Previously, we proposed a probabilistic data generation model represented by an unobservable tree and a sequential updating method to calculate a posterior distribution over a set of trees. The set is called a meta-tree. In this paper, we propose a more efficient batch updating method.

In this paper, we explore privacy-preserving techniques in federated learning, including those can be used with both neural networks and decision trees. We begin by identifying how information can be leaked in federated learning, after which we present methods to address this issue by introducing two privacy-preserving frameworks that encompass many existing privacy-preserving federated learning (PPFL) systems. Through experiments with publicly available financial, medical, and Internet of Things datasets, we demonstrate the effectiveness of privacy-preserving federated learning and its potential to develop highly accurate, secure, and privacy-preserving machine learning systems in real-world scenarios. The findings highlight the importance of considering privacy in the design and implementation of federated learning systems and suggest that privacy-preserving techniques are essential in enabling the development of effective and practical machine learning systems.

Multiparty computation (MPC) is a cryptographic method that enables a set of parties to compute an arbitrary joint function of the private inputs of all parties and does not reveal any information other than the output. MPC based on a secret sharing scheme (SS-MPC) and garbled circuit (GC) is known as the most common MPC schemes. Another cryptographic method, homomorphic encryption (HE), computes an arbitrary function represented as a circuit by using ciphertexts without decrypting them. These technologies are in a trade-off relationship for the communication/round complexities, and the computation cost. The private decision tree evaluation (PDTE) is one of the key applications of these technologies. There exist several constant-round PDTE protocols based on GC, HE, or the hybrid schemes that are secure even if a malicious adversary who can deviate from protocol specifications corrupts some parties. There also exist other protocols based only on SS-MPC that are secure only if a semi-honest adversary who follows the protocol specification corrupts some parties. However, to the best of our knowledge, there are currently no constant-round PDTE protocols based only on SS-MPC that are secure against a malicious adversary. In this work, we propose a constant-round four-party PDTE protocol that achieves malicious security. Our protocol provides the PDTE securely and efficiently even when the communication environment has a large latency.

Multiparty computation (MPC) is the technology that computes an arbitrary function represented as a circuit without revealing input values. Typical MPC uses secret sharing (SS) schemes, garbled circuit (GC), and homomorphic encryption (HE). These cryptographic technologies have a trade-off relationship for the computation cost, communication cost, and type of computable circuit. Hence, the optimal choice depends on the computing resources, communication environment, and function related to applications. The private decision tree evaluation (PDTE) is one of the important applications of secure computation. There exist several PDTE protocols with constant communication rounds using GC, HE, and SS-MPC over the field. However, to the best of our knowledge, PDTE protocols with constant communication rounds using MPC based on SS over the ring (requiring only lower computation costs and communication complexity) are non-trivial and still missing. In this paper, we propose a PDTE protocol based on a three-party computation (3PC) protocol over the ring with one corruption. We also propose another three-party PDTE protocol over the field with one corruption that is more efficient than the naive construction.

In this paper, we propose the first private decision tree evaluation (PDTE) schemes which are suitable for use in Machine Learning as a Service (MLaaS) scenarios. In our schemes, a user and a model owner send the ciphertexts of a sample and a decision tree model, respectively, and a single server classifies the sample without knowing the sample nor the decision tree. Although many PDTE schemes have been proposed so far, most of them require to reveal the decision tree to the server. This is undesirable because the classification model is the intellectual property of the model owner, and/or it may include sensitive information used to train the model, and therefore the model also should be hidden from the server. In other PDTE schemes, multiple servers jointly conduct the classification process and the decision tree is kept secret from the servers under the assumption they do not collude. Unfortunately, this assumption may not hold because MLaaS is usually provided by a single company. In contrast, our schemes do not have such problems. In principle, fully homomorphic encryption allows us to classify an encrypted sample based on an encrypted decision tree, and in fact, the existing non-interactive PDTE scheme can be modified so that the server classifies only handling ciphertexts. However, the resulting scheme is less efficient than ours. We also show the experimental results for our schemes.

Social media channels, such as Facebook, Twitter, and Instagram, have altered our world forever. People are now increasingly connected than ever and reveal a sort of digital persona. Although social media certainly has several remarkable features, the demerits are undeniable as well. Recent studies have indicated a correlation between high usage of social media sites and increased depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Twitter user based on both, his/her network behavior and tweets. For this purpose, we trained and tested classifiers to distinguish whether a user is depressed or not using features extracted from his/her activities in the network and tweets. The results showed that the more features are used, the higher are the accuracy and F-measure scores in detecting depressed users. This method is a data-driven, predictive approach for early detection of depression or other mental illnesses. This study's main contribution is the exploration part of the features and its impact on detecting the depression level.

