Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add more filters










Database
Language
Publication year range
1.
Data Brief ; 52: 110026, 2024 Feb.
Article in English | MEDLINE | ID: mdl-38260861

ABSTRACT

Date fruit grading and inspection is a challenging and crucial process in the industry. The grading process requires skilled and experienced labour. Moreover, the labour turnover in the date processing industries has been increased regularly. Therefore, due to the lack of trained labour, the quality of date fruit is often compromised. It leads to fruit wastage and instability of fruit prices. Currently, deep learning algorithms have achieved the research community's attention in solving the problems in the agriculture sector. The pre-trained models like VGG16 and VGG19 have been applied for the classification of date fruit [1,2]. Furthermore, machine learning techniques like K-Nearest Neighbors, Support Vector Machine, Random Forest and a few others [3], [4], [5], [6] have been used for grading of date fruit. Therefore, classification and sorting of date fruit problems have become common in the industry. The classification and grading of date fruit needed a neat and clean dataset. In this article, an indigenous and state-of-the-art dataset of date fruit is offered. The dataset contains images of four date fruit varieties. It consists of 3004 pre-processed images of different classes and grades. Moreover, images have been sorted based on size as large, medium, and small. Additionally, it is graded based on the quality as grade 1, grade 2, and grade 3. This dataset is separated into eighteen different directories for the facilitation of the researchers. It may contribute to develop an intelligent system to grade and inspect date fruit. This system may add value to the sustainable economic growth of fruit processing industries and farmers locally and internationally.

2.
Sensors (Basel) ; 10(3): 1447-72, 2010.
Article in English | MEDLINE | ID: mdl-22294881

ABSTRACT

Full network level privacy has often been categorized into four sub-categories: Identity, Route, Location and Data privacy. Achieving full network level privacy is a critical and challenging problem due to the constraints imposed by the sensor nodes (e.g., energy, memory and computation power), sensor networks (e.g., mobility and topology) and QoS issues (e.g., packet reach-ability and timeliness). In this paper, we proposed two new identity, route and location privacy algorithms and data privacy mechanism that addresses this problem. The proposed solutions provide additional trustworthiness and reliability at modest cost of memory and energy. Also, we proved that our proposed solutions provide protection against various privacy disclosure attacks, such as eavesdropping and hop-by-hop trace back attacks.


Subject(s)
Computer Security , Telemetry , Algorithms , Computer Communication Networks , Geography , Humans , Models, Theoretical
3.
Sensors (Basel) ; 9(8): 5989-6007, 2009.
Article in English | MEDLINE | ID: mdl-22454568

ABSTRACT

Existing anomaly and intrusion detection schemes of wireless sensor networks have mainly focused on the detection of intrusions. Once the intrusion is detected, an alerts or claims will be generated. However, any unidentified malicious nodes in the network could send faulty anomaly and intrusion claims about the legitimate nodes to the other nodes. Verifying the validity of such claims is a critical and challenging issue that is not considered in the existing cooperative-based distributed anomaly and intrusion detection schemes of wireless sensor networks. In this paper, we propose a validation algorithm that addresses this problem. This algorithm utilizes the concept of intrusion-aware reliability that helps to provide adequate reliability at a modest communication cost. In this paper, we also provide a security resiliency analysis of the proposed intrusion-aware alert validation algorithm.

SELECTION OF CITATIONS
SEARCH DETAIL
...