Timeliness Of Detection Research Articles

Detecting changes in population trends in infection surveillance using community SARS-CoV-2 prevalence as an exemplar.

Detecting and quantifying changes in growth rates of infectious diseases is vital to informing public health strategy and can inform policymakers' rationale for implementing or continuing interventions aimed at reducing impact. Substantial changes in SARS-CoV-2 prevalence with emergence of variants provides opportunity to investigate different methods to do this. We included PCR results from all participants in the UK's COVID-19 Infection Survey between August 2020-June 2022. Change-points for growth rates were identified using iterative sequential regression (ISR) and second derivatives of generalised additive models (GAMs). Consistency between methods and timeliness of detection were compared. Of 8,799,079 visits, 147,278 (1.7%) were PCR-positive. Change-points associated with emergence of major variants were estimated to occur a median 4 days earlier (IQR 0-8) in GAMs versus ISR. When estimating recent change-points using successive data periods, four change-points (4/96) identified by GAMs were not found when adding later data or by ISR. Change-points were detected 3-5 weeks after they occurred in both methods but could be detected earlier within specific subgroups. Change-points in growth rates of SARS-CoV-2 can be detected in near real-time using ISR and second derivatives of GAMs. To increase certainty about changes in epidemic trajectories both methods could be run in parallel.

Viral invasion, incubation, and outbreak under the normalized operation of urban systems: a spatial cognition-driven transmission model of infectious diseases

ABSTRACT Large-scale epidemics, such as COVID-19, pose significant threats to human health and social stability due to their rapid and covert transmission, emerging as one of the main challenges to maintaining a well-functioning urban system. During the pandemic, the spatial transmission mechanisms and their influencing factors of infectious diseases have received as a central topic. Scholars concentrated on researching the phase of extensive dissemination and mandatory intervention, utilizing multiple datasets. However, there remains a notable gap in the investigation of virus spatial transmission mechanisms under normalized urban operations due to limitations in detection timeliness and data collection issues. Moreover, compared to various intervention strategies, the influence of human behavioral dynamics and spatial cognition remains understudied. The paper simulates invasion, incubation, and outbreak of the Omicron variant in Zhuhai City in 2022, validating the results against real-world epidemic data. By comparing spatial diffusion patterns under three levels of spatial cognition, it sheds light on the delayed impact of human spatial cognitive abilities on urban pandemic outbreaks and their influence on virus invasion orders. The simulation model and revealed diffusion mechanisms will provide important guidance for the proactive prevention and control of unpredictable large-scale epidemics in future urban systems.

Integrating satellite-based forest disturbance alerts improves detection timeliness and confidence

Satellite-based near-real-time forest disturbance alerting systems have been widely used to support law enforcement actions against illegal and unsustainable human activities in tropical forests. The availability of multiple optical and radar-based forest disturbance alerts, each with varying detection capabilities depending mainly on the satellite sensor used, poses a challenge for users in selecting the most suitable system for their monitoring needs and workflow. Integrating multiple alerts holds the potential to address the limitations of individual systems. We integrated radar-based RAdar for Detecting Deforestation (RADD) (Sentinel-1), and optical-based Global Land Analysis and Discovery Sentinel-2 (GLAD-S2) and GLAD-Landsat alerts using two confidence rulesets at ten 1° sites across the Amazon Basin. Alert integration resulted in faster detection of new disturbances by days to months, and also shortened the delay to increased confidence. An increased detection rate to an average of 97% when combining alerts highlights the complementary capabilities of the optical and cloud-penetrating radar sensors in detecting largely varying drivers and environmental conditions, such as fires, selective logging, and cloudy circumstances. The most improvement was observed when integrating RADD and GLAD-S2, capitalizing on the high temporal observation density and spatially detailed 10 m Sentinel-1 and 2 data. We introduced the highest confidence class as an addition to the low and high confidence classes of the individual systems, and showed that this displayed no false detection. Considering spatial neighborhood during alert integration enhanced the overall labeled alert confidence level, as nearby alerts mutually reinforced their confidence, but it also led to an increased rate of false detections. We discuss implications of this study for the integration of multiple alert systems. We demonstrate that alert integration is an important data preparation step to make use of multiple alerts more user-friendly, providing stakeholders with reliable and consistent information on new forest disturbances in a timely manner. Google Earth Engine code to integrate various alert datesets is made openly available.

