Search results

This paper proposes a novel deep learning based method towards the identification of a pistachio tree cultivar from its image.

The investigated scope of this study includes Iranian commercial pistachios (Jumbo, Long, Round and Super long) trees. Effective use of high-resolution images with standard deep models is addressed in this study. A novel image patches extraction method is also used to boost the number of samples and dataset augmentation. In the proposed method, handcrafted ORB features are used to detect and extract patches which may contain identifiable information. An innovative algorithm is proposed for searching and extracting these patches. After extracting patches from initial images, a Convolutional Neural Network, named EfficientNet-B1, was fine-tuned on it. In the testing phase, several patches were extracted from the prompted image using the ORB-based method, and the results of their prediction were consolidated. In this method, patch prediction scores were in descending order, sorted by the highest score in a list, and finally, the average of a few list tops was calculated and the final decision was made.

Examining the proposed method on the test images led to an achievement of a recognition rate of 97.2% accuracy. Investigation of decision-making in the test dataset could reveal that this method outperformed human experts.

Cultivar identification using deep learning methods, due to their high recognition speed, lack of specialist requirement, and independence from human decision-making error is considered as a breakthrough in horticultural science. Variety cultivars of pistachio trees possess variant characteristics or traits, accordingly recognising cultivars is crucial to reduce the costs, prevent damages and harvest the optimal yields.

Despite the availability of prior studies on the Internet of Things (IoT) development, they have largely focused on challenges associated with evolving IoT. Hence, identifying requirements for IoT development, as a multifaceted phenomenon, whereby the challenges would be tackled remains a less-explored valuable line of inquiry. The purpose of this paper is to present a holistic view of crucial building blocks of IoT development, in order to fill this gap.

This paper conducts empirical research using a grounded theory (GT), centering on semi-structured interviews with 25 experts involved in the Iranian IoT development effort. Data were analyzed by using MAXQDA software.

This study presents a conceptual framework of requirements for IoT development, consisting of 14 concepts and 5 categories. The findings reveal that strategic, interactive, institutional, market-oriented and information and communication technology (ICT) infrastructure requirements play a salient role in facilitating IoT development.

The findings of this study shed some light on the momentous aspects of IoT development. Practitioners including governmental policymakers, industry and private sectors could benefit from the policy recommendations offered in this study in terms of strategic viewpoint, legal issues, business perspective and technological readiness.

From the methodological aspect, the present research is among the first studies on utilizing GT for exploration of requirements for IoT development. From the theoretical perspective, a remarkable achievement of this study is to profoundly discover some less-explored concepts of IoT development such as commercialization, feasibility study, futurology and institutional aspects. Furthermore, findings of this study highlight the contribution of innovation systems theory for the IoT development area in terms of alignment of the emerged requirements for IoT development with the functions of this theory.

Currently, the health system is a treatment-oriented system focused on service providers. In this system, the main focus is on the health market, with little attention on insured. One way to get out of existing conditions is to empower the insured in order to involve them actively in maintaining and improving health. The paper aims to discuss these issues.

This qualitative study was done using the content analysis method. Based on the purposive sampling method and theoretical saturation criterion, 24 individuals including 12 health insurance experts and 12 insured participated in the study in 2018. The semi-structured interview method was used to collect data. Data were analyzed using MAXQDA10 software.

Having analyzed the interviews, 750 codes were obtained. These codes were categorized into two categories of “insurance experts” and “insured” and ten subcategories of “informing and educating, cost reduction, intersectional activities, expectations from the insured, services package, access to services, inability to pay costs, participation, and expectations from the insurance organization.”

This qualitative study was conducted to assess and determine the effective strategies for empowering the insured under health insurance. The results of this study are helpful to the health insurance organizations and health decision makers to detect the effective ways to develop the quality of insurance services, improve the status of insured, and increase access to health care goods and services.