Average Performance Improvement Research Articles

Exploring Prior Knowledge from Human Mobility Patterns for POI Recommendation

Point of interest (POI) recommendation is an important task in location-based social networks. It plays a critical role in smart tourism and makes it more likely for tourists to have personalized travel experiences. However, most current recommendation methods are based on learning the users’ check-in history and the users’ relationship network in the social network to make recommendations.Therefore, urban crowds’ regular travel patterns cannot be effectively utilized. In this paper, we propose a POI recommendation algorithm (HMRec) based on prior knowledge of human mobility patterns to solve this problem. Specifically, we propose the Human Mobility Pattern Extraction (HMPE) framework, which utilizes graph neural networks as extractors for human mobility patterns. The framework incorporates attention mechanisms to capture spatio-temporal information in urban traffic patterns. HMPE employs downstream tasks and design upsampling modules to reconstruct representation vectors for task objectives, enabling end-to-end training of the framework and obtaining pre-trained parameters for the human mobility pattern extractor. Furthermore, we introduce the Human Mobility Recommendation (HMRec) algorithm, which improves feature cross-interactions in the breadth model and incorporates prior knowledge of human patterns. This ensures that the recommendation results align more closely with human travel patterns in urban environments. Comparative experiments conducted on the Foursquare dataset demonstrate that HMRec outperforms baseline models with an average performance improvement of approximately 3%. Finally, we discuss existing challenges and future research directions, including approaches to address the issue of data sparsity.

Energy-efficient smart solar system cooling for real-time dynamic weather changes in mild-climate regions

With changes in climatic conditions, the performance of photovoltaic power plant installations fluctuates, mainly due to excessive heat. The question of their efficient cooling comes to the fore, especially direct cooling, either by cooling media or air. Here, it is proven that the active cooling of photovoltaic panels leads to an increase in the performance, but the overall costs may exceed the benefits (especially for smaller/household installations). Moreover, in conventional approaches, increasing efficiency does not take into account sudden weather changes in the areas that have long been considered stable, such as the temperate climate zone. The proposed solution addresses the maximum number of parameters that can affect the cooling efficiency and introduces effortless rapid decision making system to ensure whether the conditions for active smart cooling are met or not. Parameters such as the amount of cooling medium (rainwater), its temperature, flow control, panel temperature, and the current prediction of local weather conditions based on the rapid changes in barometric pressure are monitored and then used for intelligent automation. By implementing efficient cooling system control that has to evaluate series of input parameters in real-time it was experimentally verified that the performance of photovoltaic panel installation using the spray cooling control system achieves average performance improvement of 14%.

Boosting the transferability of adversarial attacks with adaptive points selecting in temporal neighborhood

Deep neural networks are highly susceptible to imperceptible noise, even to the human eye. While high attack success rate has been achieved in white-box setting, the attack performance tends to decline in black-box environments. To address this challenge, this study introduces a novel adaptive points selecting iterative fast gradient sign method, named AI-FGSM, which leverages temporal neighborhoods to enhance transferability performance in black-box environments. AI-FGSM is unique in that it extracts gradients from additional points in the temporal neighborhood and adjusts the current gradient using previous gradients to maintain the updated trend's stability. This gradient correction enables faster optimization and restricts falling into local optima. Experimental results on the ImageNet dataset show that AI-FGSM outperforms advanced gradient-based attack methods such as MI-FGSM and NI-FGSM in terms of attack success rate and transferability. Moreover, in black-box environments, AI-FGSM achieves an average attack performance improvement of 44.2% for some models with adversarial training and 32.9% for several models without adversarial training. These results confirm the performance and effectiveness of AI-FGSM, underscoring its potential as a powerful tool for improving the transferability of adversarial attacks.

