Coffee and cashew nut dataset: A dataset for detection, classification, and yield estimation for machine learning applications.

Conventional methods of crop yield estimation are costly, inefficient, and prone to error resulting in poor yield estimates. This affects the ability of farmers to appropriately plan and manage their crop production pipelines and market processes. There is therefore a need to develop automated methods of crop yield estimation. However, the development of accurate machine-learning methods for crop yield estimation depends on the availability of appropriate datasets. There is a lack of such datasets, especially in sub-Saharan Africa. We present curated image datasets of coffee and cashew nuts acquired in Uganda during two crop harvest seasons. The datasets were collected over nine months, from September 2022 to May 2023. The data was collected using a high-resolution camera mounted on an Unmanned Aerial Vehicle . The datasets contain 3000 coffee and 3086 cashew nut images, constituting 6086 images. Annotated objects of interest in the coffee dataset consist of five classes namely: unripe, ripening, ripe, spoilt, and coffee_tree. Annotated objects of interest in the cashew nut dataset consist of six classes namely: tree, flower, premature, unripe, ripe, and spoilt. The datasets may be used for various machine-learning tasks including flowering intensity estimation, fruit maturity stage analysis, disease diagnosis, crop variety identification, and yield estimation.

Implementing Smartphone-Based Telemedicine for Cervical Cancer Screening in Uganda: Qualitative Study of Stakeholders' Perceptions.

BACKGROUND: In Uganda, cervical cancer (CaCx) is the commonest cancer, accounting for 35.7% of all cancer cases in women. The rates of human papillomavirus vaccination and CaCx screening remain low. Digital health tools and interventions have the potential to improve different aspects of CaCx screening and control in Uganda. OBJECTIVE: This study aimed to describe stakeholders' perceptions of the telemedicine system we developed to improve CaCx screening in Uganda. METHODS: We developed and implemented a smartphone-based telemedicine system for capturing and sharing cervical images and other clinical data, as well as an artificial intelligence model for automatic analysis of images. We conducted focus group discussions with health workers at the screening clinics (n=27) and women undergoing screening (n=15) to explore their perceptions of the system. The focus group discussions were supplemented with field observations and an evaluation survey of the health workers on system usability and the overall project. RESULTS: In general, both patients and health workers had positive opinions about the system. Highlighted benefits included better cervical visualization, the ability to obtain a second opinion, improved communication between nurses and patients (to explain screening findings), improved clinical data management, performance monitoring and feedback, and modernization of screening service. However, there were also some negative perceptions. For example, some health workers felt the system is time-consuming, especially when it had just been introduced, while some patients were apprehensive about cervical image capture and sharing. Finally, commonplace challenges in digital health (eg, lack of interoperability and problems with sustainability) and challenges in cancer screening in general (eg, arduous referrals, inadequate monitoring and quality control) also resurfaced. CONCLUSIONS: This study demonstrates the feasibility and value of digital health tools in CaCx screening in Uganda, particularly with regard to improving patient experience and the quality of screening services. It also provides examples of potential limitations that must be addressed for successful implementation.

Using machine learning for image-based analysis of sweetpotato root sensory attributes.

The sweetpotato breeding process involves assessing different phenotypic traits, such as the sensory attributes, to decide which varieties to progress to the next stage during the breeding cycle. Sensory attributes like appearance, taste, colour and mealiness are important for consumer acceptability and adoption of new varieties. Therefore, measuring these sensory attributes is critical to inform the selection of varieties during breeding. Current methods using a trained human panel enable screening of different sweetpotato sensory attributes. Despite this, such methods are costly and time-consuming, leading to low throughput, which remains the biggest challenge for breeders. In this paper, we describe an approach to apply machine learning techniques with image-based analysis to predict flesh-colour and mealiness sweetpotato sensory attributes. The developed models can be used as high-throughput methods to augment existing approaches for the evaluation of flesh-colour and mealiness for different sweetpotato varieties. The work involved capturing images of boiled sweetpotato cross-sections using the DigiEye imaging system, data pre-processing for background elimination and feature extraction to develop machine learning models to predict the flesh-colour and mealiness sensory attributes of different sweetpotato varieties. For flesh-colour the trained Linear Regression and Random Forest Regression models attained R2 values of 0.92 and 0.87, respectively, against the ground truth values given by a human sensory panel. In contrast, the Random Forest Regressor and Gradient Boosting model attained R2 values of 0.85 and 0.80, respectively, for the prediction of mealiness. The performance of the models matched the desirable R2 threshold of 0.80 for acceptable comparability to the human sensory panel showing that this approach can be used for the prediction of these attributes with high accuracy. The machine learning models were deployed and tested by the sweetpotato breeding team at the International Potato Center in Uganda. This solution can automate and increase throughput for analysing flesh-colour and mealiness sweetpotato sensory attributes. Using machine learning tools for analysis can inform and quicken the selection of promising varieties that can be progressed for participatory evaluation during breeding cycles and potentially lead to increased chances of adoption of the varieties by consumers.

Time-aware deep neural networks for needle tip localization in 2D ultrasound.

