Silicon lifecycle management (SLM) is essential for ensuring the reliability and quality of silicon products. Traditional approaches primarily rely on off-chip solutions to detect malware, diagnose hardware bugs, and characterize silicon health metrics. However, these methods do not incorporate hardware/software co-design for SLM. This work introduces On- Chip Telemetry-based Anomaly Notification Engine (OCTANE), designed to monitor chip status using performance counters and sensors. OCTANE features a compute- and memory-efficient, unsupervised anomaly detection mechanism implemented on-chip (OCTANE-edge) using fixed-point arithmetic. Furthermore, it enhances on-chip anomaly detection through unsupervised feature ranking based on telemetry feature information entropy and compression index. This unsupervised feature ranking technique is workload-independent and provides the generalizability required for SLM. The proposed solution extends to an end-to-end anomaly-informed diagnosis model that leverages OCTANE-edge compacted anomaly telemetry signatures to diagnose chip security or safety incidents (OCTANE-cloud). All telemetry data is collected via model-specific register space using open-source Linux tools and the performance counter monitor. To validate our approach, we capture chip telemetry signatures from the PAMPAR benchmark suite under anomaly-inducing events such as security attacks (e.g., Rowhammer and Spectre) and voltage droops across two Intel platforms. OCTANE demonstrates highly effective unsupervised on-chip anomaly detection with minimal area and idle power overhead (1.2% and 2.6%). OCTANE provides anomaly detection/diagnosis with accuracy surpassing 0.96/0.98.

Memory and compute constraints make anomaly detection model training infeasible on Internet of Things (IoT) resource-limited edge devices. Many solutions train anomaly detection models (e.g., deep neural networks or DNNs) on the cloud and deploy them on IoT edge devices for inferencing. However, cloud-based training does not address overall communication latency and potential data leakage. Moreover, because anomalies rarely occur, using labels to define anomalies is impractical. Hence, supervised learning mechanisms are unsuitable for anomaly detection. There is a need for effective unsupervised anomaly detection for resource-constrained edge devices. We present the discretized isolation Forest (DIF) to address memory- and compute-efficient unsupervised anomaly detection for resource-constrained edge devices. We also present a discretization function, based on information entropy, to inform the growth of the isolation Forest (IF) ensemble to create the DIF. The DIF reduces the training time (memory usage) of the original IF by$79.38\times (166.66\times)$. We test the DIF against general anomaly detection benchmarks and edge-anomaly detection benchmarks. The edge-anomaly detection benchmarks were curated from the built-in iPhone edge sensors. Across all the edge-sensor anomaly detection datasets and against all the other considered models, the discretized isolation resulted in the lowest training time, lowest memory usage, preserved anomaly detection performance, and highest inference speeds. In addition, across all general anomaly detection benchmarks and against all considered models, DIF incurs lower training time and memory usage while retaining competitive inferencing execution time and anomaly detection performance.

Silicon lifecycle management (SLM) is needed to ensure silicon-product reliability and quality. Prior methods utilize off-chip solutions to identify malware, diagnose bugs, and characterize silicon health metrics. These methods do not explore hardware/software codesign for SLM. In this work, we present a new method called Efficient-Spatial Clustering-based OUlier detection through Telemetry (E-SCOUT) to monitor a chip’s status through performance counters/sensors. E-SCOUT includes a compute- and memory-efficient unsupervised 32-bit floating point outlier detection mechanism implemented on-chip (E-SCOUT edge). In addition, it enhances on-chip outlier detection through unsupervised feature ranking based on the telemetry feature information entropy. We also provide microarchitectural recommendations to enable a hardware/software co-design of E-SCOUT edge. The proposed solution includes an end-to-end outlier-informed diagnosis model with real telemetry data (E-SCOUT cloud). All telemetry data is collected through the model-specific register space using open-source Linux tools and Intel’s performance counter monitor. We capture the chip telemetry signatures of the PAMPAR benchmark suite in the presence of outlier events such as security attacks (e.g., Rowhammer and SPECTRE) and voltage droops. E-SCOUT provides effective unsupervised on-chip outlier detection performance with high accuracy levels (over 0.9) and with low area and low power over-head (2.2% die area overhead and 1% idle power consumption). Outlier diagnosis can identify the chip’s status with classification accuracy and F1-scores that exceed 0.8.