AttSec: protein secondary structure prediction by capturing local patterns from attention map

BackgroundProtein secondary structures that link simple 1D sequences to complex 3D structures can be used as good features for describing the local properties of protein, but also can serve as key features for predicting the complex 3D structures of protein. Thus, it is very important to accurately predict the secondary structure of the protein, which contains a local structural property assigned by the pattern of hydrogen bonds formed between amino acids. In this study, we accurately predict protein secondary structure by capturing the local patterns of protein. For this objective, we present a novel prediction model, AttSec, based on transformer architecture. In particular, AttSec extracts self-attention maps corresponding to pairwise features between amino acid embeddings and passes them through 2D convolution blocks to capture local patterns. In addition, instead of using additional evolutionary information, it uses protein embedding as an input, which is generated by a language model.ResultsFor the ProteinNet DSSP8 dataset, our model showed 11.8% better performance on the entire evaluation datasets compared with other no-evolutionary-information-based models. For the NetSurfP-2.0 DSSP8 dataset, it showed 1.2% better performance on average. There was an average performance improvement of 9.0% for the ProteinNet DSSP3 dataset and an average of 0.7% for the NetSurfP-2.0 DSSP3 dataset.ConclusionWe accurately predict protein secondary structure by capturing the local patterns of protein. For this objective, we present a novel prediction model, AttSec, based on transformer architecture. Although there was no dramatic accuracy improvement compared with other models, the improvement on DSSP8 was greater than that on DSSP3. This result implies that using our proposed pairwise feature could have a remarkable effect for several challenging tasks that require finely subdivided classification. Github package URL is https://github.com/youjin-DDAI/AttSec.

Cochlear implantation in children with congenital inner ear malformations - Our experience

To share our experience of the surgical challenges faced in cochlear implanted patients with inner ear malformation and to assess the auditory and speech perception outcomes. Clinical records of 502 cochlear implant procedures were reviewed and data of 122 patients who had inner ear malformations were enrolled in the study. Their auditory and speech performances were evaluated post implantation for 3 years. Cerebrospinal fluid gusher was encountered during opening of cochlea in 42 patients (34.4%) and one patient was re-explored within 24h. In 30.3% of cases facial anomaly was found. Significant improvement in average performance was seen in all malformation types except in cochlear hypoplasia at 12 months postoperatively. Surgical challenges can be overcome with expertise and giving special attention to preoperative imaging. Our experience suggests that outcomes are favourable in patients with inner ear malformations too.

Meta-relation assisted knowledge-aware coupled graph neural network for recommendation

Currently, the sparsity of user–item interaction data limits the performance of recommender systems. To alleviate the problems caused by data sparsity, researchers are devoted to designing more powerful graph neural network models to fuse the auxiliary information of users and items (social relationships, item dependencies, etc.). However, the lack of in-depth exploration of auxiliary information and the lack of optimization of the spatially distributed properties of the generated representations (known as embeddings) make it difficult to further improve the recommendation performance of these models. To address the above challenges, we propose a meta-relation-assisted knowledge-aware coupled graph neural network (MKCGN). Specifically, we design meta-relationship-guided graph neural networks for capturing collaborative signals from user and item domains and introduce coupled graph neural networks to inject local relationships into user/item representations. In addition, we design an auxiliary task that optimizes the distribution properties (alignment and uniformity) of the representation on the unit hypersphere to improve the quality of the representation. To evaluate the performance of MKCGN, we compare it with the state-of-the-art model on two real-world datasets with average performance improvements of 5.26% and 4.87%(using HR@N and NDCG@N as evaluation metrics), respectively. Our implemented model is available via https://github.com/Ganoder/MKCGN.

Enhanced Multicore Performance Using Novel Thread-Aware Cache Coherence and Prefetch-Control Mechanism

We propose a hardware technique for cache coherence over the existing approaches that ensure that shared and less frequently used cache blocks bypass private caches of multiple cores. Furthermore, this manuscript proposes a mechanism to tune the aggressiveness of a data prefetcher. Increased cache hit rate and improved performance have been observed since coherence management and prefetching delays are avoided using the proposed bypassing and thread progress-aware prefetch controlling mechanism. Our approach shows around 19% improvement in cache hit rate and 29% average performance improvement over existing state-of-the-art techniques for Parsec & Splash-2 multithreaded benchmarks.

