Improve Processing Speed Research Articles

Feature Intensification Using Perception-Guided Regional Classification for Remote Sensing Image Super-Resolution

In recent years, super-resolution technology has gained widespread attention in the field of remote sensing. Despite advancements, current methods often employ uniform reconstruction techniques across entire remote sensing images, neglecting the inherent variability in spatial frequency distributions, particularly the distinction between high-frequency texture regions and smoother areas, leading to computational inefficiency, which introduces redundant computations and fails to optimize the reconstruction process for regions of higher complexity. To address these issues, we propose the Perception-guided Classification Feature Intensification (PCFI) network. PCFI integrates two key components: a compressed sensing classifier that optimizes speed and performance, and a deep texture interaction fusion module that enhances content interaction and detail extraction. This network mitigates the tendency of Transformers to favor global information over local details, achieving improved image information integration through residual connections across windows. Furthermore, a classifier is employed to segment sub-image blocks prior to super-resolution, enabling efficient large-scale processing. The experimental results on the AID dataset indicate that PCFI achieves state-of-the-art performance, with a PSNR of 30.87 dB and an SSIM of 0.8131, while also delivering a 4.33% improvement in processing speed compared to the second-best method.

An Efficient Network Intrusion Detection and Classification System using Machine Learning

In today's digital landscape, network security is of paramount importance, with intrusion detection systems (IDS) playing a crucial role in protecting sensitive data from malicious attacks. Traditional IDS, often reliant on signature-based methods, struggle with high false positive rates, difficulty in adapting to novel threats, and significant computational demands. This paper explores the development of an efficient network intrusion detection and classification system utilizing machine learning techniques to address these challenges. By leveraging datasets such as NSL-KDD and UNSW-NB15, our study employs a combination of supervised learning algorithms, including Support Vector Machines (SVM), Random Forests, and Neural Networks, alongside comprehensive data preprocessing and feature engineering strategies. The evaluation of our models through metrics like accuracy, precision, recall, and ROC-AUC demonstrates a marked improvement in detection capabilities and computational efficiency. Our findings suggest that machine learning-based IDS can significantly enhance network security by reducing false positives and adapting to emerging threats more effectively than traditional systems. This research not only underscores the potential of advanced machine learning techniques in IDS but also provides a robust framework for future developments in the field. In the rapidly evolving landscape of cybersecurity, effective network intrusion detection and classification systems are critical for safeguarding sensitive data and maintaining operational integrity. This paper presents a novel approach utilizing machine learning techniques to enhance the efficiency and accuracy of intrusion detection systems (IDS). By employing a combination of supervised and unsupervised learning algorithms, our system can identify and classify both known and unknown threats in real-time. We leverage advanced feature selection methods to optimize the performance of our models, ensuring high detection rates with minimal false positives. Our experimental results, validated on benchmark datasets, demonstrate significant improvements in detection accuracy and processing speed compared to traditional IDS solutions. The proposed system not only strengthens network defenses but also provides a scalable and adaptive framework for future cybersecurity challenges..

Improvement of fatigue, depression, and processing speed two weeks post Natalizumab infusion in Multiple Sclerosis: No difference between standard and extended interval dosing schedules

