RESUMEN

Widespread and ever-increasing cybersecurity attacks against Internet of Things (IoT) systems are causing a wide range of problems for individuals and organizations. The IoT is self-configuring and open, making it vulnerable to insider and outsider attacks. In the IoT, devices are designed to self-configure, enabling them to connect to networks autonomously without extensive manual configuration. By using various protocols, technologies, and automated processes, self-configuring IoT devices are able to seamlessly connect to networks, discover services, and adapt their configurations without requiring manual intervention or setup. Users' security and privacy may be compromised by attackers seeking to obtain access to their personal information, create monetary losses, and spy on them. A Denial of Service (DoS) attack is one of the most devastating attacks against IoT systems because it prevents legitimate users from accessing services. A cyberattack of this type can significantly damage IoT services and smart environment applications in an IoT network. As a result, securing IoT systems has become an increasingly significant concern. Therefore, in this study, we propose an IDS defense mechanism to improve the security of IoT networks against DoS attacks using anomaly detection and machine learning (ML). Anomaly detection is used in the proposed IDS to continuously monitor network traffic for deviations from normal profiles. For that purpose, we used four types of supervised classifier algorithms, namely, Decision Tree (DT), Random Forest (RF), K Nearest Neighbor (kNN), and Support Vector Machine (SVM). In addition, we utilized two types of feature selection algorithms, the Correlation-based Feature Selection (CFS) algorithm and the Genetic Algorithm (GA) and compared their performances. We also utilized the IoTID20 dataset, one of the most recent for detecting anomalous activity in IoT networks, to train our model. The best performances were obtained with DT and RF classifiers when they were trained with features selected by GA. However, other metrics, such as training and testing times, showed that DT was superior.

RESUMEN

The work carried out in this paper consists of the classification of the physiological signal generated by eye movement called Electrooculography (EOG). The human eye performs simultaneous movements, when focusing on an object, generating a potential change in origin between the retinal epithelium and the cornea and modeling the eyeball as a dipole with a positive and negative hemisphere. Supervised learning algorithms were implemented to classify five eye movements; left, right, down, up and blink. Wavelet Transform was used to obtain information in the frequency domain characterizing the EOG signal with a bandwidth of 0.5 to 50 Hz; training results were obtained with the implementation of K-Nearest Neighbor (KNN) 69.4%, a Support Vector Machine (SVM) of 76.9% and Decision Tree (DT) 60.5%, checking the accuracy through the Jaccard index and other metrics such as the confusion matrix and ROC (Receiver Operating Characteristic) curve. As a result, the best classifier for this application was the SVM with Jaccard Index.

Asunto(s)

RESUMEN

Ganoderma boninense (G. boninense) infection reduces the productivity of oil palms and causes a serious threat to the palm oil industry. This catastrophic disease ultimately destroys the basal tissues of oil palm, causing the eventual death of the palm. Early detection of G. boninense is vital since there is no effective treatment to stop the continuing spread of the disease. This review describes past and future prospects of integrated research of near-infrared spectroscopy (NIRS), machine learning classification for predictive analytics and signal processing towards an early G. boninense detection system. This effort could reduce the cost of plantation management and avoid production losses. Remarkably, (i) spectroscopy techniques are more reliable than other detection techniques such as serological, molecular, biomarker-based sensor and imaging techniques in reactions with organic tissues, (ii) the NIR spectrum is more precise and sensitive to particular diseases, including G. boninense, compared to visible light and (iii) hand-held NIRS for in situ measurement is used to explore the efficacy of an early detection system in real time using ML classifier algorithms and a predictive analytics model. The non-destructive, environmentally friendly (no chemicals involved), mobile and sensitive leads the NIRS with ML and predictive analytics as a significant platform towards early detection of G. boninense in the future.

