Use of rule base data mining algorithm for intrusion detection

Elekar, Kailas; Waghmare, M.M.; Priyadarshi, Amrit

doi:10.1109/pervasive.2015.7087051

Cited by 11 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When analyzing Table III, it possible to conclude that the best classification algorithms, at the performance level, are as follows: trees.RandomForest [16] [14], lazy.IBk [15] [13], trees.J48 [9] [12] and rules.PART [11] [18]. We have obtained figures, like the one shown in Figure 5, to the analyse the best nights resulting from the study for the selected four algorithms/models.…”

Section: Tests and Resultsmentioning

confidence: 99%

Non-invasive monitoring with Ballistocardiographic sensors for sleep management

Silva

Marinheiro

2021

2021 Telecoms Conference (ConfTELE)

View full text Add to dashboard Cite

Sleep has an important impact on people's daily lives. A successful methodology for monitoring sleep is Polysomnography (PSG). This is an accurate and reliable approach but, unfortunately, very invasive. PSG uses expensive sensors that must be positioned by experts, what, in practice, makes its adoption only viable in hospital setups. Therefore, there is a demand for better non-invasive alternatives, such as Ballistocardiography (BCG). BCG uses cheaper sensors, easy to install and ideal for domestic use. This allows its integration in solutions that manage sleep, using mobile apps not only for presenting valuable information to users but may also for acting on the environment, through actuators, such as sound.This work uses this principle to help users to wake up smoothly. Sleep monitoring is performed with Murata SCA11H BCG external sensors. Low-pass filters have been implemented, using a sliding exponential average, for all metrics. The Random Forest algorithm was then selected for sleep phase classification, that presented the best performance when using the Weka exploration tool for learning methods. With the implemented model, it has been proved that four sleep phases are predicted. It was then possible to define a strategy for avoiding waking up alarms to be fired during deep sleep. It consists on the analysis 15 minutes prior to the alarm and, when deep sleep is detected, a relaxing sound is played.This work demonstrated that non-invasive sleep monitoring can be used to actuate on, and improve, the user environment, in a home setup with cheap sensors.

show abstract

Section: Tests and Resultsmentioning

confidence: 99%

Non-invasive monitoring with Ballistocardiographic sensors for sleep management

Silva

Marinheiro

2021

2021 Telecoms Conference (ConfTELE)

View full text Add to dashboard Cite

show abstract

“…Data yang digunakan untuk mengetahui kinerja dari fuzzy Sugeno dalam penelitian ini diperoleh dari pengusaha kain tenun Mlaki Wanarejan Utara Pemalang, berupa jumlah produksi kain tenun, yang dipengaruhi oleh banyaknya biaya produksi, permintaan dari pelanggan, dan stok yang tersedia. Selanjutnya, data tersebut digunakan untuk membangun sebuah rule dengan menggunakan pohon keputusan random tree yang dieksekusi oleh tools WEKA [4]. Digunakannya random tree salah satunya untuk membuat rule secara otomatis dari data yang tersedia tanpa perlu berkonsultasi dengan pakar [5], selain itu untuk memperkenalkan random tree dalam bidang penelitian karena masih sedikitnya penelitian yang menggunakan pohon keputusan tersebut.…”

Section: Pendahuluanunclassified

Kinerja Logika Fuzzy Sugeno dalam Menangani Prediksi Kain Tenun dengan Kombinasi Random Tree dalam Membangun Rule

Tundo

2021

j. nas. pendidik. teknik. inform.

View full text Add to dashboard Cite

This study describes the performance of Sugeno fuzzy logic in determining the amount of woven fabric production by using a combination of random tree decision trees in forming rules. The criteria used in determining the amount of production, namely, production costs, demand, and stock obtained from woven fabric entrepreneurs in Mlaki Wanarejan Utara Pemalang. The random tree decision tree is used, one of which is to automatically generate rules from the available data without consulting with experts, in addition to introducing random trees in the field of research because there are still few studies using this decision tree. The results of this study, it was found that the accuracy while the prediction results tested obtained an Average Forecasting Error Rate (AFER) of 42% with a value 58% truth after being compared with the actual production data.Keywords : Fuzzy Logic, Fuzzy Sugeno Method, Rule, Random tree, Prediction.

show abstract

“…Com o objetivo de avaliar a estratégia de aprendizagem de máquina, foram utilizados os conjuntos de treinamento e teste kddcup.data 10 percent 7 e corrected 8 . A KDD Cup 99 é considerada umas das principais bases utilizadas na avaliação de mecanismos para detecção de tentativas de ataques a servidores de rede [26].…”

Section: Avaliação Da Estratégia Baseada Em Aprendizagem De Máquinaunclassified

[SA]2: uma abordagem consciente de situação para segurança em infraestruturas computacionais

Machado

Almeida

Rosa

et al. 2016

Revista Brasileira De Computação Aplicada

View full text Add to dashboard Cite

As tecnologias computacionais estão cada vez mais integradas à vida cotidiana das pessoas, nas comunicações, no setor financeiro e até no entretenimento. Entretanto, todas as facilidades e oportunidades por elas oferecidas também acabam sendo objeto de interesse de pessoas mal-intencionadas, que usam esses recursos para cometer fraudes e ataques contra os sistemas de informação e/ou seus usuários. Logo, as organizações muitas vezes implementam tecnologias de propósitos específicos para promover a segurança de seus sistemas. Apesar de essas tecnologias auxiliarem na segurança do ambiente computacional, elas não proporcionam uma visão do ambiente como um todo. Tendo isso em vista, este artigo apresenta uma abordagem ciente de situação para segurança de ambientes computacionais, denominada [SA] 2. A solução destaca-se pela arquitetura concebida para o fornecimento da ciência de situação, explorando diferentes funcionalidades desde a coleta, passando por um processamento híbrido de contexto, o armazenamento de dados contextuais e a decorrente atuação. A abordagem foi avaliada em um ambiente formado por servidores destinados a prover serviços de internet, mostrando-se estável e flexível quanto à visibilidade de aspectos de segurança em ambientes computacionais, possibilitando a detecção de situações de interesse a partir de eventos provenientes de fontes heterogêneas, atendendo às premissas de flexibilidade e dinamicidade das atuais infraestruturas de redes. Palavras-chave: Ciência de situação. Processamento de eventos. Segurança da informação.

show abstract

Use of rule base data mining algorithm for intrusion detection

Cited by 11 publications

References 18 publications

Non-invasive monitoring with Ballistocardiographic sensors for sleep management

Non-invasive monitoring with Ballistocardiographic sensors for sleep management

Kinerja Logika Fuzzy Sugeno dalam Menangani Prediksi Kain Tenun dengan Kombinasi Random Tree dalam Membangun Rule

[SA]2: uma abordagem consciente de situação para segurança em infraestruturas computacionais

Contact Info

Product

Resources

About