Explore the vast range of titles available.

Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Machine learning algorithms are generally computationally and memory intensive, making them unsuitable for resource-constrained environments such as embedded and mobile devices. In order to efficiently implement these compute and memory-intensive algorithms within the embedded and mobile computing space, innovative optimization techniques are required at the algorithm and hardware levels. To this end, this survey aims at exploring current research trends within this circumference. First, we present a brief overview of compute intensive machine learning algorithms such as hidden Markov models (HMM), k-nearest neighbors (k-NNs), support vector machines (SVMs), Gaussian mixture models (GMMs), and deep neural networks (DNNs). Furthermore, we consider different optimization techniques currently adopted to squeeze these computational and memory-intensive algorithms within resource-limited embedded and mobile environments. Additionally, we discuss the implementation of these algorithms in microcontroller units, mobile devices, and hardware accelerators. Conclusively, we give a comprehensive overview of key application areas of EML technology, point out key research directions and highlight key take-away lessons for future research exploration in the embedded machine learning domain.

Nowadays, hackers take illegal advantage of distributed resources in a network of computing devices (i.e., botnet) to launch cyberattacks against the Internet of Things (IoT). Recently, diverse Machine Learning (ML) and Deep Learning (DL) methods were proposed to detect botnet attacks in IoT networks. However, highly imbalanced network traffic data in the training set often degrade the classification performance of state-of-the-art ML and DL models, especially in classes with relatively few samples. In this paper, we propose an efficient DL-based botnet attack detection algorithm that can handle highly imbalanced network traffic data. Specifically, Synthetic Minority Oversampling Technique (SMOTE) generates additional minority samples to achieve class balance, while Deep Recurrent Neural Network (DRNN) learns hierarchical feature representations from the balanced network traffic data to perform discriminative classification. We develop DRNN and SMOTE-DRNN models with the Bot-IoT dataset, and the simulation results show that high-class imbalance in the training data adversely affects the precision, recall, F1 score, area under the receiver operating characteristic curve (AUC), geometric mean (GM) and Matthews correlation coefficient (MCC) of the DRNN model. On the other hand, the SMOTE-DRNN model achieved better classification performance with 99.50% precision, 99.75% recall, 99.62% F1 score, 99.87% AUC, 99.74% GM and 99.62% MCC. Additionally, the SMOTE-DRNN model outperformed state-of-the-art ML and DL models.

In this paper, an optimal model is developed for path loss predictions using the Feed-Forward Neural Network (FFNN) algorithm. Drive test measurements were carried out in Canaanland Ota, Nigeria and Ilorin, Nigeria to obtain path loss data at varying distances from 11 different 1,800 MHz base station transmitters. Single-layered FFNNs were trained with normalized terrain profile data (longitude, latitude, elevation, altitude, clutter height) and normalized distances to produce the corresponding path loss values based on the Levenberg-Marquardt algorithm. The number of neurons in the hidden layer was varied (1-50) to determine the Artificial Neural Network (ANN) model with the best prediction accuracy. The performance of the ANN models was evaluated based on different metrics: Mean Absolute error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), standard deviation, and regression coefficient (R). Results of the machine learning processes show that the FNN architecture adopting a tangent activation function and 48 hidden neurons produced the least prediction error, with MAE, MSE, RMSE, standard deviation, and R values of 4.21 dB, 30.99 dB, 5.56 dB, 5.56 dB, and 0.89, respectively. Regarding generalization ability, the predictions of the optimal ANN model yielded MAE, MSE, RMSE, standard deviation, and R values of 4.74 dB, 39.38 dB, 6.27 dB, 6.27 dB, and 0.86, respectively, when tested with new data not previously included in the training process. Compared to the Hata, COST 231, ECC-33, and Egli models, the developed ANN model performed better in terms of prediction accuracy and generalization ability.