Asunto(s)

RESUMEN

Objective: The main objective of this paper is to easily identify thyroid symptom for treatment. Methods: In this paper two main techniques are proposed for mining the hidden pattern in the dataset. Ensemble-I and Ensemble- II both are machine learning techniques. Ensemble-I generated from decision tree, over fitting and neural network and Ensemble-II generated from combinations of Bagging and Boosting techniques. Finally proposed experiment is conducted by Ensemble-I vs. Ensemble-II. Results: In the entire experimental setup find an ensemble ­II generated model is the higher compare to other ensemble-I model. In each experiment observe and compare the value of all the performance of ROC, MAE, RMSE, RAE and RRSE. Stacking (ensemble-I) ensemble model estimate the weights for input with output model by thyroid dataset. After the measurement find out the results ROC=(98.80), MAE= (0.89), 6RMSE=(0.21), RAE= (52.78), RRSE=(83.71)and in the ensemble-II observe thyroid dataset and measure all performance of the model ROC=(98.79), MAE= (0.31), RMSE=(0.05) and RAE= (35.89) and RRSE=(52.67). Finally concluded that (Bagging+ Boosting) ensemble-II model is the best compare to other.

Asunto(s)

RESUMEN

BACKGROUND: Prompt, accurate, objective assessment of concussion is crucial, particularly for children/adolescents and young adults. While there is currently no gold standard for the diagnosis of concussion, the importance of multidimensional/multimodal assessments has recently been emphasized. METHODS: Concussed subjects (N = 177), matched controls (N = 187) and healthy volunteers (N = 204) represented a convenience sample of male and female subjects between the ages of 13 and 25 years, enrolled at 29 Colleges and 19 High Schools in the US. Subjects were tested at time of injury and at multiple time points during recovery. Assessments included EEG, neurocognitive tests and standard concussion assessment tools. Multimodal classifiers to maximally separate controls from concussed subjects with prolonged recovery (≥14 days) were derived using quantitative EEG, neurocognitive and vestibular measures, informed feature reduction and a Genetic Algorithm methodology for classifier derivation. The methodology protected against overtraining using an internal cross-validation framework. An enhanced multimodal Brain Function Index (eBFI) was derived from the classifier output and mapped to a percentile scale which expressed the index relative to non-injured controls. RESULTS: At time of injury eBFIs were significantly different between controls and concussed subjects with prolonged recovery, showing return to non-concussed levels at return-to-play plus 45 days. For the combined concussed population, and for the short recovery subjects, a more rapid recovery was seen. CONCLUSIONS: This multivariate, multimodal, objective index of brain function impairment can potentially be used, along with other tools, to aid in diagnosis, assessment, and tracking of recovery from concussion.

Asunto(s)

Asunto(s)

RESUMEN

BACKGROUND: There is an urgent need for objective criteria adjunctive to standard clinical assessment of acute Traumatic Brain Injury (TBI). Details of the development of a quantitative index to identify structural brain injury based on brain electrical activity will be described. METHODS: Acute closed head injured and normal patients (n=1470) were recruited from 16 US Emergency Departments and evaluated using brain electrical activity (EEG) recorded from forehead electrodes. Patients had high GCS (median=15), and most presented with low suspicion of brain injury. Patients were divided into a CT positive (CT+) group and a group with CT negative findings or where CT scans were not ordered according to standard assessment (CT-/CT_NR). Three different classifier methodologies, Ensemble Harmony, Least Absolute Shrinkage and Selection Operator (LASSO), and Genetic Algorithm (GA), were utilized. RESULTS: Similar performance accuracy was obtained for all three methodologies with an average sensitivity/specificity of 97.5%/59.5%, area under the curves (AUC) of 0.90 and average Negative Predictive Validity (NPV)>99%. Sensitivity was highest for CT+ cases with potentially life threatening hematomas, where two of three classifiers were 100%. CONCLUSION: Similar performance of these classifiers suggests that the optimal separation of the populations was obtained given the overlap of the underlying distributions of features of brain activity. High sensitivity to CT+ injuries (highest in hematomas) and specificity significantly higher than that obtained using ED guidelines for imaging, supports the enhanced clinical utility of this technology and suggests the potential role in the objective, rapid and more optimal triage of TBI patients.

Asunto(s)