The Influence of Deflector on the Performance of Cross-Flow Savonius Turbine

Several factors, including the accessibility of energy sources, influence the movement of human activities in this era. However, humans still rely on fossil energy sources. For example, petroleum is non-renewable and can pollute the environment. As a result, researchers have recently been competing to produce various forms of using renewable energy sources. Ocean current energy is one of Indonesia's greatest energy potentials and a hydrokinetic turbine is a device that can harness it. Due to its ability to run on low-speed currents, the vertical-type Savonius turbine has been developed by numerous researchers up until this point. However, there has not yet to be much advancement in the cross-flow type Savonius turbine. The turbine's performance is investigated in this study by adding a flow deflector because the water flow that propels the returning blade is diverted and intensifies the advancing blade flow. Computational Fluid Dynamics (CFD) software has been used to conduct the analysis. The deflector has been added, and the results have showed an average performance improvement of 12% in overall variations. The maximum Cp of 0.299 has been achieved with a deflector configuration angle of 42° at a TSR of 0.74.

Anomaly detection using a model-agnostic meta-learning-based variational auto-encoder for facility management

In a smart building, various types of sensor data are generated and employed to control devices within the building. Detecting anomalies in these sensor data is critical for effective facility management because it can prevent device malfunction or failure. Although deep learning-based methods have been used to detect anomalies, effective model construction is challenging because abnormal data tend to be rare under real-world conditions. In image classification and load forecasting, model-agnostic meta-learning (MAML) has recently been proposed to alleviate this problem using common knowledge learned from various tasks. This paper proposes an MAML-based unsupervised anomaly detection method called MAVAE for time-series sensor data. The proposed method uses a variational auto-encoder (VAE) as an anomaly detection model and adapts the model to a new target task with few unlabeled anomaly data via MAML. To our knowledge, this is the first study to train a VAE using MAML with time-series data. Extensive experiments on public data reveals that the proposed method outperforms existing anomaly detection methods, achieving an average improvement in prediction performance of 45% compared to state-of-the-art methods. The robustness of the proposed method is also demonstrated by evaluating its performance with a different number of samples for MAML. Our code is available at github.com/17011813/MAVAE.

ACCURATE: Accuracy Maximization for Real-Time Multicore Systems With Energy-Efficient Way-Sharing Caches

Improving result accuracy in approximate computing (AC)-based real-time applications without violating deadlines has recently become an active research domain. Execution time of AC real-time tasks can individually be separated into: execution of the mandatory part to obtain a result of acceptable quality, followed by a partial/complete execution of the optional part to improve the result accuracy of the initial result within a given deadline. However, obtaining higher result accuracy at the cost of enhanced execution time may lead to deadline violation, along with higher energy usage. We present ACCURATE, a novel hybrid offline–online approximate real-time scheduling approach that first schedules AC-based tasks on multicore with an objective to maximize result accuracy and determines operational processing speeds for each task constrained by system-wide power limit, deadline, and task dependency. At runtime, by employing a way-sharing technique (WH_LLC) at the last level cache (LLC), ACCURATE improves performance, which is further leveraged, to enhance result accuracy by executing more from the optional part and to improve the energy efficiency of the cache by turning off a controlled number of cache ways. ACCURATE also exploits the slacks either to improve the result accuracy of the tasks or to enhance the energy efficiency of the underlying system, or both. ACCURATE achieves 85% QoS with 36% average reduction in cache leakage consumption with a 24% average gain in energy-delay product (EDP) for a 4-core-based chip multiprocessor (CMP) with 6.4% average improvement in performance.

Feedback-Assisted Automatic Target and Clutter Discrimination Using a Bayesian Convolutional Neural Network for Improved Explainability in SAR Applications

