Automated food detection and recognition methods have been studied to enhance an end-user life. However, most of the existing research focused on food ingredient type recognition with little work has been done for food ingredient state recognition. Successful recognition of food ingredient state plays a significant role in handling the food ingredient by an intelligent system. In this work, we propose a new novel cascaded multi-head approach based on deep learning for simultaneously recognizing the state and type of food ingredients. We trained and evaluated the proposed approach on a benchmark dataset of food ingredients images with 9 different food states and 18 food types. We compared the proposed approach with a non-cascaded deep learning approach. The cascaded deep learning approach shows improvement in food ingredient state recognition with an accuracy of 87% compared to 81% using a non-cascaded deep learning method. Our proposed method broadly applies to various tasks where food ingredient state recognition is important, such as feeding elderly and disabled person, and for automation of food recognition and preparation.

The novel coronavirus disease 2019 (COVID-19) added tremendous pressure on healthcare services worldwide. COVID-19 early detection is of the utmost importance to control the spread of the coronavirus pandemic and to reduce pressure on health services. There have been many approaches to detect COVID-19; the most commonly used one is the nasal swab technique. Before that was available chest X-ray radiographs were used. X-ray radiographs are a primary care method to reveal lung infections, which allows physicians to assess and plan a course of treatment. X-ray machines are prevalent, which makes this method a preferable first approach for the detection of new diseases. However, this method requires a radiologist to assess each chest X-ray image. Therefore, different automated methods using machine learning techniques have been proposed to assist in speeding up diagnoses and improving the decision-making process. In this paper, we review deep learning approaches for COVID-19 detection using chest X-ray images. We found that the majority of deep learning approaches for COVID-19 detection use transfer learning. A discussion of the limitations and challenges of deep learning in radiography images is presented. Finally, we provide potential improvements for higher accuracy and generalisability when using deep learning models for COVID-19 detection.

Most pictures shared online are accompanied by temporal metadata (i.e., the day and time they were taken), which makes it possible to associate an image content with real-world events. Maliciously manipulating this metadata can convey a distorted version of reality. In this work, we present the emerging problem of detecting timestamp manipulation. We propose an end-to-end approach to verify whether the purported time of capture of an outdoor image is consistent with its content and geographic location. We consider manipulations done in the hour and/or month of capture of a photograph. The central idea is the use of supervised consistency verification, in which we predict the probability that the image content, capture time, and geographical location are consistent. We also include a pair of auxiliary tasks, which can be used to explain the network decision. Our approach improves upon previous work on a large benchmark dataset, increasing the classification accuracy from 59.0% to 81.1%. We perform an ablation study that highlights the importance of various components of the method, showing what types of tampering are detectable using our approach. Finally, we demonstrate how the proposed method can be employed to estimate a possible time-of-capture in scenarios in which the timestamp is missing from the metadata.

One major challenge in fluid power is the improvement and optimization of the efficiency of mobile hydraulic systems. Conventional fluid power systems often exhibit relatively low overall efficiencies caused by inefficiencies in the various components, such as a prime mover, variable displacement pump, valves, fittings, hoses, and actuators. While each component contributes to the losses in the overall system, the pump converts the mechanical shaft energy from the prime mover to energy transmitted hydraulically and is one of the most crucial components impacting overall system efficiency. Using on/off technologies, new pump architectures have enabled the opportunity to increase the efficiency over conventional designs using positive sealing valves in place of conventional port plate designs. This work proposes, investigates, and assesses the development and optimization of a digital variable displacement pump using a novel cam actuation technique on radial piston pumps. The novelty of this work is the development and parameter optimization of a mechanically actuated digital radial piston pump that can achieve high efficiencies from minimum to maximum displacement compared to common conventional variable displacement pump technologies. In this study, a sensitivity analysis is conducted to study the parameters of the system to optimize the pump. The parameters assessed in this study include: the valve bore size, cam transition and compression angles, piston diameter, and dead volume in the pumping chamber. The simulation results show that after optimizing the parameters of the system, the pump in design could reach a maximum efficiency of approximately 93% and was capable of upholding efficiencies above 80% between 30–100% displacement.