The classification of human face shapes, a pivotal aspect of one's appearance, plays a crucial role in diverse fields like beauty, cosmetics, healthcare, and security. In this paper, we present a ...multi-step methodology for face shape classification, harnessing the potential of transfer learning and a pretrained EfficientNetV2S neural network. Our approach comprises key phases, including preprocessing, augmentation, training, and testing, ensuring a comprehensive and reliable solution. The preprocessing step involves precise face detection, cropping, and image scaling, laying a solid foundation for accurate feature extraction. Our methodology utilizes a publicly available dataset of female celebrities, comprising five face shape classes: heart, oblong, oval, round, and square. By augmenting this dataset during training, we magnify its diversity, enabling better generalization and enhancing the model's robustness. With the EfficientNetV2S neural network, we employ transfer learning, leveraging pretrained weights to optimize accuracy, training speed, and parameter size. The result is a highly efficient and effective model, which outperforms state-of-the-art approaches on the same dataset, boasting an outstanding overall accuracy of 96.32%. Our findings demonstrate the efficiency of our approach, proving its potential in the field of face shape classification. The success of our methodology holds promise for various applications, offering valuable insights into beauty analysis, cosmetic recommendations, and personalized healthcare.
Numerous advanced methods have been applied throughout the years for the use in Network Intrusion Detection Systems (NIDS). Among these are various Deep Learning models, which have shown great ...success for attack classification. Nevertheless, false positive rate and detection rate of these systems remains a concern. This is mostly because of the low-sample, imbalanced nature of realistic datasets, which make models challenging to train.
Considering this, we applied a novel semi-supervised EC-GAN method for network flow classifi- cation of CIC-IDS-2017 dataset. EC-GAN uses synthetic data to aid the training of a supervised classifier on low-sample data. To achieve this, we modified the original EC-GAN to work with tabular data. In our approach, WCGAN-GP is used for synthetic tabular data generation, while a simple deep neural network is used for classification. The conditional nature of WCGAN-GP diminishes the class imbalance problem, while GAN itself solves the low-sample problem. This approach was successful in generating believable synthetic data, which was consequently used for training and testing the EC-GAN.
To obtain our results, we trained a classifier on progressively smaller versions of the CIC-DIS-2017 dataset, first via a novel EC-GAN method and then in the conventional way, without the help of synthetic data. We then compared these two sets of results with another author's results using accuracy, false positive rate, detection rate and macro F1 score as metrics. Our results showed that supervised classifier trained with EC-GAN can achieve significant results even when trained on as little as 25% of the original imbalanced dataset.
This paper proposes an open ontology for self-sustainable human settlements in an effort to set the common language for modelling self-sustainable systems and address the issues regarding ...heterogeneity of physical devices, protocols, software components, data and message formats and other relevant factors, which proved to be unavoidable in implementations of smart systems in the domain of self-sustainability, smart homes, Internet of things, smart energy management systems, demand side systems, and related areas of research and engineering. Although the existing body of research is showing significant results in related, specialized research areas, currently there is no common formal language available which would bring the diversity of such research efforts under a single umbrella and thus enhance and integrate such efforts, which is often pointed out by the researchers in related fields. This paper discuses self- sustainable systems and associated areas, argues the need for the ontology development, presents its scope, development methodology, domain's architecture and metamodel, and finally the proposed ontology itself, implemented in an open OWL format.
In the field of face biometrics, finding the identity of a person in an image is most researched, but there are other, soft biometric information that are equally as important, such as age, gender, ...ethnicity or emotion. Nowadays, ethnicity classification has a wide application area and is a prolific area of research. This paper gives an overview of recent advances in ethnicity classification with focus on convolutional neural networks (CNNs) and proposes a new ethnicity classification method using only the middle part of the face and CNN. The paper also compares the differences in results of CNN with and without plotted landmarks. The proposed model was tested using holdout testing method on UTKFace dataset and FairFace dataset. The accuracy of the model was 80.34% for classification into five classes and 61.74% for classification into seven classes, which is slightly better than state-of-the-art, but it is also important to note that results in this paper are obtained by using only the middle part of the face which reduces the time and resources necessary.
This paper gives an overview of development in research concerning the influence of video games on cognitive development and intelligence. The first part of the paper mentions three categories used ...by different researchers in their research: generally speaking, the development of constructs and commercial games. StarCraft is mentioned in the paper, one of the most complex strategical games of all time, and its influence on professional players in eSport. Additionally, it presents a taxonomy of strategy games compared to real world situations, such as crisis management and control. The papers indexed in Scopus and Web of Science databases are chosen for this research since they are based on the cognitive relations between the games and players. One of the conclusions is that games can influence the enhancement of cognitive abilities in both directions.