In this paper, a feedback training approach for efficiently dealing with distribution shift in synthetic aperture radar target detection using a Bayesian convolutional neural network is proposed. After training the network on in-distribution data, it is tested on out-of-distribution data. Samples that are classified incorrectly with high certainty are fed back for a second round of training. This results in the reduction of false positives in the out-of-distribution dataset. False positive target detections challenge human attention, sensor resource management, and mission engagement. In these types of applications, a reduction in false positives thus often takes precedence over target detection and classification performance. The classifier is used to discriminate the targets from the clutter and to classify the target type in a single step as opposed to the traditional approach of having a sequential chain of functions for target detection and localisation before the machine learning algorithm. Another aspect of automated synthetic aperture radar detection and recognition problems addressed here is the fact that human users of the output of traditional classification systems are presented with decisions made by “black box” algorithms. Consequently, the decisions are not explainable, even to an expert in the sensor domain. This paper makes use of the concept of explainable artificial intelligence via uncertainty heat maps that are overlaid onto synthetic aperture radar imagery to furnish the user with additional information about classification decisions. These uncertainty heat maps facilitate trust in the machine learning algorithm and are derived from the uncertainty estimates of the classifications from the Bayesian convolutional neural network. These uncertainty overlays further enhance the users’ ability to interpret the reasons why certain decisions were made by the algorithm. Further, it is demonstrated that feeding back the high-certainty, incorrectly classified out-of-distribution data results in an average improvement in detection performance and a reduction in uncertainty for all synthetic aperture radar images processed. Compared to the baseline method, an improvement in recall of 11.8%, and a reduction in the false positive rate of 7.08% were demonstrated using the Feedback-assisted Bayesian Convolutional Neural Network or FaBCNN.

Image Contrast Enhancement in CT SCAN for Determining Cervical Cancer Area

The quality of the contrast enhancement, which is deemed to be vague in contrast between one region and another, is a problem that many doctors face once identifying their patients with CT scan images. Image correction was used in this study to help doctors gain good CT scan images. In addition to reducing errors in the administering of radiation doses during treatment, accurate images are used to locate and assess the extent of cancer in patients. In this study, a computer application program to improve image contrast was created using the linear regression equation method. In this investigation, the cancer area is still being manually marked by doctors. Additionally, the proportion of the cancer area in the image that the doctor marked from the corrected image is calculated by comparing the ratio of cancer pixels to body pixels. The severity of the cancer is estimated using the proportion of the affected area. The error percentage for the average improvement in application performance is 0.15689%.

Reinforcement Learning-Based Joint Reliability and Performance Optimization for Hybrid-Cache Computing Servers

Computing servers play a key role in the development and process of emerging compute-intensive applications in recent years. However, they need to operate efficiently from an energy perspective viewpoint, while maximizing the performance and lifetime of the hottest server components (i.e., cores and cache). Previous methods focused on either improving energy efficiency by adopting new hybrid-cache architectures including the resistive random-access memory (RRAM) and static random-access memory (SRAM) at the hardware level, or exploring tradeoffs between lifetime limitation and performance of multicore processors under stable workloads conditions. Therefore, no work has so far proposed a co-optimization method with hybrid-cache-based server architectures for real-life dynamic scenarios taking into account scalability, performance, lifetime reliability, and energy efficiency at the same time. In this article, we first formulate a reliability model for the hybrid-cache architecture to enable precise lifetime reliability management and energy efficiency optimization. We also include the performance and energy overheads of cache switching, and optimize the benefits of hybrid-cache usage for better energy efficiency and performance. Then, we propose a runtime <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$q$ </tex-math></inline-formula> -learning-based reliability management and performance optimization approach for multicore microprocessors with the hybrid-cache architecture, jointly incorporated with a dynamic preemptive priority queue management method to improve the overall tasks’ performance by targeting to respect their end time limits. Experimental results show that our proposed method achieves up to 44% average performance (i.e., tasks execution time) improvement, while maintaining the whole system design lifetime longer than five years, when compared to the latest state-of-the-art energy efficiency optimization and reliability management methods for computing servers.

Design of Ternary Logic Circuits using Pseudo N-type CNTFETs

In this paper, a novel method is presented to design ternary logic circuits for nanoelectronics applications. The ternary logic is a best alternative to the binary logic because it offers reduced interconnects, faster operating speed and reduced chip area. The digital logic circuit designs are developed using Pseudo N-type carbon nanotube field effect transistors (CNTFETs). The threshold voltage of CNTFETs is altered by the CNT diameter that is defined by the chirality vector. The ternary inverters such as standard inverter (SI), positive inverter (PI) and negative inverter (NI) and ternary basic gates such as AND, NAND, OR and NOR gates are designed. Furthermore, the half adder circuits developed which assists to develop complex circuit schematics. The proposed ternary schematics are designed and simulated using the HSPICE simulator. Moreover, the performance of the proposed circuits are investigated in terms of delay, power dissipation and power delay product (PDP) and compared with the existing circuits. It is observed that the proposed circuits show average performance improvement up to 47.48% over the existing circuits.