BackgroundFatigue, depression and slow processing speed are debilitating symptoms in people with Relapsing-Remitting Multiple Sclerosis (RRMS) that significantly impacts on the quality of life. Natalizumab, a disease-modifying treatment, improves clinical symptoms but questions remain about the comparative efficacy between its standard interval dosing (SID) and extended interval dosing (EID) schedules. ObjectiveTo examine the impact of short term natalizumab dosing schedules—SID versus EID—on the so called “invisible symptoms”, specifically focusing on symptom exacerbation during the 'wearing-off' phase before infusion and the subsequent relief post-infusion. MethodsForty-two RRMS patients were assessed one week before (T0) and two weeks after pre-and post-natalizumab infusion (T1) for fatigue symptoms using the Fatigue Scale for Motor and Cognitive Functions (FSMC), the Modified Fatigue Impact Scale (MFIS), and the Fatigue Symptoms and Impacts Questionnaire–Relapsing Multiple Sclerosis (FSIQ-RMS). Processing speed and depression were measured by the symbol digit modality test (SDMT), and the Beck Depression Inventory-II (BDI-II). Participants were categorized into either the SID or EID dosing schedules of natalizumab, and their outcomes were compared. ResultsForty-two patients (21 SID; 21 EID) completed the study. Fatigue severity scales, SDMT, and BDI-II scores improved from T0 to T1. No significant differences in fatigue symptoms were found between the SID and EID groups, whether during the "wearing-off" period (T0) or post-infusion (T1). ConclusionsBoth SID and EID dosing regimens of natalizumab are similarly effective in reducing fatigue symptoms, depression and improving processing speed in individuals with RRMS, with no observed differences during the "wearing-off" periods or after re-infusion.

An Energy-Efficient Dynamic Feedback Image Signal Processor for Three-Dimensional Time-of-Flight Sensors.

With the recent prominence of artificial intelligence (AI) technology, various research outcomes and applications in the field of image recognition and processing utilizing AI have been continuously emerging. In particular, the domain of object recognition using 3D time-of-flight (ToF) sensors has been actively researched, often in conjunction with augmented reality (AR) and virtual reality (VR). However, for more precise analysis, high-quality images are required, necessitating significantly larger parameters and computations. These requirements can pose challenges, especially in developing AR and VR technologies for low-power portable devices. Therefore, we propose a dynamic feedback configuration image signal processor (ISP) for 3D ToF sensors. The ISP achieves both accuracy and energy efficiency through dynamic feedback. The proposed ISP employs dynamic area extraction to perform computations and post-processing only for pixels within the valid area used by the application in each frame. Additionally, it uses dynamic resolution to determine and apply the appropriate resolution for each frame. This approach enhances energy efficiency by avoiding the processing of all sensor data while maintaining or surpassing accuracy levels. Furthermore, These functionalities are designed for hardware-efficient implementation, improving processing speed and minimizing power consumption. The results show a maximum performance of 178 fps and a high energy efficiency of up to 123.15 fps/W. When connected to the hand pose estimation (HPE) accelerator, it demonstrates an average mean squared error (MSE) of 10.03 mm, surpassing the baseline ISP value of 20.25 mm. Therefore, the proposed ISP can be effectively utilized in low-power, small form-factor devices.

UAV Geo-Localization Dataset and Method Based on Cross-View Matching.

The stable flight of drones relies on Global Navigation Satellite Systems (GNSS). However, in complex environments, GNSS signals are prone to interference, leading to flight instability. Inspired by cross-view machine learning, this paper introduces the VDUAV dataset and designs the VRLM network architecture, opening new avenues for cross-view geolocation. First, to address the limitations of traditional datasets with limited scenarios, we propose the VDUAV dataset. By leveraging the virtual-real mapping of latitude and longitude coordinates, we establish a digital twin platform that incorporates 3D models of real-world environments. This platform facilitates the creation of the VDUAV dataset for cross-view drone localization, significantly reducing the cost of dataset production. Second, we introduce a new baseline model for cross-view matching, the Virtual Reality Localization Method (VRLM). The model uses FocalNet as its backbone and extracts multi-scale features from both drone and satellite images through two separate branches. These features are then fused using a Similarity Computation and Feature Fusion (SCFF) module. By applying a weighted fusion of multi-scale features, the model preserves critical distinguishing features in the images, leading to substantial improvements in both processing speed and localization accuracy. Experimental results demonstrate that the VRLM model outperforms FPI on the VDUAV dataset, achieving an accuracy increase to 83.35% on the MA@20 metric and a precision of 74.13% on the RDS metric.

