Precision agriculture allows for the sustainable improvement of agricultural products by introducing technologies that provide crop-specific data, which supervised algorithms can process. However, supervised algorithm...
详细信息
ISBN:
(纸本)9789819754403;9789819754410
Precision agriculture allows for the sustainable improvement of agricultural products by introducing technologies that provide crop-specific data, which supervised algorithms can process. However, supervised algorithms require expert-labeled data, which can be highly expensive in agricultural applications. Given this problem, active learning (AL) arises as an alternative to reduce the need to annotate training examples manually. This paper analyzes the use of AL in classifying agricultural crop images. To evaluate AL, two datasets with information on fruit and vegetable images were used on two neural network-based algorithms. The classification results indicate that AL reduced the number of training examples to achieve a given performance. Additionally, the pseudo-labels of the supervised algorithms, a stopping criterion, and the explainability of the predictions were analyzed. These analyses allowed to assess the applicability of AL in agriculture to understand the learning process of the supervised algorithms.
The paper provides an overview of advancements in bird detection and recognition systems using Machine Learning and Artificial Intelligence (AI). It highlights the increasing adoption of wind farms amid rising electri...
详细信息
ISBN:
(纸本)9783031820724;9783031820731
The paper provides an overview of advancements in bird detection and recognition systems using Machine Learning and Artificial Intelligence (AI). It highlights the increasing adoption of wind farms amid rising electricity demand, underscoring their environmental impact on avian species. To address these ecological challenges, the development of bird recognition solutions is crucial. The paper analyzes various techniques, including radar systems, sound recognition, Convolutional Neural networks (CNNs), electromagnetic detection, YOLOv5, and color segmentation, discussing their features, computational costs, and constraints. It concludes that while deep learning models offer superior results, they need a balance between accuracy and speed, alongside training with large and representative datasets. Ultimately, the paper aims to contribute to efforts aimed at mitigating the adverse effects of wind farms on bird populations through advanced technologies. Additionally, through this paper we intend to shed light over the state of the art on bird detection systems and provide insights that intends to solve some of these drawbacks.
We used deep learning methods to create an innovative system for early detection of depression based on user comments on social networks. This revolutionary approach exploits large amounts of textual data available on...
详细信息
ISBN:
(纸本)9783031850660;9783031850677
We used deep learning methods to create an innovative system for early detection of depression based on user comments on social networks. This revolutionary approach exploits large amounts of textual data available online to identify depression. The data set originates from the eRisk 2022 competition. Thanks to natural language and statistical modeling techniques, our system can analyze user comments and detect their depression. We applied deep learning methods, in particular the BiLSTM(Bidirectional Long Short-Term Memory) model. Using the approach, we obtained an F-score of 42.96%.
The Internet of Things describes the network of electronic devices that are consistently interconnected via Internet. These devices, which encompass sensors, software, and similar mediums, interact with other devices ...
详细信息
ISBN:
(纸本)9789819754403;9789819754410
The Internet of Things describes the network of electronic devices that are consistently interconnected via Internet. These devices, which encompass sensors, software, and similar mediums, interact with other devices or systems. As the quantity of these interconnected devices on the Internet has surged dramatically, there has been an increasing interest among certain malicious individuals to exploit these devices for their own gain. Anotable instance of this is illustrated by the Mirai Botnet case. To counteract the potential manipulation of these devices by malicious entities, researchers have embarked on proposing models to comprehend the behaviors of these Botnets and their propagation patterns. In this sense, we aim to investigate one of these models, namely the NIMFA model. This model is noteworthy for its impressive scalability, enabling effective modeling of networks with up to 100,000 nodes with quadratic time complexity. Consequently, we propose to design a scalable SIS stochastic epidemiological model based on the N-intertwined Mean-Field Approximation (NIMFA) model for security analysis in IoT networks. Moreover, the outcomes of the NIMFA model closely align with those of other models, such as the Gillespie Simulation Algorithm.
Ocean exploration and inspection missions involving underwater robotic systems have gained increasing popularity in various domains such as marine science, archaeology, and defense in recent years. However, deploying ...
详细信息
ISBN:
(纸本)9783031809453;9783031809460
Ocean exploration and inspection missions involving underwater robotic systems have gained increasing popularity in various domains such as marine science, archaeology, and defense in recent years. However, deploying vessels and robotic solutions for such research activities entails significant costs for acquisition and maintenance. This is primarily due to the logistical challenges involved in transporting equipment between locations, which necessitates a substantial financial investment, in addition to expenses associated with crew and research personnel. Effective planning of survey campaigns is crucial to avoid costly missteps arising from poor organization. It ensures that expenditures are justified and that objectives are achieved without unnecessary setbacks or errors. In this context, the utilization of simulation methodologies adds invaluable value in mitigating costs and exploring various solutions before the mission is carried out in the real world. Their utility extends beyond the examination of specific sensors or setups;they are also a valuable tool for planning different campaigns with different mission objectives. In this paper, a simulation framework that integrates an Autonomous Underwater Vehicle with a Multibeam Echo Sounder as the perception sensor is presented. The objective is to streamline acoustic survey mission planning and generate synthetic acoustic image data incorporating the modeling of typical error sources, simplifying the evaluation of output data for real applications. This system can also be utilized as a Software-in-the-loop system for testing and verification of control systems and algorithms.
