Internet of Things (IoT) Security Enhancement Using XGboost Machine Learning Techniques

The rapid adoption of the Internet of Things(IoT)across industries has revolutionized daily life by providing essential services and leisure activities.However,the inadequate software protection in IoT devices exposes them to cyberattacks with severe consequences.Intrusion Detection Systems(IDS)are vital in mitigating these risks by detecting abnormal network behavior and monitoring safe network traffic.The security research community has shown particular interest in leveraging Machine Learning(ML)approaches to develop practical IDS applications for general cyber networks and IoT environments.However,most available datasets related to Industrial IoT suffer from imbalanced class distributions.This study proposes a methodology that involves dataset preprocessing,including data cleaning,encoding,and normalization.The class imbalance is addressed by employing the Synthetic Minority Oversampling Technique(SMOTE)and performing feature reduction using correlation analysis.Multiple ML classifiers,including Logistic Regression,multi-layer perceptron,Decision Trees,Random Forest,and XGBoost,are employed to model IoT attacks.The effectiveness and robustness of the proposed method evaluate using the IoTID20 dataset,which represents current imbalanced IoT scenarios.The results highlight that the XGBoost model,integrated with SMOTE,achieves outstanding attack detection accuracy of 0.99 in binary classification,0.99 in multi-class classification,and 0.81 in multiple sub-classifications.These findings demonstrate our approach’s significant improvements to attack detection in imbalanced IoT datasets,establishing its superiority over existing IDS frameworks.

Estimating the Properties of Ground-Waste-Brick Mortars Using DNN and ANN

In this study,deep-neural-network(DNN)-and artificial-neural-network(ANN)-based models along with regression models have been developed to estimate the pressure,bending and elongation values of ground-brick(GB)-added mortar samples.This study is aimed at utilizing GB as a mineral additive in concrete in the ratios 0.0%,2.5%,5.0%,7.5%,10.0%,12.5%and 15.0%.In this study,756 mortar samples were produced for 84 different series and were cured in tap water(W),5%sodium sulphate solution(SS5)and 5%ammonium nitrate solution(AN5)for 7 days,28 days,90 days and 180 days.The developed DNN models have three inputs and two hidden layers with 20 neurons and one output,whereas the ANN models have three inputs,one output and one hidden layer with 15 neurons.Twenty-five previously obtained experimental sample datasets were used to train these developed models and to generate the regression equation.Fifty-nine non-training-attributed datasets were used to test the models.When these test values were attributed to the trained DNN,ANN and regression models,the brick-dust pressure as well as the bending and elongation values have been observed to be very close to the experimental values.Although only a small fraction(30%)of the experimental data were used for training,both the models performed the estimation process at a level that was in accordance with the opinions of experts.The fact that this success has been achieved using very little training data shows that the models have been appropriately designed.In addition,the DNN models exhibited better performance as compared with that exhibited by the ANN models.The regression model is a model whose performance is worst and unacceptable;further,the prediction error is observed to be considerably high.In conclusion,ANN-and DNN-based models are practical and effective to estimate these values.

An Activity Recognition System at Home Based on CO2 Sensors

Activity recognition of indoor occupants using indirect sensing with less privacy violation is one of the hot research topics. This paper proposes a CO2 sensor-based indoor occupant activity monitoring system. Using the IoT sensor node that contains CO2 sensors, the measured CO2 concentrations in three locations (laboratory, office, and bedroom) were stored in a cloud server for up to 35 days starting July 1, 2023. The CO2 measurements stored at 30-second intervals were statistically processed to produce a heat-mapped display of the hourly average or maximum CO2 concentration. From the heatmap visualizations of CO2 concentration, the proposed system estimated meeting, heating water using a portable stove, and sleep for the occupants’ activity recognition.

