A high-performance, hardware-based deep learning system for disease diagnosis.

Modern deep learning schemes have shown human-level performance in the area of medical science. However, the implementation of deep learning algorithms on dedicated hardware remains a challenging task because modern algorithms and neuronal activation functions are generally not hardware-friendly and require a lot of resources. Recently, researchers have come up with some hardware-friendly activation functions that can yield high throughput and high accuracy at the same time. In this context, we propose a hardware-based neural network that can predict the presence of cancer in humans with 98.23% accuracy. This is done by making use of cost-efficient, highly accurate activation functions, Sqish and LogSQNL. Due to its inherently parallel components, the system can classify a given sample in just one clock cycle, i.e., 15.75 nanoseconds. Though this system is dedicated to cancer diagnosis, it can predict the presence of many other diseases such as those of the heart. This is because the system is reconfigurable and can be programmed to classify any sample into one of two classes. The proposed hardware system requires about 983 slice registers, 2,655 slice look-up tables, and only 1.1 kilobits of on-chip memory. The system can predict about 63.5 million cancer samples in a second and can perform about 20 giga-operations per second. The proposed system is about 5-16 times cheaper and at least four times speedier than other dedicated hardware systems using neural networks for classification tasks.

In Vitro Role of Pumpkin Parts as Pharma-Foods: Antihyperglycemic and Antihyperlipidemic Activities of Pumpkin Peel, Flesh, and Seed Powders, in Alloxan-Induced Diabetic Rats.

Pumpkin is a well-known vegetable, among the members of Cucurbitaceae family, due to its importance as pharma food. Keeping in view the antidiabetic and plasma lipids lowering potential of pumpkin, the present study was conducted to investigate that, which part of pumpkin (peel, flesh, and seeds), possess more bioactive compounds, exhibiting antihyperglycemic and antihyperlipidemic potential. Albino rats with 190-210 g body weight were divided into 11 groups. Five rats were included in each group; group A was negative control, group B was positive control, and groups C to K were diabetic rats fed with pumpkin peel, flesh, and seed powders. Diabetes was induced in rats with the help of alloxan monohydrate. During 28 days of experimental period, blood glucose level of different rat's groups was checked with the help of glucometer, at every 7 days interval and at the end of 28 days study, plasma lipids were checked with the help of commercial kits. A significant decrease in blood glucose level (128.33 ± 1.67 mg/dl), TC (88.43 ± 0.66 mg/dl), TG (69.79 ± 0.49 mg/dl), and LDL-C (21.45 ± 0.08 mg/dl) was recorded in rat groups fed with 15 g pumpkin seed powder, at the end of study. After pumpkin seeds, second significant antihyperglycemic and antihyperlipidemic effect was recorded in rat's groups fed with 15 g pumpkin peel powder. Pumpkin flesh powder effect in lowering blood glucose level and plasma lipids was less significant as compared to seeds and peel powder. As the dose of the pumpkin powders was increased from 5 to 10 and then 15 g, the blood glucose-lowering and plasma lipid-lowering effect became more significant. Similarly, as the experimental duration was expanded from first week to 28 days, this antihyperglycemic and antihyperlipidemic effect became more significant. These results were sufficient to conclude that pumpkin has high potential to be used in human diet to cope with noncommunicable diseases like diabetes and hypercholesterolemia.

Seasonal Fluctuations of N, P and K in Leaves Influenced Nutrient Requirement During Fruit Development Stages in Different Olive Genotypes

Abstract: Olive is grown in semi-arid climatic conditions; however, little is known about mineral changes in olive plant and nutrient requirements during the production period. Hence, the current study was conducted under Pothwar agro-climatic conditions in order to select appropriate stage of macronutrients (N, P, K) application in relation to soil and leaf nutritional status during 2017 and 2018 growing seasons. Soil and leaf analysis were performed at four different phenological stages (i.e. flowering, fruit setting, fruit enlargement and fruit maturity stages). The results revealed that the assessed macronutrient in leaf and soil varied significantly among varieties, phenological stages and growing year. The results revealed also that nitrogen level was found to decrease from fruit set (1.56%) to fruit enlargement stage (1.47%). Leaf and soil N, P and K contents were found higher before the flowering (stage 1) and depleted after fruit harvesting (stage 4), regardless of olive varieties. However, high yielding varieties showed lower nutrients after fruit harvesting (stage 4). Therefore, N content in leaf and soil gradually decreased during fruit growth and development. Whereas, K content in leaf and soil sharply declined from fruit maturity to fruit ripening stage. Overall, the trend of nutrient depletion showed that plants need phosphorus for fruit setting, nitrogen before and after fruit setting, and potash after pit hardening or at oil accumulation stages.