The use of Machine Learning (ML) models in cybersecurity solutions requires high-quality data that is stripped of redundant, missing, and noisy information. By selecting the most relevant features, data integrity and ...
详细信息
ISBN:
(纸本)9783031764585;9783031764592
The use of Machine Learning (ML) models in cybersecurity solutions requires high-quality data that is stripped of redundant, missing, and noisy information. By selecting the most relevant features, data integrity and model efficiency can be significantly improved. This work evaluates the feature sets provided by a combination of different feature selection methods, namely Information Gain, Chi-Squared Test, Recursive Feature Elimination, Mean Absolute Deviation, and Dispersion Ratio, in multiple IoT network datasets. The influence of the smaller feature sets on both the classification performance and the training time of ML models is compared, with the aim of increasing the computational efficiency of IoT intrusion detection. Overall, the most impactful features of each dataset were identified, and the ML models obtained higher computational efficiency while preserving a good generalization, showing little to no difference between the sets.
The prediction of stock prices has recently gained considerable attention as a complex and challenging issue within the realms of economics and finance. Stock prices are affected by various factors, such as the busine...
详细信息
ISBN:
(纸本)9783031820724;9783031820731
The prediction of stock prices has recently gained considerable attention as a complex and challenging issue within the realms of economics and finance. Stock prices are affected by various factors, such as the business environment, stock market operations, inflation, and unexpected events. Since the stock market is volatile and nonlinear, finding the most effective model to forecast stock prices is one of the most challenging problems. Researchers have increasingly explored various Machine Learning (ML) and Deep Learning (DL) models to address this issue due to their capacity to handle time series data and nonlinear patterns. These models often outperform traditional approaches in predicting stock prices with high accuracy and lower root mean square error (RMSE). This paper reviews various works that have utilized ML approaches for stock price prediction, covering research published between 2017 and 2023. This literature review discusses various techniques, their performance, limitations, and future work. We assess the latest techniques in many studies, including ML and DL models. The findings of this review conclude that Neural networks (NNs) are the most commonly used approaches in predicting stock prices due to their effectiveness in detecting complex patterns in financial data.
Graphical argument structures such as Goal Structuring Notation (GSN) are increasingly being used in practice as a means to provide safety assurance to stakeholders, such as regulatory authorities, regarding the depen...
详细信息
ISBN:
(纸本)9783031718472;9783031718489
Graphical argument structures such as Goal Structuring Notation (GSN) are increasingly being used in practice as a means to provide safety assurance to stakeholders, such as regulatory authorities, regarding the dependability and safety of a system. These argument-based assurance cases are utilized in practice to demonstrate that a system is suitable for its intended use. In this paper, we present Structured GSN (SGSN), an open-source tool to create and edit assurance cases. In addition to basic functionalities related to the creation of GSN, we added two types of analysis, syntactic analysis which checks if the developed GSN satisfies structured criteria, and semantic analysis which checks compartmental properties. For the semantic analysis, we mapped the GSN to a formal model i.e., Markov Decision Process (MDP), and checked properties expressed in PCTL using a probabilistic model-checker.
作者:
Bula, IneseUniv Latvia
Dept Math Jelgavas St 3 LV-1004 Riga Latvia Univ Latvia
Inst Math & Comp Sci Raina Bulv 29 LV-1048 Riga Latvia
In the paper a convex game with discontinuous payoff functions is considered. This paper introduces the concept of quasi-Nash equilibrium, which allows us to analyze games with discontinuous payoff functions by approx...
详细信息
ISBN:
(纸本)9783031739965;9783031739972
In the paper a convex game with discontinuous payoff functions is considered. This paper introduces the concept of quasi-Nash equilibrium, which allows us to analyze games with discontinuous payoff functions by approximating them with continuous and concave functions. We show that if the approximation is close enough, then the quasi-Nash equilibrium is close to the true Nash equilibrium (if it exists).
Blockchain is one of the core technologies of the present world. Its decentralized architecture has received extensive research attention. Peer-to-peer technology has given freedom and transparency to the user. With t...
详细信息
ISBN:
(数字)9789819754410
ISBN:
(纸本)9789819754403;9789819754410
Blockchain is one of the core technologies of the present world. Its decentralized architecture has received extensive research attention. Peer-to-peer technology has given freedom and transparency to the user. With the implementation of blockchain inside investment, finance, or trading platforms the problem of security, transparency, and trust can also be addressed. The most suitable consensus protocol can help in fault tolerance. Distribution of blockchain-like hyper ledger promises strong consistency of state and can perform thousands of operations at the same time. Blockchain technology can be helpful in tracing carbon footprints and can be proven helpful in controlling global warming. This paper illustrates what blockchain is, its different consensus mechanisms, its implementation inside an application, its distribution hyper ledger, and how blockchain can be used for tracing carbon footprints.
暂无评论