Pakistan’s economy is largely driven by agriculture, and wheat, mostly, stands out as its second most produced crop every year. On the other hand, the average consumption of wheat is steadily increasing as well, due to which its exports are not proportionally growing, thereby, threatening the country’s economy in the years to come. This work focuses on developing an accurate wheat production forecasting model using the Long Short Term Memory (LSTM) neural networks, which are considered to be highly accurate for time series prediction. A data pre-processing smoothing mechanism, in conjunction with the LSTM based model, is used to further improve the prediction accuracy. A comparison of the proposed mechanism with a few existing models in literature is also given. The results verify that the proposed model achieves better performance in terms of forecasting, and reveal that while the wheat production will gradually increase in the next ten years, the production to consumption ratio will continue to fall and pose threats to the overall economy. Our proposed framework, therefore, may be used as guidelines for wheat production in particular, and is amenable to other crops as well, leading to sustainable agriculture development in general.

Melanoma is the deadliest type of skin cancer with highest mortality rate. However, the annihilation in its early stage implies a high survival rate therefore, it demands early diagnosis. The accustomed diagnosis methods are costly and cumbersome due to the involvement of experienced experts as well as the requirements for the highly equipped environment. The recent advancements in computerized solutions for this diagnosis are highly promising with improved accuracy and efficiency. In this article, a method for the identification and classification of the lesion based on probabilistic distribution and best features selection is proposed. The probabilistic distribution such as normal distribution and uniform distribution are implemented for segmentation of lesion in the dermoscopic images. Then multi-level features are extracted and parallel strategy is performed for fusion. A novel entropy-based method with the combination of Bhattacharyya distance and variance are calculated for the selection of best features. Only selected features are classified using multi-class support vector machine, which is selected as a base classifier. The proposed method is validated on three publicly available datasets such as PH2, ISIC (i.e. ISIC MSK-2 and ISIC UDA), and Combined (ISBI 2016 and ISBI 2017), including multi-resolution RGB images and achieved accuracy of 97.5%, 97.75%, and 93.2%, respectively. The base classifier performs significantly better on proposed features fusion and selection method as compared to other methods in terms of sensitivity, specificity, and accuracy. Furthermore, the presented method achieved satisfactory segmentation results on selected datasets.

Fruit Freshness categorization is crucial in the agriculture industry. A system, which precisely assess the fruits’ freshness, is required to save labor costs related to tossing out rotten fruits during the manufacturing stage. A subset of modern machine learning techniques, which are known as Deep Convolution Neural Networks (DCNN), have been used to classify images with success. There have recently been many changed CNN designs that gradually added more layers to achieve better classification accuracy. This study proposes an efficient and accurate fruit freshness classification method. The proposed method has several interconnected steps. After the fruits data is gathered, data is preprocessed using color uniforming, image resizing, augmentation, and image labelling. Later, the AlexNet model is loaded in which we use eight layers, including five convolutional layers and three fully connected layers. Meanwhile, the transfer learning and fine tuning of the CNN is performed. In the final stage, the softmax classifier is used for final classification. Detailed simulations are performed on three publicly available datasets. Our proposed model achieved highly favorable results on all three datasets in which 98.2%, 99.8%, and 99.3%, accuracy is achieved on aforesaid datasets, respectively. In addition, our developed method is also computationally efficient and consumes 8 ms on average to yield the final classification result.

Deep learning techniques, particularly convolutional neural networks, have shown great potential in computer vision and medical imaging applications. However, deep learning models are computationally demanding as they require enormous computational power and specialized processing hardware for model training. To make these models portable and compatible for prototyping, their implementation on low-power devices is imperative. In this work, we present the implementation of Modified U-Net on Intel/Movidius Neural Compute Stick 2 (NCS-2) for the segmentation of medical images. We selected U-Net because, in medical image segmentation, U-Net is a prominent model that provides improved performance for medical image segmentation even if the dataset size is small. The modified U-Net model is evaluated for performance in terms of dice score. Experiments are reported for segmentation task on three medical imaging datasets: BraTs dataset of brain MRI, heart MRI dataset, and Ziehl–Neelsen sputum smear microscopy image (ZNSDB) dataset. For the proposed model, we reduced the number of parameters from 30 million in the U-Net model to 0.49 million in the proposed architecture. Experimental results show that the modified U-Net provides comparable performance while requiring significantly lower resources and provides inference on the NCS-2. The maximum dice scores recorded are 0.96 for the BraTs dataset, 0.94 for the heart MRI dataset, and 0.74 for the ZNSDB dataset.

Eye and systemic diseases are known to manifest themselves in retinal vasculature. Segmentation of retinal vessel is one of the important steps in retinal image analysis. A simple unsupervised method based on Gabor wavelet and Multiscale Line Detector is proposed for retinal vessel segmentation. Vessels are enhanced by linear superposition of first scale Gabor wavelet image and complemented Green channel. Multiscale Line Detector is used to segment the blood vessels. Finally, a simple post processing scheme based on median filtering is deployed to remove false positives. The proposed scheme was evaluated with publicly available datasets called DRIVE, STARE and HRF, obtaining an accuracy of 0.9470, 0.9472, and 0.9559, and a sensitivity of 0.7421, 0.8004, and 0.7207, respectively. These results are comparable to the state-of-the-art methods, albeit with a simpler approach.

Subcutaneous veins localization is usually performed manually by medical staff to find suitable vein to insert catheter for medication delivery or blood sample function. The rule of thumb is to find large and straight enough vein for the medication to flow inside of the selected blood vessel without any obstruction. The problem of peripheral difficult venous access arises when patient’s veins are not visible due to any reason like dark skin tone, presence of hair, high body fat or dehydrated condition, etc. To enhance the visibility of veins, near infrared imaging systems is used to assist medical staff in veins localization process. Optimum illumination is crucial to obtain a better image contrast and quality, taking into consideration the limited power and space on portable imaging systems. In this work a hyperspectral image quality assessment is done to get the optimum range of illumination for venous imaging system. A database of hyperspectral images from 80 subjects has been created and subjects were divided in to four different classes on the basis of their skin tone. In this paper the results of hyper spectral image analyses are presented in function of the skin tone of patients. For each patient, four mean images were constructed by taking mean with a spectral span of 50 nm within near infrared range, i.e. 750–950 nm. Statistical quality measures were used to analyse these images. It is concluded that the wavelength range of 800 to 850 nm serve as the optimum illumination range to get best near infrared venous image quality for each type of skin tone.