An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

With the advancement of machine learning methods, audio sentiment analysis has become an active research area in recent years. For example, business organizations are interested in persuasion tactics from vocal cues and acoustic measures in speech. A typical approach is to find a set of acoustic features from audio data that can indicate or predict a customer's attitude, opinion, or emotion state. For audio signals, acoustic features have been widely used in many machine learning applications, such as music classification, language recognition, emotion recognition, and so on. For emotion recognition, previous work shows that pitch and speech rate features are important features. This thesis work focuses on determining sentiment from call center audio records, each containing a conversation between a sales representative and a customer. The sentiment of an audio record is considered positive if the conversation ended with an appointment being made, and is negative otherwise. In this project, a data processing and machine learning pipeline for this problem has been developed. It consists of three major steps: 1) an audio record is split into segments by speaker turns; 2) acoustic features are extracted from each segment; and 3) classification models are trained on the acoustic features to predict sentiment. Different set of features have been used and different machine learning methods, including classical machine learning algorithms and deep neural networks, have been implemented in the pipeline. In our deep neural network method, the feature vectors of audio segments are stacked in temporal order into a feature matrix, which is fed into deep convolution neural networks as input. Experimental results based on real data shows that acoustic features, such as Mel frequency cepstral coefficients, timbre and Chroma features, are good indicators for sentiment. Temporal information in an audio record can be captured by deep convolutional neural networks for improved prediction accuracy.

Deep Neural Networks (DNNs) have made significant improvements to reach the desired accuracy to be employed in a wide variety of Machine Learning (ML) applications. Recently the Google Brain's team demonstrated the ability of Capsule Networks (CapsNets) to encode and learn spatial correlations between different input features, thereby obtaining superior learning capabilities compared to traditional (i.e., non-capsule based) DNNs. However, designing CapsNets using conventional methods is a tedious job and incurs significant training effort. Recent studies have shown that powerful methods to automatically select the best/optimal DNN model configuration for a given set of applications and a training dataset are based on the Neural Architecture Search (NAS) algorithms. Moreover, due to their extreme computational and memory requirements, DNNs are employed using the specialized hardware accelerators in IoT-Edge/CPS devices. In this paper, we propose NASCaps, an automated framework for the hardware-aware NAS of different types of DNNs, covering both traditional convolutional DNNs and CapsNets. We study the efficacy of deploying a multi-objective Genetic Algorithm (e.g., based on the NSGA-II algorithm). The proposed framework can jointly optimize the network accuracy and the corresponding hardware efficiency, expressed in terms of energy, memory, and latency of a given hardware accelerator executing the DNN inference. Besides supporting the traditional DNN layers, our framework is the first to model and supports the specialized capsule layers and dynamic routing in the NAS-flow. We evaluate our framework on different datasets, generating different network configurations, and demonstrate the tradeoffs between the different output metrics. We will open-source the complete framework and configurations of the Pareto-optimal architectures at https://github.com/ehw-fit/nascaps.

Modern software systems are increasingly including machine learning (ML) as an integral component. However, we do not yet understand the difficulties faced by software developers when learning about ML libraries and using them within their systems. To fill that gap this thesis reports on a detailed (manual) examination of 3,243 highly-rated Q&A posts related to ten ML libraries, namely Tensorflow, Keras, scikitlearn, Weka, Caffe, Theano, MLlib, Torch, Mahout, and H2O, on Stack Overflow, a popular online technical Q&A forum. Our findings reveal the urgent need for software engineering (SE) research in this area. The second part of the thesis particularly focuses on understanding the Deep Neural Network (DNN) bug characteristics. We study 2,716 high-quality posts from Stack Overflow and 500 bug fix commits from Github about five popular deep learning libraries Caffe, Keras, Tensorflow, Theano, and Torch to understand the types of bugs, their root causes and impacts, bug-prone stage of deep learning pipeline as well as whether there are some common antipatterns found in this buggy software. While exploring the bug characteristics, our findings imply that repairing software that uses DNNs is one such unmistakable SE need where automated tools could be beneficial; however, we do not fully understand challenges to repairing and patterns that are utilized when manually repairing DNNs. So, the third part of this thesis presents a comprehensive study of bug fix patterns to address these questions. We have studied 415 repairs from Stack Overflow and 555 repairs from Github for five popular deep learning libraries Caffe, Keras, Tensorflow, Theano, and Torch to understand challenges in repairs and bug repair patterns. Our key findings reveal that DNN bug fix patterns are distinctive compared to traditional bug fix patterns and the most common bug fix patterns are fixing data dimension and neural network connectivity. Finally, we propose an automatic technique to detect ML Application Programming Interface (API) misuses. We started with an empirical study to understand ML API misuses. Our study shows that ML API misuse is prevalent and distinct compared to non-ML API misuses. Inspired by these findings, we contributed Amimla (Api Misuse In Machine Learning Apis) an approach and a tool for ML API misuse detection. Amimla relies on several technical innovations. First, we proposed an abstract representation of ML pipelines to use in misuse detection. Second, we proposed an abstract representation of neural networks for deep learning related APIs. Third, we have developed a representation strategy for constraints on ML APIs. Finally, we have developed a misuse detection strategy for both single and multi-APIs. Our experimental evaluation shows that Amimla achieves a high average accuracy of ∼80% on two benchmarks of misuses from Stack Overflow and Github.