Deep Learning Approach for Arm Fracture Detection Based on an Improved YOLOv8 Algorithm

Artificial intelligence (AI)-assisted computer vision is an evolving field in medical imaging. However, accuracy and precision suffer when using the existing AI models for small, easy-to-miss objects such as bone fractures, which affects the models’ applicability and effectiveness in a clinical setting. The proposed integration of the Hybrid-Attention (HA) mechanism into the YOLOv8 architecture offers a robust solution to improve accuracy, reliability, and speed in medical imaging applications. Experimental results demonstrate that our HA-modified YOLOv8 models achieve a 20% higher Mean Average Precision (mAP 50) and improved processing speed in arm fracture detection.

Efficacy of transcranial magnetic stimulation treatment in reducing neuropsychiatric symptomatology after traumatic brain injury.

Neuropsychiatric disorders are highly disabling in traumatic brain injury (TBI) patients, and psychopharmacological treatments often fail to adequately mitigate their detrimental effects. Repetitive transcranial magnetic stimulation (rTMS) is an emerging treatment in neurology and psychiatry, showing potential in treating psychiatric disorders. This study investigates the efficacy of a novel, dual-site sequential rTMS protocol designed to treat neuropsychiatric symptoms in a TBI patient who was refractory to conventional treatments. A 34-year-old woman with severe head trauma and complex psychopathology underwent 20 daily sessions of focal-coil rTMS, combining inhibitory stimulation (1 Hz) on the right dorsolateral prefrontal cortex (DLPFC) and excitatory (10 Hz) on the left DLPFC, guided by a neuronavigation system. Psychiatric and neurocognitive assessments were conducted at baseline and at 2, 4, and 8 weeks following the beginning of rTMS treatment. After 2 weeks of treatment, the patient showed decreased impulsivity and obsessive-compulsive symptoms, along with improvements in attention and processing speed. After 4 weeks, impulsivity further declined, though no other significant changes were noted. At 8 weeks, a persistent positive effect was observed, including enhanced positive emotions. These findings suggest that guided, alternating neurostimulation of the DLPFC may modulate activity within cortico-striato-thalamo-cortical circuits, providing a promising alternative for managing neuropsychiatric symptoms in TBI patients who are resistant to traditional treatments.

Effects of aerobic, strength, and combined exercise on cognitive functions in older adults: a systematic review

Introduction: Aging is associated with a decline in cognitive functions, increasing the risk of neurocognitive impairment and limitation of activities of daily living and participation. Previous literature has pointed to physical exercise as an effective intervention; however, its characteristics still need to be specified. Objective: The aim was to synthesize the appropriate intensity, duration, frequency, and type of exercise for different types of cognitive variables. Method: A systematic review was carried out according to PRISMA, using three databases: PubMed, Scopus, and Web of Science. Experimental longitudinal studies were included, whether randomised or not, which performed physical exercise and with a control group in people over 60 years of age. Methodological quality was assessed using the PEDro scale. Results: The results yielded 11 studies finding significant improvements in all of them after performing the intervention (7 of aerobic exercise, 3 of resistance exercise and 2 of combined exercise) finding improvements in attention, memory, processing speed, executive function, inhibition, concentration, perceptual reasoning, orientation, visuospatial perception, and visuomotor organisation. Conclusions: Physical exercise appears to be a beneficial intervention for cognition in older people, with aerobic exercise being the most studied, although further research is needed. The results could benefit decision-making in rehabilitation to work on cognition in cognitively healthy older people. Keywords: prevention; aging; cognition; cognitive impairment; rehabilitation.

Frequency domain attention network for copper chain defect detection in tobacco cutting machine

AbstractThe detection of defects on the copper chain in the production process of tobacco cutters is crucial for ensuring product quality. Traditional defect detection methods often rely on spatial domain image analysis, which not only has a large computational load but also performs poorly in handling high‐frequency noise and complex backgrounds. To address this issue, this paper proposes a novel neural network model based on frequency domain analysis, called frequency domain attention network. This network first utilizes discrete cosine transform to transform the image from the spatial domain to the frequency domain, effectively reducing computational complexity and improving processing speed. Subsequently, through the innovative frequency domain attention module, the network automatically identifies and enhances key discriminative features in the frequency domain, thereby strengthening the model's ability to identify defects. Finally, the frequency domain attention map, after feature extraction and integration, is inputted into the coupling detection head to achieve high‐precision defect detection. The experimental results show that our method outperforms the SOTA method with an increase of 0.03 in AP and 21 in FPS.