Difficulties in Assessing the Economic Burden of Alzheimer's Disease

Background. Age-related changes associated with the decrease in health and autonomy drastically increase the cost of medical care, maintenance and treatment. Late detection of ilnesses is the root cause of escalating the economic weight from age-related diseases, causing a surge in costs for the recovery, treatment and care of those needing outside assistance. One of the age-associated diseases is Alzheimer's disease. Alzheimer's disease is one of the many manifestations of age-related dementia, accompanied by a violation of human cognitive abilities. This cluster of diseases does not affect other systems (cardiovascular, musculoskeletal, digestive), and they can operate normally. An important effect of this disease for society is the impossibility of conducting a full-fledged work activity, as memory, attention, etc. are disturbed. That is, with absolutely normally functioning body systems, a person cannot perform the simplest operations. Another important feature is the lack of an effective way to treat this disease. The pathogenesis is so complex that today there is no method of treatment aimed at all links. Also of great importance is the timeliness of detection of this disease. Due to the fact that recently there were test systems and express diagnostics for the early detection of Alzheimer's disease, it became possible to start treatment earlier, which increased the chances of recovery and reduced treatment costs in case of diagnosing moderate and severe Alzheimer's disease gravity. Aim. Revealing the difficulties of assessing the economic burden of Alzheimer's Disease. Materials and methods. To identify the difficulties of assessing the economic burden, free sources, publications on Alzheimer's disease, data from clinical guidelines, the standard for providing medical care to elderly and senile patients with cognitive disorders, information on maximum selling prices registered and included in the State Register of Vital and Essential Drugs Prices, statistical data, compulsory health insurance tariffs. Results. The main problematic issues of the difficulty of assessing the economic burden of Alzheimer's disease are identified. Conclusion. Diseases of the nervous system are of particular importance for the health of the patient, since disorders affecting this system do not allow the patient to fully and fully fulfill their labor duties. In this regard, the development of a method for assessing the cost-effectiveness of Alzheimer's disease, as one of the most common disorders of cognitive functions, is an extremely important social task aimed at optimizing the treatment process, early detection and effective treatment aimed at recovery.

GEO spacecraft maneuver detection based on causal inference

Geosynchronous (GEO) spacecraft maneuver detection is deemed crucial for space domain awareness (SDA) as it helps to maintain catalogs of high value resident space objects (RSOs). However, several difficulties in resolving maneuver time and requirements for historical data quality still exist for the current research. This paper proposes a method based on causal inference for accurate and timely detection of the maneuver using real-time observational data from optical sensors. Firstly, the residual information of time series observations is obtained through counterfactual reasoning. Secondly, according to the Gaussianity of the optical sensor observation noise, a structural causal equation (SCE) of the residuals of time series observations is derived. Lastly, the maneuver is abstracted as a soft intervention, and the minimum average treatment effect (MATE) is proposed to estimate the effect of the maneuver and used as a feature parameter to identify the GEO spacecraft maneuver. After experimental analysis, the detection rate and detection timeliness of the proposed method reach more than 90%, a significant improvement compared with the conventional χ2, skewness, and kurtosis test methods.