The present generation of mobile handheld devices comes equipped with a large number of sensors. The key sensors include the Ambient Light Sensor, Proximity Sensor, Gyroscope, Compass and the Accelerometer. Many mobile applications are driven based on the readings obtained from either one or two of these sensors. However the presence of multiple-sensors will enable the determination of more detailed activities that are carried out by the user of a mobile device, thus enabling smarter mobile applications to be developed that responds more appropriately to user behavior and device usage. In the proposed research we use recent advances in machine learning to fuse together the data obtained from all key sensors of a mobile device. We investigate the possible use of single and ensemble classifier based approaches to identify a mobile device’s behavior in the space it is present. Feature selection algorithms are used to remove non-discriminant features that often lead to poor classifier performance. As the sensor readings are noisy and include a significant proportion of missing values and outliers, we use machine learning based approaches to clean the raw data obtained from the sensors, before use. Based on selected practical case studies, we demonstrate the ability to accurately recognize device behavior based on multi-sensor data fusion.

Current automatic acoustic detection and classification of microchiroptera utilize global features of individual calls (i.e., duration, bandwidth, frequency extrema), an approach that stems from expert knowledge of call sonograms. This approach parallels the acoustic phonetic paradigm of human automatic speech recognition (ASR), which relied on expert knowledge to account for variations in canonical linguistic units. ASR research eventually shifted from acoustic phonetics to machine learning, primarily because of the superior ability of machine learning to account for signal variation. To compare machine learning with conventional methods of detection and classification, nearly 3000 search-phase calls were hand labeled from recordings of five species: Pipistrellus bodenheimeri, Molossus molossus, Lasiurus borealis, L. cinereus semotus, and Tadarida brasiliensis. The hand labels were used to train two machine learning models: a Gaussian mixture model (GMM) for detection and classification and a hidden Markov model (HMM) for classification. The GMM detector produced 4% error compared to 32% error for a baseline broadband energy detector, while the GMM and HMM classifiers produced errors of 0.6 +/- 0.2% compared to 16.9 +/- 1.1% error for a baseline discriminant function analysis classifier. The experiments showed that machine learning algorithms produced errors an order of magnitude smaller than those for conventional methods.

Machine Learning (ML) is becoming a ubiquitous technology employed in many real-world applications in diverse areas such as agriculture, human health, entomology, and engineering. In some applications, sensors measure the environment while supervised ML algorithms are responsible for interpreting these data to make an automatic decision. Generally, these devices face three main restrictions: power consumption, cost, and lack of infrastructure. Most of these challenges can be better addressed by embedding ML classifiers in the hardware that senses the environment. Thus, we need highly-efficient classifiers suitable to execute in unresourceful hardware. However, this scenario conflicts with the state-of-practice of ML, in which classifiers are frequently implemented in high-level interpreted languages (e.g., Java or Python), make unrestricted use of floating-point operations and assume plenty of resources such as memory, processing and energy. In this work, we present a software tool named Embedded Machine Learning (EmbML) that implements a pipeline to develop classifiers for low-power microcontrollers. This pipeline starts with learning a classifier in a desktop or server computer using popular software packages or libraries as WEKA or scikit-learn. EmbML converts the classifier into a carefully crafted C++ code with support for resource-constrained hardware, such as the avoidance of unnecessary use of main memory and implementation of fixed-point operations for non-integer numbers. Our experimental evaluation on benchmark datasets and a variety of microcontrollers shows that EmbML classifiers achieve competitive results in terms of accuracy, classification time, and memory cost. Compared to classifiers from some existing related tools, ours achieved the best time and memory performances in at least 70% of the cases. Lastly, we conduct experiments in a real-world application to describe the complete pipeline for using EmbML and assessing its classifiers with an intelligent trap to classify and capture flying insects.

Recently, Speech synthesis is one of the growing techniques in the research domain that takes input as text and provides output as acoustical form. The speech synthesis system is more advantageous to physically impaired people. In execution process, there arise some complications by surrounding noises and communication style. To neglect such unnecessary noises various machine learning techniques are employed. In this paper, we described various techniques adopted to improve the naturalness and quality of synthesized speech. The main contribution of this paper is to elaborate and compare the characteristics of techniques utilized in speech synthesis for different languages. The techniques such as support vector machine, Artificial Neural Network, Gaussian mixture modeling, Generative adversarial network, Deep Neural Network and Hidden Markov Model are employed in this work to enhance the speech naturalness and quality of synthesized speech signals. KeywordsText to speechSyllablesDatabaseArtificial neural networkGaussian mixture modelingDeep neural networkHidden Markov model

