首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    First Affiliated Hospital of Xi’an Jiaotong University Reports Findings in Rectal Cancer (The effect of robotic surgery on low anterior resection syndrome in patients with lower rectal cancer: a propensity score-matched analysis)

    76-77页
    查看更多>>摘要:New research on Oncology - Rectal Cancer is the subject of a report. According to news reporting from Shaanxi, People’s Republic of China, by NewsRx journalists, research stated, “Many patients experience anorectal dysfunction after rectal surgery, which is known as low anterior resection syndrome (LARS). Robotic systems have many technical advantages that may be suitable for functional preservation after low rectal resection.” Financial supporters for this research include National Natural Science Foundation of China, Shaanxi Province Science Foundation. The news correspondents obtained a quote from the research from the First Affiliated Hospital of Xi’an Jiaotong University, “Thus, the study aimed to explore whether robotic surgery can reduce the incidence and severity of LARS. Patients undergoing minimally invasive sphincter-sparing surgery for low rectal cancer were enrolled between January 2015 and December 2020. The patients were divided into robotic or laparoscopic groups. The LARS survey was conducted at 6, 12 and 18 months postoperatively. Major LARS scores were analysed as the primary endpoint. In order to reduce confounding factors, one-to-two propensity score matches were used. In total, 342 patients were enrolled in the study. At 18 months postoperatively, the incidence of LARS was 68.7% (235/342); minor LARS was identified in 112/342 patients (32.7%), and major LARS in 123/342 (36.0%). After matching, the robotic group included 74 patients, and the laparoscopic group included 148 patients. The incidence of major LARS in the robotic group was significantly lower than that in the laparoscopic group at 6, 12, and 18 months after surgery. In multivariate logistic regression analysis, tumour location, laparoscopic surgery, intersphincteric resection, neoadjuvant therapy, and anastomotic leakage were independent risk factors for major LARS after minimally invasive sphincter-sparing surgery for low rectal cancer. Furthermore, a major LARS prediction model was constructed. Results of model evaluation showed that the nomogram had good prediction accuracy and efficiency. Patients with low rectal cancer may benefit from robotic surgery to reduce the incidence and severity of LARS.”

    Guilin Medical University Reports Findings in Chemicals and Chemistry [Effects of Benzo (a) Pyrene and 2,2’,4,4’-Tetrabromodiphenyl Ether Exposure on the Thyroid Gland in Rats by Attenuated Total Reflection Fourier-Transform Infrared ...]

    77-78页
    查看更多>>摘要:New research on Chemicals and Chemistry is the subject of a report. According to news reporting out of Guangxi, People’s Republic of China, by NewsRx editors, research stated, “Benzo[]pyrene (B[]P) and 2,2’,4,4’-tetrabromodiphenyl ether (BDE-47) are widespread environmental pollutants and can destroy thyroid function. We assessed the biochemical changes in the thyroid tissue of rats exposed to B[]P and BDE-47 using attenuated total reflection Fourier-transform infrared spectroscopy combined with support vector machine(SVM).” Financial support for this research came from Specific Research Project of Guangxi for Research Bases and Talents. Our news journalists obtained a quote from the research from Guilin Medical University, “After B[]P and BDE-47 treatment in rats, the structure of thyroid follicles was destroyed and epithelial cells were necrotic, indicating that B[]P and BDE-47 may lead to changes of the thyroid morphology of the rats. These damages are mainly related to C=O stretch vibrations of lipids (1743 cm), as well as the secondary structure of proteins [amide I (1645 cm) and amide Ⅱ (1550 cm)], and carbohydrates [C-OH (1138 cm), C-O (1106 cm, 1049 cm, 991 cm), C-C (1106 cm) stretching] and collagen (phosphodiester stretching at 922 cm) vibration modes.”

    University of Glasgow Reports Findings in Colon Cancer (Machine learning-based classifiers to predict metastasis in colorectal cancer patients)