Optimal Deployment of Sensors along Freeway Corridors for Traffic Accident Detection

Sensor deployment is important to the detection performance of traffic accidents on freeways. However, the temporally and spatially varying effects of accident risks are seldom considered in sensor deployment, which can induce a decrease in accident detection accuracy and detection timeliness. To address this problem, this paper proposes an optimal deployment method of sensors according to the temporal-spatial effect of accidents on traffic flow. Considering the uncertainty of traffic accidents, the temporal-spatial distribution of accident risk is estimated according to historical accident data. Then the kinematic wave model and Van Aerder model are introduced to analyze the temporal-spatial effect of accidents on traffic flow. To obtain the optimal locations of sensors, the sensor deployment problem is converted into a coverage problem on accident risk in time and space, and an optimal deployment model of sensors is built by considering the temporal-spatial effect of accident risk, the coverage rate on accident risk, the detection timeliness of the accident, and deployment cost. The particle swarm optimization algorithm is introduced to solve it. A case study is carried out to validate the proposed method using consistency, sensitivity, reliability, and comparison experiments. The results show that the proposed method is effective and reliable under different traffic volumes, and it outperforms the uniform spacing method in traffic accident detection.

Implementation of the 7-1-7 target for detection, notification, and response to public health threats in five countries: a retrospective, observational study

Suboptimal detection and response to recent outbreaks, including COVID-19 and mpox (formerly known as monkeypox), have shown that the world is insufficiently prepared for public health threats. Routine monitoring of detection and response performance of health emergency systems through timeliness metrics has been proposed to evaluate and improve outbreak preparedness and contain health threats early. We implemented 7-1-7 to measure the timeliness of detection (target of ≤7 days from emergence), notification (target of ≤1 day from detection), and completion of seven early response actions (target of ≤7 days from notification), and we identified bottlenecks to and enablers of system performance. In this retrospective, observational study, we conducted reviews of public health events in Brazil, Ethiopia, Liberia, Nigeria, and Uganda with staff from ministries of health and national public health institutes. For selected public health events occurring from Jan 1, 2018, to Dec 31, 2022, we calculated timeliness intervals for detection, notification, and early response actions, and synthesised identified bottlenecks and enablers. We mapped bottlenecks and enablers to Joint External Evaluation (second edition) indicators. Of 41 public health events assessed, 22 (54%) met a target of 7 days to detect (median 6 days [range 0-157]), 29 (71%) met a target of 1 day to notify (0 days [0-24]), and 20 (49%) met a target of 7 days to complete all early response actions (8 days [0-72]). 11 (27%) events met the complete 7-1-7 target, with variation among event types. 25 (61%) of 41 bottlenecks to and 27 (51%) of 53 enablers of detection were at the health facility level, with delays to notification (14 [44%] of 32 bottlenecks) and response (22 [39%] of 56 bottlenecks) most often at an intermediate public health (ie, municipal, district, county, state, or province) level. Rapid resource mobilisation for responses (six [9%] of 65 enablers) from the national level enabled faster responses. The 7-1-7 target is feasible to measure and to achieve, and assessment with this framework can identify areas for performance improvement and help prioritise national planning. Increased investments must be made at the health facility and intermediate public health levels for improved systems to detect, notify, and rapidly respond to emerging public health threats. Bill & Melinda Gates Foundation.

Tear nanoDSF Denaturation Profile Is Predictive of Glaucoma.

Primary open-angle glaucoma (POAG) is a frequent blindness-causing neurodegenerative disorder characterized by optic nerve and retinal ganglion cell damage most commonly due to a chronic increase in intraocular pressure. The preservation of visual function in patients critically depends on the timeliness of detection and treatment of the disease, which is challenging due to its asymptomatic course at early stages and lack of objective diagnostic approaches. Recent studies revealed that the pathophysiology of glaucoma includes complex metabolomic and proteomic alterations in the eye liquids, including tear fluid (TF). Although TF can be collected by a non-invasive procedure and may serve as a source of the appropriate biomarkers, its multi-omics analysis is technically sophisticated and unsuitable for clinical practice. In this study, we tested a novel concept of glaucoma diagnostics based on the rapid high-performance analysis of the TF proteome by differential scanning fluorimetry (nanoDSF). An examination of the thermal denaturation of TF proteins in a cohort of 311 ophthalmic patients revealed typical profiles, with two peaks exhibiting characteristic shifts in POAG. Clustering of the profiles according to peaks maxima allowed us to identify glaucoma in 70% of cases, while the employment of artificial intelligence (machine learning) algorithms reduced the amount of false-positive diagnoses to 13.5%. The POAG-associated alterations in the core TF proteins included an increase in the concentration of serum albumin, accompanied by a decrease in lysozyme C, lipocalin-1, and lactotransferrin contents. Unexpectedly, these changes were not the only factor affecting the observed denaturation profile shifts, which considerably depended on the presence of low-molecular-weight ligands of tear proteins, such as fatty acids and iron. Overall, we recognized the TF denaturation profile as a novel biomarker of glaucoma, which integrates proteomic, lipidomic, and metallomic alterations in tears, and monitoring of which could be adapted for rapid non-invasive screening of the disease in a clinical setting.