Active learning and transfer learning are two different methodologies that address the common problem of insufficient labels. Transfer learning addresses this problem by using the knowledge gained from a related and already labeled data source, whereas active learning focuses on selecting a small set of informative samples for manual annotation. Recently, there has been much interest in developing frameworks that combine both transfer and active learning methodologies. A few such frameworks reported in literature perform transfer and active learning in two separate stages. In this work, we present an integrated framework that performs transfer and active learning simultaneously by solving a single convex optimization problem. The proposed framework computes the weights of source domain data and selects the samples from the target domain data simultaneously, by minimizing a common objective of reducing distribution difference between the data set consisting of reweighted source and the queried target domain data and the set of unlabeled target domain data. Comprehensive experiments on three real world data sets demonstrate that the proposed method improves the classification accuracy by 5% to 10% over the existing two-stage approach

Active Learning is a machine learning and data mining technique that selects the most informative samples for labeling and uses them as training data; it is especially useful when there are large amount of unlabeled data and labeling them is expensive. Recently, batch-mode active learning, where a set of samples are selected concurrently for labeling, based on their collective merit, has attracted a lot of attention. The objective of batch-mode active learning is to select a set of informative samples so that a classifier learned on these samples has good generalization performance on the unlabeled data. Most of the existing batch-mode active learning methodologies try to achieve this by selecting samples based on certain criteria. In this article we propose a novel criterion which achieves good generalization performance of a classifier by specifically selecting a set of query samples that minimize the difference in distribution between the labeled and the unlabeled data, after annotation. We explicitly measure this difference based on all candidate subsets of the unlabeled data and select the best subset. The proposed objective is an NP-hard integer programming optimization problem. We provide two optimization techniques to solve this problem. In the first one, the problem is transformed into a convex quadratic programming problem and in the second method the problem is transformed into a linear programming problem. Our empirical studies using publicly available UCI datasets and two biomedical image databases demonstrate the effectiveness of the proposed approach in comparison with the state-of-the-art batch-mode active learning methods. We also present two extensions of the proposed approach, which incorporate uncertainty of the predicted labels of the unlabeled data and transfer learning in the proposed formulation. In addition, we present a joint optimization framework for performing both transfer and active learning simultaneously unlike the existing approaches of learning in two separate stages, that is, typically, transfer learning followed by active learning. We specifically minimize a common objective of reducing distribution difference between the domain adapted source, the queried and labeled samples and the rest of the unlabeled target domain data. Our empirical studies on two biomedical image databases and on a publicly available 20 Newsgroups dataset show that incorporation of uncertainty information and transfer learning further improves the performance of the proposed active learning based classifier. Our empirical studies also show that the proposed transfer-active method based on the joint optimization framework performs significantly better than a framework which implements transfer and active learning in two separate stages.

Active Learning is a machine learning and data mining technique that selects the most informative samples for labeling and uses them as training data; it is especially useful when there are large amount of unlabeled data and labeling them is expensive. Recently, batch-mode active learning, where a set of samples are selected concurrently for labeling, based on their collective merit, has attracted a lot of attention. The objective of batch-mode active learning is to select a set of informative samples so that a classifier learned on these samples has good generalization performance on the unlabeled data. Most of the existing batch-mode active learning methodologies try to achieve this by selecting samples based on varied criteria. In this paper we propose a novel criterion which achieves good generalization performance of a classifier by specifically selecting a set of query samples that minimizes the difference in distribution between the labeled and the unlabeled data, after annotation. We explicitly measure this difference based on all candidate subsets of the unlabeled data and select the best subset. The proposed objective is an NP-hard integer programming optimization problem. We provide two optimization techniques to solve this problem. In the first one, the problem is transformed into a convex quadratic programming problem and in the second method the problem is transformed into a linear programming problem. Our empirical studies using publicly available UCI datasets and a biomedical image dataset demonstrate the effectiveness of the proposed approach in comparison with the state-of-the-art batch-mode active learning methods. We also present two extensions of the proposed approach, which incorporate uncertainty of the predicted labels of the unlabeled data and transfer learning in the proposed formulation. Our empirical studies on UCI datasets show that incorporation of uncertainty information improves performance at later iterations while our studies on 20 Newsgroups dataset show that transfer learning improves the performance of the classifier during initial iterations.