    78-79页
    查看更多>>摘要:New research on Oncology - Colon Cancer is the subject of a report. According to news reporting originating from Glasgow, United Kingdom, by NewsRx correspondents, research stated, “The increasing prevalence of colorectal cancer (CRC) in Iran over the past three decades has made it a key public health burden. This study aimed to predict metastasis in CRC patients using machine learning (ML) approaches in terms of demographic and clinical factors.” Our news editors obtained a quote from the research from the University of Glasgow, “This study focuses on 1,127 CRC patients who underwent appropriate treatments at Taleghani Hospital, a tertiary care facility. The patients were divided into training and test datasets in an 80:20 ratio. Various ML methods, including Naive Bayes (NB), random rorest (RF), support vector machine (SVM), neural network (NN), decision tree (DT), and logistic regression (LR), were used for predicting metastasis in CRC patients. Model performance was evaluated using 5-fold cross-validation, reporting sensitivity, specificity, the area under the curve (AUC), and other indexes. Among the 1,127 patients, 183 (16%) had experienced metastasis. In the predictionof metastasis, both the NN and RF algorithms had the highest AUC, while SVM ranked third in both the original and balanced datasets. The NN and RF algorithms achieved the highest AUC (100%), sensitivity (100% and 100%, respectively), and accuracy (99.2% and 99.3%, respectively) on the balanced dataset, followed by the SVM with an AUC of 98.8%, a sensitivity of 97.5%, and an accuracy of 97%. Moreover, lower false negative rate (FNR), false positive rate (FPR), and higher negative predictive value (NPV) can be confirmed by these two methods. The results also showed that all methods exhibited good performance in the test datasets, and the balanced dataset improved the performance of most ML methods. The most important variables for predicting metastasis were the tumor stage, the number of involved lymph nodes, and the treatment type. In a separate analysis of patients with tumor stages I-III, it was identified that tumor grade, tumor size, and tumor stage are the most important features. This study indicated that NN and RF were the best among ML-based approaches for predicting metastasis in CRC patients.”

    Researchers Submit Patent Application, 'Method And System For Preprocessing Optimization Of Streaming Video Data', for Approval (USPTO 20240040108)

    79-83页
    查看更多>>摘要:From Washington, D.C., NewsRx journalists report that a patent application by the inventor Ajgaonkar, Amol (Chandler, AZ, US), filed on July 13, 2023, was made available online on February 1, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: “This disclosure relates generally to the optimization of preprocessing of streaming video data and, more specifically, to the optimization of preprocessing parameters to improve a main output of a main artificial intelligence model. “Cameras are beneficial for use in many areas of commercial and personal practice. For example, security cameras are used within (and outside) commercial warehouses and on private personal property. Other applications use cameras along assembly lines for quality control purposes. With the increased capabilities of cameras having higher quality imagery (i.e., resolution) and a wider field of view, more area can be shown in the streaming video by the camera. A large portion of the frame/field of view may be of little or no interest to the consumer (e.g., a security or manufacturing company). However, current practices relay the entirety of the streaming video (i.e., the entire frame/field of view) to the consumer, which can be time and resource consuming due to the need to transfer large frame (i.e., field of view), high resolution video data.”

    Patent Issued for Automatically-generated labels for time series data and numerical lists to use in analytic and machine learning systems (USPTO 11887015)

    83-86页
    查看更多>>摘要:A patent by the inventors Das, Sreeji Krishnan (Fremont, CA, US), Fahmy, Amr Fawzy (Foxboro, MA, US), Kumaresan, Dhileeban (Foster City, CA, US), Sutton, Eric L. (Redwood City, CA, US), Wong, Adrienne (Redwood City, CA, US), Yoon, Jae Young (San Mateo, CA, US), filed on April 23, 2020, was published online on January 30, 2024, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents. Patent number 11887015 is assigned to Oracle International Corporation (Redwood Shores, California, United States). The following quote was obtained by the news editors from the background information supplied by the inventors: “A time series dataset is typically represented in two dimensions: one dimension representing time and another dimension representing numerical data points. For example, a time series dataset may track processor utilization of a server over a fixed window of time where each respective data point in the dataset indicates a respective measured utilization rate at a different point in time within the fixed window. These data points may provide useful information about the behavior of the underlying system, such as when the processor utilization rate is prone to spikes and drop offs. A monitoring system may be configure to track several other metric time series, such as memory throughput, active database sessions, input/output (I/O) operations, server requests, and server response times.

    Researchers Submit Patent Application, 'Time-Frequency Planning For Radars On Vehicles In A Warehouse Environment', for Approval (USPTO 20240036584)

    87-89页
    查看更多>>摘要:From Washington, D.C., NewsRx journalists report that a patent application by the inventors Ali, Murtaza (Cedar Park, TX, US); Ertan, Ali Erdem (Austin, TX, US); Stark, Wayne E. (Ann Arbor, MI, US), filed on July 26, 2023, was made available online on February 1, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: “The use of radar to determine range, velocity, and angle (elevation or azimuth) of objects in an environment is important in a number of applications including automotive radar and gesture detection. Radar systems typically transmit a radio frequency (RF) signal and listen for the reflection of the radio signal from objects in the environment. A radar system estimates the location of objects, also called targets, in the environment by correlating delayed versions of the received radio signal with the transmitted radio signal. A radar system can also estimate the velocity of the target by Doppler processing. A radar system with multiple transmitters and multiple receivers can also determine the angular position of a target. Depending on antenna scanning and/or the number of antenna/receiver channels and their geometry, different angles (e.g., azimuth or elevation) can be determined.

