Zia Ul Haq

Post-harvest losses of mango (Mangifera indica L.) in developing economies are estimated at 5% to 30%, largely due to manual management practices that depend on subjective visual assessments. This paper proposes a lightweight deep learning architecture, termed SE-DBIRNet, for real-time classification of mangoes into five shelf-life stages: unripe, semi-ripe, fully ripe, overripe, and perished. The model incorporates three key design strategies: (i) depthwise separable convolutions, achieving an 88.5% reduction in parameters when integrated into the ResNet50 backbone; (ii) a double-branch inverted residual (DBIR) module designed to enhance feature diversity and richness; and (iii) a squeeze-and-excitation (SE) attention mechanism for adaptive channel-wise recalibration. Using a public benchmark dataset of 4428 RGB images (Mendeley Data) under 10-fold cross-validation, SE-DBIRNet achieved 98.24% accuracy. Among lightweight CNN architectures (EfficientNetB0, MobileNetV2, ResNet50), SE-DBIRNet outperformed the best lightweight baseline (EfficientNetB0: 96.57%) by 1.67 percentage points. While dedicated attention-based DenseNet variants (e.g., DSA-DenseNet: 99.20%) achieved higher accuracy, SE-DBIRNet offers a superior trade-off among accuracy, inference speed (56.9 ± 1.8 FPS), and memory efficiency (8871 ± 45 MB CPU memory). EigenCAM activation visualizations revealed that the model focuses on biologically relevant and stage-discriminative features, including surface color gradients, texture uniformity, lenticel patterns, and decay boundaries. Overall, SE-DBIRNet achieves a Pareto-optimal balance among accuracy, speed, and memory efficiency, making it a strong candidate for real-time, edge-deployable post-harvest mango quality-monitoring systems, particularly when computational resources are limited.

Peanut also called groundnut (Arachis hypogaea L.) is an important oilseed and cash crop that is grown in tropical and subtropical regions of the world. Nowadays, tractor mounted peanut threshers without grading systems are commonly used to thresh the harvested groundnut plants, which results in the mixing of standard quality groundnut pods with immature/dead pods, mud/clods, and other impurities. To address this challenge, the conventional thresher was incorporated with a grader. The modified thresher was evaluated during the threshing season of 2023-24 in district Rawalpindi, Pothwar region of Punjab, Pakistan. The performance of the newly developed groundnut thresher (TH₁) was compared with conventional thresher (TH₂) based on threshing productivity (capacity) (kg h-1), pod breakage percentage (%), cleaning efficiency (%), and threshing efficiency (%) at three different ranges of moisture contents viz. M₁ = 19-23%, M₂ = 14-17%, M₃ = 8-12%. Experimental data were collected and statistically analyzed at a 5% level of probability. The experimental results revealed that maximum cleaning efficiency in the improved (TH₁) and conventional (TH₂) threshers were 97.88% and 84.92% respectively at the minimum moisture content (8-12%) while the minimum pod damage percentage was observed 2.24% and 4.44% at higher moisture content (19-23%). The overall performance of improved groundnut thresher was more satisfactory than the conventional thresher based on cleaning efficiency and pod damage percentage while it performed equally for threshing productivity and threshing efficiency. From the experimental results, it reveals that the modified groundnut thresher performed better to clean and grade the groundnut pods in one operation.

Hydroponic farming enables year-round vegetable production, however, it requires specific temperature and humidity control for optimal plant growth. In winter, when ambient temperatures drop below 16 °C, supplemental heating becomes essential. To address this challenge, an indigenous air-heating system was developed and evaluated for its effectiveness in three greenhouse types including glasshouse, fiberglass house and polythene house. Three types of fuels (wood, crop residues and solid waste) were used during experimentation. Wood shown better performance for heating of greenhouse as compared to its competitors (crop waste, solid waste) because of its higher calorific value. However, crop waste and solid waste fuels were more economical as well as abundantly available. Results showed that the glasshouse provided the most effective temperature regulation due to its higher heat transfer efficiency under higher temperature gradients. The fiberglass house demonstrated moderate performance with an average heat output of 26,000 Btu, while the polythene house was least effective, producing only 18,000 Btu with poor heat distribution. Inadequate heating in the polythene house delayed plant growth and fruit ripening. Overall, the study highlights the importance of greenhouse design in achieving efficient heating for hydroponic crop production under cold climatic conditions.