A Machine-Learning-Based System for Prediction of Cardiovascular and Chronic Respiratory Diseases.

Cardiovascular and chronic respiratory diseases are global threats to public health and cause approximately 19 million deaths worldwide annually. This high mortality rate can be reduced with the use of technological advancements in medical science that can facilitate continuous monitoring of physiological parameters-blood pressure, cholesterol levels, blood glucose, etc. The futuristic values of these critical physiological or vital sign parameters not only enable in-time assistance from medical experts and caregivers but also help patients manage their health status by receiving relevant regular alerts/advice from healthcare practitioners. In this study, we propose a machine-learning-based prediction and classification system to determine futuristic values of related vital signs for both cardiovascular and chronic respiratory diseases. Based on the prediction of futuristic values, the proposed system can classify patients' health status to alarm the caregivers and medical experts. In this machine-learning-based prediction and classification model, we have used a real vital sign dataset. To predict the next 1-3 minutes of vital sign values, several regression techniques (i.e., linear regression and polynomial regression of degrees 2, 3, and 4) have been tested. For caregivers, a 60-second prediction and to facilitate emergency medical assistance, a 3-minute prediction of vital signs is used. Based on the predicted vital signs values, the patient's overall health is assessed using three machine learning classifiers, i.e., Support Vector Machine (SVM), Naive Bayes, and Decision Tree. Our results show that the Decision Tree can correctly classify a patient's health status based on abnormal vital sign values and is helpful in timely medical care to the patients.

On the classification of Microsoft-Windows ransomware using hardware profile.

Due to the expeditious inclination of online services usage, the incidents of ransomware proliferation being reported are on the rise. Ransomware is a more hazardous threat than other malware as the victim of ransomware cannot regain access to the hijacked device until some form of compensation is paid. In the literature, several dynamic analysis techniques have been employed for the detection of malware including ransomware; however, to the best of our knowledge, hardware execution profile for ransomware analysis has not been investigated for this purpose, as of today. In this study, we show that the true execution picture obtained via a hardware execution profile is beneficial to identify the obfuscated ransomware too. We evaluate the features obtained from hardware performance counters to classify malicious applications into ransomware and non-ransomware categories using several machine learning algorithms such as Random Forest, Decision Tree, Gradient Boosting, and Extreme Gradient Boosting. The employed data set comprises 80 ransomware and 80 non-ransomware applications, which are collected using the VirusShare platform. The results revealed that extracted hardware features play a substantial part in the identification and detection of ransomware with F-measure score of 0.97 achieved by Random Forest and Extreme Gradient Boosting.

Phenolic Profile and Thermal Stability of Monovarietal Extra Virgin Olive Oils Based on Synchronous Fluorescence Spectroscopy.

The olive oil production in Pakistan has recently been started with the cultivation of exotic cultivars that are successfully adapted at Barani Agriculture Research center (BARI), Chakwal, Pakistan in Potohar valley. Therefore, characterization of extra virgin olive oil (EVOO) from this agro-climatic region is mandatory in establishing its biochemical profile and thermal stability. Seventeen monovarietal EVOOs extracted from these cultivars were analysed using synchronous fluorescence spectroscopy (SFS) and subjected to heating at 115, 150 and 170 °C for 15 min to identify their thermal stability. SFS emission spectra differentiated EVOOs on the basis of phenolic compounds that are denatured at high temperature, further chlorophyll contents also decreased with increasing temperature. The strong emission at ca. 351 nm, suggested to be vanillic acid, 391-471 nm for blue green region (BGR) assigned to other phenolic compounds and two peaks at 672 and 723 nm for chlorophyll became the bases for grouping through Hierarchical clustering. Most of the EVOOs were stable at 150 °C but showed denatured spectra at 170 °C, the only EVOO extracted from Spanish cultivar Arbequina was found to have moderate fluorescence emission from both vanillic acid and BGR that are more likely to impart oxidative stability even after heating at 170 °C, also confirmed by lowest values of specific extinction co-efficient (K232 and K270). Moreover, variation in phenolic contents of Arbequina EVOO was observed with different harvesting stages and the early harvested olives produced more thermally stable oil as compared to late harvested olives. Arbequina oil grown in Pakistan can be better suited for cooking at high temperatures, moreover can be blended with other monovarietal EVOOs to enhance the nutritional benefits and thermal stability.