Квантовые вычисления в медицинской физике: особенности алгоритмов и их перспективы

Background: Quantum computing represents a paradigm leap in computational capabilities, with potential applications across various scientific disciplines. The complicated computations required for imaging, radiation therapy, and molecular modeling in medical physics give novel prospects for quantum computing. Objective: This article investigates the role of quantum computing in medical physics research, with an emphasis on its potential to improve computational efficiency and accuracy and develop novel treatment approaches. Methods: A thorough literature analysis was undertaken to investigate recent advances in quantum computing and their implications in medical physics. Case studies were reviewed to demonstrate practical applications and possible advantages. Theoretical models were tested to forecast future developments. Statistical data from quantum computing implementations were gathered from many sources, particularly on improving processing speed and accuracy in medical physics applications. Results: The findings show that quantum computing can significantly improve the processing speed of complex simulations and imaging techniques, with some quantum algorithms outperforming classical algorithms by up to 100 times. In radiation therapy planning, quantum computing has exhibited a 25% boost in dose distribution calculation precision. Quantum algorithms have lowered calculation times in molecular modeling by about 40%, potentially boosting drug development and customized therapy by 30%. Conclusion: Quantum computing has the potential to alter medical physics by increasing computational capacity, which could lead to advancements in diagnostics, treatment planning, and medication development. The statistical results corroborate the promise of quantum computing in these domains, emphasizing the importance of ongoing interdisciplinary collaboration and research to fully achieve these benefits and address present hurdles in incorporating quantum computing into clinical practice.

Топологические изоляторы в электронных и спинтронных устройствах

Background: Topological insulators (TIs) are materials with distinctive features, including insulating interiors and conducting surface states protected by time-reversal symmetry. These features make TIs extremely promising for electrical and spintronic device applications, where manipulating electron spin without charge transfer is advantageous. Objective: This study aims to investigate of TIs to improve the performance and efficiency of electrical and spintronic devices. We look at the special qualities of TIs that may be used to improve device functionality, such as reduced power consumption and higher operational speed. Methods: To investigate electron transport behaviour on the surfaces of different TIs, we used a mix of quantum mechanical models and experimental settings. Devices based on bismuth telluride (Bi2Te3) and thallium arsenide (TlAs) were built to test their performance in real-world applications. Results: TI devices showed considerable gains in spin transport efficiency and thermal stability compared to conventional materials. Spintronic devices based on TIs demonstrated a 50% reduction in energy usage and a 30% improvement in data processing speed. Conclusion: Including topological insulators in electrical and spintronic devices offers a promising path to more efficient and speedier technologies. Future research should concentrate on the scalable integration of TIs into commercial devices and the discovery of novel materials with topological insulating characteristic.

Cognitive processing speed improvement after cochlear implantation.

Untreated hearing loss has an effect on cognition. It is hypothesized that the additional processing required to compensate for the sensory loss affects the cognitive resources available for other tasks and that this could be mitigated by a hearing device. The impact on cognition of cochlear implants (CIs) was tested in 100 subjects, ≥60 years old, with bilateral moderately-severe to profound post linguistic deafness using hearing aids. Data was compared pre and 12 and 18 months after cochlear implantation for the speech spatial qualities questionnaire, Mini Mental State Examination (MMSE), Trail making test B (TMTB) and digit symbol coding (DSC) from the Wechsler Adult Intelligence Scale version IV and finally the timed up and go test (TUG). Subjects were divided into young old (60-64), middle old (65-75) and old old (75+) groups. Cognitive test scores and times were standardized according to available normative data. Hearing significantly improved pre- to post-operatively across all age groups. There was no change post-implant in outcomes for TMTB, TUG or MMSE tests. Age-corrected values were within normal expectations for all age groups for the TUG and MMSE. However, DSC scores and TMTB times were worse than normal. There was a significant increase in DSC scores between baseline and 12-months for 60- to 64-year-olds (t[153] = 2.608, p = 0.027), which remained at 18 months (t[153] = 2.663, p = 0.023). The improved attention and processing speed in the youngest age group may be a consequence of reallocation of cognitive resources away from auditory processing due to greatly improved hearing. The oldest age group of participants had cognition scores closest to normal values, suggesting that only the most able older seniors tend to come forward for a CI. Severe to profoundly deaf individuals with hearing aids or cochlear implants were still poorer than age-equivalent normally hearing individuals with respect to cognitive flexibility, attention, working memory, processing speed and visuoperceptual functions. Due to a lack of data for the TUG, TMTB and DSC in the literature for hearing impaired individuals, the results reported here provide an important set of reference data for use in future research.