We consider the characterization of muscle fatigue through a noninvasive sensing mechanism such as Surface ElectroMyoGraphy (SEMG). While changes in the properties of SEMG signals with respect to muscle fatigue have been reported in the literature, the large variation in these signals across different individuals makes the task of modeling and classification of SEMG signals challenging. Indeed, the variation in SEMG parameters from subject to subject creates differences in the data distribution. In this article, we propose two transfer learning frameworks based on the multisource domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed frameworks, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the first framework is a novel weighting scheme that addresses the conditional probability distribution differences across multiple domains (subjects) and the key feature of the second framework is a two-stage domain adaptation methodology which combines weighted data from multiple sources based on marginal probability differences (first stage) as well as conditional probability differences (second stage), with the target domain data. The weights for minimizing the marginal probability differences are estimated independently, while the weights for minimizing conditional probability differences are computed simultaneously by exploiting the potential interaction among multiple sources. We also provide a theoretical analysis on the generalization performance of the proposed multisource domain adaptation formulation using the weighted Rademacher complexity measure. We have validated the proposed frameworks on Surface ElectroMyoGram signals collected from 8 people during a fatigue-causing repetitive gripping activity. Comprehensive experiments on the SEMG dataset demonstrate that the proposed method improves the classification accuracy by 20% to 30% over the cases without any domain adaptation method and by 13% to 30% over existing state-of-the-art domain adaptation methods.

We consider the characterization of muscle fatigue through noninvasive sensing mechanism such as surface electromyography (SEMG). While changes in the properties of SEMG signals with respect to muscle fatigue have been reported in the literature, the large variation in these signals across different individuals makes the task of modeling and classification of SEMG signals challenging. Indeed, the variation in SEMG parameters from subject to subject creates differences in the data distribution. In this paper, we propose a transfer learning framework based on the multi-source domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed framework, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the proposed framework is a novel weighting scheme that addresses the conditional probability distribution differences across multiple domains (subjects). We have validated the proposed framework on Surface Electromyogram signals collected from 8 people during a fatigue-causing repetitive gripping activity. Comprehensive experiments on the SEMG data set demonstrate that the proposed method improves the classification accuracy by 20% to 30% over the cases without any domain adaptation method and by 13% to 30% over the existing state-of-the-art domain adaptation methods.

Discriminative learning when training and test data belong to different distributions is a challenging and complex task. Often times we have very few or no labeled data from the test or target distribution but may have plenty of labeled data from multiple related sources with different distributions. The difference in distributions may be in both marginal and conditional probabilities. Most of the existing domain adaptation work focuses on the marginal probability distribution difference between the domains, assuming that the conditional probabilities are similar. However in many real world applications, conditional probability distribution differences are as commonplace as marginal probability differences. In this paper we propose a two-stage domain adaptation methodology which combines weighted data from multiple sources based on marginal probability differences (first stage) as well as conditional probability differences (second stage), with the target domain data. The weights for minimizing the marginal probability differences are estimated independently, while the weights for minimizing conditional probability differences are computed simultaneously by exploiting the potential interaction among multiple sources. We also provide a theoretical analysis on the generalization performance of the proposed multi-source domain adaptation formulation using the weighted Rademacher complexity measure. Empirical comparisons with existing state-of-the-art domain adaptation methods using three real-world datasets demonstrate the effectiveness of the proposed approach.

Ubiquitous and pervasive computing systems are characterized by intelligent sensing and computing. These systems seamlessly understand and respond to the environment with little human intervention. Since such systems are required to be small and inobtrusive, embedded systems play an important role in their design. Furthermore, these systems need to run sophisticated applications in a resource constrained environment. In this paper we focus on computer vision applications in such systems. As these applications require larger memory and are computationally intensive, optimization of these algorithms is imperative. This paper discusses some optimization techniques and their impact on execution time in a complex real-world face tracking example. In certain scenarios, the requirement may be to suggest a hardware architecture for achieving a specific response time. This is especially important for mission critical applications in the fields of automotive, medical or defence. However, the estimation of hardware architecture parameters such as core-clock frequency, memory requirement, optimal number of parallel execution paths for a given application is not straight forward. In this paper, we also present a structured approach to determine the hardware architecture for a driver assistance and safety application with stringent performance constraints.

The advent of third generation smart cameras has increased the use of digital video in the areas of defense and civil surveillance and transportation systems. Advances in processor architecture, coupled with improved image processing algorithms, have made it feasible to design and operate, complex vision applications on a smart camera. This paper presents an efficient traffic-monitoring algorithm to detect stationary vehicles in varying environmental lighting conditions. Illumination invariance is achieved by using adaptive thresholds based on reflectance modeling. The algorithm is implemented on a DSP-based smart camera and optimized to run in real-time. We explain the different optimizations implemented to achieve real-time performance of nearly 30 frames per second along with extensive experimental results to prove the efficiency of the system.