Extracting the mechanical properties of a composite hydrogel; e.g., bioglass (BG)–collagen (COL), is often difficult due to the complexity of the experimental procedure. BGs could be embedded in the COL and thereby improve the mechanical properties of COL for bone tissue engineering applications. This paper proposed a deep-learning-based approach to extract the mechanical properties of a composite hydrogel directly from the microstructural images. Four datasets of various shapes of BGs (9000 2D images) generated by a finite element analysis showed that the deep neural network (DNN) model could efficiently predict the mechanical properties of the composite hydrogel, including the Young’s modulus and Poisson’s ratio. ResNet and AlexNet architecture were tuned to ensure the excellent performance and high accuracy of the proposed methods with R-values greater than 0.99 and a mean absolute error of the prediction of less than 7%. The results for the full dataset revealed that AlexNet had a better performance than ResNet in predicting the elastic material properties of BGs-COL with R-values of 0.99 and 0.97 compared to 0.97 and 0.96 for the Young’s modulus and Poisson’s ratio, respectively. This work provided bridging methods to combine a finite element analysis and a DNN for applications in diverse fields such as tissue engineering, materials science, and medical engineering. 

/pdf/prediction-of-composite-mechanical-properties-integration-of-1kly9azm.pdf

Prediction of Composite Mechanical Properties: Integration of Deep Neural Network Methods and Finite Element Analysis

This paper presents a low power audio front end for keyword spotting. A multi-stage approach is used to reduce the power consumption of the system by only using different stages when they are required. A working prototype was created and tested to verify its functionality. The effectiveness of the multistage approach is shown by comparing the power consumption of the system in its idle state to the systems active state. The prototype has a power consumption of 4.1 mW in the idle state that can be reduced below 3 mW with a keyword detection accuracy of 87 %.

Low-Power Low-Cost Audio Front-End for Keyword Spotting

Abstract Intrusion detection ( ID ) methods are security frameworks designed to safeguard network information systems. The strength of an intrusion detection method is dependent on the robustness of the feature selection method. This study developed a multi-level random forest algorithm for intrusion detection using a fuzzy inference system. The strengths of the filter and wrapper approaches are combined in this work to create a more advanced multi-level feature selection technique, which strengthens network security. The first stage of the multi-level feature selection is the filter method using a correlation-based feature selection to select essential features based on the multi-collinearity in the data. The correlation-based feature selection used a genetic search method to choose the best features from the feature set. The genetic search algorithm assesses the merits of each attribute, which then delivers the characteristics with the highest fitness values for selection. A rule assessment has also been used to determine whether two feature subsets have the same fitness value, which ultimately returns the feature subset with the fewest features. The second stage is a wrapper method based on the sequential forward selection method to further select top features based on the accuracy of the baseline classifier. The selected top features serve as input into the random forest algorithm for detecting intrusions. Finally, fuzzy logic was used to classify intrusions as either normal, low, medium, or high to reduce misclassification. When the developed intrusion method was compared to other existing models using the same dataset, the results revealed a higher accuracy, precision, sensitivity, specificity, and F1-score of 99.46%, 99.46%, 99.46%, 93.86%, and 99.46%, respectively. The classification of attacks using the fuzzy inference system also indicates that the developed method can correctly classify attacks with reduced misclassification. The use of a multi-level feature selection method to leverage the advantages of filter and wrapper feature selection methods and fuzzy logic for intrusion classification makes this study unique. 

https://link.springer.com/content/pdf/10.1007/s44196-023-00205-w.pdf

A Multi-level Random Forest Model-Based Intrusion Detection Using Fuzzy Inference System for Internet of Things Networks

Speech sounds produced by human depends on movement of various articulators. Dimensions and shape of the various elements of speech production organs also have impact on nature of speech produced. Vocal tract plays a major role like characteristics of linear time invariant system. In this paper, analysis of vocal tract parameters, in terms of resonances of vocal tract, also referred as formants is done. Of the different speech sounds, vowels carry most significant clues of speech. Despite specific properties of different vowels, there is much variability of vowel characteristics among speakers. It gives characteristics of vocal tract related to acoustic resonances. At large, first four formants are useful to categorize vowel sounds. The variation in formants for same speech sounds is a challenge to speech recognition algorithms in which vowel spectral characteristics are assumed to be invariant among speakers. But the same variability of formants among speaker is useful in speaker recognition. The method used for formant estimation is based on designing all-zero filters to track the formants and voicing detection-based formant extraction filters to estimate the first four formants. Vocal tract parameters in terms of formants are analyzed using twelve vowel sounds from different speakers. From the experimental analysis, it is observed that the first formant specifically represents the pertinent characteristics of vowel speech, whereas there is very little consistency of higher-order formants for same speech sounds by different speakers, indicating the impact of physiological nature as well as behavioral aspects of individual on nature of speech produced.

Analyzing Vocal Tract Parameters of Speech

Due to the own features of openness, hugeness and complexity in DNS , and the lack of consideration for security when designing DNS, DNS is now faced with a very serious security threat, with man-made attack and destruction. There are various forms of DNS attacks. This paper selects two of the attack forms, DDoS attack against DNS and DNS amplification attack. Combined with HMM model, we do research on DNS attack detection, and use simulation experiments and data to prove the feasibility and effectiveness of the detection method.

Research on DNS Attack Detection Based on HMM

The Internet of Things (IoT) is a complicated security feature in which datagrams are protected by integrity, confidentiality, and authentication services. The network is protected from external interruptions and intrusions. Because IoT devices run with a range of heterogeneous technologies and process data over time, standard solutions may not be practical. It is necessary to develop intelligent procedures that can be used for multiple levels of data flow in the system. This study examines metainnovations using deep learning-based IDS. Per the findings of the earlier tests, BiLSTMs are better for binary (regular/attacker) classification; however, sequential models (LSTM or BiLSTM) are better for detecting some brutal attacks in multiclass classifiers. According to experts, deep learning-based intrusion detection systems can now recognize and select the best structure for each category. However, specific difficulties will need to be solved in the future. Two topics should be studied further in future attempts. One of the researchers’ concerns is the impact of various data processing techniques, such as artificial intelligence or metamethods, on IDS. The BiLSTM approach has chosen the safest instances with the highest accuracy among the models. According to the findings, the most reliable and suitable solution for evaluating DDoS attacks in IoT is the BiLSTM design.

/pdf/ml-ddosnet-iot-intrusion-detection-based-on-denial-of-3b9tstvw.pdf

ML-DDoSnet: IoT Intrusion Detection Based on Denial-of-Service Attacks Using Machine Learning Methods and NSL-KDD

Extraction of pitch and formant frequencies is an important issue in speech processing. Pitch frequency is the fundamental frequency of the speech signal, and formant frequencies are essentially resonance frequencies of the vocal tract. These frequencies vary among different persons and words, but they are within certain frequency range. Practically, the first three formants are enough for coding and other processes. The most common methods for estimating formants are cepstrum and linear predictive coding. In this study, a wavelet based method using filter bank concepts is presented to estimate these frequencies.

Seyed Amir Yousef Hosseini Goki

Papers

ML-DDoSnet: IoT Intrusion Detection Based on Denial-of-Service Attacks Using Machine Learning Methods and NSL-KDD

Extraction of Speech Pitch and Formant Frequencies using Discrete Wavelet Transform