It is imperative to establish an automated system for the identification of neonates (1–28 days old) and infants (29 days–12 months old) through the utilisation of the readily accessible 500 ppi fingerprint reader. This measure is crucial in addressing the issue of newborn swapping, facilitating the identification of missing children, monitoring immunisation records, maintaining comprehensive medical history, and other related purposes. The objective of this study is to demonstrate the potential for future identification of infants using fingerprints obtained from a 500 ppi fingerprint reader by employing a fusion technique that combines multiple instances of fingerprints, specifically the left thumb and right index fingers. The fingerprints were acquired from babies who were between the ages of one day and six months at the enrolment session. The sum-score fusion algorithm was implemented. The approach mentioned above yielded verification accuracies of 73.8%, 69.05%, and 57.14% for time intervals of 1 month, 3 months, and 6 months, respectively, between the enrolment and query fingerprints.

The field of wireless communication networks has witnessed a dramatic change over the last decade due to sophisticated technologies deployed to satisfy various demands peculiar to different data-intensive wireless applications. Consequently, this has led to the aggressive use of the available propagation channels to fulfill the minimum quality of service (QoS) requirement. A major barometer used to gauge the performance of a wireless communication system is the spectral efficiency (SE) of its communication channels. A key technology used to improve SE substantially is the multiple input multiple output (MIMO) technique. This article presents a detailed survey of MIMO channel models in wireless communication systems. First, we present the general MIMO channel model and identified three major MIMO channel models, viz., the physical, analytical, and standardized models. The physical models describe the MIMO channel using physical parameters. The analytical models show the statistical features of the MIMO channel with respect to the measured data. The standardized models provide a unified framework for modern radio propagation architecture, advanced signal processing, and cutting-edge multiple access techniques. Additionally, we examined the strengths and limitations of the existing channel models and discussed model design, development, parameterization, implementation, and validation. Finally, we present the recent 3GPP-based 3D channel model, the transitioning from 2D to 3D channel modeling, discuss open issues, and highlight vital lessons learned for future research exploration in MIMO communication systems.

Cyber attackers exploit a network of compromised computing devices, known as a botnet, to attack Internet-of-Things (IoT) networks. Recent research works have recommended the use of Deep Recurrent Neural Network (DRNN) for botnet attack detection in IoT networks. However, for high feature dimensionality in the training data, high network bandwidth and a large memory space will be needed to transmit and store the data, respectively in IoT back-end server or cloud platform for Deep Learning (DL). Furthermore, given highly imbalanced network traffic data, the DRNN model produces low classification performance in minority classes. In this paper, we exploit the joint advantages of Long Short-Term Memory Autoencoder (LAE), Synthetic Minority Oversampling Technique (SMOTE), and DRNN to develop a memory-efficient DL method, named LS-DRNN. The effectiveness of this method is evaluated with the Bot-IoT dataset. Results show that the LAE method reduced the dimensionality of network traffic features in the training set from 37 to 10, and this consequently reduced the memory space required for data storage by 86.49%. SMOTE method helped the LS-DRNN model to achieve high classification performance in minority classes, and the overall detection rate increased by 10.94%. Furthermore, the LS-DRNN model outperformed state-of-the-art models.

Image retrieval via traditional Content-Based Image Retrieval (CBIR) often incurs the semantic gap problem-non-correlation of image retrieval results with human semantic interpretation of images. In this paper, Relevance Feedback (RF) mechanism was incorporated into a traditional Query by Visual Example CBIR (QVER) system. The inherent curse of dimensionality associated with RF mechanism was catered for by performing feature selection using Principal Component Analysis (PCA). The amount of feature dimension retained was determined based on a not more than 5% loss constrain imposed on average precision of retrieval result. While the asymmetry and small sample size nature of the resultant image dataset informed the use of a modified One-Class Support Vector Machine (OC-SVM) classifier, three image databases (DB10, DB20 and DB100) were used to test the OC-SVM RF mechanism. Across DB10, DB20 and DB100, Average Indexing Time of 0.451, 0.3017, and 0.0904s were recorded, respectively. For a critical recall value of 0.3, precision values for QVER were 0.7881, 0.7200 and 0.9112, while OC-SVM RF yielded precision of 0.8908, 0.8409, and 0.9503, respectively. Also, the use of PCA yielded tolerable degradation of 3.54, 4.39 and 7.40% in precision on DB10, DB20, and DB100, respectively, with 80% reduction in feature dimension. The OC-SVM RF increased the precision and invariably the reliability of the CBIR system by ranking most of the relevant images higher. Also, the target class was identified faster than the conventional method, thereby reducing the image retrieval time of the OC-SVM RF.

