementations to ensure reproducibility and fairness. Inference was conducted with a confidence threshold of 0.25 and a non-maximum suppression (NMS) IoU threshold of 0.45, with test-time augmentation (TTA) disabled. Evaluation employed precision, recall, mAP@0.5, and mAP@0.5:0.95, along with inference latency and parameter counts to capture accuracy–efficiency trade-offs. Results show that larger models, such as YOLO11x, achieved the best detection accuracy (mAP@0.5 = 81.5%), whereas lightweight models like YOLOv8n and YOLOv9t offered the fastest inference ( 27 msper image) but with reduced accuracy. Across classes, cotton growth stages were detected reliably, but broadleaf and grass weeds remained challenging, especially under stricter localization thresholds. These findings highlight that the key bottleneck lies in small-object detection and precise localization rather than architectural design. By providing the first direct comparison across successive YOLO generations for weed detection in cotton, this work offers a practical reference for researchers and practitioners selecting models for real-world, resource-constrained cotton–weed management.

The use of intelligent crop recommendation systems has become crucial in the era of smart agriculture to increase yield and enhance resource utilization. In this study, we compared different machine learning (ML), and deep learning (DL) models utilizing structured tabular data for crop recommendation. During our experimentation, both ML and DL models achieved decent performance. However, their architectures are not suited for setting up conversational systems. To overcome this limitation, we converted the structured tabular data to descriptive textual data and utilized it to fine-tune Large Language Models (LLMs), including BERT and GPT-2. In comprehensive experiments, we demonstrated that GPT-2 achieved a higher accuracy of 99.55% than the best-performing ML and DL models, while maintaining precision of 99.58% and recall of 99.55%. We also demonstrated that GPT-2 not only keeps up competitive accuracy but also offers natural language interaction capabilities. Due to this capability, it is a viable option to be used for real-time agricultural decision support systems.

Among renewable resources, solar energy is abundant and cost effective. However, the efficiency and performance of photovoltaic panels (PVs) are adversely affected by the rise in the surface temperature of solar cells. This paper analyzes the idea of utilizing thermoelectric modules (TEMs) to enhance the efficiency and performance of PV panels. The proposed hybrid solar thermoelectric generation (HSTEG) system employs TEMs as thermoelectric coolers (TECs) to enhance panel efficiency and as thermoelectric generators (TEGs) to convert excess heat into additional electricity. This study includes an extensive evaluation of the proposed idea using MATLAB Simulink and experimental validation in indoor as well as outdoor environments. The use of TECs for the active cooling of the PV system leads to an increase in its efficiency by 9.54%. Similarly, the passive cooling by TECs along with the additional power generated by the TEGs from the excessive heat led to an increase in the efficiency of the PV system of 15.50%. The results demonstrate the HSTEG system’s potential to significantly improve PV panel efficiency and energy generation, offering a promising avenue for advancing solar energy technology.

Researchers have created cryptography algorithms that encrypt data using a public or private key to secure it from intruders. It is insufficient to protect the data by using such a key. No research article has identified an algorithm capable of protecting both the data and the associated key, nor has any mechanism been developed to determine whether access to the data is permissible or impermissible based on the authentication of the key. This paper presents a WEDEx-Kerberotic Framework for data protection, in which a user-defined key is firstly converted to a cipher key using the “Secure Words on Joining Key (SWJK)” algorithm. Subsequently, a WEDEx-Kerberotic encryption mechanism is created to protect the data by encrypting it with the cipher key. The first reason for making the WEDEx-Kerberotic Framework is to convert the user-defined key into a key that has nothing to do with the original key, and the length of the cipher key is much shorter than the original key. The second reason is that each ciphertext and key value are interlinked. When an intruder utilizes the snatching mechanism to obtain data, the attacker obtains data or a key unrelated to the original data. No matter how efficient the algorithm is, an attacker cannot access the data when these methods and algorithms are used to protect it. Finally, the proposed algorithm is compared to the previous approaches to determine the uniqueness of the algorithm and assess its superiority to the previous algorithms.