PURPOSE: Accurate placement of the needle is critical in interventions like biopsies and regional anesthesia, during which incorrect needle insertion can lead to procedure failure and complications. Therefore, ultrasound guidance is widely used to improve needle placement accuracy. However, at steep and deep insertions, the visibility of the needle is lost. Computational methods for automatic needle tip localization could improve the clinical success rate in these scenarios. METHODS: We propose a novel algorithm for needle tip localization during challenging ultrasound-guided insertions when the shaft may be invisible, and the tip has a low intensity. There are two key steps in our approach. First, we enhance the needle tip features in consecutive ultrasound frames using a detection scheme which recognizes subtle intensity variations caused by needle tip movement. We then employ a hybrid deep neural network comprising a convolutional neural network and long short-term memory recurrent units. The input to the network is a consecutive plurality of fused enhanced frames and the corresponding original B-mode frames, and this spatiotemporal information is used to predict the needle tip location. RESULTS: We evaluate our approach on an ex vivo dataset collected with in-plane and out-of-plane insertion of 17G and 22G needles in bovine, porcine, and chicken tissue, acquired using two different ultrasound systems. We train the model with 5000 frames from 42 video sequences. Evaluation on 600 frames from 30 sequences yields a tip localization error of [Formula: see text] mm and an overall inference time of 0.064 s (15 fps). Comparison against prior art on challenging datasets reveals a 30% improvement in tip localization accuracy. CONCLUSION: The proposed method automatically models temporal dynamics associated with needle tip motion and is more accurate than state-of-the-art methods. Therefore, it has the potential for improving needle tip localization in challenging ultrasound-guided interventions.

Demonstrating delay-based reservoir computing using a compact photonic integrated chip.

Photonic delay-based reservoir computing (RC) has gained considerable attention lately, as it allows for simple technological implementations of the RC concept that can operate at high speed. In this paper, we discuss a practical, compact and robust implementation of photonic delay-based RC, by integrating a laser and a 5.4 cm delay line on an InP photonic integrated circuit. We demonstrate the operation of this chip with 23 nodes at a speed of 0.87 GSa/s, showing performances that is similar to previous non-integrated delay-based setups. We also investigate two other post-processing methods to obtain more nodes in the output layer. We show that these methods improve the performance drastically, without compromising the computation speed.

Training Passive Photonic Reservoirs With Integrated Optical Readout.

As Moore's law comes to an end, neuromorphic approaches to computing are on the rise. One of these, passive photonic reservoir computing, is a strong candidate for computing at high bitrates (>10 Gb/s) and with low energy consumption. Currently though, both benefits are limited by the necessity to perform training and readout operations in the electrical domain. Thus, efforts are currently underway in the photonic community to design an integrated optical readout, which allows to perform all operations in the optical domain. In addition to the technological challenge of designing such a readout, new algorithms have to be designed in order to train it. Foremost, suitable algorithms need to be able to deal with the fact that the actual on-chip reservoir states are not directly observable. In this paper, we investigate several options for such a training algorithm and propose a solution in which the complex states of the reservoir can be observed by appropriately setting the readout weights, while iterating over a predefined input sequence. We perform numerical simulations in order to compare our method with an ideal baseline requiring full observability as well as with an established black-box optimization approach (CMA-ES).

Numerical demonstration of neuromorphic computing with photonic crystal cavities.

We propose a new design for a passive photonic reservoir computer on a silicon photonics chip which can be used in the context of optical communication applications, and study it through detailed numerical simulations. The design consists of a photonic crystal cavity with a quarter-stadium shape, which is known to foster interesting mixing dynamics. These mixing properties turn out to be very useful for memory-dependent optical signal processing tasks, such as header recognition. The proposed, ultra-compact photonic crystal cavity exhibits a memory of up to 6 bits, while simultaneously accepting bitrates in a wide region of operation. Moreover, because of the inherent low losses in a high-Q photonic crystal cavity, the proposed design is very power efficient.

Low-Loss Photonic Reservoir Computing with Multimode Photonic Integrated Circuits.

We present a numerical study of a passive integrated photonics reservoir computing platform based on multimodal Y-junctions. We propose a novel design of this junction where the level of adiabaticity is carefully tailored to capture the radiation loss in higher-order modes, while at the same time providing additional mode mixing that increases the richness of the reservoir dynamics. With this design, we report an overall average combination efficiency of 61% compared to the standard 50% for the single-mode case. We demonstrate that with this design, much more power is able to reach the distant nodes of the reservoir, leading to increased scaling prospects. We use the example of a header recognition task to confirm that such a reservoir can be used for bit-level processing tasks. The design itself is CMOS-compatible and can be fabricated through the known standard fabrication procedures.

All-optical NRZ wavelength conversion based on a single hybrid III-V/Si SOA and optical filtering.

We demonstrate all-optical wavelength conversion (AOWC) of non-return-to-zero (NRZ) signal based on cross-gain modulation in a single heterogeneously integrated III-V-on-silicon semiconductor optical amplifier (SOA) with an optical bandpass filter. The SOA is 500 µm long and consumes less than 250 mW electrical power. We experimentally demonstrate 12.5 Gb/s and 40 Gb/s AOWC for both wavelength up and down conversion.