Blind Carrier Phase Recovery Using Extended Kalman Filtering in Probabilistically Shaped Coherent Systems

In this paper, we propose an Extended Kalman Filtering with phase noise reconstruction (EKF-PC) scheme to enhance the carrier recovery capability for probabilistic shaping of coherent optical communication systems with various shaping factors. We first investigate the weights of the shaping factor and the noise rejection window length of EKF-PC for PS-64QAM at a fixed signal-to-noise ratio (SNR). After that, we jointly optimize the shaping factor and the noise rejection window length to obtain the maximum achievable information rate at a variety of SNRs. Then, we numerically analyze the carrier recovery performance of the EKF-PC for different linewidths and SF conditions. Finally, we conduct simulation experiments to compare EKF-PC, PCPE, and other currently available Kalman CPE algorithms with the SFs of 0.02, 0.025, 0.03, and 0.035 under back-to-back (B2B) scenarios. The experimental results show that EKF-PC obtains an average SNR improvement of 0.13–0.5 dB compared to PCPE and an average performance improvement of 0.5–1 dB compared to other Kalman algorithms.

Power controlled outage-aware optimal protocol for NOMA-assisted underlay D2D networks

Underlay device-to-device (D2D) and non-orthogonal multiple access (NOMA) are two promising technologies that have potential to enhance the spectral efficiency for future wireless communication systems. This paper studies an underlay D2D-NOMA system in an uplink cellular network. Different from the previous works, we minimize the outage probability (OP) while allocating optimal power to the D2D group receivers. Specifically, a D2D power allocation (DPA) problem is formulated and a globally-optimal solution is obtained. As a special case, closed-form expressions are also derived for asymptotic OP-based DPA. Results are numerically validated, and an overall average performance improvement of at least 24% is observed over existing conventional power control schemes.

Performance evaluation of short-term cross-building energy predictions using deep transfer learning strategies

Performing accurate building energy prediction (BEP) is one of the most important foundations for achieving energy resource allocation and developing energy efficiency measures. Buildings are diverse and operate under complex conditions leading to distribution differences of energy-related data among different buildings. Owing to such differences, the already reported data-driven BEP models exhibit poor cross-building prediction performance since they only use insufficient operation data of a single building. Although several deep transfer learning (DTL) strategies have been applied with improved cross-building prediction performance, there is still a lack of comparison of various DTL strategies, which would help to determine the optimal DTL strategy for different scenarios. Hence, three DTL strategies were compared: network-based Fine-tune, adversarial-based domain adversarial neural network (DANN), and mapping-based domain adaptive neural network (DaNN). The usefulness of the DTL strategy was validated using the open source dataset Building Data Genome Project 2 in the scenario of insufficient available data for real buildings. The influences of several factors were analysed, such as the available data volumes of the source and target domains within the training set. The applicability of different DTL strategies was discussed considering both accuracy and computational cost. Results show that the three DTL strategies outperform the traditional long short-term memory (LSTM) with an average BEP performance improvement ratio (PIR) of 0.75. For the extremely limited amount of available training data scenario, Fine-tune was recommended for the next-few-weeks prediction owing to its good balance between time cost and prediction performance. For the data shortage scenario of BEP tasks for nearly a year, DANN was recommended owing to its outperforming prediction accuracy. This provides insights for practical applications of DTL during the development of BEP models for cross-building BEP tasks without sufficient operation data.

