Real-time data-driven missing data imputation for short-term sensor data of marine systems. A comparative study

The idea of the Internet of Things (IoT) is to connect or give access to everything to the Internet. IoT environment not only provides the facility of Human to Machine connectivity, however, it also creates Machine to Machine connectivity. As everything is going to connect to the Internet and also generating the data. So, the data generating by these devices is growing up rapidly, that huge amount of data is called Big Data. This data has huge Volume, High Velocity, and different Variety. The security of this data is a risk. As we know that, the IoT devices have constraints like low power and less computational speed and the traditional encryption algorithms like DES, 3DES, and AES are more complex. Traditional encryption algorithm seems not feasible for IoT devices. So, we need to develop Lightweight encryption algorithm for IoT devices for secure communication and secure data transmission in IoT environment. Cryptography and Steganography techniques are used for securing the data over the Internet. Cryptography encrypts the data by using a key and make a ciphertext that cannot be readable by the normal user. Steganography hides the data by concealing it into another medium like data, image, audio, video, or mixed. This paper provides a review of important lightweight cryptographic techniques used for IoT devices.

A review of data security and cryptographic techniques in IoT based devices

Background: Data collected by an actigraphy device worn on the wrist or waist can provide objective measurements for studies related to physical activity; however, some data may contain intervals where values are missing. In previous studies, statistical methods have been applied to impute missing values on the basis of statistical assumptions. Deep learning algorithms, however, can learn features from the data without any such assumptions and may outperform previous approaches in imputation tasks.
Objective: The aim of this study was to impute missing values in data using a deep learning approach.
Methods: To develop an imputation model for missing values in accelerometer-based actigraphy data, a denoising convolutional autoencoder was adopted. We trained and tested our deep learning–based imputation model with the National Health and Nutrition Examination Survey data set and validated it with the external Korea National Health and Nutrition Examination Survey and the Korean Chronic Cerebrovascular Disease Oriented Biobank data sets which consist of daily records measuring activity counts. The partial root mean square error and partial mean absolute error of the imputed intervals (partial RMSE and partial MAE, respectively) were calculated using our deep learning–based imputation model (zero-inflated denoising convolutional autoencoder) as well as using other approaches (mean imputation, zero-inflated Poisson regression, and Bayesian regression).
Results: The zero-inflated denoising convolutional autoencoder exhibited a partial RMSE of 839.3 counts and partial MAE of 431.1 counts, whereas mean imputation achieved a partial RMSE of 1053.2 counts and partial MAE of 545.4 counts, the zero-inflated Poisson regression model achieved a partial RMSE of 1255.6 counts and partial MAE of 508.6 counts, and Bayesian regression achieved a partial RMSE of 924.5 counts and partial MAE of 605.8 counts.
Conclusions: Our deep learning–based imputation model performed better than the other methods when imputing missing values in actigraphy data.

/pdf/deep-learning-approach-for-imputation-of-missing-values-in-2tdtzw1sa5.pdf

Deep Learning Approach for Imputation of Missing Values in Actigraphy Data: Algorithm Development Study

Stacked DeBERT: All attention in incomplete data for text classification.

Data security has become essential to provide secure communication that is free of attacks. A combination of steganography and cryptography provides very secure communication, where steganography hides the secret data and cryptography scrambles the secret data into an unreadable form. This paper proposes a message security scheme that applies audio steganography and cryptography to provide a secure communication by embedding a secret message inside an audio file. The Blowfish algorithm is used for cryptography and the LSB coding technique is used for steganography. The LSB coding alternates between the left channel and the right channel respectively. The proposed scheme is evaluated in terms of the mean square error (MSE), peak signal to noise ratio (PSNR), a hearing test and a comparison between the waveform plots of the cover and stego audios. The results prove that the proposed scheme exhibits very good performance. In addition, it is found to surpass other proposed schemes from the literature with much higher PSNR values.

Blowfish–Secured Audio Steganography

Missing values becomes one of the problems that frequently occur in the data observation or data recording process. The needs of data completeness of the observation data for the uses of advanced analysis becomes important to be solved. Conventional method such as mean and mode imputation, deletion, and other methods are not good enough to handle missing values as those method can caused bias to the data. Estimation or imputation to the missing data with the values produced by some procedures or algorithms can be the best possible solution to minimized the bias effect of the conventional method of the data. So that at last, the data will be completed and ready to use for another step of analysis or data mining. In this paper, we will explain and describe several previous studies about missing values handling methods or approach on time series data. This paper also discuss some plausible option of methods to estimate missing values to be used by other researchers in this field of study. The discussion's aim is to help them to figure out what method is commonly used now along with its advantages and drawbacks.