МЕТОД И МАТЕМАТИЧЕСКАЯ МОДЕЛЬ ОЦЕНКИ ЭФФЕКТИВНОСТИ СИСТЕМЫ ЗАЩИТЫ ПОДВИЖНОГО ОБЪЕКТА ОТ МАЛОРАЗМЕРНОГО РОБОТОТЕХНИЧЕСКОГО КОМПЛЕКСА

The purpose of the study is to evaluate the effectiveness of the system for protecting a mobileprotected object from a small unmanned aerial vehicle (UAV). In connection with the peculiarityof the construction of the protection system for a mobile object, associated with the movementsynchronously with the object of the critical zone, into which the UAV should not fall, it was necessaryto develop a method and a mathematical model for assessing the effectiveness of the UAV. As an indicator of efficiency, the probability of diverting the UAV from the critical zone was taken.It is analyzed that the removal of the UAV from the critical zone is carried out due to the timelydetection of the UAV and its transition from navigation using the signals of satellite navigationsystems to the onboard inertial navigation system. The timeliness of detection is determined by thedetection range of the UA. The detection range is determined, first of all, by the parameters of thedetection means themselves, the topology of their placement, the size of the critical zone aroundthe protected object, and the direction of movement of the UAV. The size of the critical zone isdetermined by the danger of video filming from the UAV or payload drop. The direction of movementof the UAV most vulnerable to the protected object is the movement to the meeting point withthe protected object. The results of the analysis and the developed algorithms for the functioningof the protection system against a small UAV were taken into account when developing a mathematicalmodel for assessing the effectiveness of protecting a protected object. Due to the fact thatsome of the parameters of the BVS are not known in advance, their values were played withequiprobability. The method of statistical tests (Monte Carlo method) was used to calculate theefficiency indicator. In each test, random parameters of the UAV were played out, initial datawere set, the processes of movement of the protected object and the UAV, changes in the positionof the critical zone were reproduced, the UAV hitting the viewing areas of the detection tools,moving away from the general course of the UAV and getting into the limits of the critical zonewere evaluated. The developed method and mathematical model for evaluating the effectivenessmade it possible to conduct a numerical experiment aimed at assessing the influence of the UAVspeed on the protection efficiency of a mobile guarded object. The results of the work can be usedin the design and development of a system for protecting a protected object from UA, in a comparativeanalysis of alternative systems for protecting against UA. The proposed method and mathematicalmodel can also be used in the underwater marine environment when evaluating the effectivenessof protecting a protected inhabited / uninhabited object from marine robotic systems.

Collection, nucleic acid release, amplification, and visualization platform for rapid field detection of rice false smut.