Predicting Stock Market Volatility from Candlestick Charts: A Multiple Attention Mechanism Graph Neural Network Approach

As an important part of financial market, stock market price volatility analysis has been the focus of academic and industry attention. Candlestick chart, as the most widely used indicator for evaluating stock market price volatility, has been intensively studied and explored. With the continuous development of computer technology, the stock market analysis method based on candlestick chart is gradually changed from manual to intelligent algorithm. However, how to effectively use stock market graphical indicators to analyze stock market price fluctuations has been pending solution, and deep learning algorithms based on structured data such as deep neural networks (DNN) and recurrent neural networks (RNNs) always have the problems of making it difficult to capture the laws and low generalization ability for stock market graphical indicators data processing. Therefore, this paper proposes a quantification method of stock market candlestick chart based on Hough variation, using the graph structure embedding method to represent candlestick chart features and multiple attention graph neural network for stock market price fluctuation prediction. The experimental results show that the proposed method can interpret the candlestick chart features more accurately and has superiority performance over state-of-the-art deep learning methods, including SVM, CNN, LSTM, and CNN-LSTM. Relative to these algorithms, the proposed method achieves an average performance improvement of 20.51% in terms of accuracy and further achieves at least 26.98% improvement in strategy returns in quantitative investment experiments.

A Novel Reinforcement Learning Approach for Spark Configuration Parameter Optimization.

Apache Spark is a popular open-source distributed data processing framework that can efficiently process massive amounts of data. It provides more than 180 configuration parameters for users to manually select the appropriate parameter values according to their own experience. However, due to the large number of parameters and the inherent correlation between them, manual tuning is very tedious. To solve the problem of tuning through personal experience, we designed and implemented a reinforcement-learning-based Spark configuration parameter optimizer. First, we trained a Spark application performance prediction model with deep neural networks, and verified the accuracy and effectiveness of the model from multiple perspectives. Second, in order to improve the search efficiency of better configuration parameters, we improved the Q-learning algorithm, and automatically set start and end states in each iteration of training, which effectively improves the agent’s poor performance in exploring better configuration parameters. Lastly, comparing our proposed configuration with the default configuration as the baseline, experimental results show that the optimized configuration gained an average performance improvement of 47%, 43%, 31%, and 45% for four different types of Spark applications, which indicates that our Spark configuration parameter optimizer could efficiently find the better configuration parameters and improve the performance of various Spark applications.

STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors

We proposed 2D piezoelectric FET (PeFET)–based compute-enabled non-volatile memory for ternary deep neural networks (DNNs). PeFETs hinge on ferroelectricity for bit storage and piezoelectricity for bit sensing, exhibiting inherently amenable features for computation-in-memory of dot products of weights and inputs in the signed ternary regime. PeFETs consist of a material with ferroelectric and piezoelectric properties coupled with a transition metal dichalcogenide channel. We utilized (a) ferroelectricity to store binary bits (0/1) in the form of polarization (−P/+P) and (b) polarization-dependent piezoelectricity to read the stored state by means of strain-induced bandgap change in the transition metal dichalcogenide channel. The unique read mechanism of PeFETs enables us to expand the traditional association of +P (−P) with low (high) resistance states to their dual high (low) resistance depending on read voltage. Specifically, we demonstrated that +P (−P) stored in PeFETs can be dynamically configured in (a) a low (high) resistance state for positive read voltages and (b) their dual high (low) resistance states for negative read voltages, without afflicting a read disturb. Such a feature, which we named as polarization-preserved piezoelectric effect reversal with dual voltage polarity (PiER), is unique to PeFETs and has not been shown in hitherto explored memories. We leveraged PiER to propose a Strain-enabled Ternary Precision Computation-in-Memory (STeP-CiM) cell with capabilities of computing the scalar product of the stored weight and input, both of which are represented with signed ternary precision. Furthermore, using multi-word line assertion of STeP-CiM cells, we achieved massively parallel computation of dot products of signed ternary inputs and weights. Our array-level analysis showed 91% lower delay and improvements of 15% and 91% in energy for in-memory multiply-and-accumulate operations compared to near-memory design approaches based on 2D FET–based SRAM and PeFET, respectively. We also analyzed the system-level implications of STeP-CiM by deploying it in a ternary DNN accelerator. STeP-CiM exhibits 6.11× to 8.91× average improvement in performance and 3.2× average improvement in energy over SRAM-based near-memory design. We also compared STeP-CiM to near-memory design based on PeFETs showing 5.67× to 6.13× average performance improvement and 6.07× average energy savings.