Automatic Speaker Recognition Using Mel-Frequency Cepstral Coefficients Through Machine Learning

Automatic speaker recognition(ASR)systems are the field of Human-machine interaction and scientists have been using feature extraction and feature matching methods to analyze and synthesize these signals.One of the most commonly used methods for feature extraction is Mel Frequency Cepstral Coefficients(MFCCs).Recent researches show that MFCCs are successful in processing the voice signal with high accuracies.MFCCs represents a sequence of voice signal-specific features.This experimental analysis is proposed to distinguish Turkish speakers by extracting the MFCCs from the speech recordings.Since the human perception of sound is not linear,after the filterbank step in theMFCC method,we converted the obtained log filterbanks into decibel(dB)features-based spectrograms without applying the Discrete Cosine Transform(DCT).A new dataset was created with converted spectrogram into a 2-D array.Several learning algorithms were implementedwith a 10-fold cross-validationmethod to detect the speaker.The highest accuracy of 90.2%was achieved using Multi-layer Perceptron(MLP)with tanh activation function.The most important output of this study is the inclusion of human voice as a new feature set.

A Low-Cost Active Control Multi-Fan Turbulence Wind Tunnel with an Embedded System to Generate Natural Wind

This paper describes a new actively controlled multi-fan wind tunnel that generates natural wind as a type of turbulence wind tunnel at a reduced cost. The driving section of the wind tunnel has 100 PC cooling fans that are controlled by an original embedded system. The fluctuating velocity wind is successfully generated with a mean velocity of 7 m/s and two turbulent intensities of 2% and 3% based on Karman’s power spectrum density function. The case of 2% has the integral scales of 5 m, 10m and 20 m, and the case of 3% has the integral scales of 3 m, 6 m and 15 m with a turbulence grid. In particular, the wind with the turbulent intensity of 2% satisfies the Kolmogorov’s -5/3 multiplication rule of inertial subrange with the frequency range from 0.01 Hz to 2.0 Hz. Consequently, the new wind tunnel can be used for studying engineering technology and research regarding conditions with natural wind.

Man Overboard Detection System Using IoT for Navigation Model

Security measures and contingency plans have been established in order to ensure human safety especially in the floating elements like ferry,roro,catamaran,frigate,yacht that are the vehicles services for the purpose of logistic and passenger transport.In this paper,all processes in the event of Man overboard(MOB)are initiated for smart transportation.In MOB the falling person is totally dependent on the person who first saw the falling person.The main objective of this paper is to develop a solution to this significant problem.If a staff member or a passenger does not see the fall into the sea,undesirable situations such as disappearance,injury and death can occur during the period until the absence of the fallen person is noticed.In this paper,a comprehensive and improved solution is provided in terms of personnel and passenger security especially in all the floating elements,in which human resources are intensively involved like passengers,freight,logistics,fishing,business,yacht,leisure and naval vessels.In this case,if the ship’s personnel or passengers fall into the sea in any way,it detected the fallen person into the sea by the sensors in the portable emergency device,which each person will carry.The warning system is activated via the in-ship automation system to which the information is transmitted by wireless communication.Thus,the case of MOB will be determined quickly.Internet of things(IoT)has a key role in identifying the location and information of the person falling into the sea through sensors,radio frequency,GPS and connected devices.Simultaneously,the alarm system on board will be activated and MOB flag(Oscar)will automatically be opened.This paper enables the Search and rescue(SAR)operations to be initiated and accelerated without losing time through decision-making process.