For cloud data center, Virtual Machine (VM) consolidation is an effective way to save energy and improve efficiency. However, inappropriate consolidation of VMs, especially aggressive consolidation, can lead to performance problems, and even more serious Service Level Agreement (SLA) violations. Therefore, it is very important to solve the tradeoff between reduction in energy use and reduction of SLA violation level. In this paper, we propose two Host State Detection algorithms and an improved VM placement algorithm based on our proposed Host State Binary Decision Tree Prediction model for SLA-aware and energy-efficient consolidation of VMs in cloud data centers. We propose two formulas of conditions for host state estimate, and our model uses them to build a Binary Decision Tree manually for host state detection. We extend Cloudsim simulator to evaluate our algorithms by using PlanetLab workload and random workload. The experimental results show that our proposed model can significantly reduce SLA violation rates while keeping energy cost efficient, it can reduce the metric of SLAV by at most 98.12% and the metric of Energy by at most 33.96% for real world workload.

In order to provide an alternative solution of human machine interfaces, this paper proposed to recognize 10 human hand gestures regularly used in the consumer electronics controlling scenarios based on a three-dimensional radar array. This radar array was composed of three low cost 24GHz K-band Doppler CW (Continuous Wave) miniature I/Q (In-phase and Quadrature) transceiver sensors perpendicularly mounted to each other. Temporal and spectral analysis was performed to extract magnitude and phase features from six channels of I/Q signals. Two classifiers were proposed to implement the recognition. Firstly, a decision tree classifier performed a fast responsive recognition by using the supervised thresholds. To improve the recognition robustness, this paper further studied the recognition using a two layer CNN (Convolutional Neural Network) classifier with the frequency spectra as the inputs. Finally, the paper demonstrated the experiments and analysed the performances of the radar array respectively. Results showed that the proposed system could reach a high recognition accurate rate higher than 92%.

Visual object detection on embedded systems involves a multi-objective optimization problem in the presence of trade-offs between power consumption, processing performance, and detection accuracy. For a new Pareto solution with high processing performance and low power consumption, this paper proposes a hardware architecture for decision tree ensemble using multiple channels of features. For efficient detection, the proposed architecture utilizes the dimensionality of feature channels in addition to parallelism in image space and adopts task scheduling to attain random memory access without conflict. Evaluation results show that an FPGA implementation of the proposed architecture with an aggregated channel features pedestrian detector can process 229 million samples per second at 100MHz operation frequency while it requires a relatively small amount of resources. Consequently, the proposed architecture achieves 350fps processing performance for 1080P Full HD images and outperforms conventional object detection hardware architectures developed for embedded systems.

Index generation functions model content-addressable memory, and are useful in virus detectors and routers. Linear decompositions yield simpler circuits that realize index generation functions. This paper proposes a balanced decision tree based heuristic to efficiently design linear decompositions for index generation functions. The proposed heuristic finds a good linear decomposition of an index generation function by using appropriate cost functions and a constraint to construct a balanced tree. Since the proposed heuristic is fast and requires a small amount of memory, it is applicable even to large index generation functions that cannot be solved in a reasonable time by existing heuristics. This paper shows time and space complexities of the proposed heuristic, and experimental results using some large examples to show its efficiency.

High Efficiency Video Coding (HEVC) is the latest coding standard. Compared with Advanced Video coding (H.264/AVC), HEVC offers about a 50% bitrate reduction at the same reconstructed video quality. However, this new coding standard leads to enormous computational complexity, which makes it difficult to encode video in real time. Therefore, in this paper, aiming at the high complexity of intra coding in HEVC, a new fast coding unit (CU) splitting algorithm is proposed based on the decision tree. Decision tree, as a method of machine learning, can be designed to determine the size of CUs adaptively. Here, two significant features, Just Noticeable Difference (JND) values and coding bits of each CU can be extracted to train the decision tree, according to their relationships with the CUs' partitions. The experimental results have revealed that the proposed algorithm can save about 34% of time, on average, with only a small increase of BD-rate under the “All_Intra” setting, compared with the HEVC reference software.

Flow classification is of great significance for network management. Machine-learning-based flow classification is widely used nowadays, but features which depict the non-Gaussian characteristics of network flows are still absent. In this paper, we propose the Windowed Higher-order Statistical Analysis (WHOSA) for machine-learning-based flow classification. In our methodology, a network flow is modeled as three different time series: the flow rate sequence, the packet length sequence and the inter-arrival time sequence. For each sequence, both the higher-order moments and the largest singular values of the Bispectrum are computed as features. Some lower-order statistics are also computed from the distribution to build up the feature set for contrast, and C4.5 decision tree is chosen as the classifier. The results of the experiment reveals the capability of WHOSA in flow classification. Besides, when the classifier gets fully learned, the WHOSA feature set exhibit stronger discriminative power than the lower-order statistical feature set does.

This paper studies a privacy-preserving decision tree learning protocol (PPDT) for vertically partitioned datasets. In vertically partitioned datasets, a single class (target) attribute is shared by both parities or carefully treated by either party in existing studies. The proposed scheme allows both parties to have independent class attributes in a secure way and to combine multiple class attributes in arbitrary boolean function, which gives parties some flexibility in data-mining. Our proposed PPDT protocol reduces the CPU-intensive computation of logarithms by approximating with a piecewise linear function defined by light-weight fundamental operations of addition and constant multiplication so that information gain for attributes can be evaluated in a secure function evaluation scheme. Using the UCI Machine Learning dataset and a synthesized dataset, the proposed protocol is evaluated in terms of its accuracy and the sizes of trees*.

