Wildlife Monitoring on the Edge: A Performance Evaluation of Embedded Neural Networks on Microcontrollers for Animal Behavior Classification.

Monitoring animals' behavior living in wild or semi-wild environments is a very interesting subject for biologists who work with them. The difficulty and cost of implanting electronic devices in this kind of animals suggest that these devices must be robust and have low power consumption to increase their battery life as much as possible. Designing a custom smart device that can detect multiple animal behaviors and that meets the mentioned restrictions presents a major challenge that is addressed in this work. We propose an edge-computing solution, which embeds an ANN in a microcontroller that collects data from an IMU sensor to detect three different horse gaits. All the computation is performed in the microcontroller to reduce the amount of data transmitted via wireless radio, since sending information is one of the most power-consuming tasks in this type of devices. Multiples ANNs were implemented and deployed in different microcontroller architectures in order to find the best balance between energy consumption and computing performance. The results show that the embedded networks obtain up to 97.96% ± 1.42% accuracy, achieving an energy efficiency of 450 Mops/s/watt.

Performance Evaluation of Deep Learning-Based Prostate Cancer Screening Methods in Histopathological Images: Measuring the Impact of the Model's Complexity on Its Processing Speed.

Prostate cancer (PCa) is the second most frequently diagnosed cancer among men worldwide, with almost 1.3 million new cases and 360,000 deaths in 2018. As it has been estimated, its mortality will double by 2040, mostly in countries with limited resources. These numbers suggest that recent trends in deep learning-based computer-aided diagnosis could play an important role, serving as screening methods for PCa detection. These algorithms have already been used with histopathological images in many works, in which authors tend to focus on achieving high accuracy results for classifying between malignant and normal cases. These results are commonly obtained by training very deep and complex convolutional neural networks, which require high computing power and resources not only in this process, but also in the inference step. As the number of cases rises in regions with limited resources, reducing prediction time becomes more important. In this work, we measured the performance of current state-of-the-art models for PCa detection with a novel benchmark and compared the results with PROMETEO, a custom architecture that we proposed. The results of the comprehensive comparison show that using dedicated models for specific applications could be of great importance in the future.

Monotherapy with boosted PIs as an ART simplification strategy in clinical practice.

BACKGROUND: Data on the efficacy of simplifying therapy using darunavir/ritonavir and lopinavir/ritonavir monotherapy in clinical practice remain limited. METHODS: A retrospective single-centre study including patients initiating darunavir/ritonavir or lopinavir/ritonavir monotherapy with a plasma HIV-1 viral load (pVL) <50 copies/mL and at least one subsequent follow-up visit. The primary endpoint was the percentage of patients remaining free of virological failure (VF; defined as a confirmed pVL >50 copies/mL or as any change in the regimen after a single determination with a pVL >50 copies/mL) during the follow-up. We also evaluated the percentage of patients remaining free of treatment failure (TF; defined as VF or the early discontinuation of monotherapy for any reason) and compared the effectiveness of the two regimens. Effectiveness was evaluated using cumulative survival analysis (at Weeks 48 and 96). Factors associated with VF and TF were analysed using Cox regression. RESULTS: A total of 522 patients were included (309 receiving lopinavir/ritonavir and 213 receiving darunavir/ritonavir). The median follow-up was 64.3 (30.5-143.0) weeks. The percentage of patients free of VF and TF was 94% (95% CI 91%-96%) and 79% (95% CI 75%-82%) at 48 weeks, respectively, and 86% (95% CI 81%-89%) and 62% (95% CI 57%-67%) at 96 weeks, respectively. The risk of VF was similar for the two regimens (HR=1.0, 95% CI 0.6-1.8; P=0.962). Lopinavir/ritonavir monotherapy was associated with a 1.5-fold greater risk of TF (95% CI 1.1-2.1; P=0.012) and a 2.3-fold greater risk of discontinuation of therapy due to adverse events (95% CI 1.3-3.9; P=0.003). CONCLUSIONS: The virological efficacy of darunavir/ritonavir and lopinavir/ritonavir monotherapy is high in clinical practice. Treatment discontinuation due to safety issues is more frequent with lopinavir/ritonavir.