Rice false smut (RFS) has brought serious food safety problems to the world. Reliable diagnostic tools are needed for the field detection of RFS. Traditional polymerase chain reaction (PCR) is inefficient due to sample transport and preparation, which cannot adapt to the needs of field detection. Herein, we successfully developed a simple, portable microfluidic test platform to rapidly detect RFS. To simplify the operation, we integrated spore purification, nucleic acid release, and amplification into one chip. A micro air pump was used to separate the spores from the impurities and complete the collection of the spores through the airflow. We rapidly lysed spores and released nucleic acids by the benzyl chloride method. The loop-mediated isothermal amplification (LAMP) products could be combined with SYBR Green I to observe the results visually. On-chip sample tests showed that the spore collection efficiency was approximately 78%. By providing on-chip detection results, the chip had 100% specificity and a detection limit of 100 copies/reaction. At the same time, the stability (CV < 5%) and quantitative ability (R2 = 0.989) of the chip were also guaranteed. Through the visual detection of large samples, the on-chip detection results were highly concordant with the classical RT-PCR detection results, and the detection timeliness was greatly enhanced. Compared with RT-PCR, the single-sample detection time was shortened by about twenty minutes. The proposed micro-diagnostic tool did not require any large end-point detection instruments and avoided the complicated operation of nucleic acid extraction. As a result, in the future, our microfluidic chip could be used for rapid and real-time monitoring and early warning of rice false smut spores in rice paddies.

NETWORK TRAFFIC DETECTION THROUGH MACHINE LEARNING

In imbalanced network traffic, malicious cyber-attacks can often hide in large amounts of normal data. It exhibits a high degree of stealth and obfuscation in cyberspace, making it difficult for Network Intrusion Detection System (NIDS) to ensure the accuracy and timeliness of detection. This paper researches machine learning and deep learning for intrusion detection in imbalanced network traffic. It proposes a novel Difficult Set Sampling Technique (DSSTE) algorithm to tackle the class imbalance problem. To verify the proposed method, we conduct experiments on the classic intrusion dataset NSL-KDD and the newer and comprehensive intrusion dataset CSE-CIC-IDS2018. We use classical classification models: random forest(RF), Support Vector Machine(SVM), XGBoost, MLP AlexNet, Mini-VGGNet.

Early diagnosis and surgical treatment of craniosynostoses

Craniosynostosis is a craniofacial anomaly, characterized by premature fusion of one or more of the cranial sutures. Each suture and their combination correspond to a special type of deformation.Purpose. The study aimed at indicating the difficulties of early diagnostics of various forms of the craniosynostosis and evaluating the quality of treatment of patients with this disease depending on their age.Material and methods. A survey of parents with craniosynostosis who were treated at the Almazov National Medical Research Centre in 2018–2019 was conducted. The parents of 107 patients were surveyed. The main objectives of our research were: to evaluate the timeliness of diagnosis of craniosynostosis at primary health care at patient’s place of residence; to compare the methods of diagnosis verification and to present the results of the parents’ subjective assessment of the results of surgical treatment at the early and long-term postoperative period.Results. The median age of children when they were diagnosed with craniosystosis was 5 months, the median age of patients when they underwent a surgical treatment was 16 months. The median duration of the catamnesis was 6 months. We revealed that the preliminary diagnosis was established by a neurologist and pediatrician only in 21% of cases. Only at 28% of cases, children were directed to neurosurgeon, who confirm the diagnosis. In 38 (35.3%) cases, patient’s parents independently sought medical advice. The diagnosis was verified by the results of the computer tomography in 55% of patients. on because primary care specialists due to the lack of primary care specialists’ awareness about the diagnosis of craniosynostoses and attempts at long-term monitoring and conservative treatment. The timeliness of detection of craniosynostosis in the newborn period and in the|first month of life can significantly improve the cosmetic and functional outcomes of the disease.

Global Variations in Event-Based Surveillance for Disease Outbreak Detection: Time Series Analysis.