An improved YOLOv8 model enhanced with detail and global features for underwater object detection

Underwater object detection is significant for the practical research of mastering existing marine biological resources. In response to the challenges posed by complex underwater environments such as water scattering and variations in object scales, researchers have developed YOLOv8 for object detection, driven by the rising popularity and iteration of deep learning. Building upon this model, we propose an enhanced underwater object detection model named YOLOv8-DGF. Firstly, we replace the convolutional layers of Spatial Pyramid Pooling Fusion (SPPF) with Invertible Neural Networks to further augment the fusion capacity of detailed features, facilitating the preservation of pivotal information while mitigating the impact of noise. Additionally, we introduce a global attention mechanism into Convolution to Fully Connected (C2f), which weights the input features, thereby emphasizing or suppressing feature information from different locations. Through our ‘Detail to Global’ strategy, the model achieved mAP@0.5 scores of 87.7% and 84.8% on the RUOD and URPC2020 datasets, respectively, with improved processing speed. Extensive ablation experiments on the Pascal VOC dataset demonstrate that YOLOv8-DGF outperforms other methods, achieving the best overall performance.

X-News dataset for online news categorization

PurposeThe objective is to develop a more effective model that simplifies and accelerates the news classification process using advanced text mining and deep learning (DL) techniques. A distributed framework utilizing Bidirectional Encoder Representations from Transformers (BERT) was developed to classify news headlines. This approach leverages various text mining and DL techniques on a distributed infrastructure, aiming to offer an alternative to traditional news classification methods.Design/methodology/approachThis study focuses on the classification of distinct types of news by analyzing tweets from various news channels. It addresses the limitations of using benchmark datasets for news classification, which often result in models that are impractical for real-world applications.FindingsThe framework’s effectiveness was evaluated on a newly proposed dataset and two additional benchmark datasets from the Kaggle repository, assessing the performance of each text mining and classification method across these datasets. The results of this study demonstrate that the proposed strategy significantly outperforms other approaches in terms of accuracy and execution time. This indicates that the distributed framework, coupled with the use of BERT for text analysis, provides a robust solution for analyzing large volumes of data efficiently. The findings also highlight the value of the newly released corpus for further research in news classification and emotion classification, suggesting its potential to facilitate advancements in these areas.Originality/valueThis research introduces an innovative distributed framework for news classification that addresses the shortcomings of models trained on benchmark datasets. By utilizing cutting-edge techniques and a novel dataset, the study offers significant improvements in accuracy and processing speed. The release of the corpus represents a valuable contribution to the field, enabling further exploration into news and emotion classification. This work sets a new standard for the analysis of news data, offering practical implications for the development of more effective and efficient news classification systems.