An Efficient and Reliable Multicasting for Smart Cities

The Internet of thing(IoT)is a growing concept for smart cities,and it is compulsory to communicate data between different networks and devices.In the IoT,communication should be rapid with less delay and overhead.For this purpose,flooding is used for reliable data communication in a smart cities concept but at the cost of higher overhead,energy consumption and packet drop etc.This paper aims to increase the efficiency in term of overhead and reliability in term of delay by using multicasting and unicasting instead of flooding during packet forwarding in a smart city using the IoT concept.In this paper,multicasting and unicasting is used for IoT in smart cities within a receiver-initiated mesh-based topology to disseminate the data to the cluster head.Smart cities networks are divided into cluster head,and each cluster head or core node will be responsible for transferring data to the desired receiver.This protocol is a novel approach according to the best of our knowledge,and it proves to be very useful due to its efficiency and reliability in smart cities concept because IoT is a collection of devices and having a similar interest for transmission of data.The results are implemented in Network simulator 2(NS-2).The result shows that the proposed protocol shows performance in overhead,throughput,packet drop,delay and energy consumption as compared to benchmark schemes.

CAS-Based Approach for Automatic Data Integration

Research of automatic integration of structured and semi-structured data has not resulted in success over the past fifty years. No theory of data integration exists. It is unknown what the theoretical necessary requirements are, to fully support automatic data integration from autonomous heterogeneous data sources. Therefore, it is not possible to objectively evaluate if and how much new algorithms, techniques, and specifically Data Definition Languages, move towards meeting such theoretical requirements. To overcome the serious reverse salient the field and industry are in, it will be helpful if a data integration theory would be developed. This article proposes a new look at data integration by using complex adaptive systems principles to analyze current shortcomings and propose a direction that may lead to a data integration theory.

AndroidCare: A Simple and Low Cost Assisted Living Solution

Population aging places a growing stress on society’s resources. There is a need for Assisted Living (AL) technologies that allow the elderly to live independently as long as possible. The AndroidCare open source project aims to explore what functionality can be provided in a low cost AL solution where no professional health organization is involved in the deployment or maintenance of the solution, nor in supervising the pa-tient;all these tasks are carried out by a relative of the elder. Therefore, in the system’s design simplicity of use has prevailed over having a lot of features. It is based on stan-dard off-the-shell commodity hardware (a smartphone) and it provides 1) assistance to the elder in complying with the treatment of chronic diseases;2) monitors and alerts of the occurrence of risk situations such as falls;and 3) simplifies the supervision of the elder’s therapy and behavior by the caregiver.

ConfDTree: A Statistical Method for Improving Decision Trees

Decision trees have three main disadvantages： reduced performance when the training set is small; rigid decision criteria; and the fact that a single ＂uncharacteristic＂ attribute might ＂derail＂ the classification process. In this paper we present ConfDTree （Confidence-Based Decision Tree） -- a post-processing method that enables decision trees to better classify outlier instances. This method, which can be applied to any decision tree algorithm, uses easy-to-implement statistical methods （confidence intervals and two-proportion tests） in order to identify hard-to-classify instances and to propose alternative routes. The experimental study indicates that the proposed post-processing method consistently and significantly improves the predictive performance of decision trees, particularly for small, imbalanced or multi-class datasets in which an average improvement of 5%-9% in the AUC performance is reported.

A Context—Aware Infrastructure for Supporting Applications with Pen—Based Interaction

Pen-based user interfaces which leverage the affordances of the pen provide userswith more flexibility and natural interaction. However, it is difficult to construct usable pen-baseduser interfaces because of the lack of support for their development. Toolkit-level support has beenexploited to solve this problem, but this approach makes it hard to gain platform independence,easy maintenance and easy extension. In this paper a context-aware infrastructure is created,called WEAVER, to provide pen interaction services for both novel pen-based applications andlegacy GUI-based applications. WEAVER aims to support the pen as another standard interactivedevice along with the keyboard and mouse and present a high-level access interface to pen input.It employs application context to tailor its service to different applications. By modeling theapplication context and registering the relevant action adapters, WEAVER can offer services,such as gesture recognition, continuous handwriting and other fundamental ink manipulations, toappropriate applications. One of the distinct features of WEAVER is that off-the-shelf GUI-basedsoftware packages can be easily enhanced with pen interaction without modifying the existing code.In this paper, the architecture and components of WEAVER are described. In addition, examplesand feedbacks of its use are presented.