One of the goals of Word Bank's Identification for Development (ID4D) is the realization of robust digital identification systems as a means of sustainable development priority. ID4D's most recent report shows about 1.1 billion of the world's population are yet to be identified for development. Africa represents about half of that number while Nigeria represents about a quarter of Africa's share. Biometrics is the state-of-the-art approach for identification using human behavioral and/or physiological digitally calibrated traits and one such trait is the voice. The backbone of biometric research is the database employed in the design of biometric systems. Although many voice databases are publicly available such as the THCHS-30 for Chinese and Microsoft Indian language Speech Corpus for Indians, none is currently publicly available or free for Nigerians. The creation of such an indigenous database (or corpus) can open doors to Nigerian automatic speaker recognition as well as for indigenous language, ethnicity, gender, age group and emotion classification amongst others. This work is a first step in the direction of creating a Nigerian Voice Corpus (NVC) to aid indigenous voice biometric research. A voice corpus of popular Nigerians was created by curation of audio samples of 14 women and 23 men from YouTube. The corpus contains 10 different samples of 5 seconds duration for each individual resulting in a total of 370 samples. The created corpus was used to carry out speaker recognition experiment by dividing the audio samples into 25ms non-overlapping frame durations. Silent frames were excluded using short-term spectral energy threshold for Voice Activity Detection (VAD). This was followed by extraction of Mel Frequency Cepstral Coefficient (MFCC) as descriptors to discriminate different speakers using Support Vector Machine (SVM) with median Gaussian function. An overall recognition accuracy of 93.24% was achieved demonstrating the feasibility and research potential in this direction.

In the proposed 5G architecture where cell densification is expected to be used for network capacity enhancement, the deployment of millimetre wave (mmWave) massive multiple-input multiple-output (MIMO) in urban microcells located outdoor is expected to be used for high channel capacity small cell wireless traffic backhauling as the use of copper and optic-fibre cable becomes infeasible owing to the high cost and issues with right of way. The high cost of radio frequency (RF) chain and its prohibitive power consumption are big drawbacks for mmWave massive MIMO transceiver implementation and the complexity of using optimal detection algorithm as a result of inter-channel interference (ICI) as the base station antenna approaches large numbers. Spatial modulation (SM) and Generalized Spatial Modulation (GSM) are new novel techniques proposed as a low-complexity, low cost and low-power-consumption MIMO candidate with the ability to further reduce the RF chain for mmWave massive MIMO hybrid beamforming systems. In this work, we present the principles of generalized spatial modulation aided hybrid beamforming (GSMA-HBF) and its use for cost-effective, high energy efficient mmWave massive MIMO transceiver for small cell wireless backhaul in a 5G ultra-dense network.

[...]in this work a feature dimensionality reduction technique based on principal component analysis (PCA) is implemented. Feature dimensionality reduction (ProQuest: ... denotes formulae omitted.) 1.INTRODUCTION One of the challenges of relevance feedback (RF) in image retrieval is the inherent curse of dimensionality occasioned by small sample size with high feature dimension. [...]for RF techniques which are based on training classifier using feedback examples, the curse of dimensionality can deteriorate the classifier performance, thereby leading to poor retrieval results. Feature selection model In a generic system, it is extremely difficult to know the particular feature model(s) to be used to uniquely identify certain groups of images. [...]a combination of several image feature models is usually employed with the assumption that at least one will have the ability to capture the unique identity of the targeted images. In view of this, including too many features is obviously not feasible for application involving human-machine interaction. Since such system is expected to be fast enough for smooth interaction, the selection of most appropriate features to relduce computational burden becomes imperative and to achieve this, a procedure that uses Principal Component Analysis is employed in this work.