Packet classification is a fundamental task in the control of network traffic, protection from cyber threats. Most layer 3 and higher network devices have a packet classification capability that determines whether to permit or discard incoming packets by comparing their headers with a set of rules. Although linear search is an intuitive implementation of packet classification, it is very inefficient. Srinivasan et al. proposed a novel lookup scheme using a hierarchical trie instead of linear search, which realizes faster packet classification with time complexity proportional to rule length rather than the number of rules. However, the hierarchical trie and its various improved algorithms allow only single prefix rules to be processed. Since it is necessary for layer 4 and higher packet classifications to deal with arbitrary bitmask rules in the hierarchical trie, we propose a run-based trie based on the hierarchical trie, but extended to deal with arbitrary bitmask rules. Our proposed algorithm achieves O((dW)2) query time and O(NdW) space complexity with N rules of length dW. The query time of our novel alrorithm doesn't depend on the number of rules. It solves the latency problem caused by increase of the rules in firewalls.

This paper describes a novel method to improve the performance of second language speech recognition when the mother tongue of users is known. Considering that second language speech usually includes less fluent pronunciation and more frequent pronunciation mistakes, the authors propose using a reduced phoneme set generated by a phonetic decision tree (PDT)-based top-down sequential splitting method instead of the canonical one of the second language. The authors verify the efficacy of the proposed method using second language speech collected with a translation game type dialogue-based English CALL system. Experiments show that a speech recognizer achieved higher recognition accuracy with the reduced phoneme set than with the canonical phoneme set.

A two-stage classifier is proposed that identifies criminal charges and a range of punishments given a set of case facts and attributes. Our supervised-learning model focuses only on the offences against life and body section of the criminal law code of Thailand. The first stage identifies a set of diagnostic issues from the case facts using a set of artificial neural networks (ANNs) modularized in hierarchical order. The second stage extracts a set of legal elements from the diagnostic issues by employing a set of C4.5 decision tree classifiers. These linked modular networks of ANNs and decision trees form an effective system in terms of determining power and the ability to trace or infer the relevant legal reasoning behind the determination. Isolated and system-integrated experiments are conducted to measure the performance of the proposed system. The overall accuracy of the integrated system can exceed 90%. An actual case is also demonstrated to show the effectiveness of the proposed system.

Automatic modulation classification (AMC) involves extracting a set of unique features from the received signal. Accuracy and uniqueness of the features along with the appropriate classification algorithm determine the overall performance of AMC systems. Accuracy of any modulation feature is usually limited by the blindness of the signal information such as carrier frequency, symbol rate etc. Most papers do not sufficiently consider these impairments and so do not directly target practical applications. The AMC system proposed herein is trained with probable input signals, and the appropriate decision tree should be chosen to achieve robust classification. Six unique features are used to classify eight analog and digital modulation schemes which are widely used by low frequency mobile emergency radios around the globe. The Proposed algorithm improves the classification performance of AMC especially for the low SNR regime.

Decision tree-based clustering and parameter estimation are essential steps in the training part of an HMM-based speech synthesis system. These two steps are usually performed based on the maximum likelihood (ML) criterion. However, one of the drawbacks of the ML criterion is that it is sensitive to outliers which usually result in quality degradation of the synthesized speech. In this letter, we propose an approach to detect and remove outliers for HMM-based speech synthesis. Experimental results show that the proposed approach can improve the synthetic speech, particularly when the available training speech database is insufficient.

This paper proposes likelihood smoothing techniques to improve decision tree-based acoustic models, where decision trees are used as replacements for Gaussian mixture models to compute the observation likelihoods for a given HMM state in a speech recognition system. Decision trees have a number of advantageous properties, such as not imposing restrictions on the number or types of features, and automatically performing feature selection. This paper describes basic configurations of decision tree-based acoustic models and proposes two methods to improve the robustness of the basic model: DT mixture models and soft decisions for continuous features. Experimental results for the Aurora 2 speech database show that a system using decision trees offers state-of-the-art performance, even without taking advantage of its full potential and soft decisions improve the performance of DT-based acoustic models with 16.8% relative error rate reduction over hard decisions.

Scene-context plays an important role in scene analysis and object recognition. Among various sources of scene-context, we focus on scene-context scale, which means the effective scale of local context to classify an image pixel in a scene. This paper presents random forests based image categorization using the scene-context scale. The proposed method uses random forests, which are ensembles of randomized decision trees. Since the random forests are extremely fast in both training and testing, it is possible to perform classification, clustering and regression in real time. We train multi-scale texton forests which efficiently provide both a hierarchical clustering into semantic textons and local classification in various scale levels. The scene-context scale can be estimated by the entropy of the leaf node in the multi-scale texton forests. For image categorization, we combine the classified category distributions in each scale and the estimated scene-context scale. We evaluate on the MSRC21 segmentation dataset and find that the use of the scene-context scale improves image categorization performance. Our results have outperformed the state-of-the-art in image categorization accuracy.