Evaluating cognitive assessment tools for patients with major depressive disorder receiving electroconvulsive therapy: A systematic review and meta-analysis

BackgroundMajor Depressive Disorder (MDD) affects 350 million people worldwide. Electroconvulsive therapy (ECT) is effective, yet research on cognitive assessments post-treatment is lacking. This study systematically reviews and meta-analyzes the effectiveness of cognitive assessment tools post-ECT to optimize MDD treatment. MethodsFollowing PRISMA guidelines, this review was pre-registered on PROSPERO (CRD42023470318). Searches were conducted across nine databases up to November 12, 2023. Quality assessment for Randomized Controlled Trials (RCTs) and quasi-experimental studies was performed using the Cochrane risk of bias tool, JBI critical appraisal tools, and the Jadad scale. Meta-analyses for short-term and long-term cognitive function involved 24 and 18 tools, respectively. FindingsThirty studies (20 RCTs and 10 quasi-experimental) involving 2462 MDD patients were evaluated. Results indicated no significant differences in overall short-term and long-term cognitive functions post-ECT. Short-term analysis showed impairments in memory, learning, and verbal abilities but improvements in attention and processing speed. Long-term analysis revealed enhancements in memory, learning, verbal, and visuospatial abilities compared to baseline. Based on GRADE classification, we recommend 11 tools for assessing acute cognitive function and 10 tools for chronic cognitive impairment. These tools demonstrated high reliability and validity, supporting their clinical use. InterpretationThese findings provide critical evidence for future ECT clinical guidelines in managing MDD. The recommended tools can aid clinicians in adjusting ECT regimens, identifying early cognitive changes, and improving therapeutic outcomes in MDD treatment.

An optimized hybrid encryption framework for smart home healthcare: Ensuring data confidentiality and security

This study proposes an optimized hybrid encryption framework combining ECC-256r1 with AES-128 in EAX mode, tailored for smart home healthcare environments, and conducts a comprehensive investigation to validate its performance. Our framework addresses current limitations in securing sensitive health data and demonstrates resilience against emerging quantum computing threats. Through rigorous experimental evaluation, we show that the proposed configuration outperforms existing solutions by delivering unmatched security, processing speed, and energy efficiency. It employs a robust yet streamlined approach, meticulously designed to ensure simplicity and practicality, facilitating seamless integration into existing systems without imposing undue complexity. Our investigation affirms the framework's capability to resist common cybersecurity threats like MITM, replay, and Sybil attacks while proactively considering quantum resilience. The proposed method excels in processing speed (0.006 seconds for client and server) and energy efficiency (3.65W client, 95.4W server), offering a quantum-resistant security level comparable to AES-128. This represents a security-efficiency ratio of 21.33 bits per millisecond, a 25.6% improvement in client-side processing speed, and up to 44% reduction in server-side energy consumption compared to conventional RSA-2048 methods. These improvements enable real-time encryption of continuous health data streams in IoT environments, making it ideal for IoT devices where AES-128′s smaller footprint is advantageous. By prioritizing high-grade encryption alongside ease of use and implementation, the proposed framework presents a future-proof solution that anticipates the trajectory of cryptographic standards amid advancing quantum computing technologies, signifying a pivotal advancement in safeguarding IoT-driven healthcare data.

Immediate post-concussion assessment and cognitive testing Pediatric (ImPACT Pediatric) change scores and factors associated with performance in patients aged 5-9 years following concussion: Preliminary findings