Robust and flexible infectious disease surveillance is crucial for public health. Event-based surveillance (EBS) was developed to allow timely detection of infectious disease outbreaks by using mostly web-based data. Despite its widespread use, EBS has not been evaluated systematically on a global scale in terms of outbreak detection performance. The aim of this study was to assess the variation in the timing and frequency of EBS reports compared to true outbreaks and to identify the determinants of variability by using the example of seasonal influenza epidemic in 24 countries. We obtained influenza-related reports between January 2013 and December 2019 from 2 EBS systems, that is, HealthMap and the World Health Organization Epidemic Intelligence from Open Sources (EIOS), and weekly virological influenza counts for the same period from FluNet as the gold standard. Influenza epidemic periods were detected based on report frequency by using Bayesian change point analysis. Timely sensitivity, that is, outbreak detection within the first 2 weeks before or after an outbreak onset was calculated along with sensitivity, specificity, positive predictive value, and timeliness of detection. Linear regressions were performed to assess the influence of country-specific factors on EBS performance. Overall, while monitoring the frequency of EBS reports over 7 years in 24 countries, we detected 175 out of 238 outbreaks (73.5%) but only 22 out of 238 (9.2%) within 2 weeks before or after an outbreak onset; in the best case, while monitoring the frequency of health-related reports, we identified 2 out of 6 outbreaks (33%) within 2 weeks of onset. The positive predictive value varied between 9% and 100% for HealthMap and from 0 to 100% for EIOS, and timeliness of detection ranged from 13% to 94% for HealthMap and from 0% to 92% for EIOS, whereas system specificity was generally high (59%-100%). The number of EBS reports available within a country, the human development index, and the country's geographical location partially explained the high variability in system performance across countries. We documented the global variation of EBS performance and demonstrated that monitoring the report frequency alone in EBS may be insufficient for the timely detection of outbreaks. In particular, in low- and middle-income countries, low data quality and report frequency impair the sensitivity and timeliness of disease surveillance through EBS. Therefore, advances in the development and evaluation and EBS are needed, particularly in low-resource settings.

Intrusion Detection System Using K-Means and Edited Nearest Neighbour Algorithm

In imbalanced network traffic, malicious cyber-attacks can often hide in large amounts of normal data. It exhibits a high degree of stealth and obfuscation in cyberspace, making it difficult for Network Intrusion Detection System (NIDS) to ensure the accuracy and timeliness of detection. This paper researches machine learning and deep learning for intrusion detection in imbalanced network traffic. It proposes a novel Difficult Set Sampling Technique (DSSTE) algorithm to tackle the class imbalance problem. First, use the Edited Nearest Neighbor (ENN) algorithm to divide the imbalanced training set into the difficult set and the easy set. Next, use the K- Means algorithm to compress the majority samples in the difficult set to reduce the majority. Zoom in and out the minority samples’ continuous attributes in the difficult set synthesize new samples to increase the minority number. Finally, the easy set, the compressed set of majority in the difficult, and the minority in the difficult set are combined with its augmentation samples to make up a new training set. The algorithm reduces the imbalance of the original training set and provides targeted data augment for the minority class that needs to learn. It enables the classifier to learn the differences in the training stage better and improve classification performance. To verify the proposed method, we conduct experiments on the classic intrusion dataset NSL-KDD. We use classical classification models: random forest(RF), Support Vector Machine (SVM), XGBoost, Long and Short- term Memory (LSTM), Adaboost, AlexNet, Mini- VGGNet.

Prediction of Air Leakage Rate of Sintering Furnace Based on BP Neural Network Optimized by PSO

Aiming at the difficulty of air leakage detection in the sintering process of the sintering furnace, especially the problems of high detection cost and poor timeliness of detection results when traditional methods are used for detection, we propose an air leakage rate prediction algorithm. Firstly, we use the particle swarm optimization algorithm to optimize the initial parameters of the neural network based on back propagation and get the best set of initial parameters through continuous search. Secondly, the optimized parameters are substituted into the neural network to train them with training data, and the trained parameters are obtained. Finally, the air leakage rate of the test set data is predicted by using the trained parameters. Compared with traditional calculation methods such as gas analysis and calorimetry, the proposed method can greatly simplify the detection process, shorten the detection time, and control the error within 5%, allowing the user to deal with the air leakage problem more timely and improve the overall sintering quality.