    'Identifying Similar Digital Assets From Results Of A Multi-User Search Of Digital Assets, Comparing Digital Assets And Providing Persistent Search Results Of The Multi-User Search' in Patent Application Approval Process (USPTO 20240037139)

    89-93页
    查看更多>>摘要:A patent application by the inventors CHANDA, Rupen (Austin, TX, US); JACKSON, Peter (Orinda, CA, US), filed on October 5, 2023, was made available online on February 1, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application is assigned to Haworth Inc. (Holland, Michigan, United States). The following quote was obtained by the news editors from the background information supplied by the inventors: “A user can search one or more sources of digital images or digital asset management (DAM) systems using search keywords. When the user receives search results from a source of digital images (e.g., a search engine, or a proprietary digital asset management system), it is difficult to share the search results with other users. The user can either download all search results to a local storage and then send the search results via an email or some other medium to the other users. The user could also upload the search results to a cloud-based storage and send a link to the storage location to other users so that they can view the search results. This method is very time consuming and may not be very useful, especially when there are a large number of digital images. The user who has performed the search could send a link that initiates a similar or same search to the other users. The other users can select the link to rerun the similar or same search. However, the other users may get different search results due to various reasons. For example, different geographical locations of users can cause differences in search results as some digital images may not be available in certain geographical location of the world. Further, when different users use the same link to rerun a search at different times, they can receive different search results as some digital images may not be available or accessible to the search engine at a later time or there may be new digital images that are available, such that different results are provided to the users based on when the search is performed. In some cases, accessing the link can provide the digital images to different users in different order or in a different arrangement. When searching for digital assets, a user may want to search sources of digital assets for digital assets similar to one or more search results. In this case, the user needs to save the search results to a local storage and then upload the stored search results to a search engine for further searching. This process can be time consuming, especially when users in a multi-user search and review session need to search similar digital assets corresponding to multiple search results. All these issues can reduce the effectiveness of search, review and selection of digital images.

    'Cell Directing Apparatus And Robot For Assisting Picking' in Patent Application Approval Process (USPTO 20240033917)

    93-96页
    查看更多>>摘要:A patent application by the inventors Jeong, Seokhoon (Seoul, KR); Lee, Seung Hoon (Seoul, KR); Lee, Sucheol (Seoul, KR); Yu, Hoyeon (Seoul, KR), filed on July 25, 2023, was made available online on February 1, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background information supplied by the inventors: ““Picking” may refer to an operation of taking out or bringing a target object from a place in a distribution warehouse where the target object is stored. In general, the distribution warehouse includes a plurality of racks, and the racks include a plurality of cells. A worker who performs picking has to check which cell of which rack the target object is placed, and take the target object from the cell having the target object. However, when the worker directly checks the location information of the location of the cell having the target object and finds the cell and takes the target object, there is a problem in that the picking process is delayed.

    'Image Analysis And Identification Using Machine Learning With Output Estimation' in Patent Application Approval Process (USPTO 20240037652)

    97-99页
    查看更多>>摘要:A patent application by the inventors DAGLEY, Geoffrey (McKinney, TX, US); HOOVER, Jason Richard (Grapevine, TX, US); PRICE, Micah (Plano, TX, US); TANG, Qiaochu (The Colony, TX, US); VASISHT, Sunil Subrahmanyam (Flowermound, TX, US); WYLIE, Stephen Michael (Carrollton, TX, US), filed on April 18, 2023, was made available online on February 1, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application is assigned to Capital One Services LLC (McLean, Virginia, United States). The following quote was obtained by the news editors from the background information supplied by the inventors: “Customers have limited methods for receiving accurate quotes and pricing when attempting to finance a vehicle purchase. For example, in a typical method, a customer visits an automobile dealership and selects a vehicle to purchase. After negotiating the vehicle price, the customer then fills out a lengthy credit application at the dealership and provides any information needed to complete the financing. After receiving dealership credit approval, the customer signs a contract reflecting the purchase and financing terms, such as the monthly payments and Annual Percentage Rate (APR).

    'Cleaning Pad Washing' in Patent Application Approval Process (USPTO 20240033781)

    100-104页
    查看更多>>摘要:A patent application by the inventors Doughty, Brian W. (Framingham, MA, US); Heinrichs, Winston (Brighton, MA, US); Ohm, Timothy R. (Grover Beach, CA, US); Torrente, Leo (Somerville, MA, US), filed on August 1, 2022, was made available online on February 1, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background information supplied by the inventors: “Cleaning robots include mobile robots that autonomously perform cleaning tasks within an environment, e.g., a home. Some cleaning robots hold a cleaning pad that collects debris. A cleaning robot can navigate to a docking station to charge the cleaning robot or evacuate debris from the cleaning robot.”