Background Computerized neurocognitive testing is one component of a multidomain assessment of concussion. However, the use of computerized neurocognitive testing has been limited to patients aged 11 years and up, leaving clinicians with few options to evaluate younger children. Purpose To examine the change in Immediate Post-concussion Assessment and Cognitive Testing Pediatric (ImPACT Pediatric) (ImPACT Applications, 2021) scores and factors associated with performance in children aged 5-9 years following a concussion. Methods Participants included 63 children (42% [n = 27] female) aged 5-9 (M = 7.5 ± 1.0) years within 30 (M = 8.5 ± 5.9) days of a concussion. All participants completed the ImPACT Pediatric at their initial visit and at medical clearance for their return to activity (RTA) visit. The ImPACT Pediatric test is a computerized neurocognitive battery that includes 5 tests that assess memory and visual processing speed. Multivariate and univariate analyses of variance and paired t-tests were used to compare ImPACT Pediatric scores from the initial visit to medical clearance. Multivariate and univariate analyses of covariance and multiple linear regression examined factors associated with ImPACT Pediatric performance. Results Participants demonstrated improved overall performance from the initial visit to the medical clearance visit (F(4, 59)=3.08, p = 0.02, Wilks’ Λ = 0.83, ηp 2=0.17), with significant improvement in Rapid Processing Speed (F(1, 62)=7.48, p < 0.01, ηp 2=0.11). When controlling for age, sex, history of ADHD, and days to clinic, the improvement in overall performance remained significant (F(4, 51)=2.99, p = 0.03, Wilks’ Λ = 0.81, ηp 2=0.19). Older age was significantly associated with the Rapid Processing composite score at the initial visit (F(4, 59)=5.9, p < 0.001, Adj. R2=0.25) and medical clearance visit (F(4, 59)=3.8, p = 0.008, Adj. R2=0.16), with older children associated with better performance at both time points (Initial visit: B = 8.17, p < 0.001; Medical Clearance: B = 3.62, p = 0.03). Conclusion Our main findings suggest that children aged 5-9 years improved significantly in Rapid Processing on the ImPACT Pediatric from the initial visit to medical clearance. However, no differences were found for the memory components of the ImPACT Pediatric. Older children also performed better on processing speed than younger children. The findings suggest that the processing speed components of ImPACT Pediatric are useful for monitoring improvements in neurocognitive functioning following concussion in children aged 5-9 years, but that age differences need to be considered when interpreting performance.

Efficient Processing-in-Memory System Based on RISC-V Instruction Set Architecture

A lot of research on deep learning and big data has led to efficient methods for processing large volumes of data and research on conserving computing resources. Particularly in domains like the IoT (Internet of Things), where the computing power is constrained, efficiently processing large volumes of data to conserve resources is crucial. The processing-in-memory (PIM) architecture was introduced as a method for efficient large-scale data processing. However, PIM focuses on changes within the memory itself rather than addressing the needs of low-cost solutions such as the IoT. This paper proposes a new approach using the PIM architecture to overcome memory bottlenecks effectively in domains with computing performance constraints. We adopt the RISC-V instruction set architecture for our proposed PIM system’s design, implementation, and comprehensive performance evaluation. Our proposal expects to efficiently utilize low-spec systems like the IoT by minimizing core modifications and introducing PIM instructions at the ISA level to enable solutions that leverage PIM capabilities. We evaluate the performance of our proposed architecture by comparing it with existing structures using convolution operations, the fundamental unit of deep-learning and big data computations. The experimental results show our proposed structure achieves a 34.4% improvement in processing speed and 18% improvement in power consumption compared to conventional von Neumann-based architectures. This substantiates its effectiveness at the application level, extending to fields such as deep learning and big data.

Optimizing Data Pipeline Efficiency with Machine Learning Techniques

In the era of big data, efficient data processing is crucial for timely insights and decision-making. Traditional data pipelines face challenges such as latency, scalability, and fault tolerance. This paper explores the application of machine learning (ML) techniques to optimize data pipeline efficiency. We propose a framework that integrates ML models for predictive resource allocation, anomaly detection, and dynamic scaling within data pipelines. Our experiments demonstrate significant improvements in processing speed, resource utilization, and reliability. Key Words: Data Engineering, Data Pipelines, Machine Learning, Predictive Resource Allocation, Anomaly Detection, Dynamic Scaling

Design and implementation of deep learning-based object detection and tracking system

Many human tracking methods by deep learning rely on powerful computing resources. For embedded platforms with limited resources, efficient use of resources is a priority. In this paper, we design an object detection and tracking system based on deep learning methods. We propose an efficient system with software and hardware design. We apply the framework of Vitis AI and its Deep Learning Processing Unit using a hardware/software co-design approach. This approach capitalizes on a higher-level acceleration design framework, where the convolutional models can be updated more flexibly and rapidly. This design approach not only provides a fast design flow but also has good performance in terms of throughput. We facilitate the design and accelerate the object detection model YOLO v3 to achieve higher throughput and energy efficiency. Our tracking method achieves a 1.27x improvement in processing speed with the addition of a single-object tracker. Our proposed human tracking methods can achieve better performance than the others in precision with the same test sequences.