FSODS: A Lightweight Metalearning Method for Few-Shot Object Detection on SAR Images

At present, few-shot object detection research in the field of optical remote sensing images has been conducted, but few-shot object detection in the field of SAR images have rarely been explored. To this end, this paper proposes a lightweight meta-learning-based SAR image few-shot object detection method, which improves the accuracy and speed of SAR image few-shot object detection from a more balanced perspective. First, we introduce the latest FSODM method in optical remote sensing as a benchmark framework. Second, a lightweight meta-feature extractor named DarknetS is designed to enhance the feature representation of SAR images and improve detection timeliness. Furthermore, we build a new aggregation module called AggregationS, which encodes support features and query features into the same feature subspace via a novel transformer encoder. This module design can better extract the correlation and saliency between different classes in the support set, improve the detection accuracy of the query set, and enhance the detection generalization performance of new classes. Finally, we built several real-world SAR image few-shot object detection datasets to verify the effectiveness of the method. Experimental results show that FSODS can achieve a better object detection performance compared to the baseline model under the condition that only a small amount of labelled data is required for new classes of SAR image objects.

Continuous unobtrusive assessment of meaningful change in older adults with cancer: The Pacific Aging &amp; Cancer Study Collaborative—PACS collaborative.

1569 Background: Knowledge of changes in health that precede a cancer diagnosis is challenging because of a lack of longitudinal, objective measurement techniques. Current approaches rely on periodic assessment via self-report which may miss when and how health changes, particularly when changes may appear subtly over time. Remote-monitoring technologies provide a mechanism to continuously, passively, and unobtrusively monitor changes in health so that trajectories of change in relation to a life event (i.e., cancer diagnosis, treatment) can be detected and described. We examined the changes in digital indicators of health and life events 1 year before and after a self-reported cancer diagnosis in community-dwelling adults aged 65 and older. Methods: This is a secondary, retrospective data analysis of older adults who self-reported a new cancer diagnosis in the Oregon Center for Aging &amp; Technology (ORCATECH) cohort. Ten older adults (age = 71.8±4.9 years, 30% women) were included with various cancer types (esophageal, prostate, uterine, pancreatic, b-cell follicular lymphoma, multiple myeloma, basal cell melanoma, basal and/or squamous cell carcinoma). Daily physical activity was measured using step counts derived from an actigraph watch. Weekly health and life events (pain severity, loneliness, hospitalization/emergency room (ER) visits, days away from home overnight) were self-reported from weekly online surveys. Results: A total of 3,624 days of actigraphy data (210 ± 88 days pre-cancer; 153 ± 81 days post-cancer) and 750 weeks of self-reported online survey data (36 ± 12 weeks pre-cancer; 39 ± 14 weeks post-cancer) were collected. Longitudinal linear mixed-effects models revealed that the trajectory of step counts was different pre- and post-cancer (β = -1.52, p &lt;.001), with a gradual decrease in step counts before a cancer diagnosis. The trajectory of pain severity was different pre- and post-cancer (β = 0.01, p &lt;.001), with a gradual increase in pain severity before a cancer diagnosis. There was a gradual increase in the occurrence of hospitalization/ER visits (OR = 1.07, p = 0.02) and days away from home overnight (OR = 1.04, p = 0.01) before a cancer diagnosis. Feelings of loneliness increased over time, regardless of pre- or post-cancer (OR = 1.04, p &lt;.001). Conclusions: Changes in health and life events 1-year before a cancer diagnosis in older adults with varying cancer types and severity were unobtrusively observed. This study suggests that a remote-monitoring technology platform deployed in homes can detect meaningful intra-individual changes before and after a cancer diagnosis. Future studies can employ this technology as a pathway for improving the timeliness of detection and more effective therapeutic follow-up for older adults.