A hybrid model comprised of Gaussian Mixtures Models (GMMs) and Hidden Markov Models (HMMs) is used to model generic sounds with large intra class perceptual variations. Each class has variable number of mixture components in the GMM. The number of mixture components is derived using the Minimum Description Length (MDL) criterion. The overall performance of the hybrid model was compared against models based on HMMs and GMMs with a fixed number of mixture components across all classes. We show that a hybrid model outperforms both class-based GMMs, HMMs, and GMMs based on fixed number of components. Further, our experiments revealed that the contribution of transitions between states in HMMs has no significant effect on the overall classification performance of generic sounds when large intra class perceptual variations are present among sounds in the training and test datasets. Sounds that show multi-event structure with events that tend to be similar (repetitive) indicated improved performance when modeled with HMMs that can be attributed to HMM’s state transition property. Conversely, GMMs indicate better performance when the sound samples show subtle or no repetitive behavior. These results were validated using the MuscleFish sound database.

The past 5 years have seen an explosion of interest in the use of artificial intelligence (AI) and machine learning techniques in medicine. This has been driven by the development...

Information Theory (IT) has been used in Machine Learning (ML) from early days of this field. In the last decade, advances in Deep Neural Networks (DNNs) have led to surprising improvements in many applications of ML. The result has been a paradigm shift in the community toward revisiting previous ideas and applications in this new framework. Ideas from IT are no exception. One of the ideas which is being revisited by many researchers in this new era, is Information Bottleneck (IB); a formulation of information extraction based on IT. The IB is promising in both analyzing and improving DNNs. The goal of this survey is to review the IB concept and demonstrate its applications in deep learning. The information theoretic nature of IB, makes it also a good candidate in showing the more general concept of how IT can be used in ML. Two important concepts are highlighted in this narrative on the subject, i) the concise and universal view that IT provides on seemingly unrelated methods of ML, demonstrated by explaining how IB relates to minimal sufficient statistics, stochastic gradient descent, and variational auto-encoders, and ii) the common technical mistakes and problems caused by applying ideas from IT, which is discussed by a careful study of some recent methods suffering from them.

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

Machine learning in natural and engineered water systems

Deep-sea ecosystems, harbouring extraordinary biodiversity and geological wonders, remain largely unexplored due to their remote and inhospitable nature. Recent technological advancements, particularly in the realm of machine learning (ML), offer promising avenues for unravelling the mysteries of the deep and safeguarding its fragile ecosystems. This abstract presents an overview of the manifold applications of ML in deep-sea ecosystem analysis, focusing on key areas such as species identification, habitat characterization, and event detection. Primarily, ML algorithms, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and Random Forests, are deployed for automated species identification, leveraging vast repositories of underwater imagery. By discerning intricate visual patterns, these algorithms facilitate rapid biodiversity assessment and aid in monitoring shifts in species distributions. Moreover, ML techniques, such as Decision Trees, K-Nearest Neighbour (KNN), and deep learning architectures, are instrumental in habitat classification endeavours. Through the analysis of multifaceted sensor data, these algorithms enable the delineation of distinct seafloor habitats, empowering conservationists with invaluable insights into ecosystem structure and function. Furthermore, ML-based anomaly detection algorithms, Hidden Markov Models (HMMs), and reinforcement learning (RL) strategies contribute to event detection efforts in the deep sea. By scrutinizing temporal data streams from underwater sensors, these algorithms detect aberrations indicative of natural phenomena or anthropogenic disturbances, thus facilitating timely interventions and mitigative actions. In conclusion, the integration of ML techniques into deep-sea ecosystem analysis represents a paradigm shift in our approach to understanding and preserving these enigmatic realms. By automating labor-intensive tasks, enhancing data processing capabilities, and fostering real-time monitoring, ML empowers scientists and conservationists to unlock the secrets of the deep and embark on a journey towards sustainable stewardship of these invaluable ecosystems.

Machine learning applications for anomaly detection in Smart Water Metering Networks: A systematic review

Dialect Identification is the process of identifies the dialects of particular standard language. The Telugu Language is one of the historical and important languages. Like any other language Telugu also contains mainly three dialects Telangana, Costa Andhra and Rayalaseema. The research work in dialect identification is very less compare to Language identification because of dearth of database. In any dialects identification system, the database and feature engineering play vital roles because of most the words are similar in pronunciation and also most of the researchers apply statistical approaches like Hidden Markov Model (HMM), Gaussian Mixture Model (GMM), etc. to work on speech processing applications. But in today's world, neural networks play a vital role in all application domains and produce good results. One of the types of the neural networks is Deep Neural Networks (DNN) and it is used to achieve the state of the art performance in several fields such as speech recognition, speaker identification. In this, the Deep Neural Network (DNN) based model Multilayer Perceptron is used to identify the regional dialects of the Telugu Language using enhanced Mel Frequency Cepstral Coefficients (MFCC) features. To do this, created a database of the Telugu dialects with the duration of 5h and 45m collected from different speakers in different environments. The results produced by DNN model compared with HMM and GMM model and it is observed that the DNN model provides good performance.