A newly developed agent-based framework for modeling, simulation, and evaluation of resource management in self-sustainable human settlements is presented, along with the ability of the framework to ...prolong the self-sustainability of the observed human settlement system in the simulation environment. In this study the focus is on the analysis of a conducted water management simulation based on observations of an existing eco-village in Croatia, in the context of producing, storing, and consuming water as a resource. The conducted research shows that the developed framework was able to prolong the self-sustainability of localized water production, storage, and consumption dynamics when managing the water allocation with the use of self-sustainability mechanisms, in comparison to water management without using such mechanisms, under the same initial conditions. The work is placed within the context of sustainable development, Internet of Things, as well as Environmental Internet of Things areas of research, analyzing the ambiguous relationship between the terms 'sustainable development' and 'self-sustainability'.
•Establishes a new direction in software engineering for the Internet of Things.•Argues that we will soon have to manage systems where millions of agents interact.•Proposes organization theory as the ...necessary foundation ontology.•Provides examples of possible application areas•Gives a roadmap for future developments.
Display omitted
Computing is increasingly ubiquitous, with everyday items including smartphones, cars, clothes and household appliances gaining increasingly sophisticated computing and communication capacities. With the development of the Internet of Things, it is just a matter of time before devices have to collaborate and compete with each other, in order to provide better services to mankind.
These embedded software systems are increasingly autonomous and connected, and can thus be modeled as multiagent systems (MAS). Only 30 years ago it was science fiction that over a billion people will exchange billions of e-mails on a daily basis. Today a scenario of millions of collaborating agents sometimes embedded in gadgets and appliances, sometimes in form of networked and big data services, may also sound futuristic. However given the current rate of development in electronics, we will soon have to manage large scale MAS where millions of agents exist, collaborate and compete. Organization theory provides the necessary methodology to approach complex systems in order to design, implement and strategically manage them towards success.
In this paper a state-of-the-art on organizational design techniques for large-scale MAS will be presented, missing advancements will be identified and a roadmap for future developments and application scenarios will be provided.
An Active Game Bot Detection with Security Bots Tomičić, Igor; Peharda, Tomislav; Bernik, Andrija
Central European Conference on Information and Intelligent Systems,
01/2021
Conference Proceeding
Odprti dostop
Cheating in computer games can cause legit players to feel deprived, lose their interest and in time leave the game - which further leads to the decrease of profit in the gaming industry. Avoiding ...such a scenario is the main focus ofresearch papers dealing with game cheating and cheat detection mechanisms within computer games, where there is a seemingly simple question to answer - is this player a legit human player, or an artificial bot? Most of the research is trying to identify patterns that could give away the presence of the bot, and in the same time, research is being done on building the bots with human-like behaviours which might deceive such mechanisms. In this paper, we present an active bot detection method implemented within a "security bot" - an artificial player which is infiltrated within the game and is able to identify suspicious game players, approach them, and perform a form of the Turing test on them, in order to identify possible cheating bots which have successfully deceived all the existing passive detection methods.
In this work-in-progress article we focus on the application of programming language for communication flows specification in multi-agent systems on real-world use cases. Agents orchestration in ...multi-agent systems architecture may be very troublesome, mainly due to agents being independent units that may be implemented differently. The proposed programming language for communication flows specification attempts to overcome this challenge by providing explicit communication flows definitions, that agents' communications component relies on, which enables enhanced orchestration capabilities. Use cases that are covered in this paper are in the domains of streaming audio, video, and sensors data, and provide a couple of examples of how the proposed programming language may be used.
Cognitive agents are artificial intelligence systems that are able to communicate in a way that is as much as possible acceptable to humans. Technologies like natural language processing (NLP), text ...to speech (TTS), speech to text (STT) and motion capture (MoCap) are usually applied to provide such an interface. In this work-in-progess paper we present the current state of the Beautiful ARtificial Intelligence Cognitive Agent (B.A.R.I.C.A.) infrastructure that we have developed. This infrastructure allows for the implementation of open source cognitive agents in a wide spectrum of domains that are able to communicate using the Croatian language. The aim of this study is to analyze possible applications of B.A.R.I.C.A. to smart mobility in order to highlight possible gaps to be overcome, applications that are possible as well as provide guidelines for implementation.