Evaluation of the efficiency of preventive examinations of the adult population, aimed at early tuberculosis diagnosis

BACKGROUND: In Russia, compared with other countries, at least 65% of the population must undergo an annual fluorographic examination for early tuberculosis detection.&#x0D; AIM: This study aimed to assess the impact of mass fluorographic examinations of the adult population on the main epidemiological factors and indicators of prompt tuberculosis detection.&#x0D; MATERIALS AND METHODS: The morbidity and mortality from tuberculosis have been analyzed along with the efficiency of its detection during preventive examinations, the proportion of destructive forms of the disease, and the 1-year mortality rate in four federal districts from 2014 to 2019.&#x0D; RESULTS: For all districts, low efficiency of preventive examinations was registered (1 patient per 2,0005,000 people examined), as well as its strong correlation with morbidity and, in case of its absence, with the coverage of examinations. The change in morbidity and mortality rates over time was independent of the mass screening volume of the adult population. The relative risk indicators of increased morbidity and mortality with a decreased number of examinations were 0.4 and 0.3, respectively. The increased coverage of the population with examinations was not accompanied by an improved indicator of detection timeliness, namely a decreased incidence of destructive forms and 1-year mortality rate. The incidence of tuberculosis is determined by socioeconomic factors, which influence the level and living conditions of the population.&#x0D; CONCLUSIONS: This study established the low efficiency of mass fluorographic examinations of the population, lack of influence of coverage with examinations on the epidemiological situation, and the timeliness of tuberculosis detection.

Dynamic, Incremental, and Continuous Detection of Cyberbullying in Online Social Media

The potentially detrimental effects of cyberbullying have led to the development of numerous automated, data-driven approaches, with emphasis on classification accuracy. Cyberbullying, as a form of abusive online behavior, although not well-defined, is a repetitive process, i.e., a sequence of aggressive messages sent from a bully to a victim over a period of time with the intent to harm the victim. Existing work has focused on harassment (i.e., using profanity to classify toxic comments independently) as an indicator of cyberbullying, disregarding the repetitive nature of this harassing process. However, raising a cyberbullying alert immediately after an aggressive comment is detected can lead to a high number of false positives. At the same time, two key practical challenges remain unaddressed: (i) detection timeliness, which is necessary to support victims as early as possible, and (ii) scalability to the staggering rates at which content is generated in online social networks. In this work, we introduce CONcISE , a novel approach for timely and accurate Cyberbullying detectiON in online social media SEssions. CONcISE is a two-stage online approach designed to reduce the time to raise a cyberbullying alert by sequentially examining comments as they become available over time, and minimizing the number of feature evaluations necessary for a decision to be made for each comment. Extensive experiments on a real-world Instagram dataset with users and comments demonstrate the effectiveness, scalability, and timeliness of our approach and its benefits over existing methods. Additional experiments using a Twitter dataset offer evidence in support of the potential generalizability of CONcISE to other social media platforms.

Intrusion Detection of Imbalanced Network Traffic Based on Machine Learning and Deep Learning

In imbalanced network traffic, malicious cyber-attacks can often hide in large amounts of normal data. It exhibits a high degree of stealth and obfuscation in cyberspace, making it difficult for Network Intrusion Detection System(NIDS) to ensure the accuracy and timeliness of detection. This paper researches machine learning and deep learning for intrusion detection in imbalanced network traffic. It proposes a novel Difficult Set Sampling Technique(DSSTE) algorithm to tackle the class imbalance problem. First, use the Edited Nearest Neighbor(ENN) algorithm to divide the imbalanced training set into the difficult set and the easy set. Next, use the KMeans algorithm to compress the majority samples in the difficult set to reduce the majority. Zoom in and out the minority samples' continuous attributes in the difficult set synthesize new samples to increase the minority number. Finally, the easy set, the compressed set of majority in the difficult, and the minority in the difficult set are combined with its augmentation samples to make up a new training set. The algorithm reduces the imbalance of the original training set and provides targeted data augment for the minority class that needs to learn. It enables the classifier to learn the differences in the training stage better and improve classification performance. To verify the proposed method, we conduct experiments on the classic intrusion dataset NSL-KDD and the newer and comprehensive intrusion dataset CSE-CIC-IDS2018. We use classical classification models: random forest(RF), Support Vector Machine(SVM), XGBoost, Long and Short-term Memory(LSTM), AlexNet, Mini-VGGNet. We compare the other 24 methods; the experimental results demonstrate that our proposed DSSTE algorithm outperforms the other methods.