To speed up the olive harvesting process, a tractor-driven olive harvesting machine was designed and manufactured at the Institute of Agricultural Engineering (AEI), Islamabad. This newly developed equipment was tested on the Bari Zaitoon-I cultivar for its performance evaluation. This innovative technology has proven valuable in efficiently replacing expensive manual harvesting operations with timely and economic alternative. It was experimentally evaluated at different PTO speeds, stroke lengths (SL), and vertical clamp positions (CP) on the tree to find the harvested and leftover fruit (%) and field capacity (trees/h) of the machine. Data collected was statistically analyzed by using “Statistix 8.1” software at a 5 % le vel of probability. The best results were recorded as 92.4 % harvested fruit, 7.6 % leftover fruit and 23.6 trees/h field capacity at the PTO speed of 300 rpm along with the stroke length of 10 cm and clamp position of 1 m on the tree trunk from the ground. The use of the developed equipment will make it possible to harvest olives in a shorter time than with manual harves ting without reducing the quality and weight of the obtained products.

Mechanical seed coating has been globally adapted to protect them from fungus, soil-borne diseases, and other harmful substances. In crop production, attaining the potential yield is the main concern of farmers. Among the other problems of low yield, fungal attack is associated with germination stage. To avoid this problem, farmers are using fungicides with the help of bags or clothes. The traditional method is time-consuming, labor-intensive, costly as well as inefficient for uniform coating of seed. To address this challenge and to speed up seed coating process, a manually/motor-operated seed coating machine was designed at CAD/CAM Lab by using Auto CAD software and developed at Agricultural Engineering Workshop of Arid Agriculture University, Rawalpindi. The newly developed machine was tested at two levels, manually/motor-operated and compared with a traditional method. Its performance was evaluated using (metalaxyl + mancozeb) fungicide under three treatments levels: T1 (traditional coating method), T2 (manual coating method), and T3 (mechanical coating method). The data from the experiment on fully coated seed percentage, semi-coated seed percentage, and uncoated seed percentage were collected and statistically analyzed by using Statistix 8.1. Mechanical seed coating method T3 demonstrates superior results, achieving coating efficiencies of 79.2%, 85.4%, and 93.2% at 2-, 4-, and 6-minutes’ intervals, respectively. The machine offers a cost-effective and efficient solution for cotton-seed treatment, significantly enhancing seed coating uniformity and reducing seed breakage compared to conventional practices.

Rice (Oryza sativa) is an important cereal grain used as a staple food to fulfill daily calories requirement. Conventionally, rice seeds are sown in a nursery and then transplanted manually into the paddy fields with the help of skilled labor, but this method is time-consuming, costly, and as well as labor-intensive. This conventional method may result in irregular plant patterns, decreased plant population, and ultimately reduction of farm yield and profit. Nowadays, rice transplanter machines are selectively used. The performance of Ride-On and Walk-After Rice Transplanters were evaluated to assess their feasibility in local field conditions. The key performance indicators i.e. Effective Field Capacity, Field Efficiency and Seedling Losses were selected to assess the efficacy of these machines. The data collected were investigated at a 5% level of probability and the trials were conducted with the experimental design following Randomized Complete Block Design (RCBD) with three replications. The Ride-On Rice Transplanter (SPV-8C) had maximum mean Effective Field Capacity (0.67ha/h) and Field Efficiency (73.6%) at speed of 5 km/h while the seedling losses (1.23%) were minimum for Walk-After Rice Transplanter (SPW-48C) at speed of 2 km/h. The experimental results shown that Effective Field Capacity and Field Efficiency was found better for Ride-On Rice Transplanter (SPV-8C) as compared to Ride-On Rice Transplanter (SPV-6CMD) and Walk-After Rice Transplanter (SPW-48C).

Hydroponic (soilless culture) is an alternative flowers, fruits and vegetables production method. It may comprise pure water or substrate culture. Greenhouses are permanent structure that allow the farmers to grow vegetables and fruits year-round with mechanically-controlled temperature and irrigation system. Crop yield increases with ideal water and fertilizer use in hydroponic agriculture. Farmers are growing broccoli under greenhouse conditions using irrigation water with random nutrients application. However, database for optimum production of broccoli is required in order to reduce cost of production and increasing profit. Broccoli was grown on tap water, straight fertilizers and soluble fertilizer. The evaluation of these treatments (fertilizer concentration) was conducted on the basis of sulforaphane content, vitamin C, nitrate, weight of broccoli florets and total broccoli yield. Data collected from the experiment were statistically analyzed at 5% level of probability. Statical results shown that hydroponic recipe with soluble fertilizer shown better performance as compared to tap water and NPK straight fertilizer.