Factors associated with visible anogenital warts among HIV-uninfected Peruvian men who have sex with men and transwomen: a cross-sectional study.

BACKGROUND: Visible, anogenital warts may be associated with risk factors for HIV infection. This cross-sectional study examined the factors associated with visible anogenital warts among HIV-uninfected Peruvian men who have sex with men (MSM) and transwomen. METHODS: Six hundred HIV-uninfected MSM and transwomen were recruited from a community-based setting in metropolitan Lima, Peru, through outreach activities. Participants were tested for syphilis, completed a behavioral questionnaire, and were examined for visible anogenital warts. Logistic regression was used to assess the independent association between sample characteristics, HIV-related risk factors, and visible anogenital warts. RESULTS: A tertiary education versus a primary/secondary (adjusted odds ratio [AOR], 1.79; 95% confidence interval [CI], 1.07-2.99), a first experience of anal intercourse at age 20 years or older versus younger ages (AOR, 2.80; 95% CI, 1.45-5.38), and self-reporting of current sexually transmitted infection symptoms (AOR, 2.38; 95% CI, 1.61-3.52) were significant correlates of visible anogenital warts, whereas syphilis infection, transactional sex, receptive anal intercourse, and self-identifying as a transwoman were not. CONCLUSIONS: Although not associated with key risk factors for HIV infection in Peruvian MSM and transwomen, the presence of visible anogenital warts should prompt clinicians to consider the possibility of unreported same-sex sexual behaviors and other risk sexually transmitted infection/HIV risk factors.

An Event-Based Digital Time Difference Encoder Model Implementation for Neuromorphic Systems.

Neuromorphic systems are a viable alternative to conventional systems for real-time tasks with constrained resources. Their low power consumption, compact hardware realization, and low-latency response characteristics are the key ingredients of such systems. Furthermore, the event-based signal processing approach can be exploited for reducing the computational load and avoiding data loss due to its inherently sparse representation of sensed data and adaptive sampling time. In event-based systems, the information is commonly coded by the number of spikes within a specific temporal window. However, the temporal information of event-based signals can be difficult to extract when using rate coding. In this work, we present a novel digital implementation of the model, called time difference encoder (TDE), for temporal encoding on event-based signals, which translates the time difference between two consecutive input events into a burst of output events. The number of output events along with the time between them encodes the temporal information. The proposed model has been implemented as a digital circuit with a configurable time constant, allowing it to be used in a wide range of sensing tasks that require the encoding of the time difference between events, such as optical flow-based obstacle avoidance, sound source localization, and gas source localization. This proposed bioinspired model offers an alternative to the Jeffress model for the interaural time difference estimation, which is validated in this work with a sound source lateralization proof-of-concept system. The model was simulated and implemented on a field-programmable gate array (FPGA), requiring 122 slice registers of hardware resources and less than 1 mW of power consumption.

Safe Experimentation in Optical Levitation of Charged Droplets Using Remote Labs.

The work presents an experiment that allows the study of many fundamental physical processes, such as photon pressure, diffraction of light or the motion of charged particles in electrical fields. In this experiment, a focused laser beam pointing upwards levitate liquid droplets. The droplets are levitated by the photon pressure of the focused laser beam which balances the gravitational force. The diffraction pattern created when illuminated with laser light can help measure the size of a trapped droplet. The charge of the trapped droplet can be determined by studying its motion when a vertically directed electrical field is applied. There are several reasons motivating this experiment to be remotely controlled. The investments required for the setup exceeds the amount normally available in undergraduate teaching laboratories. The experiment requires a laser of Class 4, which is harmful to both skin and eyes and the experiment uses voltages that are harmful.