A review of missing values handling methods on time-series data

In the internet age, the security of data exchange becomes risky from some tapping attacks. One of the ways to maintain the data's security is by using steganography techniques. In this paper, steganography is combined with cryptography for security enhancement. The cover media is mp3 audio file. Since mp3 is a file that has been widely used in the Internet as a medium of entertainment, the secret message has been embedded to the homogenous frame of mp3 file. Before being embedded into the mp3 file, the secret message was encrypted with Advance Encryption Standard (AES) algorithm using a key that had been processed by Message Digest 5 (MD5) hash function. The secret message file type inserted could be in the form of text, image, audio, video, or compressed file. The result shows that the steganographic capacity does not depend on the size of mp3 but on the number of homogeneous frames owned by mp3 audio file. The result also shows that the method which combined steganography and cryptography, was successfully done without reducing the quality of used mp3 audio file.

Increasing the security of mp3 steganography using AES Encryption and MD5 hash function

Electronic mail or email is among the most popular data or message carrier. One of its powerful features is the sent message history records which have a long lifetime without big memory devices. However, with those technology advancements, the security aspects have become a serious concern. The ease of access to the networks has made an exposed leakage for some irresponsible parties who have the competencies to steal the information while the delivery streams take place. The email user is advised to add another security act such as encrypting toward the email contents before it being sent using ESP service. In this paper AES and 3DES cryptography method successfully implemented to securing email text messages. Email message being encrypted first using both algorithms, and then being evaluated and analyzed from various aspects. Evaluation’s results shows that AES is better in terms of compile time, while 3DES is better in terms of increasing message’s size after the encryption process, but the change in the addition of bytes is not significant. So based on the results of tests, email users are recommended to use AES encryption.

Effectiveness comparison of the AES and 3DES cryptography methods on email text messages

Bandwidth merupakan aspek penting untuk kelancaran dan kenyamanan dalam akses internet. Dalam penggunaan bandwidth internet, setiap pengguna menginginkan kecepatan akses secara maksimal. Kecepatan akses secara maksimal tentu akan berhubungan dengan bandwidth yang tersedia dalam jaringan tersebut. Untuk mendapatkan kecepatan yang maksimal dengan bandwidth yang terbatas, maka diperlukan pengaturan penggunaan bandwidth yang baik untuk menjaga kestabilan trafik lalu-lintas data pada jaringan. Berdasarkan hal tersebut maka dilakukan upaya untuk menyempurnakan teknik manajemen bandwidth. RouterOS merupakan sistem operasi berbasis linux yang dipergunakan pada router untuk menangani manajemen jaringan dan dapat berjalan di PC maupun routerboard . Dengan sistem operasi RouterOS memungkinkan untuk membuat sebuah router sendiri dari komputer langsung. Penelitian ini menekankan bagaimana mengalokasikan bandwidth secara optimal atau merata sesuai dengan kebutuhan pengguna internet dengan model penerapan simpangan baku atau deviasi standar pada queue pada router mikrotik Dengan menerapkan metode hierarchical token bucket pada queue akan dianalisa kemampuan algoritma tersebut dalam upaya optimalisasi QoS dalam konsep pemerataan bandwidth . Analisa yang dilakukan dengan mencari nilai paling optimal dari pemerataan bandwidth, yaitu diperolehnya deviasi atau simpangan rata-rata bandwidth pada metode simple queue dan hierarchical token bucket . Pengujian dilakukan dengan membatasi pemakaian bandwidth dengan memberikan limitasi untuk batas minimum dan maksimum bandwidth secara dinamis. Hasil pengujian menunjukkan model penerapan hierarchical token bucket mampu meningkatkan QoS, yaitu dengan diperoleh nilai simpangan lebih sedikit dari nilai rata-rata keseluruhan. Dengan demikian pemakaian bandwidth lebih merata sesuai dengan kebutuhan.

/pdf/analisis-manajemen-bandwidth-menggunakan-hierarchical-token-e53iw149iq.pdf

Analisis Manajemen Bandwidth Menggunakan Hierarchical Token Bucket Pada Router dengan Standar Deviasi

Least significant bit (LSB) is one of the classical methods commonly used for steganography audio Because of its simplicity, many researchers have interested to develop it This paper aims to determine the maximum limit of adding bits and its effects on audio quality based on modified LSB method consisting of LSB+1, LSB+2 and LSB+3 Then, this method is evaluated by counting steganography capacity, peak signal to noise ratio (PSNR) and bit error rate (BER) values Evaluation results show that LSB+3 has the best performance by obtaining the maximum bit of steganography capacity and acceptable of PSNR value

Rini Indrayani

Papers

A review of missing values handling methods on time-series data

Increasing the security of mp3 steganography using AES Encryption and MD5 hash function

Effectiveness comparison of the AES and 3DES cryptography methods on email text messages

Analisis Manajemen Bandwidth Menggunakan Hierarchical Token Bucket Pada Router dengan Standar Deviasi

An evaluation of MP3 steganography based on modified LSB method